Name: Teoh Len Khaei Edwin
Student Number: 220645397
Path to Data: hdfs://lena-master/user/lteoh001/credit_score_train.csv
Introduction
For this project, we will use the Credit Score Classification dataset obtained from Kaggle. The dataset is available here.
We will explore the dataset and compare several machine learning models, including Multilayer Perceptron, Decision Tree Classifier, and Random Forest Classifier, using PySpark to determine which is best suited for this use case. Our goal is to create a credit score classifier using as few columns as possible to maximize efficiency. Additionally, we aim to develop a model that can sufficiently predict a credit score based on selected customer characteristics and financial statistics. The model will not track individual performance over time, so this project does not include a time-series component.
This project will take approximately 2 hours to run due to the machine learning model implementations.
Proposal
The business application of this project is to determine a customer's credit score using the existing dataset, which helps banks assess a person's debt capacity. We will compare the machine learning models mentioned above from the PySpark library. While the dataset contains a time-series component for tracking customers over time, we will not be utilizing it. This model is intended to assist bankers and stakeholders in early credit score identification, potentially streamlining the review process or, ideally, operating without manual intervention.
Implementation
Uploading the dataset to HDFS
The code below sets up the environment to enable command-line usage within the notebook. Since the files have already been uploaded to the Lena site, the following code will transfer them to Hadoop.
# set hadoop environment variable
import os, sys
os.environ["HADOOP_VERSION"] = "3.3.0"
os.environ["HADOOP_TOOLS"] = "/opt/hadoop/current/share/hadoop/tools/lib"
os.environ["JAVA_HOME"] = "/usr/lib/jvm/default-java"
# Setup user name
os.environ["USER"] = "lteoh001"
# here we assume that our workspace is a folder called hadoop
os.environ["WORKSPACE"] = "/home/" + os.getenv("USER") + "/hadoop"
# append hadoop executable paths to the existing system path
%set_env PATH=/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/opt/jupyterhub/bin:/opt/hadoop/current/bin:/opt/spark/current/bin:/opt/hadoop/current/bin:/opt/mahout/current/binenv: PATH=/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/opt/jupyterhub/bin:/opt/hadoop/current/bin:/opt/spark/current/bin:/opt/hadoop/current/bin:/opt/mahout/current/bin%%sh
# List local files
ls
# Upload datasets into HDFS
hadoop fs -put credit_score_test.csv
hadoop fs -put credit_score_train.csv
# Make Directory for Spark Checkpoints
hadoop fs -mkdir spark_checkpoints
# Check if the file is uploaded and folder created
hadoop fs -lsCoursework2_lteoh001_initialDraft.ipynb
Coursework2_lteoh001.ipynb
Coursework 2_main.ipynb
credit_score_test.csv
credit_score_train.csv
spark-warehouse
Found 77 items
drwxr-xr-x - lteoh001 users 0 2023-10-12 19:48 .sparkStaging
drwxr-xr-x - lteoh001 users 0 2023-08-14 18:03 1_minmaxdiff
-rw-r--r-- 3 lteoh001 users 173604485 2023-08-09 05:22 200704hourly.txt
drwxr-xr-x - lteoh001 users 0 2023-08-15 15:28 2_dailymin
drwxr-xr-x - lteoh001 users 0 2023-08-15 15:17 3_meanvariance
drwxr-xr-x - lteoh001 users 0 2023-08-15 19:47 4_correlation
-rw-r--r-- 3 lteoh001 users 12078583 2023-06-17 19:19 books.txt
-rw-r--r-- 3 lteoh001 users 15366486 2023-09-22 12:27 credit_score_test.csv
-rw-r--r-- 3 lteoh001 users 31136044 2023-09-22 12:28 credit_score_train.csv
drwxr-xr-x - lteoh001 users 0 2023-08-17 16:48 docs
drwxr-xr-x - lteoh001 users 0 2023-08-17 20:27 docs-canopy-centroids
drwxr-xr-x - lteoh001 users 0 2023-08-30 20:27 docs-kmeans-clusters-Cosine10-100
drwxr-xr-x - lteoh001 users 0 2023-08-30 20:25 docs-kmeans-clusters-Cosine10-50
drwxr-xr-x - lteoh001 users 0 2023-08-30 20:48 docs-kmeans-clusters-Cosine120-100
drwxr-xr-x - lteoh001 users 0 2023-08-30 20:46 docs-kmeans-clusters-Cosine120-50
drwxr-xr-x - lteoh001 users 0 2023-08-30 20:54 docs-kmeans-clusters-Cosine160-100
drwxr-xr-x - lteoh001 users 0 2023-08-30 20:52 docs-kmeans-clusters-Cosine160-50
drwxr-xr-x - lteoh001 users 0 2023-08-30 20:32 docs-kmeans-clusters-Cosine20-100
drwxr-xr-x - lteoh001 users 0 2023-08-30 20:30 docs-kmeans-clusters-Cosine20-50
drwxr-xr-x - lteoh001 users 0 2023-08-30 20:37 docs-kmeans-clusters-Cosine40-100
drwxr-xr-x - lteoh001 users 0 2023-08-30 20:35 docs-kmeans-clusters-Cosine40-50
drwxr-xr-x - lteoh001 users 0 2023-08-30 20:43 docs-kmeans-clusters-Cosine80-100
drwxr-xr-x - lteoh001 users 0 2023-08-30 20:40 docs-kmeans-clusters-Cosine80-50
drwxr-xr-x - lteoh001 users 0 2023-08-29 17:42 docs-kmeans-clusters-euclidean10
drwxr-xr-x - lteoh001 users 0 2023-08-29 16:14 docs-kmeans-clusters-euclidean10-40
drwxr-xr-x - lteoh001 users 0 2023-08-29 16:15 docs-kmeans-clusters-euclidean10-80
drwxr-xr-x - lteoh001 users 0 2023-08-18 13:30 docs-kmeans-clusters-euclidean11
drwxr-xr-x - lteoh001 users 0 2023-08-18 13:36 docs-kmeans-clusters-euclidean12
drwxr-xr-x - lteoh001 users 0 2023-08-18 13:43 docs-kmeans-clusters-euclidean13
drwxr-xr-x - lteoh001 users 0 2023-08-18 13:49 docs-kmeans-clusters-euclidean14
drwxr-xr-x - lteoh001 users 0 2023-08-18 13:55 docs-kmeans-clusters-euclidean15
drwxr-xr-x - lteoh001 users 0 2023-08-18 14:01 docs-kmeans-clusters-euclidean16
drwxr-xr-x - lteoh001 users 0 2023-08-29 14:22 docs-kmeans-clusters-euclidean160
drwxr-xr-x - lteoh001 users 0 2023-08-18 14:07 docs-kmeans-clusters-euclidean17
drwxr-xr-x - lteoh001 users 0 2023-08-18 14:11 docs-kmeans-clusters-euclidean18
drwxr-xr-x - lteoh001 users 0 2023-08-18 14:14 docs-kmeans-clusters-euclidean19
drwxr-xr-x - lteoh001 users 0 2023-08-18 12:49 docs-kmeans-clusters-euclidean2
drwxr-xr-x - lteoh001 users 0 2023-08-29 17:49 docs-kmeans-clusters-euclidean20
drwxr-xr-x - lteoh001 users 0 2023-08-29 16:28 docs-kmeans-clusters-euclidean20-40
drwxr-xr-x - lteoh001 users 0 2023-08-29 16:54 docs-kmeans-clusters-euclidean20-80
drwxr-xr-x - lteoh001 users 0 2023-08-18 12:55 docs-kmeans-clusters-euclidean3
drwxr-xr-x - lteoh001 users 0 2023-08-18 13:01 docs-kmeans-clusters-euclidean4
drwxr-xr-x - lteoh001 users 0 2023-08-29 17:54 docs-kmeans-clusters-euclidean40
drwxr-xr-x - lteoh001 users 0 2023-08-29 17:08 docs-kmeans-clusters-euclidean40-40
drwxr-xr-x - lteoh001 users 0 2023-08-29 17:34 docs-kmeans-clusters-euclidean40-80
drwxr-xr-x - lteoh001 users 0 2023-08-18 13:03 docs-kmeans-clusters-euclidean5
drwxr-xr-x - lteoh001 users 0 2023-08-18 13:09 docs-kmeans-clusters-euclidean6
drwxr-xr-x - lteoh001 users 0 2023-08-18 13:15 docs-kmeans-clusters-euclidean7
drwxr-xr-x - lteoh001 users 0 2023-08-18 13:16 docs-kmeans-clusters-euclidean8
drwxr-xr-x - lteoh001 users 0 2023-08-29 14:20 docs-kmeans-clusters-euclidean80
drwxr-xr-x - lteoh001 users 0 2023-08-18 13:23 docs-kmeans-clusters-euclidean9
drwxr-xr-x - lteoh001 users 0 2023-08-18 15:00 docs-kmeans-clusters-manhattan10
drwxr-xr-x - lteoh001 users 0 2023-08-18 15:02 docs-kmeans-clusters-manhattan11
drwxr-xr-x - lteoh001 users 0 2023-08-18 15:05 docs-kmeans-clusters-manhattan12
drwxr-xr-x - lteoh001 users 0 2023-08-18 15:08 docs-kmeans-clusters-manhattan13
drwxr-xr-x - lteoh001 users 0 2023-08-18 15:10 docs-kmeans-clusters-manhattan14
drwxr-xr-x - lteoh001 users 0 2023-08-18 15:13 docs-kmeans-clusters-manhattan15
drwxr-xr-x - lteoh001 users 0 2023-08-18 15:16 docs-kmeans-clusters-manhattan16
drwxr-xr-x - lteoh001 users 0 2023-08-29 14:40 docs-kmeans-clusters-manhattan160
drwxr-xr-x - lteoh001 users 0 2023-08-18 15:19 docs-kmeans-clusters-manhattan17
drwxr-xr-x - lteoh001 users 0 2023-08-18 15:22 docs-kmeans-clusters-manhattan18
drwxr-xr-x - lteoh001 users 0 2023-08-18 15:25 docs-kmeans-clusters-manhattan19
drwxr-xr-x - lteoh001 users 0 2023-08-18 14:36 docs-kmeans-clusters-manhattan2
drwxr-xr-x - lteoh001 users 0 2023-08-18 15:27 docs-kmeans-clusters-manhattan20
drwxr-xr-x - lteoh001 users 0 2023-08-18 14:38 docs-kmeans-clusters-manhattan3
drwxr-xr-x - lteoh001 users 0 2023-08-18 14:40 docs-kmeans-clusters-manhattan4
drwxr-xr-x - lteoh001 users 0 2023-08-29 14:30 docs-kmeans-clusters-manhattan40
drwxr-xr-x - lteoh001 users 0 2023-08-18 14:42 docs-kmeans-clusters-manhattan5
drwxr-xr-x - lteoh001 users 0 2023-08-18 14:45 docs-kmeans-clusters-manhattan6
drwxr-xr-x - lteoh001 users 0 2023-08-18 14:50 docs-kmeans-clusters-manhattan7
drwxr-xr-x - lteoh001 users 0 2023-08-18 14:54 docs-kmeans-clusters-manhattan8
drwxr-xr-x - lteoh001 users 0 2023-08-29 14:34 docs-kmeans-clusters-manhattan80
drwxr-xr-x - lteoh001 users 0 2023-08-18 14:57 docs-kmeans-clusters-manhattan9
drwxr-xr-x - lteoh001 users 0 2023-08-17 17:15 docs-seqfiles
drwxr-xr-x - lteoh001 users 0 2023-08-30 20:53 docs-vectors
drwxr-xr-x - lteoh001 users 0 2023-10-09 03:54 spark_checkpoints
drwxr-xr-x - lteoh001 users 0 2023-08-31 01:33 tmpput: `credit_score_test.csv': File exists
put: `credit_score_train.csv': File exists
mkdir: `spark_checkpoints': File existsLibraries
The code below is a compilation of all the libraries required for this project.
# Import required libraries
from pyspark import SparkContext, SparkConf
from pyspark.sql import SparkSession
from pyspark.sql.functions import udf
from pyspark.sql.functions import col
from pyspark.sql.functions import coalesce
import pyspark.sql.functions as F
from pyspark.sql.types import *Initializing SparkContext and SparkSession
The code below is to initialize the SparkContext and Sparksession for this project.
# Initialize SparkContext and SparkSession
#sc.stop() # =================================== TO BE REMOVED !!!!!!
#spark.stop()
sc = SparkContext()
sc.setCheckpointDir('hdfs://lena-master/user/lteoh001/spark_checkpoints')
spark = SparkSession.builder \
.master('local[*]') \
.appName('cw2_lteoh001') \
.getOrCreate()Loading the Datasets into PySpark
The code below is to load the dataset into spark from the HDFS.
# Loading the datasets
credit_score_train = spark.read.csv('hdfs://lena-master/user/lteoh001/credit_score_train.csv',
header=True, inferSchema=True, nullValue='NA')
credit_score_test = spark.read.csv('hdfs://lena-master/user/lteoh001/credit_score_test.csv',
header=True, inferSchema=True, nullValue='NA')
# Printing both the dataset
print(credit_score_train.show(1, vertical=True))
print(credit_score_test.show(1, vertical=True))-RECORD 0----------------------------------------
ID | 0x1602
Customer_ID | CUS_0xd40
Month | January
Name | Aaron Maashoh
Age | 23
SSN | 821-00-0265
Occupation | Scientist
Annual_Income | 19114.12
Monthly_Inhand_Salary | 1824.8433333333328
Num_Bank_Accounts | 3
Num_Credit_Card | 4
Interest_Rate | 3
Num_of_Loan | 4
Type_of_Loan | Auto Loan, Credit...
Delay_from_due_date | 3
Num_of_Delayed_Payment | 7
Changed_Credit_Limit | 11.27
Num_Credit_Inquiries | 4.0
Credit_Mix | _
Outstanding_Debt | 809.98
Credit_Utilization_Ratio | 26.822619623699016
Credit_History_Age | 22 Years and 1 Mo...
Payment_of_Min_Amount | No
Total_EMI_per_month | 49.57494921489417
Amount_invested_monthly | 80.41529543900253
Payment_Behaviour | High_spent_Small_...
Monthly_Balance | 312.49408867943663
Credit_Score | Good
only showing top 1 row
None
-RECORD 0----------------------------------------
ID | 0x160a
Customer_ID | CUS_0xd40
Month | September
Name | Aaron Maashoh
Age | 23
SSN | 821-00-0265
Occupation | Scientist
Annual_Income | 19114.12
Monthly_Inhand_Salary | 1824.8433333333328
Num_Bank_Accounts | 3
Num_Credit_Card | 4
Interest_Rate | 3
Num_of_Loan | 4
Type_of_Loan | Auto Loan, Credit...
Delay_from_due_date | 3
Num_of_Delayed_Payment | 7
Changed_Credit_Limit | 11.27
Num_Credit_Inquiries | 2022.0
Credit_Mix | Good
Outstanding_Debt | 809.98
Credit_Utilization_Ratio | 35.03040185583525
Credit_History_Age | 22 Years and 9 Mo...
Payment_of_Min_Amount | No
Total_EMI_per_month | 49.57494921489417
Amount_invested_monthly | 236.64268203272135
Payment_Behaviour | Low_spent_Small_v...
Monthly_Balance | 186.26670208571772
only showing top 1 row
NoneThe Kaggle dataset consists of two files, which are train.csv and test.csv. The data is split based on dates in the third column. The training dataset covers January to August, while the testing dataset spans September to December. Notably, the test dataset does not include the target variable (label). Consequently, we cannot evaluate model performance using this test set after training. Therefore, we will proceed using only the training dataset for this project.
# Printing the columns in both the dataset
print("== credit_score_train ===")
print("The number of columns: ", len(credit_score_train.columns))
print("The columns: ", credit_score_train.columns)
print()
print("== credit_score_test ===")
print("The number of columns: ", len(credit_score_test.columns))
print("The columns: ", credit_score_test.columns)== credit_score_train ===
The number of columns: 28
The columns: ['ID', 'Customer_ID', 'Month', 'Name', 'Age', 'SSN', 'Occupation', 'Annual_Income', 'Monthly_Inhand_Salary', 'Num_Bank_Accounts', 'Num_Credit_Card', 'Interest_Rate', 'Num_of_Loan', 'Type_of_Loan', 'Delay_from_due_date', 'Num_of_Delayed_Payment', 'Changed_Credit_Limit', 'Num_Credit_Inquiries', 'Credit_Mix', 'Outstanding_Debt', 'Credit_Utilization_Ratio', 'Credit_History_Age', 'Payment_of_Min_Amount', 'Total_EMI_per_month', 'Amount_invested_monthly', 'Payment_Behaviour', 'Monthly_Balance', 'Credit_Score']
== credit_score_test ===
The number of columns: 27
The columns: ['ID', 'Customer_ID', 'Month', 'Name', 'Age', 'SSN', 'Occupation', 'Annual_Income', 'Monthly_Inhand_Salary', 'Num_Bank_Accounts', 'Num_Credit_Card', 'Interest_Rate', 'Num_of_Loan', 'Type_of_Loan', 'Delay_from_due_date', 'Num_of_Delayed_Payment', 'Changed_Credit_Limit', 'Num_Credit_Inquiries', 'Credit_Mix', 'Outstanding_Debt', 'Credit_Utilization_Ratio', 'Credit_History_Age', 'Payment_of_Min_Amount', 'Total_EMI_per_month', 'Amount_invested_monthly', 'Payment_Behaviour', 'Monthly_Balance']As shown in the previous cell, the credit score test dataset lacks the Credit_Score column. Unfortunately, this missing target variable prevents us from using a significant portion of the original data for model evaluation.
Exploring the Columns
The code below is used to explore individual columns. We must understand the data's context before training, which involves looking for missing values, identifying inconsistent entries, and deciding which columns should be dropped.
Data Types and Structure of the Columns
Although we specified inferSchema=True in the CSV read function, some columns, such as Num_of_Loan, were categorized as strings. This likely occurred due to inconsistencies or errors in the dataset that caused the read function to interpret these columns as string data.
# For the sake of convenience writing the code later
credit_score = credit_score_train
credit_score.cache()
credit_score = credit_score.checkpoint()credit_score.printSchema()root
|-- ID: string (nullable = true)
|-- Customer_ID: string (nullable = true)
|-- Month: string (nullable = true)
|-- Name: string (nullable = true)
|-- Age: string (nullable = true)
|-- SSN: string (nullable = true)
|-- Occupation: string (nullable = true)
|-- Annual_Income: string (nullable = true)
|-- Monthly_Inhand_Salary: double (nullable = true)
|-- Num_Bank_Accounts: integer (nullable = true)
|-- Num_Credit_Card: integer (nullable = true)
|-- Interest_Rate: integer (nullable = true)
|-- Num_of_Loan: string (nullable = true)
|-- Type_of_Loan: string (nullable = true)
|-- Delay_from_due_date: integer (nullable = true)
|-- Num_of_Delayed_Payment: string (nullable = true)
|-- Changed_Credit_Limit: string (nullable = true)
|-- Num_Credit_Inquiries: double (nullable = true)
|-- Credit_Mix: string (nullable = true)
|-- Outstanding_Debt: string (nullable = true)
|-- Credit_Utilization_Ratio: double (nullable = true)
|-- Credit_History_Age: string (nullable = true)
|-- Payment_of_Min_Amount: string (nullable = true)
|-- Total_EMI_per_month: double (nullable = true)
|-- Amount_invested_monthly: string (nullable = true)
|-- Payment_Behaviour: string (nullable = true)
|-- Monthly_Balance: string (nullable = true)
|-- Credit_Score: string (nullable = true)
Using distinct count
The following code calculates the distinct count for all columns to provide a quick initial overview of the data distribution.
# Store the list of columnns
column_list = credit_score.columns
# Initialize the result dictionary
unique_count_dict = {}
unique_value_dict = {}
# Looping through the column list
for column in column_list:
# Check if the column is in the results dictionary
if column not in unique_value_dict.keys() and column not in unique_count_dict.keys():
# Storing the distinct values of each column
unique_value_dict[column] = credit_score.select(column).distinct().collect()
# Storing the count of each column
unique_count_dict[column] = credit_score.select(column).distinct().count()
# Print out the result
print(f"Column: {column}\nCount: {unique_count_dict[column]}")
Column: ID
Count: 100000
Column: Customer_ID
Count: 12500
Column: Month
Count: 8
Column: Name
Count: 10140
Column: Age
Count: 1788
Column: SSN
Count: 12501
Column: Occupation
Count: 16
Column: Annual_Income
Count: 18940
Column: Monthly_Inhand_Salary
Count: 13236
Column: Num_Bank_Accounts
Count: 943
Column: Num_Credit_Card
Count: 1179
Column: Interest_Rate
Count: 1750
Column: Num_of_Loan
Count: 434
Column: Type_of_Loan
Count: 6261
Column: Delay_from_due_date
Count: 73
Column: Num_of_Delayed_Payment
Count: 750
Column: Changed_Credit_Limit
Count: 4384
Column: Num_Credit_Inquiries
Count: 1224
Column: Credit_Mix
Count: 4
Column: Outstanding_Debt
Count: 13178
Column: Credit_Utilization_Ratio
Count: 100000
Column: Credit_History_Age
Count: 405
Column: Payment_of_Min_Amount
Count: 3
Column: Total_EMI_per_month
Count: 14950
Column: Amount_invested_monthly
Count: 91050
Column: Payment_Behaviour
Count: 7
Column: Monthly_Balance
Count: 98793
Column: Credit_Score
Count: 3Dropping Columns that represent identification
Because we would like to use columns that represent the charcteristics of the customer and their financial stats, identification type columns (ID, Customer_ID, Name, SSN) can be dropped and removed as they do not provide any useful information in predicting the credit score. It may be useful to keep track of the individual perfomance of a customer, tracking on how they perform overtime. For instance, their credit score, expenditure or monthly balances trending upwards or downwards overtime and any financial stats that represent a red flag. But this would be out of scope for what we want to achieve this time for the project.
Based on the count of the column 'ID' and the count of 'Customer ID' and 'SSN', we can note that 'ID' has a higher count than both 'Customer ID' and 'SSN'. We can infer that there are recurring customers throughout the dataset. But because we will not be tracking the credit and financial performance of the customer overtime, we also not need to have a time-related column, 'Month'.
This will be done later after pre-processing the other columns.
# Listing the identification type columns, and month
id_features = ['ID', 'Customer_ID', 'Name', 'SSN', 'Month']Other than Dropping Identification Columns
We will need to explore which columns have a bigger affect to the change in Credit Score. We can first create a correlation matrix to filter. This is because, during the initial draft, as attached in the folder. The first attempt at this project, had many issues because we tried to explore all the columns individual, one at a time, which cause pyspark to slow down significantly and not work as intended, even though it seem as the code should not have any error, or I could have mistaken somewhere which cause a stack of errors. Either way, if the purpose was to create an efficient credit score classifier with as little column as possible, this step will be needed.
One matter that was noted from the previous attempt is that many of the columns have mix of wrongly input column values. For instance, a customer could have a '16' in 7 rows, but '160', '3828', or '8_', where there either could be a typo or an underscore that makes the column into a string. Therefore, we will firstly need to filter to see which of these columns will need to be process before making the corelation matrix. Furthermore, it is noted that because this dataset initially, had a time element, which could explain repeating customers but they might have slightly different values, such has number of loans increasing over time. But because we will not be implementing, time aspect of the data here in this project, there might be a lot of duplicates that may be dropped, especially when the preprocessing, involves filling the wrongly input values with the most occuring value.
# Initialize columns want to be dropped
columns_to_drop = []Looking into dropping more
Before we go into more processing of data, we can have a general understanding and view of the dataset and see if there are any that require dropping. For example, the column 'Annual_Income' and 'Monthly_Inhand_Salary'. We can find out if the annual income and montly in hand salary are derivative of one another, and if it is required to have two columns providing very similar information. On the other hand, the difference between the two might be big enough to be.
We will be individually going through the following columns, as these column might have the potential to be dropped as they might not contribute as heavily to the classification model, the meaning of the column is not self explanatory or :
- Occupation
- Annual Income
- Monthly In Hand Salary
- Type of Loan
- Number of Loan
- Delay from Due Date
- Number Credit Inquiries
- Credit Mix
- Credit Utilization Ratio
- Credit History Age
- Total EMI per month
Checking for Missing Values
We can first make a list that shows each columns number of missing values. Therefore, we can prepare to process and explore the changes required later.
# Store the dataset columns
columns = credit_score.columns
# To store those that are missing
columns_with_missing_values = {}
for column in columns:
count = credit_score.select(column)\
.filter(col(column).isNull()).count()
if count != 0:
columns_with_missing_values[column] = count
print(column + ': ' + str(columns_with_missing_values[column])
+ ' missing values')Name: 9985 missing values
Monthly_Inhand_Salary: 15002 missing values
Type_of_Loan: 11408 missing values
Num_of_Delayed_Payment: 7002 missing values
Num_Credit_Inquiries: 1965 missing values
Credit_History_Age: 9030 missing values
Amount_invested_monthly: 4479 missing values
Monthly_Balance: 1200 missing valuesChecking for Underscore
As mentioned in the above cell, there are values with underscore where there are not supposed to. We will need to explore these columns and see if the underscores need to be removed.
# Initialize list to store the columns with underscores in them
columns_with_underscore = []
print('Number of rows that consists of "_" in the values')
# Looping through the columns
# Columns was initialized above
for column in columns:
# If the column are in id_features
if column in id_features:
# Skip, as they will be dropped anyways
continue
else:
# Select only the intended column
# Filter it based on if it contains the '_'
# Get count of the relevant rows of data, store it
column_count = credit_score.select(column)\
.filter(col(column)\
.contains('_'))\
.count()
# If the column count is not 0, means it has underscore
if column_count != 0:
# Store the column into the list
columns_with_underscore.append(column)
print(column + ': ' + str(column_count))
for column in columns_with_underscore:
print('Column ' + column + ' consists of unique values: ')
credit_score.select(column).distinct().show()Number of rows that consists of "_" in the values
Age: 4939
Occupation: 13294
Annual_Income: 6980
Num_of_Loan: 4785
Num_of_Delayed_Payment: 2744
Changed_Credit_Limit: 2091
Credit_Mix: 20195
Outstanding_Debt: 1009
Amount_invested_monthly: 4305
Payment_Behaviour: 92400
Monthly_Balance: 9
Column Age consists of unique values:
+-----+
| Age|
+-----+
| 7711|
| 31_|
| 7762|
| 5645|
| 1512|
| 1436|
| 6731|
| 6248|
| 8306|
| 2756|
| 3441|
| 4894|
| 6558|
| 1394|
| 5657|
| 2275|
|1102_|
| 853|
| 4975|
| 6366|
+-----+
only showing top 20 rows
Column Occupation consists of unique values:
+-------------+
| Occupation|
+-------------+
| Scientist|
|Media_Manager|
| Musician|
| Lawyer|
| Teacher|
| Developer|
| Writer|
| Architect|
| Mechanic|
| Entrepreneur|
| Journalist|
| Doctor|
| Engineer|
| Accountant|
| Manager|
| _______|
+-------------+
Column Annual_Income consists of unique values:
+------------------+
| Annual_Income|
+------------------+
| 16578.115|
| 14224.655|
| 94454.1|
| 96582.24|
| 42399.03|
|113383.13999999998|
| 42435.63|
| 46092.27|
| 30450.84_|
| 33077.82|
| 59759.68|
| 73376.94|
| 107774.28_|
| 58194.33|
| 18249395.0|
| 101910.75|
| 20498.12_|
| 40372.5|
| 97174.44_|
| 70897.32|
+------------------+
only showing top 20 rows
Column Num_of_Loan consists of unique values:
+-----------+
|Num_of_Loan|
+-----------+
| 1159|
| 1372|
| 1241|
| 926|
| 1265|
| 7|
| 447|
| 1_|
| 613|
| 574|
| 581|
| 1485|
| 462|
| 1171_|
| 54|
| 1008|
| 282|
| 940|
| 1412|
| 1496|
+-----------+
only showing top 20 rows
Column Num_of_Delayed_Payment consists of unique values:
+----------------------+
|Num_of_Delayed_Payment|
+----------------------+
| 2162|
| 829|
| 1572|
| 1473_|
| 3858|
| 2237_|
| 853|
| 2756|
| 800|
| 3368|
| 926|
| 666|
| 3200|
| 7|
| 1953|
| 4249|
| 3861_|
| 1_|
| 4262|
| 3491|
+----------------------+
only showing top 20 rows
Column Changed_Credit_Limit consists of unique values:
+--------------------+
|Changed_Credit_Limit|
+--------------------+
| 20.64|
| 28.79|
| 17.759999999999994|
| 13.87|
| 5.1099999999999985|
| 17.42|
| 3.3699999999999988|
| 7.16|
| 8.5|
| 10.7|
| 23.97|
| -1.77|
| 1.7199999999999998|
| 19.06|
| 1.5399999999999991|
| -4.95|
| -3.35|
| -3.85|
| -2.33|
| 15.920000000000002|
+--------------------+
only showing top 20 rows
Column Credit_Mix consists of unique values:
+----------+
|Credit_Mix|
+----------+
| _|
| Good|
| Bad|
| Standard|
+----------+
Column Outstanding_Debt consists of unique values:
+----------------+
|Outstanding_Debt|
+----------------+
| 2797.17|
| 1247.3|
| 919.98|
| 162.21|
| 429.12|
| 355.39|
| 1410.49|
| 244.5|
| 223.31|
| 827.59|
| 770.97|
| 1490.4|
| 1348.97|
| 700.43|
| 1368.27|
| 1112.8|
| 143.92|
| 1703.99|
| 2538.7|
| 816.39|
+----------------+
only showing top 20 rows
Column Amount_invested_monthly consists of unique values:
+-----------------------+
|Amount_invested_monthly|
+-----------------------+
| 298.1889114624804|
| 254.26037253709117|
| 162.57530838511798|
| 185.96036419707488|
| 83.43984726339356|
| 93.21312485406764|
| 676.2741446745866|
| 57.741131628175275|
| 50.89426938256466|
| 118.14743192537621|
| 138.37126129133998|
| 96.07291031084249|
| 598.2489360547404|
| 402.91701803112846|
| 36.679505318776606|
| 66.90170686409276|
| 768.9118214787355|
| 451.46146966353655|
| 623.1239775296488|
| 467.6140828227542|
+-----------------------+
only showing top 20 rows
Column Payment_Behaviour consists of unique values:
+--------------------+
| Payment_Behaviour|
+--------------------+
|Low_spent_Small_v...|
|High_spent_Medium...|
|High_spent_Small_...|
|Low_spent_Large_v...|
|Low_spent_Medium_...|
|High_spent_Large_...|
| !@9#%8|
+--------------------+
Column Monthly_Balance consists of unique values:
+------------------+
| Monthly_Balance|
+------------------+
| 682.5895811522233|
| 467.4934466012289|
| 860.5767671697744|
| 497.6292590355018|
| 491.0512896423376|
| 405.8771633172348|
| 47.81079412187853|
| 677.637152984246|
|339.83773691782534|
|245.56732968874363|
| 468.8080068392279|
|246.79355553278853|
| 278.4755891506759|
| 298.8369695331906|
|329.46984772308286|
|245.29153931150208|
|342.38145576581474|
|339.66939059607546|
| 482.7012017058438|
| 239.8168611686771|
+------------------+
only showing top 20 rows
Among all the columns that have underscore. The ones that need replacing are Age, Annual Income, Number of Loan, Number of Delayed Payments, Changed Credit Limit, Outstanding Debt, Amount invested monthly and Monthly Balance.
Credit Mix, Payment behavouir and Occupation will not be preprocssed by the removal of the underscore. This is because these three columns are string type columns, which the underscore either represent some form of value or the presence of it may not be as detriment to the column as an underscore being in a integer and numeric type column.
Furthermore, it is noted that credit mix has 4 unique values, 'Good', 'Bad', 'Standard' and '_'. Based on the print above, we can see that there are 20195 rows of data that is missing. Because of that, we can drop the column as a large portion the data will need to be synthesized, which will effect the result of the models.
# Add 'Credit Mix' into the drop column list
columns_to_drop.append('Credit_Mix')
# Remove unneeded columns
columns_with_underscore.remove('Payment_Behaviour')
columns_with_underscore.remove('Occupation')
columns_with_underscore.remove('Credit_Mix')
print(columns_with_underscore)['Age', 'Annual_Income', 'Num_of_Loan', 'Num_of_Delayed_Payment', 'Changed_Credit_Limit', 'Outstanding_Debt', 'Amount_invested_monthly', 'Monthly_Balance']# Loop through the columns with underscore
for column in columns_with_underscore:
# Store the changes into the main dataset
# Replace '_' with '', which means removing it
credit_score = credit_score\
.withColumn(
column,
F.regexp_replace(column, '_', '')
)
# Print to see its current datatype
print(credit_score.select(column))DataFrame[Age: string]
DataFrame[Annual_Income: string]
DataFrame[Num_of_Loan: string]
DataFrame[Num_of_Delayed_Payment: string]
DataFrame[Changed_Credit_Limit: string]
DataFrame[Outstanding_Debt: string]
DataFrame[Amount_invested_monthly: string]
DataFrame[Monthly_Balance: string]As shown above, the datatypes for most of the columns, except for Occupation, all of them are supposed to be integer or doulble type.
credit_score = credit_score.withColumn(
'Age',
col('Age').cast(IntegerType()))
credit_score = credit_score.withColumn(
'Annual_Income',
col('Annual_Income').cast(IntegerType()))
credit_score = credit_score.withColumn(
'Num_of_Loan',
col('Num_of_Loan').cast(IntegerType()))
credit_score = credit_score.withColumn(
'Num_of_Delayed_Payment',
col('Num_of_Delayed_Payment').cast(IntegerType()))
credit_score = credit_score.withColumn(
'Changed_Credit_Limit',
col('Changed_Credit_Limit').cast(IntegerType()))
credit_score = credit_score.withColumn(
'Outstanding_Debt',
col('Outstanding_Debt').cast(DoubleType()))
credit_score = credit_score.withColumn(
'Amount_invested_monthly',
col('Amount_invested_monthly').cast(DoubleType()))
credit_score = credit_score.withColumn(
'Monthly_Balance',
col('Monthly_Balance').cast(DoubleType()))
for column in columns_with_underscore:
print(credit_score.select(column))DataFrame[Age: int]
DataFrame[Annual_Income: int]
DataFrame[Num_of_Loan: int]
DataFrame[Num_of_Delayed_Payment: int]
DataFrame[Changed_Credit_Limit: int]
DataFrame[Outstanding_Debt: double]
DataFrame[Amount_invested_monthly: double]
DataFrame[Monthly_Balance: double]Filling inconsistent and missing values with most occuring value
The code below is able to handle both the missing values and the consistency of the data. The function below will group the columns by the customer ID and the intended column. Then, we can create another column that represents the occurence of the customer ID and the value of the intended column. With this, we can sort them according to the customer ID, and the count descendingly. This will cause the value of highest occurence for the customer to be on top. Then, when we use the dropDuplicates function, it will be able to remove the lower occurence values. This way, we generate a table that stores highest occuring value of a given customer. Then, we join this table to the main dataset, which will fill up initial null values or wrongly inserted values. The downside of this approach is that we are homogenizing the dataset and could lead to less unique values for the dataset.
def fill_with_most_occured(data, column):
correctStr = 'Cor'
# Group the data based on Customer_ID and the intended column
# Get the number of occurence (count) of the given value based on Customer ID
# Order ascendingly with Customer_ID and descendingly with (count)
groupData = credit_score.select('Customer_ID', column)\
.groupBy('Customer_ID', column)\
.count()\
.orderBy('Customer_ID', col('count').desc())
print('GroupData of ' + column + ' created.')
# Drop the duplicates
# Because the data is already arranged where the highest count will appear first
# Dropping the remaining will give us the value that occur the most
groupData = groupData.dropDuplicates(['Customer_ID'])\
.orderBy('Customer_ID')
print('GroupData of ' + column + '\'s "Customer_ID" duplicates dropped.')
# Renaming the ID and the intended column so that it will not mix with the
# main dataset columns
groupData = groupData.withColumnRenamed('Customer_ID', 'gdID')
groupData = groupData.withColumnRenamed(column, (correctStr + column))
print('GroupData columns renamed.')
# Join the Grouped Processed Data with the main dataset
data = data.join(
groupData,
on = (groupData['gdID'] == credit_score['Customer_ID']),
)
# Remove the unneeded columns that were from the Grouped Processed Data
data = data.drop(
'count',
'gdID',
column
)
# Rename the new column added
data = data.withColumnRenamed(
(correctStr + column),
column
)
# Output the Dataset
return dataBefore processing the missing and inconsistent values of each column, we will need to exclude the target variable or sometimes called label. The column that we want to predict, which is the credit score column. Based on the above cells, this column does not have any missing values or underscore in the columns. Furthermore, there is ony 3 unique values as well.
label_column = 'Credit_Score'
# See the distinct values
unique_value_dict['Credit_Score'][Row(Credit_Score='Good'),
Row(Credit_Score='Poor'),
Row(Credit_Score='Standard')]# Columns was initiated in the above cell
for column in columns:
if column in id_features or column == label_column:
continue
else:
credit_score = fill_with_most_occured(credit_score, column)
credit_score.cache()
credit_score = credit_score.checkpoint()
# Print the check if rows are affected
print(credit_score.count())
# Check if there are issues with the columns
credit_score.printSchema()GroupData of Age created.
GroupData of Age's "Customer_ID" duplicates dropped.
GroupData columns renamed.
GroupData of Occupation created.
GroupData of Occupation's "Customer_ID" duplicates dropped.
GroupData columns renamed.
GroupData of Annual_Income created.
GroupData of Annual_Income's "Customer_ID" duplicates dropped.
GroupData columns renamed.
GroupData of Monthly_Inhand_Salary created.
GroupData of Monthly_Inhand_Salary's "Customer_ID" duplicates dropped.
GroupData columns renamed.
GroupData of Num_Bank_Accounts created.
GroupData of Num_Bank_Accounts's "Customer_ID" duplicates dropped.
GroupData columns renamed.
GroupData of Num_Credit_Card created.
GroupData of Num_Credit_Card's "Customer_ID" duplicates dropped.
GroupData columns renamed.
GroupData of Interest_Rate created.
GroupData of Interest_Rate's "Customer_ID" duplicates dropped.
GroupData columns renamed.
GroupData of Num_of_Loan created.
GroupData of Num_of_Loan's "Customer_ID" duplicates dropped.
GroupData columns renamed.
GroupData of Type_of_Loan created.
GroupData of Type_of_Loan's "Customer_ID" duplicates dropped.
GroupData columns renamed.
GroupData of Delay_from_due_date created.
GroupData of Delay_from_due_date's "Customer_ID" duplicates dropped.
GroupData columns renamed.
GroupData of Num_of_Delayed_Payment created.
GroupData of Num_of_Delayed_Payment's "Customer_ID" duplicates dropped.
GroupData columns renamed.
GroupData of Changed_Credit_Limit created.
GroupData of Changed_Credit_Limit's "Customer_ID" duplicates dropped.
GroupData columns renamed.
GroupData of Num_Credit_Inquiries created.
GroupData of Num_Credit_Inquiries's "Customer_ID" duplicates dropped.
GroupData columns renamed.
GroupData of Credit_Mix created.
GroupData of Credit_Mix's "Customer_ID" duplicates dropped.
GroupData columns renamed.
GroupData of Outstanding_Debt created.
GroupData of Outstanding_Debt's "Customer_ID" duplicates dropped.
GroupData columns renamed.
GroupData of Credit_Utilization_Ratio created.
GroupData of Credit_Utilization_Ratio's "Customer_ID" duplicates dropped.
GroupData columns renamed.
GroupData of Credit_History_Age created.
GroupData of Credit_History_Age's "Customer_ID" duplicates dropped.
GroupData columns renamed.
GroupData of Payment_of_Min_Amount created.
GroupData of Payment_of_Min_Amount's "Customer_ID" duplicates dropped.
GroupData columns renamed.
GroupData of Total_EMI_per_month created.
GroupData of Total_EMI_per_month's "Customer_ID" duplicates dropped.
GroupData columns renamed.
GroupData of Amount_invested_monthly created.
GroupData of Amount_invested_monthly's "Customer_ID" duplicates dropped.
GroupData columns renamed.
GroupData of Payment_Behaviour created.
GroupData of Payment_Behaviour's "Customer_ID" duplicates dropped.
GroupData columns renamed.
GroupData of Monthly_Balance created.
GroupData of Monthly_Balance's "Customer_ID" duplicates dropped.
GroupData columns renamed.
100000
root
|-- ID: string (nullable = true)
|-- Customer_ID: string (nullable = true)
|-- Month: string (nullable = true)
|-- Name: string (nullable = true)
|-- SSN: string (nullable = true)
|-- Credit_Score: string (nullable = true)
|-- Age: integer (nullable = true)
|-- Occupation: string (nullable = true)
|-- Annual_Income: integer (nullable = true)
|-- Monthly_Inhand_Salary: double (nullable = true)
|-- Num_Bank_Accounts: integer (nullable = true)
|-- Num_Credit_Card: integer (nullable = true)
|-- Interest_Rate: integer (nullable = true)
|-- Num_of_Loan: integer (nullable = true)
|-- Type_of_Loan: string (nullable = true)
|-- Delay_from_due_date: integer (nullable = true)
|-- Num_of_Delayed_Payment: integer (nullable = true)
|-- Changed_Credit_Limit: integer (nullable = true)
|-- Num_Credit_Inquiries: double (nullable = true)
|-- Credit_Mix: string (nullable = true)
|-- Outstanding_Debt: double (nullable = true)
|-- Credit_Utilization_Ratio: double (nullable = true)
|-- Credit_History_Age: string (nullable = true)
|-- Payment_of_Min_Amount: string (nullable = true)
|-- Total_EMI_per_month: double (nullable = true)
|-- Amount_invested_monthly: double (nullable = true)
|-- Payment_Behaviour: string (nullable = true)
|-- Monthly_Balance: double (nullable = true)
Occupation
unique_value_dict['Occupation'][Row(Occupation='Scientist'),
Row(Occupation='Media_Manager'),
Row(Occupation='Musician'),
Row(Occupation='Lawyer'),
Row(Occupation='Teacher'),
Row(Occupation='Developer'),
Row(Occupation='Writer'),
Row(Occupation='Architect'),
Row(Occupation='Mechanic'),
Row(Occupation='Entrepreneur'),
Row(Occupation='Journalist'),
Row(Occupation='Doctor'),
Row(Occupation='Engineer'),
Row(Occupation='Accountant'),
Row(Occupation='Manager'),
Row(Occupation='_______')]It can be noted be that there are 15 unique values that can be used in the dataset. Having only 15 category for occupation. The downside of training with only 15 categorical data, is that the model will only know how to interpret these 15 occupation. But, column 'Occupation' seems like can be a big determinant to classifiying credit score, because clearly there are roles such 'Doctor' and 'Manager' might have better credit score because of their higher associated income. The decision the drop the column will be inconclusive at the moment.
unique_value_dict['Annual_Income'][Row(Annual_Income='18102.96'),
Row(Annual_Income='41516.64'),
Row(Annual_Income='10318159.0'),
Row(Annual_Income='33701.99_'),
Row(Annual_Income='64915.92'),
Row(Annual_Income='108457.74'),
Row(Annual_Income='29346.17'),
Row(Annual_Income='35389.89'),
Row(Annual_Income='77104.47'),
Row(Annual_Income='71617.92_'),
Row(Annual_Income='75992.7'),
Row(Annual_Income='45379.77_'),
Row(Annual_Income='9260.58'),
Row(Annual_Income='53315.28'),
Row(Annual_Income='70088.36'),
Row(Annual_Income='29180.37_'),
Row(Annual_Income='31306.48'),
Row(Annual_Income='142106.96_'),
Row(Annual_Income='54054.18'),
Row(Annual_Income='29337.5'),
Row(Annual_Income='144624.92'),
Row(Annual_Income='34888.64'),
Row(Annual_Income='133236.36_'),
Row(Annual_Income='43359.36'),
Row(Annual_Income='20104809.0'),
Row(Annual_Income='17709.31'),
Row(Annual_Income='140042.28'),
Row(Annual_Income='30564.96'),
Row(Annual_Income='60255.9'),
Row(Annual_Income='18836.23'),
Row(Annual_Income='19720.36_'),
Row(Annual_Income='135178.44'),
Row(Annual_Income='1127430.0'),
Row(Annual_Income='14045.15_'),
Row(Annual_Income='98983.17'),
Row(Annual_Income='35349.2'),
Row(Annual_Income='52410.5'),
Row(Annual_Income='17933.84'),
Row(Annual_Income='45749.06'),
Row(Annual_Income='60036.75'),
Row(Annual_Income='119643.12_'),
Row(Annual_Income='58511.78_'),
Row(Annual_Income='19005746.0'),
Row(Annual_Income='76428.0_'),
Row(Annual_Income='175127.04'),
Row(Annual_Income='73057.16_'),
Row(Annual_Income='18572.01'),
Row(Annual_Income='21009.425_'),
Row(Annual_Income='74557.58_'),
Row(Annual_Income='16540.38'),
Row(Annual_Income='8272.2'),
Row(Annual_Income='16578.115'),
Row(Annual_Income='14224.655'),
Row(Annual_Income='94454.1'),
Row(Annual_Income='96582.24'),
Row(Annual_Income='42399.03'),
Row(Annual_Income='113383.13999999998'),
Row(Annual_Income='42435.63'),
Row(Annual_Income='46092.27'),
Row(Annual_Income='30450.84_'),
Row(Annual_Income='33077.82'),
Row(Annual_Income='59759.68'),
Row(Annual_Income='73376.94'),
Row(Annual_Income='107774.28_'),
Row(Annual_Income='58194.33'),
Row(Annual_Income='18249395.0'),
Row(Annual_Income='101910.75'),
Row(Annual_Income='20498.12_'),
Row(Annual_Income='40372.5'),
Row(Annual_Income='97174.44_'),
Row(Annual_Income='70897.32'),
Row(Annual_Income='18925.44_'),
Row(Annual_Income='16360.215'),
Row(Annual_Income='17399.84_'),
Row(Annual_Income='10285.71'),
Row(Annual_Income='10952.32_'),
Row(Annual_Income='14822.81'),
Row(Annual_Income='37159.0'),
Row(Annual_Income='20247.61'),
Row(Annual_Income='95401.47'),
Row(Annual_Income='8983.565'),
Row(Annual_Income='17758.44'),
Row(Annual_Income='85494.5'),
Row(Annual_Income='91965.63'),
Row(Annual_Income='13864574.0'),
Row(Annual_Income='58416.36'),
Row(Annual_Income='31113.36'),
Row(Annual_Income='7689.5_'),
Row(Annual_Income='29453.84'),
Row(Annual_Income='56668.5'),
Row(Annual_Income='106168.77'),
Row(Annual_Income='39057.08'),
Row(Annual_Income='125264.96'),
Row(Annual_Income='26554.52'),
Row(Annual_Income='82382.62'),
Row(Annual_Income='33827.58'),
Row(Annual_Income='89342.58'),
Row(Annual_Income='586359.0'),
Row(Annual_Income='19257912.0'),
Row(Annual_Income='18549.28'),
Row(Annual_Income='108223.62'),
Row(Annual_Income='174179.64'),
Row(Annual_Income='25621.01_'),
Row(Annual_Income='20871.42_'),
Row(Annual_Income='31557.73'),
Row(Annual_Income='21053.37'),
Row(Annual_Income='58267.5_'),
Row(Annual_Income='88220.12'),
Row(Annual_Income='9211.98'),
Row(Annual_Income='16603.43'),
Row(Annual_Income='16538.39_'),
Row(Annual_Income='14161.865'),
Row(Annual_Income='15624.68'),
Row(Annual_Income='101926.95'),
Row(Annual_Income='120671.25_'),
Row(Annual_Income='31356.66'),
Row(Annual_Income='16756.18_'),
Row(Annual_Income='80264.88_'),
Row(Annual_Income='17568.98'),
Row(Annual_Income='37822.18_'),
Row(Annual_Income='17164.73'),
Row(Annual_Income='62380.11'),
Row(Annual_Income='10356.98_'),
Row(Annual_Income='43311.84'),
Row(Annual_Income='16472.87'),
Row(Annual_Income='57055.95'),
Row(Annual_Income='69865.22'),
Row(Annual_Income='17116.05'),
Row(Annual_Income='20025646.0'),
Row(Annual_Income='66176.67'),
Row(Annual_Income='57619.53'),
Row(Annual_Income='89190.56999999998'),
Row(Annual_Income='32357.41'),
Row(Annual_Income='51162.84'),
Row(Annual_Income='20196.67'),
Row(Annual_Income='25664.86'),
Row(Annual_Income='19835.93'),
Row(Annual_Income='62805.48'),
Row(Annual_Income='36729.93'),
Row(Annual_Income='107334.88_'),
Row(Annual_Income='16436.66_'),
Row(Annual_Income='18393.51'),
Row(Annual_Income='17277.78'),
Row(Annual_Income='61314.12'),
Row(Annual_Income='31606.46_'),
Row(Annual_Income='9871.225'),
Row(Annual_Income='172259.0'),
Row(Annual_Income='108767.37'),
Row(Annual_Income='20521.75_'),
Row(Annual_Income='33857.41'),
Row(Annual_Income='33089.51'),
Row(Annual_Income='17044.23_'),
Row(Annual_Income='129727.4'),
Row(Annual_Income='57080.22'),
Row(Annual_Income='80247.24_'),
Row(Annual_Income='31041.46'),
Row(Annual_Income='28105.59'),
Row(Annual_Income='43062.54_'),
Row(Annual_Income='179193.76'),
Row(Annual_Income='32827.25'),
Row(Annual_Income='10095.545_'),
Row(Annual_Income='89256.75'),
Row(Annual_Income='15496.42'),
Row(Annual_Income='37024.7'),
Row(Annual_Income='58962.2'),
Row(Annual_Income='14473189.0'),
Row(Annual_Income='21936192.0'),
Row(Annual_Income='14274.32'),
Row(Annual_Income='32412.72'),
Row(Annual_Income='18120.72'),
Row(Annual_Income='70154.85'),
Row(Annual_Income='19662.27'),
Row(Annual_Income='7472.54'),
Row(Annual_Income='9566.58'),
Row(Annual_Income='1729447.0'),
Row(Annual_Income='14613.65_'),
Row(Annual_Income='49880.68'),
Row(Annual_Income='29410.64_'),
Row(Annual_Income='141262.48_'),
Row(Annual_Income='43825.16'),
Row(Annual_Income='10355.675_'),
Row(Annual_Income='43704.55'),
Row(Annual_Income='20804.74'),
Row(Annual_Income='152574.76_'),
Row(Annual_Income='17887.47_'),
Row(Annual_Income='95389.71'),
Row(Annual_Income='18598.17'),
Row(Annual_Income='37002.58_'),
Row(Annual_Income='41675.64'),
Row(Annual_Income='30696.33'),
Row(Annual_Income='17131.345_'),
Row(Annual_Income='37182.62'),
Row(Annual_Income='2597096.0'),
Row(Annual_Income='30617.5_'),
Row(Annual_Income='27685.04_'),
Row(Annual_Income='86584.74'),
Row(Annual_Income='107545.2_'),
Row(Annual_Income='16934892.0'),
Row(Annual_Income='7534.185'),
Row(Annual_Income='36685.74'),
Row(Annual_Income='9817.065'),
Row(Annual_Income='10455.585'),
Row(Annual_Income='35802.82'),
Row(Annual_Income='15516.87'),
Row(Annual_Income='94587.66'),
Row(Annual_Income='14540.485'),
Row(Annual_Income='24821.36_'),
Row(Annual_Income='14956.12'),
Row(Annual_Income='14219.345'),
Row(Annual_Income='50891.94'),
Row(Annual_Income='62253.54'),
Row(Annual_Income='9022.16_'),
Row(Annual_Income='113048.46'),
Row(Annual_Income='10454.79_'),
Row(Annual_Income='28742.57_'),
Row(Annual_Income='109545.63'),
Row(Annual_Income='34476.68_'),
Row(Annual_Income='38856.53'),
Row(Annual_Income='16297.34'),
Row(Annual_Income='39887.22'),
Row(Annual_Income='14129.76'),
Row(Annual_Income='66169.56'),
Row(Annual_Income='94052.22'),
Row(Annual_Income='63635.12_'),
Row(Annual_Income='61654.84'),
Row(Annual_Income='9197.37'),
Row(Annual_Income='56510.8_'),
Row(Annual_Income='81903.8_'),
Row(Annual_Income='39460.01'),
Row(Annual_Income='131890.95_'),
Row(Annual_Income='9542.28_'),
Row(Annual_Income='15868.97'),
Row(Annual_Income='9494942.0'),
Row(Annual_Income='15652.99_'),
Row(Annual_Income='8180388.0'),
Row(Annual_Income='67726.17_'),
Row(Annual_Income='124814.04'),
Row(Annual_Income='58053.27'),
Row(Annual_Income='14619.875'),
Row(Annual_Income='3086064.0'),
Row(Annual_Income='43600.04'),
Row(Annual_Income='17800057.0'),
Row(Annual_Income='16891.04'),
Row(Annual_Income='110147.52'),
Row(Annual_Income='14241.48'),
Row(Annual_Income='31994.01_'),
Row(Annual_Income='21353.19_'),
Row(Annual_Income='14969275.0'),
Row(Annual_Income='46717.32_'),
Row(Annual_Income='20695.58'),
Row(Annual_Income='14807.4'),
Row(Annual_Income='4293824.0'),
Row(Annual_Income='14453.63_'),
Row(Annual_Income='114467.67'),
Row(Annual_Income='45070.56_'),
Row(Annual_Income='44498.78_'),
Row(Annual_Income='133455.93'),
Row(Annual_Income='20616.96'),
Row(Annual_Income='121622.84'),
Row(Annual_Income='58246.4'),
Row(Annual_Income='35883.18'),
Row(Annual_Income='9511.795_'),
Row(Annual_Income='110468.49'),
Row(Annual_Income='41550.06'),
Row(Annual_Income='67512.6'),
Row(Annual_Income='71843.52_'),
Row(Annual_Income='38334.61_'),
Row(Annual_Income='40035.02_'),
Row(Annual_Income='13982.725'),
Row(Annual_Income='15671.96_'),
Row(Annual_Income='83990.68'),
Row(Annual_Income='80213.4'),
Row(Annual_Income='9474.16'),
Row(Annual_Income='48646.5'),
Row(Annual_Income='75354.48_'),
Row(Annual_Income='133424.52_'),
Row(Annual_Income='27395.53'),
Row(Annual_Income='16907.7'),
Row(Annual_Income='115649.52_'),
Row(Annual_Income='3061925.0'),
Row(Annual_Income='18322.56'),
Row(Annual_Income='57889.44_'),
Row(Annual_Income='16559.985'),
Row(Annual_Income='19375.76_'),
Row(Annual_Income='35263.09_'),
Row(Annual_Income='952323.0'),
Row(Annual_Income='42321.5_'),
Row(Annual_Income='15618.52_'),
Row(Annual_Income='37361.02'),
Row(Annual_Income='79524.64'),
Row(Annual_Income='35771.08'),
Row(Annual_Income='22978.67'),
Row(Annual_Income='63362.6'),
Row(Annual_Income='104367.21'),
Row(Annual_Income='8103.425'),
Row(Annual_Income='128919.96'),
Row(Annual_Income='21120.835'),
Row(Annual_Income='32495.66'),
Row(Annual_Income='40923.34'),
Row(Annual_Income='79794.6'),
Row(Annual_Income='50649.60000000001_'),
Row(Annual_Income='21421.73'),
Row(Annual_Income='17807.935_'),
Row(Annual_Income='31237.94_'),
Row(Annual_Income='58048.82'),
Row(Annual_Income='8295.87'),
Row(Annual_Income='17680.69'),
Row(Annual_Income='14027.195_'),
Row(Annual_Income='109364.08'),
Row(Annual_Income='15867.45_'),
Row(Annual_Income='36165.18'),
Row(Annual_Income='24466.5'),
Row(Annual_Income='38964.65_'),
Row(Annual_Income='49400.52_'),
Row(Annual_Income='19805347.0'),
Row(Annual_Income='32700.0'),
Row(Annual_Income='34081.38_'),
Row(Annual_Income='42220.39'),
Row(Annual_Income='18759.61'),
Row(Annual_Income='17450.0'),
Row(Annual_Income='17654.72'),
Row(Annual_Income='14292.96'),
Row(Annual_Income='16632.745'),
Row(Annual_Income='36366.68'),
Row(Annual_Income='18623.23'),
Row(Annual_Income='34989.38'),
Row(Annual_Income='14274.54_'),
Row(Annual_Income='41012.42'),
Row(Annual_Income='75723.81'),
Row(Annual_Income='42277.83'),
Row(Annual_Income='27026.95'),
Row(Annual_Income='100268.73'),
Row(Annual_Income='68090.85'),
Row(Annual_Income='32401.4_'),
Row(Annual_Income='20282.38'),
Row(Annual_Income='7139.64'),
Row(Annual_Income='116690.94_'),
Row(Annual_Income='61115.16'),
Row(Annual_Income='14696.62'),
Row(Annual_Income='18393.51_'),
Row(Annual_Income='179068.04'),
Row(Annual_Income='28056.94'),
Row(Annual_Income='40216.62'),
Row(Annual_Income='15762.82_'),
Row(Annual_Income='81491.94_'),
Row(Annual_Income='16063.455'),
Row(Annual_Income='8459.02'),
Row(Annual_Income='20040.64'),
Row(Annual_Income='57943.41'),
Row(Annual_Income='22019.77'),
Row(Annual_Income='69428.72'),
Row(Annual_Income='20985.48'),
Row(Annual_Income='81815.31'),
Row(Annual_Income='88940.76_'),
Row(Annual_Income='102737.63999999998_'),
Row(Annual_Income='31604.58'),
Row(Annual_Income='53387.88_'),
Row(Annual_Income='119016.88'),
Row(Annual_Income='72886.08'),
Row(Annual_Income='77047.4'),
Row(Annual_Income='32200.64_'),
Row(Annual_Income='29378.06'),
Row(Annual_Income='66995.86'),
Row(Annual_Income='47984.19'),
Row(Annual_Income='18140.575'),
Row(Annual_Income='31217.34'),
Row(Annual_Income='61016.88'),
Row(Annual_Income='58427.31_'),
Row(Annual_Income='28045.82'),
Row(Annual_Income='17565.58_'),
Row(Annual_Income='42387.54'),
Row(Annual_Income='39369.68'),
Row(Annual_Income='9126.455'),
Row(Annual_Income='78244.68'),
Row(Annual_Income='28033.88'),
Row(Annual_Income='22311.99_'),
Row(Annual_Income='43493.93'),
Row(Annual_Income='18888.46'),
Row(Annual_Income='12833.68'),
Row(Annual_Income='130393.96'),
Row(Annual_Income='59039.52'),
Row(Annual_Income='21809.35_'),
Row(Annual_Income='73579.8'),
Row(Annual_Income='144396.68'),
Row(Annual_Income='28204.79_'),
Row(Annual_Income='88120.12_'),
Row(Annual_Income='16603.995_'),
Row(Annual_Income='20674.5'),
Row(Annual_Income='128698.76_'),
Row(Annual_Income='19737077.0'),
Row(Annual_Income='166621.84_'),
Row(Annual_Income='15811.83'),
Row(Annual_Income='21671.53'),
Row(Annual_Income='55448.74_'),
Row(Annual_Income='91404.54'),
Row(Annual_Income='57792.3'),
Row(Annual_Income='39292.44'),
Row(Annual_Income='21009.425'),
Row(Annual_Income='19879.05'),
Row(Annual_Income='24436.53'),
Row(Annual_Income='35971.49'),
Row(Annual_Income='28954.04_'),
Row(Annual_Income='126514.72'),
Row(Annual_Income='64036.88_'),
Row(Annual_Income='74733.44_'),
Row(Annual_Income='7792.475'),
Row(Annual_Income='36154.19'),
Row(Annual_Income='15713.83_'),
Row(Annual_Income='19870800.0'),
Row(Annual_Income='35205.24_'),
Row(Annual_Income='20821.8'),
Row(Annual_Income='34336.93'),
Row(Annual_Income='86446.44_'),
Row(Annual_Income='55907.52_'),
Row(Annual_Income='84114.48'),
Row(Annual_Income='49417.52_'),
Row(Annual_Income='15285.495_'),
Row(Annual_Income='16364.675'),
Row(Annual_Income='31400.96'),
Row(Annual_Income='20415.52_'),
Row(Annual_Income='83722.16'),
Row(Annual_Income='16210.85'),
Row(Annual_Income='52982.06999999999'),
Row(Annual_Income='44812.78'),
Row(Annual_Income='70556.92'),
Row(Annual_Income='14810.545_'),
Row(Annual_Income='65500.84'),
Row(Annual_Income='105226.98'),
Row(Annual_Income='31751.78_'),
Row(Annual_Income='91018.76'),
Row(Annual_Income='14696.62_'),
Row(Annual_Income='61793.46'),
Row(Annual_Income='15333374.0'),
Row(Annual_Income='14784.45'),
Row(Annual_Income='34257.69'),
Row(Annual_Income='37539.84'),
Row(Annual_Income='119877.15'),
Row(Annual_Income='44219.46'),
Row(Annual_Income='19435.6_'),
Row(Annual_Income='107595.68_'),
Row(Annual_Income='53876.66_'),
Row(Annual_Income='9956.155_'),
Row(Annual_Income='20974.05'),
Row(Annual_Income='116114.76'),
Row(Annual_Income='16923.73'),
Row(Annual_Income='67321.96'),
Row(Annual_Income='174098.52_'),
Row(Annual_Income='59658.09_'),
Row(Annual_Income='10737.365'),
Row(Annual_Income='116798.36'),
Row(Annual_Income='29489.63'),
Row(Annual_Income='17091.96'),
Row(Annual_Income='58820.44'),
Row(Annual_Income='57101.1'),
Row(Annual_Income='15427.215_'),
Row(Annual_Income='36372.21'),
Row(Annual_Income='95895.72'),
Row(Annual_Income='38821.54'),
Row(Annual_Income='22159.95'),
Row(Annual_Income='35917.16'),
Row(Annual_Income='21207973.0'),
Row(Annual_Income='16021.14'),
Row(Annual_Income='15005.31'),
Row(Annual_Income='22283.07'),
Row(Annual_Income='34319.66'),
Row(Annual_Income='70391.92'),
Row(Annual_Income='88165.12'),
Row(Annual_Income='30195.47'),
Row(Annual_Income='39928.5_'),
Row(Annual_Income='14634.1'),
Row(Annual_Income='34570.08'),
Row(Annual_Income='84687.54'),
Row(Annual_Income='95267.49'),
Row(Annual_Income='78056.04_'),
Row(Annual_Income='114300.32'),
Row(Annual_Income='58979.34'),
Row(Annual_Income='10024.955'),
Row(Annual_Income='20675.475_'),
Row(Annual_Income='14749.06'),
Row(Annual_Income='31517.47'),
Row(Annual_Income='62313.54'),
Row(Annual_Income='115645.65'),
Row(Annual_Income='165798.2'),
Row(Annual_Income='33828.19'),
Row(Annual_Income='21761.49'),
Row(Annual_Income='9001.345'),
Row(Annual_Income='114919.56_'),
Row(Annual_Income='62475.66'),
Row(Annual_Income='15165.14'),
Row(Annual_Income='8794.49'),
Row(Annual_Income='81887.8'),
Row(Annual_Income='98087.76'),
Row(Annual_Income='15291.67_'),
Row(Annual_Income='3449550.0'),
Row(Annual_Income='14283.665'),
Row(Annual_Income='14310.25'),
Row(Annual_Income='16045.125'),
Row(Annual_Income='123828.52'),
Row(Annual_Income='60552.76'),
Row(Annual_Income='38539.57_'),
Row(Annual_Income='50811.27'),
Row(Annual_Income='115800.54'),
Row(Annual_Income='17975.32'),
Row(Annual_Income='35853.56_'),
Row(Annual_Income='29344.53_'),
Row(Annual_Income='98962.77'),
Row(Annual_Income='63030.88'),
Row(Annual_Income='87636.03'),
Row(Annual_Income='19092.79'),
Row(Annual_Income='38103.74_'),
Row(Annual_Income='71903.26_'),
Row(Annual_Income='13032.705'),
Row(Annual_Income='72849.56_'),
Row(Annual_Income='73910.61'),
Row(Annual_Income='19569.27'),
Row(Annual_Income='71660.3_'),
Row(Annual_Income='7619.09_'),
Row(Annual_Income='131990.84_'),
Row(Annual_Income='20290.79_'),
Row(Annual_Income='17001.68_'),
Row(Annual_Income='8007.85'),
Row(Annual_Income='55473.18000000001_'),
Row(Annual_Income='3770651.0'),
Row(Annual_Income='60189.06'),
Row(Annual_Income='33806.55'),
Row(Annual_Income='16678.98_'),
Row(Annual_Income='98459.7'),
Row(Annual_Income='43430.88'),
Row(Annual_Income='5388987.0'),
Row(Annual_Income='17816.75'),
Row(Annual_Income='58382.0'),
Row(Annual_Income='19127.84'),
Row(Annual_Income='43609.13'),
Row(Annual_Income='14266.53'),
Row(Annual_Income='103007.7'),
Row(Annual_Income='55071.72'),
Row(Annual_Income='19575.89'),
Row(Annual_Income='142277.72'),
Row(Annual_Income='140357.32'),
Row(Annual_Income='48008.07'),
Row(Annual_Income='32991.92'),
Row(Annual_Income='27909.81'),
Row(Annual_Income='44447.88'),
Row(Annual_Income='60878.97'),
Row(Annual_Income='29041.4'),
Row(Annual_Income='121197.9'),
Row(Annual_Income='16733.85'),
Row(Annual_Income='106824.68'),
Row(Annual_Income='20823.28'),
Row(Annual_Income='146861.12_'),
Row(Annual_Income='97635.87_'),
Row(Annual_Income='125977.6'),
Row(Annual_Income='16827.15'),
Row(Annual_Income='26460.7'),
Row(Annual_Income='37361.02_'),
Row(Annual_Income='28630.01'),
Row(Annual_Income='70175.78'),
Row(Annual_Income='12498.945'),
Row(Annual_Income='11938.1'),
Row(Annual_Income='80541.51'),
Row(Annual_Income='120368.32_'),
Row(Annual_Income='138206.04'),
Row(Annual_Income='122452.65'),
Row(Annual_Income='15605.73_'),
Row(Annual_Income='10381.565_'),
Row(Annual_Income='16054.06'),
Row(Annual_Income='34849.62_'),
Row(Annual_Income='101453.49'),
Row(Annual_Income='3485700.0'),
Row(Annual_Income='19134169.0'),
Row(Annual_Income='122835.52'),
Row(Annual_Income='54284.94'),
Row(Annual_Income='11810.515_'),
Row(Annual_Income='29485.44'),
Row(Annual_Income='42989.27'),
Row(Annual_Income='121187.49'),
Row(Annual_Income='24436.53_'),
Row(Annual_Income='19852.09_'),
Row(Annual_Income='17576.52_'),
Row(Annual_Income='20574.47'),
Row(Annual_Income='16367214.0'),
Row(Annual_Income='144881.68'),
Row(Annual_Income='9983.345'),
Row(Annual_Income='10034.55_'),
Row(Annual_Income='65454.42'),
Row(Annual_Income='21484.035'),
Row(Annual_Income='45421.38'),
Row(Annual_Income='33835.16'),
Row(Annual_Income='30081.37'),
Row(Annual_Income='19199.49'),
Row(Annual_Income='83457.76'),
Row(Annual_Income='21313.765'),
Row(Annual_Income='38868.12'),
Row(Annual_Income='70939.34_'),
Row(Annual_Income='37570.83_'),
Row(Annual_Income='56183.79_'),
Row(Annual_Income='15088.35'),
Row(Annual_Income='46352.82_'),
Row(Annual_Income='66361.76'),
Row(Annual_Income='28022.9'),
Row(Annual_Income='37227.24'),
Row(Annual_Income='15723.705'),
Row(Annual_Income='18412.85'),
Row(Annual_Income='49346.88'),
Row(Annual_Income='19223.44'),
Row(Annual_Income='17517.55_'),
Row(Annual_Income='16029346.0'),
Row(Annual_Income='33477.64'),
Row(Annual_Income='20515.94'),
Row(Annual_Income='29949.1'),
Row(Annual_Income='30366.16_'),
Row(Annual_Income='128675.76'),
Row(Annual_Income='71703.22'),
Row(Annual_Income='33588.38'),
Row(Annual_Income='48101.13'),
Row(Annual_Income='93390.44'),
Row(Annual_Income='89338.36'),
Row(Annual_Income='15580.41'),
Row(Annual_Income='38334.61'),
Row(Annual_Income='48824.14_'),
Row(Annual_Income='27286.53_'),
Row(Annual_Income='120922.26'),
Row(Annual_Income='20576.69_'),
Row(Annual_Income='87246.15'),
Row(Annual_Income='79357.14_'),
Row(Annual_Income='37346.16'),
Row(Annual_Income='32227.77'),
Row(Annual_Income='56990.6'),
Row(Annual_Income='31604.58_'),
Row(Annual_Income='31751.83_'),
Row(Annual_Income='33057.46_'),
Row(Annual_Income='71015.06999999999'),
Row(Annual_Income='12975.96_'),
Row(Annual_Income='49116.74'),
Row(Annual_Income='146861.12'),
Row(Annual_Income='38955.5'),
Row(Annual_Income='8128.065'),
Row(Annual_Income='11924.59'),
Row(Annual_Income='58558.86'),
Row(Annual_Income='16477.55'),
Row(Annual_Income='38655.1'),
Row(Annual_Income='70391.92_'),
Row(Annual_Income='90292.28'),
Row(Annual_Income='41695.76'),
Row(Annual_Income='64355.72'),
Row(Annual_Income='17346.16'),
Row(Annual_Income='117827.22'),
Row(Annual_Income='129758.24_'),
Row(Annual_Income='9706.79_'),
Row(Annual_Income='126559.52_'),
Row(Annual_Income='71536.52'),
Row(Annual_Income='32152.97'),
Row(Annual_Income='56135.76_'),
Row(Annual_Income='13547543.0'),
Row(Annual_Income='109480.98'),
Row(Annual_Income='35746.07'),
Row(Annual_Income='18525.13'),
Row(Annual_Income='82668.78'),
Row(Annual_Income='14982.0'),
Row(Annual_Income='63901.05'),
Row(Annual_Income='17805.15'),
Row(Annual_Income='8052.79'),
Row(Annual_Income='177560.68_'),
Row(Annual_Income='17421.64'),
Row(Annual_Income='20048.23_'),
Row(Annual_Income='52395.84_'),
Row(Annual_Income='19436.305'),
Row(Annual_Income='27635.39'),
Row(Annual_Income='93345.76'),
Row(Annual_Income='72305.9_'),
Row(Annual_Income='16297.34_'),
Row(Annual_Income='32520.93'),
Row(Annual_Income='28005.44'),
Row(Annual_Income='17223.875_'),
Row(Annual_Income='71830.0'),
Row(Annual_Income='13461.25_'),
Row(Annual_Income='15629722.0'),
Row(Annual_Income='38839.22_'),
Row(Annual_Income='9846.715_'),
Row(Annual_Income='34269.74_'),
Row(Annual_Income='36549.68'),
Row(Annual_Income='84001.66_'),
Row(Annual_Income='28485.76'),
Row(Annual_Income='15678.385'),
Row(Annual_Income='1888622.0'),
Row(Annual_Income='19604.35_'),
Row(Annual_Income='123800.8_'),
Row(Annual_Income='24460.96'),
Row(Annual_Income='34058.47_'),
Row(Annual_Income='17640.42_'),
Row(Annual_Income='18282.34_'),
Row(Annual_Income='50212.71'),
Row(Annual_Income='36403.98_'),
Row(Annual_Income='152574.76'),
Row(Annual_Income='61634.54_'),
Row(Annual_Income='40881.38_'),
Row(Annual_Income='36320.13'),
Row(Annual_Income='31151.46_'),
Row(Annual_Income='55444.56_'),
Row(Annual_Income='27318.32'),
Row(Annual_Income='21863.8'),
Row(Annual_Income='46271.32'),
Row(Annual_Income='32876.7_'),
Row(Annual_Income='29038.58'),
Row(Annual_Income='16481.42_'),
Row(Annual_Income='21963.845'),
Row(Annual_Income='40633.86'),
Row(Annual_Income='51886.18'),
Row(Annual_Income='98035.14'),
Row(Annual_Income='31276.27'),
Row(Annual_Income='77945.08'),
Row(Annual_Income='18983.07_'),
Row(Annual_Income='81168.84'),
Row(Annual_Income='102927.08'),
Row(Annual_Income='17682.71_'),
Row(Annual_Income='60423.56999999999'),
Row(Annual_Income='40453.85'),
Row(Annual_Income='165396.2'),
Row(Annual_Income='8845.965'),
Row(Annual_Income='77233.44'),
Row(Annual_Income='9360.515_'),
Row(Annual_Income='121187.49_'),
Row(Annual_Income='29095.94'),
Row(Annual_Income='18157.95'),
Row(Annual_Income='34290.12_'),
Row(Annual_Income='33335.24_'),
Row(Annual_Income='33447.42'),
Row(Annual_Income='36591.25_'),
Row(Annual_Income='57439.12'),
Row(Annual_Income='35205.24'),
Row(Annual_Income='41812.32_'),
Row(Annual_Income='16322.12_'),
Row(Annual_Income='41113.35'),
Row(Annual_Income='1354835.0'),
Row(Annual_Income='138722.36_'),
Row(Annual_Income='43592.45_'),
Row(Annual_Income='19653.61'),
Row(Annual_Income='68845.08'),
Row(Annual_Income='30128.6_'),
Row(Annual_Income='24376.2_'),
Row(Annual_Income='19632.01'),
Row(Annual_Income='23459.45_'),
Row(Annual_Income='98646.36000000002'),
Row(Annual_Income='14378.24'),
Row(Annual_Income='23973.16'),
Row(Annual_Income='52475.7'),
Row(Annual_Income='60552.24'),
Row(Annual_Income='7703.635'),
Row(Annual_Income='35059.2'),
Row(Annual_Income='18894.02'),
Row(Annual_Income='44789.64_'),
Row(Annual_Income='19722.7'),
Row(Annual_Income='40023.81'),
Row(Annual_Income='97009.44'),
Row(Annual_Income='53466.60000000001'),
Row(Annual_Income='11687.925'),
Row(Annual_Income='30771.54'),
Row(Annual_Income='34552.7'),
Row(Annual_Income='9812.96'),
Row(Annual_Income='86529.48'),
Row(Annual_Income='52042.32_'),
Row(Annual_Income='40972.04'),
Row(Annual_Income='59018.58'),
Row(Annual_Income='36136.49_'),
Row(Annual_Income='15548.34'),
Row(Annual_Income='105150.2'),
Row(Annual_Income='28127.13_'),
Row(Annual_Income='9857.29_'),
Row(Annual_Income='9695.47'),
Row(Annual_Income='31729.38'),
Row(Annual_Income='81165.56'),
Row(Annual_Income='8736.19_'),
Row(Annual_Income='20005.22'),
Row(Annual_Income='82840.24_'),
Row(Annual_Income='17750.19'),
Row(Annual_Income='173968.96'),
Row(Annual_Income='15989.085'),
Row(Annual_Income='33835.16_'),
Row(Annual_Income='56604.96_'),
Row(Annual_Income='16454.75'),
Row(Annual_Income='17780.69'),
Row(Annual_Income='54167.61_'),
Row(Annual_Income='42237.36'),
Row(Annual_Income='46036.35000000001'),
Row(Annual_Income='32382.37'),
Row(Annual_Income='19455.49'),
Row(Annual_Income='31223.33_'),
Row(Annual_Income='106695.48'),
Row(Annual_Income='51340.92'),
Row(Annual_Income='44572.43_'),
Row(Annual_Income='43270.47_'),
Row(Annual_Income='111112.76'),
Row(Annual_Income='55473.18000000001'),
Row(Annual_Income='17715.66'),
Row(Annual_Income='66560.22_'),
Row(Annual_Income='34185.14'),
Row(Annual_Income='28481.67'),
Row(Annual_Income='44464.37'),
Row(Annual_Income='12186.425'),
Row(Annual_Income='137428.16'),
Row(Annual_Income='31408.15_'),
Row(Annual_Income='20870.46_'),
Row(Annual_Income='171280.88_'),
Row(Annual_Income='14906.56'),
Row(Annual_Income='33765.68_'),
Row(Annual_Income='30355.01'),
Row(Annual_Income='34094.94'),
Row(Annual_Income='35006.57'),
Row(Annual_Income='69388.26'),
Row(Annual_Income='87746.92_'),
Row(Annual_Income='126262.12'),
Row(Annual_Income='152947.12_'),
Row(Annual_Income='98313.12'),
Row(Annual_Income='36913.88_'),
Row(Annual_Income='95949.4'),
Row(Annual_Income='17923.435'),
Row(Annual_Income='39656.72'),
Row(Annual_Income='144342.8'),
Row(Annual_Income='115105.56'),
Row(Annual_Income='57738.06_'),
Row(Annual_Income='17831.05_'),
Row(Annual_Income='20723.8'),
Row(Annual_Income='40626.05_'),
Row(Annual_Income='40896.9'),
Row(Annual_Income='18426.025'),
Row(Annual_Income='35295.07'),
Row(Annual_Income='56070.92'),
Row(Annual_Income='125027.24'),
Row(Annual_Income='38269.83'),
Row(Annual_Income='22918.52'),
Row(Annual_Income='32507.89'),
Row(Annual_Income='19193.42'),
Row(Annual_Income='16254.6'),
Row(Annual_Income='2201567.0'),
Row(Annual_Income='19821.65'),
Row(Annual_Income='102131.04'),
Row(Annual_Income='34963.82_'),
Row(Annual_Income='34217.66'),
Row(Annual_Income='62896.78'),
Row(Annual_Income='96027.16'),
Row(Annual_Income='15279.43'),
Row(Annual_Income='7905.96_'),
Row(Annual_Income='10774.095'),
Row(Annual_Income='127928.68'),
Row(Annual_Income='39558.23'),
Row(Annual_Income='58306.26_'),
Row(Annual_Income='84373.31999999999_'),
Row(Annual_Income='20760.75'),
Row(Annual_Income='59649.39_'),
Row(Annual_Income='19827.36'),
Row(Annual_Income='19761.79'),
Row(Annual_Income='61970.81999999999_'),
Row(Annual_Income='10882.8'),
Row(Annual_Income='9536.42_'),
Row(Annual_Income='29437.24_'),
Row(Annual_Income='41319.07_'),
Row(Annual_Income='109182.72'),
Row(Annual_Income='43534.9'),
Row(Annual_Income='72936.68'),
Row(Annual_Income='11766033.0'),
Row(Annual_Income='20090.02_'),
Row(Annual_Income='71518.92_'),
Row(Annual_Income='17692.26'),
Row(Annual_Income='20803030.0'),
Row(Annual_Income='79264.86'),
Row(Annual_Income='64845.8'),
Row(Annual_Income='141477.56'),
Row(Annual_Income='103316.76'),
Row(Annual_Income='106770.21'),
Row(Annual_Income='14185.66_'),
Row(Annual_Income='102665.07_'),
Row(Annual_Income='156608.6'),
Row(Annual_Income='17373.39_'),
Row(Annual_Income='61732.23'),
Row(Annual_Income='172441.08'),
Row(Annual_Income='88044.6'),
Row(Annual_Income='142544.36'),
Row(Annual_Income='3656455.0'),
Row(Annual_Income='20592.97'),
Row(Annual_Income='45488.94'),
Row(Annual_Income='23692.52_'),
Row(Annual_Income='127706.55_'),
Row(Annual_Income='17889.32'),
Row(Annual_Income='12349.37_'),
Row(Annual_Income='30637.13_'),
Row(Annual_Income='8826.66'),
Row(Annual_Income='15923.295_'),
Row(Annual_Income='84120.45000000001'),
Row(Annual_Income='36990.53_'),
Row(Annual_Income='116611.8'),
Row(Annual_Income='60176.61_'),
Row(Annual_Income='81463.6'),
Row(Annual_Income='17393.305'),
Row(Annual_Income='70737.78'),
Row(Annual_Income='10585.1'),
Row(Annual_Income='20961.27'),
Row(Annual_Income='22219.57_'),
Row(Annual_Income='74008.84'),
Row(Annual_Income='20849.21_'),
Row(Annual_Income='47689.47_'),
Row(Annual_Income='97791.42'),
Row(Annual_Income='19300.34'),
Row(Annual_Income='30346.35_'),
Row(Annual_Income='65778.22'),
Row(Annual_Income='155726.76'),
Row(Annual_Income='20474.27'),
Row(Annual_Income='148990.16'),
Row(Annual_Income='63149.2_'),
Row(Annual_Income='17727.93'),
Row(Annual_Income='10132.985'),
Row(Annual_Income='16341.075'),
Row(Annual_Income='39094.34_'),
Row(Annual_Income='45408.84'),
Row(Annual_Income='10401.21'),
Row(Annual_Income='18940892.0'),
Row(Annual_Income='102626.97'),
Row(Annual_Income='19599.81'),
Row(Annual_Income='96882.93'),
Row(Annual_Income='16397.44'),
Row(Annual_Income='179987.28_'),
Row(Annual_Income='18122.37_'),
Row(Annual_Income='22050.56_'),
Row(Annual_Income='22320.13'),
Row(Annual_Income='83218.0'),
Row(Annual_Income='7079.32'),
Row(Annual_Income='44789.64'),
Row(Annual_Income='94545.75'),
Row(Annual_Income='44158.03'),
Row(Annual_Income='7765.195_'),
Row(Annual_Income='18798.83'),
Row(Annual_Income='57473.58_'),
Row(Annual_Income='26508.58'),
Row(Annual_Income='33755.94_'),
Row(Annual_Income='152895.44_'),
Row(Annual_Income='18579.36_'),
Row(Annual_Income='15915.73'),
Row(Annual_Income='17235.115'),
Row(Annual_Income='69860.18'),
Row(Annual_Income='43115.38_'),
Row(Annual_Income='171292.56'),
Row(Annual_Income='79878.52'),
Row(Annual_Income='29605.9'),
Row(Annual_Income='32430.82'),
Row(Annual_Income='18153.18'),
Row(Annual_Income='115362.96'),
Row(Annual_Income='30685.78'),
Row(Annual_Income='122307.96_'),
Row(Annual_Income='114948.0'),
Row(Annual_Income='24278.95'),
Row(Annual_Income='100536.2'),
Row(Annual_Income='17943.38'),
Row(Annual_Income='28762.68'),
Row(Annual_Income='61627.35000000001_'),
Row(Annual_Income='106444.68'),
Row(Annual_Income='83384.2_'),
Row(Annual_Income='16852.635'),
Row(Annual_Income='32663.41'),
Row(Annual_Income='36490.98'),
Row(Annual_Income='20639.79'),
Row(Annual_Income='20949.58_'),
Row(Annual_Income='140254.28'),
Row(Annual_Income='127921.84'),
Row(Annual_Income='32900.5_'),
Row(Annual_Income='60781.48_'),
Row(Annual_Income='38577.6'),
Row(Annual_Income='148841.56_'),
Row(Annual_Income='83675.56'),
Row(Annual_Income='87027.66_'),
Row(Annual_Income='14455.15_'),
Row(Annual_Income='86775.4'),
Row(Annual_Income='20591.2_'),
Row(Annual_Income='22438.27'),
Row(Annual_Income='2526215.0'),
Row(Annual_Income='28784.53'),
Row(Annual_Income='138154.96'),
Row(Annual_Income='104722.71'),
Row(Annual_Income='30760.15'),
Row(Annual_Income='10240.42'),
Row(Annual_Income='52770.12'),
Row(Annual_Income='10244.8'),
Row(Annual_Income='13840.485'),
Row(Annual_Income='31254.23'),
Row(Annual_Income='39560.62_'),
Row(Annual_Income='30498.76_'),
Row(Annual_Income='9377.445'),
Row(Annual_Income='85840.34_'),
Row(Annual_Income='25040.59'),
Row(Annual_Income='7711339.0'),
Row(Annual_Income='168878.08_'),
Row(Annual_Income='17482.49'),
Row(Annual_Income='86492.88_'),
Row(Annual_Income='23917.38'),
Row(Annual_Income='7711.54'),
Row(Annual_Income='37547.68'),
Row(Annual_Income='16489.74'),
Row(Annual_Income='128754.04'),
Row(Annual_Income='28686.15'),
Row(Annual_Income='29386.9_'),
Row(Annual_Income='76891.0_'),
Row(Annual_Income='18762.55'),
...]unique_value_dict['Monthly_Inhand_Salary'][Row(Monthly_Inhand_Salary=4717.9425),
Row(Monthly_Inhand_Salary=5741.443333333334),
Row(Monthly_Inhand_Salary=1957.5641666666668),
Row(Monthly_Inhand_Salary=5738.581666666666),
Row(Monthly_Inhand_Salary=1541.4008333333334),
Row(Monthly_Inhand_Salary=6285.485352194949),
Row(Monthly_Inhand_Salary=813.28125),
Row(Monthly_Inhand_Salary=2242.1983333333333),
Row(Monthly_Inhand_Salary=3157.557500000001),
Row(Monthly_Inhand_Salary=3416.265),
Row(Monthly_Inhand_Salary=756.6595833333333),
Row(Monthly_Inhand_Salary=6146.350000000001),
Row(Monthly_Inhand_Salary=2889.628582499552),
Row(Monthly_Inhand_Salary=2655.398333333333),
Row(Monthly_Inhand_Salary=6886.649999999999),
Row(Monthly_Inhand_Salary=1391.5675),
Row(Monthly_Inhand_Salary=1581.970833333333),
Row(Monthly_Inhand_Salary=447.49750000000006),
Row(Monthly_Inhand_Salary=2000.7735280112224),
Row(Monthly_Inhand_Salary=1926.5283333333332),
Row(Monthly_Inhand_Salary=1177.0291666666667),
Row(Monthly_Inhand_Salary=13814.93),
Row(Monthly_Inhand_Salary=869.4020833333334),
Row(Monthly_Inhand_Salary=1668.2516666666668),
Row(Monthly_Inhand_Salary=3037.986666666666),
Row(Monthly_Inhand_Salary=3703.8725),
Row(Monthly_Inhand_Salary=4339.36172987997),
Row(Monthly_Inhand_Salary=3264.601666666667),
Row(Monthly_Inhand_Salary=1398.235),
Row(Monthly_Inhand_Salary=1916.3125),
Row(Monthly_Inhand_Salary=1273.1875),
Row(Monthly_Inhand_Salary=6885.669999999999),
Row(Monthly_Inhand_Salary=3174.0375),
Row(Monthly_Inhand_Salary=2999.7900000000004),
Row(Monthly_Inhand_Salary=751.2870833333333),
Row(Monthly_Inhand_Salary=4983.818333333334),
Row(Monthly_Inhand_Salary=6746.080000000001),
Row(Monthly_Inhand_Salary=3143.796666666666),
Row(Monthly_Inhand_Salary=4668.42),
Row(Monthly_Inhand_Salary=9137.946666666667),
Row(Monthly_Inhand_Salary=1490.737916666667),
Row(Monthly_Inhand_Salary=1962.9225),
Row(Monthly_Inhand_Salary=931.96125),
Row(Monthly_Inhand_Salary=2033.2116666666668),
Row(Monthly_Inhand_Salary=6151.3499999999985),
Row(Monthly_Inhand_Salary=4167.3325),
Row(Monthly_Inhand_Salary=1843.9783333333332),
Row(Monthly_Inhand_Salary=5406.74),
Row(Monthly_Inhand_Salary=3025.568333333333),
Row(Monthly_Inhand_Salary=883.2241666666667),
Row(Monthly_Inhand_Salary=2266.840833333333),
Row(Monthly_Inhand_Salary=5852.846666666667),
Row(Monthly_Inhand_Salary=1123.7083333333335),
Row(Monthly_Inhand_Salary=2930.1216666666664),
Row(Monthly_Inhand_Salary=6958.141666666666),
Row(Monthly_Inhand_Salary=10021.66),
Row(Monthly_Inhand_Salary=872.9433333333333),
Row(Monthly_Inhand_Salary=2813.6783333333333),
Row(Monthly_Inhand_Salary=1617.523333333333),
Row(Monthly_Inhand_Salary=7394.325),
Row(Monthly_Inhand_Salary=1464.67125),
Row(Monthly_Inhand_Salary=6769.936269300187),
Row(Monthly_Inhand_Salary=1021.0433333333333),
Row(Monthly_Inhand_Salary=981.7591666666667),
Row(Monthly_Inhand_Salary=8510.73),
Row(Monthly_Inhand_Salary=1488.0912500000004),
Row(Monthly_Inhand_Salary=5513.5),
Row(Monthly_Inhand_Salary=2932.681666666667),
Row(Monthly_Inhand_Salary=2665.2966666666666),
Row(Monthly_Inhand_Salary=12353.87),
Row(Monthly_Inhand_Salary=6191.173333333332),
Row(Monthly_Inhand_Salary=10812.4325),
Row(Monthly_Inhand_Salary=7087.943333333334),
Row(Monthly_Inhand_Salary=1640.200833333333),
Row(Monthly_Inhand_Salary=1965.696666666667),
Row(Monthly_Inhand_Salary=6299.503333333332),
Row(Monthly_Inhand_Salary=8809.3575),
Row(Monthly_Inhand_Salary=3896.514393677528),
Row(Monthly_Inhand_Salary=14070.38),
Row(Monthly_Inhand_Salary=6685.7),
Row(Monthly_Inhand_Salary=2269.1441666666665),
Row(Monthly_Inhand_Salary=1712.570416666667),
Row(Monthly_Inhand_Salary=1509.5575),
Row(Monthly_Inhand_Salary=1622.668333333333),
Row(Monthly_Inhand_Salary=5167.5475),
Row(Monthly_Inhand_Salary=1029.1154166666663),
Row(Monthly_Inhand_Salary=3156.8625),
Row(Monthly_Inhand_Salary=7438.79),
Row(Monthly_Inhand_Salary=6563.54),
Row(Monthly_Inhand_Salary=4589.745),
Row(Monthly_Inhand_Salary=2962.13),
Row(Monthly_Inhand_Salary=5790.62),
Row(Monthly_Inhand_Salary=1729.628333333333),
Row(Monthly_Inhand_Salary=5233.76),
Row(Monthly_Inhand_Salary=615.6374999999998),
Row(Monthly_Inhand_Salary=1615.845),
Row(Monthly_Inhand_Salary=4559.05),
Row(Monthly_Inhand_Salary=2673.7716666666665),
Row(Monthly_Inhand_Salary=8441.59),
Row(Monthly_Inhand_Salary=2679.1425),
Row(Monthly_Inhand_Salary=1352.0158333333334),
Row(Monthly_Inhand_Salary=2954.5883333333336),
Row(Monthly_Inhand_Salary=5512.0583333333325),
Row(Monthly_Inhand_Salary=4325.206666666667),
Row(Monthly_Inhand_Salary=3844.9098762535073),
Row(Monthly_Inhand_Salary=8676.6425),
Row(Monthly_Inhand_Salary=1326.2366666666667),
Row(Monthly_Inhand_Salary=1421.1108333333334),
Row(Monthly_Inhand_Salary=1273.24),
Row(Monthly_Inhand_Salary=1823.4091666666666),
Row(Monthly_Inhand_Salary=4791.26),
Row(Monthly_Inhand_Salary=8478.5975),
Row(Monthly_Inhand_Salary=3081.9775000000004),
Row(Monthly_Inhand_Salary=2799.9825),
Row(Monthly_Inhand_Salary=2401.943333333333),
Row(Monthly_Inhand_Salary=5401.616666666666),
Row(Monthly_Inhand_Salary=1131.1954166666667),
Row(Monthly_Inhand_Salary=4009.396666666667),
Row(Monthly_Inhand_Salary=6280.572499999998),
Row(Monthly_Inhand_Salary=9373.8025),
Row(Monthly_Inhand_Salary=11102.589999999998),
Row(Monthly_Inhand_Salary=6427.453333333334),
Row(Monthly_Inhand_Salary=1173.1033333333332),
Row(Monthly_Inhand_Salary=6255.05),
Row(Monthly_Inhand_Salary=9088.056666666664),
Row(Monthly_Inhand_Salary=12514.426666666664),
Row(Monthly_Inhand_Salary=2090.9325),
Row(Monthly_Inhand_Salary=5208.8725),
Row(Monthly_Inhand_Salary=3374.235),
Row(Monthly_Inhand_Salary=1112.4741666666666),
Row(Monthly_Inhand_Salary=2968.0075),
Row(Monthly_Inhand_Salary=745.4941666666667),
Row(Monthly_Inhand_Salary=2763.2983333333336),
Row(Monthly_Inhand_Salary=2858.715833333333),
Row(Monthly_Inhand_Salary=1453.3149999999996),
Row(Monthly_Inhand_Salary=8273.86),
Row(Monthly_Inhand_Salary=580.8991666666667),
Row(Monthly_Inhand_Salary=1575.8475),
Row(Monthly_Inhand_Salary=685.2495833333334),
Row(Monthly_Inhand_Salary=2051.3916666666664),
Row(Monthly_Inhand_Salary=1543.1133333333335),
Row(Monthly_Inhand_Salary=3394.0625),
Row(Monthly_Inhand_Salary=811.1120833333333),
Row(Monthly_Inhand_Salary=3906.4),
Row(Monthly_Inhand_Salary=2248.925),
Row(Monthly_Inhand_Salary=626.5275),
Row(Monthly_Inhand_Salary=1151.395),
Row(Monthly_Inhand_Salary=1123.4191666666668),
Row(Monthly_Inhand_Salary=7036.1875),
Row(Monthly_Inhand_Salary=3671.879166666667),
Row(Monthly_Inhand_Salary=3405.417951238789),
Row(Monthly_Inhand_Salary=6619.56),
Row(Monthly_Inhand_Salary=1244.85375),
Row(Monthly_Inhand_Salary=1397.6674999999998),
Row(Monthly_Inhand_Salary=3028.210833333333),
Row(Monthly_Inhand_Salary=5741.505),
Row(Monthly_Inhand_Salary=9963.795),
Row(Monthly_Inhand_Salary=1479.253333333333),
Row(Monthly_Inhand_Salary=5882.16),
Row(Monthly_Inhand_Salary=2061.8858333333333),
Row(Monthly_Inhand_Salary=3543.5375),
Row(Monthly_Inhand_Salary=1770.479166666667),
Row(Monthly_Inhand_Salary=14839.7),
Row(Monthly_Inhand_Salary=3089.6650000000004),
Row(Monthly_Inhand_Salary=1176.585),
Row(Monthly_Inhand_Salary=1540.8608333333334),
Row(Monthly_Inhand_Salary=1850.4591666666665),
Row(Monthly_Inhand_Salary=6103.763333333332),
Row(Monthly_Inhand_Salary=9282.6825),
Row(Monthly_Inhand_Salary=1466.4867077223732),
Row(Monthly_Inhand_Salary=1506.3666666666668),
Row(Monthly_Inhand_Salary=7034.4675),
Row(Monthly_Inhand_Salary=2035.0275),
Row(Monthly_Inhand_Salary=8730.01),
Row(Monthly_Inhand_Salary=1697.093333333333),
Row(Monthly_Inhand_Salary=10224.3975),
Row(Monthly_Inhand_Salary=1474.3175),
Row(Monthly_Inhand_Salary=1579.9108333333334),
Row(Monthly_Inhand_Salary=9205.9475),
Row(Monthly_Inhand_Salary=5060.92),
Row(Monthly_Inhand_Salary=3618.5291666666662),
Row(Monthly_Inhand_Salary=5834.163333333334),
Row(Monthly_Inhand_Salary=10667.276666666667),
Row(Monthly_Inhand_Salary=3193.51),
Row(Monthly_Inhand_Salary=648.2766666666666),
Row(Monthly_Inhand_Salary=1737.84),
Row(Monthly_Inhand_Salary=1442.8733333333332),
Row(Monthly_Inhand_Salary=2850.4441666666667),
Row(Monthly_Inhand_Salary=10000.31),
Row(Monthly_Inhand_Salary=1937.2766666666666),
Row(Monthly_Inhand_Salary=2482.1558333333332),
Row(Monthly_Inhand_Salary=6360.038333333334),
Row(Monthly_Inhand_Salary=1165.8741666666667),
Row(Monthly_Inhand_Salary=2646.563333333333),
Row(Monthly_Inhand_Salary=3764.331666666667),
Row(Monthly_Inhand_Salary=5978.466666666667),
Row(Monthly_Inhand_Salary=1728.0875),
Row(Monthly_Inhand_Salary=5393.1925),
Row(Monthly_Inhand_Salary=2869.9833333333336),
Row(Monthly_Inhand_Salary=1446.414166666667),
Row(Monthly_Inhand_Salary=7256.3166666666675),
Row(Monthly_Inhand_Salary=5293.043333333333),
Row(Monthly_Inhand_Salary=1544.8458333333335),
Row(Monthly_Inhand_Salary=3791.81),
Row(Monthly_Inhand_Salary=1154.38875),
Row(Monthly_Inhand_Salary=13947.95),
Row(Monthly_Inhand_Salary=5995.2175),
Row(Monthly_Inhand_Salary=5333.805),
Row(Monthly_Inhand_Salary=4455.8975),
Row(Monthly_Inhand_Salary=1536.3154166666666),
Row(Monthly_Inhand_Salary=8744.915),
Row(Monthly_Inhand_Salary=3136.3633333333332),
Row(Monthly_Inhand_Salary=9452.133333333333),
Row(Monthly_Inhand_Salary=4683.505),
Row(Monthly_Inhand_Salary=4233.858333333334),
Row(Monthly_Inhand_Salary=9991.135),
Row(Monthly_Inhand_Salary=1995.3733333333332),
Row(Monthly_Inhand_Salary=1139.1774999999998),
Row(Monthly_Inhand_Salary=9694.486666666666),
Row(Monthly_Inhand_Salary=7849.6575),
Row(Monthly_Inhand_Salary=1351.45),
Row(Monthly_Inhand_Salary=706.2950000000002),
Row(Monthly_Inhand_Salary=1379.6275),
Row(Monthly_Inhand_Salary=1993.882916666667),
Row(Monthly_Inhand_Salary=644.0779166666667),
Row(Monthly_Inhand_Salary=5692.406666666668),
Row(Monthly_Inhand_Salary=5119.416666666667),
Row(Monthly_Inhand_Salary=991.2120833333332),
Row(Monthly_Inhand_Salary=1621.009166666667),
Row(Monthly_Inhand_Salary=1564.6925),
Row(Monthly_Inhand_Salary=856.215),
Row(Monthly_Inhand_Salary=3923.6675),
Row(Monthly_Inhand_Salary=2944.6133333333332),
Row(Monthly_Inhand_Salary=622.0820833333332),
Row(Monthly_Inhand_Salary=874.3475),
Row(Monthly_Inhand_Salary=5160.0),
Row(Monthly_Inhand_Salary=2078.3641666666667),
Row(Monthly_Inhand_Salary=8207.800000000001),
Row(Monthly_Inhand_Salary=15066.783333333333),
Row(Monthly_Inhand_Salary=641.4079166666667),
Row(Monthly_Inhand_Salary=6029.013333333332),
Row(Monthly_Inhand_Salary=1600.7675),
Row(Monthly_Inhand_Salary=11028.6425),
Row(Monthly_Inhand_Salary=10051.983333333334),
Row(Monthly_Inhand_Salary=1423.1591666666666),
Row(Monthly_Inhand_Salary=4666.78),
Row(Monthly_Inhand_Salary=9836.62),
Row(Monthly_Inhand_Salary=1284.9566666666667),
Row(Monthly_Inhand_Salary=3653.06),
Row(Monthly_Inhand_Salary=2764.774166666666),
Row(Monthly_Inhand_Salary=3114.3158333333336),
Row(Monthly_Inhand_Salary=1535.4633333333334),
Row(Monthly_Inhand_Salary=3608.448643429688),
Row(Monthly_Inhand_Salary=8615.116666666667),
Row(Monthly_Inhand_Salary=2401.766666666667),
Row(Monthly_Inhand_Salary=4860.83),
Row(Monthly_Inhand_Salary=1761.1895833333335),
Row(Monthly_Inhand_Salary=12016.95),
Row(Monthly_Inhand_Salary=2368.5141666666664),
Row(Monthly_Inhand_Salary=15204.633333333333),
Row(Monthly_Inhand_Salary=6998.613333333334),
Row(Monthly_Inhand_Salary=5813.338333333332),
Row(Monthly_Inhand_Salary=1005.29875),
Row(Monthly_Inhand_Salary=7162.1033333333335),
Row(Monthly_Inhand_Salary=10499.47),
Row(Monthly_Inhand_Salary=6587.426666666666),
Row(Monthly_Inhand_Salary=7667.020572626436),
Row(Monthly_Inhand_Salary=1496.678333333333),
Row(Monthly_Inhand_Salary=2352.72),
Row(Monthly_Inhand_Salary=6402.826666666668),
Row(Monthly_Inhand_Salary=10511.33),
Row(Monthly_Inhand_Salary=3635.365),
Row(Monthly_Inhand_Salary=809.6079166666667),
Row(Monthly_Inhand_Salary=5636.466666666667),
Row(Monthly_Inhand_Salary=9308.9525),
Row(Monthly_Inhand_Salary=5409.0875),
Row(Monthly_Inhand_Salary=6515.3166666666675),
Row(Monthly_Inhand_Salary=1049.8341666666668),
Row(Monthly_Inhand_Salary=8267.002499999999),
Row(Monthly_Inhand_Salary=2661.181666666667),
Row(Monthly_Inhand_Salary=1614.416666666667),
Row(Monthly_Inhand_Salary=1088.285),
Row(Monthly_Inhand_Salary=2325.875),
Row(Monthly_Inhand_Salary=4359.315),
Row(Monthly_Inhand_Salary=3127.643333333333),
Row(Monthly_Inhand_Salary=10834.46),
Row(Monthly_Inhand_Salary=3658.5166666666655),
Row(Monthly_Inhand_Salary=2825.233333333333),
Row(Monthly_Inhand_Salary=1951.6033333333332),
Row(Monthly_Inhand_Salary=1886.9558333333332),
Row(Monthly_Inhand_Salary=2693.353333333333),
Row(Monthly_Inhand_Salary=2434.233333333333),
Row(Monthly_Inhand_Salary=2807.596666666667),
Row(Monthly_Inhand_Salary=6849.399999999999),
Row(Monthly_Inhand_Salary=1875.9375),
Row(Monthly_Inhand_Salary=1272.2391666666667),
Row(Monthly_Inhand_Salary=7823.75),
Row(Monthly_Inhand_Salary=2865.4041666666667),
Row(Monthly_Inhand_Salary=829.3854166666667),
Row(Monthly_Inhand_Salary=751.4133333333333),
Row(Monthly_Inhand_Salary=9178.76),
Row(Monthly_Inhand_Salary=1096.9845833333334),
Row(Monthly_Inhand_Salary=10173.15),
Row(Monthly_Inhand_Salary=2523.2725),
Row(Monthly_Inhand_Salary=10409.565),
Row(Monthly_Inhand_Salary=5461.076666666667),
Row(Monthly_Inhand_Salary=14978.336666666668),
Row(Monthly_Inhand_Salary=9662.2575),
Row(Monthly_Inhand_Salary=7433.6475),
Row(Monthly_Inhand_Salary=12261.356666666668),
Row(Monthly_Inhand_Salary=7629.405),
Row(Monthly_Inhand_Salary=4427.9275),
Row(Monthly_Inhand_Salary=3201.728333333333),
Row(Monthly_Inhand_Salary=6776.6066666666675),
Row(Monthly_Inhand_Salary=910.5120833333334),
Row(Monthly_Inhand_Salary=9128.306666666664),
Row(Monthly_Inhand_Salary=4466.27),
Row(Monthly_Inhand_Salary=1246.6683333333333),
Row(Monthly_Inhand_Salary=4621.656666666667),
Row(Monthly_Inhand_Salary=2765.008333333333),
Row(Monthly_Inhand_Salary=9295.403333333334),
Row(Monthly_Inhand_Salary=429.77),
Row(Monthly_Inhand_Salary=4345.05),
Row(Monthly_Inhand_Salary=1954.7716666666665),
Row(Monthly_Inhand_Salary=930.5820833333332),
Row(Monthly_Inhand_Salary=2438.5425),
Row(Monthly_Inhand_Salary=1587.0625),
Row(Monthly_Inhand_Salary=1901.57),
Row(Monthly_Inhand_Salary=3296.0066666666667),
Row(Monthly_Inhand_Salary=5469.9025),
Row(Monthly_Inhand_Salary=941.5370833333333),
Row(Monthly_Inhand_Salary=1523.884166666667),
Row(Monthly_Inhand_Salary=2772.991666666667),
Row(Monthly_Inhand_Salary=9238.836666666666),
Row(Monthly_Inhand_Salary=2208.2595374405278),
Row(Monthly_Inhand_Salary=9403.683333333332),
Row(Monthly_Inhand_Salary=5287.791666666667),
Row(Monthly_Inhand_Salary=1047.2216666666666),
Row(Monthly_Inhand_Salary=1181.8741666666667),
Row(Monthly_Inhand_Salary=8488.73),
Row(Monthly_Inhand_Salary=3687.9883333333332),
Row(Monthly_Inhand_Salary=6185.233333333334),
Row(Monthly_Inhand_Salary=8457.5525),
Row(Monthly_Inhand_Salary=10003.996666666668),
Row(Monthly_Inhand_Salary=10623.655),
Row(Monthly_Inhand_Salary=835.8275),
Row(Monthly_Inhand_Salary=1411.5695833333332),
Row(Monthly_Inhand_Salary=2572.000833333333),
Row(Monthly_Inhand_Salary=5626.8533333333335),
Row(Monthly_Inhand_Salary=1617.1308333333334),
Row(Monthly_Inhand_Salary=1259.9116666666666),
Row(Monthly_Inhand_Salary=3297.1275),
Row(Monthly_Inhand_Salary=1652.343333333333),
Row(Monthly_Inhand_Salary=2460.8241666666668),
Row(Monthly_Inhand_Salary=3481.5225000000005),
Row(Monthly_Inhand_Salary=914.15),
Row(Monthly_Inhand_Salary=7990.76),
Row(Monthly_Inhand_Salary=575.7183333333334),
Row(Monthly_Inhand_Salary=1684.322916666667),
Row(Monthly_Inhand_Salary=1752.6008333333332),
Row(Monthly_Inhand_Salary=1739.6625),
Row(Monthly_Inhand_Salary=1108.9025),
Row(Monthly_Inhand_Salary=547.5595833333333),
Row(Monthly_Inhand_Salary=6137.743333333333),
Row(Monthly_Inhand_Salary=2574.453333333333),
Row(Monthly_Inhand_Salary=713.0979166666667),
Row(Monthly_Inhand_Salary=5153.66),
Row(Monthly_Inhand_Salary=2190.413333333333),
Row(Monthly_Inhand_Salary=2919.248333333333),
Row(Monthly_Inhand_Salary=3219.401666666666),
Row(Monthly_Inhand_Salary=7065.895),
Row(Monthly_Inhand_Salary=3080.005833333333),
Row(Monthly_Inhand_Salary=722.2070833333332),
Row(Monthly_Inhand_Salary=10210.693333333336),
Row(Monthly_Inhand_Salary=1490.595),
Row(Monthly_Inhand_Salary=7724.925),
Row(Monthly_Inhand_Salary=4968.56),
Row(Monthly_Inhand_Salary=3340.846666666667),
Row(Monthly_Inhand_Salary=12156.08),
Row(Monthly_Inhand_Salary=782.7470833333333),
Row(Monthly_Inhand_Salary=7111.235),
Row(Monthly_Inhand_Salary=2301.6716666666666),
Row(Monthly_Inhand_Salary=5124.730000000001),
Row(Monthly_Inhand_Salary=5198.591666666666),
Row(Monthly_Inhand_Salary=1754.690833333333),
Row(Monthly_Inhand_Salary=3485.169166666666),
Row(Monthly_Inhand_Salary=11773.03),
Row(Monthly_Inhand_Salary=10317.043333333333),
Row(Monthly_Inhand_Salary=5034.836666666667),
Row(Monthly_Inhand_Salary=5127.846666666667),
Row(Monthly_Inhand_Salary=9448.675),
Row(Monthly_Inhand_Salary=2732.6666666666665),
Row(Monthly_Inhand_Salary=5884.426666666666),
Row(Monthly_Inhand_Salary=7517.913333333334),
Row(Monthly_Inhand_Salary=3213.9441666666667),
Row(Monthly_Inhand_Salary=8261.9075),
Row(Monthly_Inhand_Salary=4935.216566171412),
Row(Monthly_Inhand_Salary=3927.3583333333336),
Row(Monthly_Inhand_Salary=1597.35),
Row(Monthly_Inhand_Salary=12277.843333333332),
Row(Monthly_Inhand_Salary=2051.8066666666664),
Row(Monthly_Inhand_Salary=1394.000833333333),
Row(Monthly_Inhand_Salary=4854.0225),
Row(Monthly_Inhand_Salary=7998.642499999999),
Row(Monthly_Inhand_Salary=7723.263333333332),
Row(Monthly_Inhand_Salary=2742.8866666666668),
Row(Monthly_Inhand_Salary=1426.868333333333),
Row(Monthly_Inhand_Salary=6656.1833333333325),
Row(Monthly_Inhand_Salary=6191.6725),
Row(Monthly_Inhand_Salary=3370.953333333333),
Row(Monthly_Inhand_Salary=1270.3891666666666),
Row(Monthly_Inhand_Salary=3355.1766666666667),
Row(Monthly_Inhand_Salary=2556.0691666666667),
Row(Monthly_Inhand_Salary=6937.696666666668),
Row(Monthly_Inhand_Salary=8083.3625),
Row(Monthly_Inhand_Salary=1303.4416666666666),
Row(Monthly_Inhand_Salary=1544.7775),
Row(Monthly_Inhand_Salary=14460.346666666665),
Row(Monthly_Inhand_Salary=3662.03),
Row(Monthly_Inhand_Salary=670.7904166666667),
Row(Monthly_Inhand_Salary=7188.516666666666),
Row(Monthly_Inhand_Salary=1074.5845833333333),
Row(Monthly_Inhand_Salary=4720.926666666667),
Row(Monthly_Inhand_Salary=7147.43),
Row(Monthly_Inhand_Salary=1188.6958333333332),
Row(Monthly_Inhand_Salary=3567.838333333333),
Row(Monthly_Inhand_Salary=9641.64),
Row(Monthly_Inhand_Salary=1874.21),
Row(Monthly_Inhand_Salary=7295.833333333332),
Row(Monthly_Inhand_Salary=5819.546666666666),
Row(Monthly_Inhand_Salary=5062.973333333333),
Row(Monthly_Inhand_Salary=5880.1433333333325),
Row(Monthly_Inhand_Salary=5144.873333333334),
Row(Monthly_Inhand_Salary=5125.8975),
Row(Monthly_Inhand_Salary=1883.79),
Row(Monthly_Inhand_Salary=1990.9325),
Row(Monthly_Inhand_Salary=4639.9625),
Row(Monthly_Inhand_Salary=14866.446666666665),
Row(Monthly_Inhand_Salary=9469.4175),
Row(Monthly_Inhand_Salary=11484.65),
Row(Monthly_Inhand_Salary=1165.8),
Row(Monthly_Inhand_Salary=6596.766666666666),
Row(Monthly_Inhand_Salary=4007.17),
Row(Monthly_Inhand_Salary=7051.435),
Row(Monthly_Inhand_Salary=1023.99125),
Row(Monthly_Inhand_Salary=8600.45),
Row(Monthly_Inhand_Salary=7954.7975),
Row(Monthly_Inhand_Salary=6757.935),
Row(Monthly_Inhand_Salary=2245.540833333333),
Row(Monthly_Inhand_Salary=4540.233333333334),
Row(Monthly_Inhand_Salary=876.9858333333334),
Row(Monthly_Inhand_Salary=3151.1983333333333),
Row(Monthly_Inhand_Salary=5971.186666666667),
Row(Monthly_Inhand_Salary=1226.7425),
Row(Monthly_Inhand_Salary=3638.8633333333332),
Row(Monthly_Inhand_Salary=1625.1658333333335),
Row(Monthly_Inhand_Salary=4699.905),
Row(Monthly_Inhand_Salary=4457.68),
Row(Monthly_Inhand_Salary=3865.231666666666),
Row(Monthly_Inhand_Salary=9617.6975),
Row(Monthly_Inhand_Salary=3204.4775000000004),
Row(Monthly_Inhand_Salary=6050.201666666668),
Row(Monthly_Inhand_Salary=6602.973333333332),
Row(Monthly_Inhand_Salary=11174.847499999998),
Row(Monthly_Inhand_Salary=961.9591666666665),
Row(Monthly_Inhand_Salary=5917.510962162808),
Row(Monthly_Inhand_Salary=2234.335),
Row(Monthly_Inhand_Salary=11557.923333333332),
Row(Monthly_Inhand_Salary=1276.4858333333334),
Row(Monthly_Inhand_Salary=7546.6325),
Row(Monthly_Inhand_Salary=1467.52125),
Row(Monthly_Inhand_Salary=864.4204166666667),
Row(Monthly_Inhand_Salary=10711.2925),
Row(Monthly_Inhand_Salary=1027.9225),
Row(Monthly_Inhand_Salary=689.1870833333335),
Row(Monthly_Inhand_Salary=2670.8633333333332),
Row(Monthly_Inhand_Salary=4767.5),
Row(Monthly_Inhand_Salary=11876.233333333332),
Row(Monthly_Inhand_Salary=1597.5829166666665),
Row(Monthly_Inhand_Salary=7526.216666666667),
Row(Monthly_Inhand_Salary=9642.0325),
Row(Monthly_Inhand_Salary=6074.4000000000015),
Row(Monthly_Inhand_Salary=870.7604166666665),
Row(Monthly_Inhand_Salary=1584.7333333333331),
Row(Monthly_Inhand_Salary=4811.25),
Row(Monthly_Inhand_Salary=3420.6),
Row(Monthly_Inhand_Salary=11144.12),
Row(Monthly_Inhand_Salary=7938.32),
Row(Monthly_Inhand_Salary=3651.896666666667),
Row(Monthly_Inhand_Salary=1530.2858333333334),
Row(Monthly_Inhand_Salary=4940.0775),
Row(Monthly_Inhand_Salary=4334.3575),
Row(Monthly_Inhand_Salary=2872.8025),
Row(Monthly_Inhand_Salary=1330.9858333333334),
Row(Monthly_Inhand_Salary=4197.695),
Row(Monthly_Inhand_Salary=2578.0766666666664),
Row(Monthly_Inhand_Salary=5674.490000000002),
Row(Monthly_Inhand_Salary=1571.666666666667),
Row(Monthly_Inhand_Salary=6999.373333333332),
Row(Monthly_Inhand_Salary=1195.1891666666666),
Row(Monthly_Inhand_Salary=3177.56),
Row(Monthly_Inhand_Salary=2782.02),
Row(Monthly_Inhand_Salary=5444.685),
Row(Monthly_Inhand_Salary=1438.51625),
Row(Monthly_Inhand_Salary=1492.8908333333331),
Row(Monthly_Inhand_Salary=4735.522445686195),
Row(Monthly_Inhand_Salary=7626.1433333333325),
Row(Monthly_Inhand_Salary=6520.255),
Row(Monthly_Inhand_Salary=973.4416666666666),
Row(Monthly_Inhand_Salary=2572.410833333333),
Row(Monthly_Inhand_Salary=1306.9633333333334),
Row(Monthly_Inhand_Salary=1528.1375),
Row(Monthly_Inhand_Salary=1611.0375),
Row(Monthly_Inhand_Salary=6476.115000000002),
Row(Monthly_Inhand_Salary=6293.827868783188),
Row(Monthly_Inhand_Salary=4824.71),
Row(Monthly_Inhand_Salary=9262.556666666664),
Row(Monthly_Inhand_Salary=10750.6875),
Row(Monthly_Inhand_Salary=2395.8383333333336),
Row(Monthly_Inhand_Salary=733.8458333333333),
Row(Monthly_Inhand_Salary=567.4620833333332),
Row(Monthly_Inhand_Salary=3019.459166666667),
Row(Monthly_Inhand_Salary=1480.0125),
Row(Monthly_Inhand_Salary=8019.1925),
Row(Monthly_Inhand_Salary=1637.925),
Row(Monthly_Inhand_Salary=3245.421666666666),
Row(Monthly_Inhand_Salary=1316.3341666666665),
Row(Monthly_Inhand_Salary=8733.823333333334),
Row(Monthly_Inhand_Salary=10373.013333333334),
Row(Monthly_Inhand_Salary=1544.5625),
Row(Monthly_Inhand_Salary=1463.45),
Row(Monthly_Inhand_Salary=1505.966666666667),
Row(Monthly_Inhand_Salary=1385.2716666666665),
Row(Monthly_Inhand_Salary=2993.82),
Row(Monthly_Inhand_Salary=6766.8899999999985),
Row(Monthly_Inhand_Salary=4369.4825),
Row(Monthly_Inhand_Salary=1389.38),
Row(Monthly_Inhand_Salary=2184.5766666666664),
Row(Monthly_Inhand_Salary=1325.1134734621792),
Row(Monthly_Inhand_Salary=6412.765),
Row(Monthly_Inhand_Salary=5912.965),
Row(Monthly_Inhand_Salary=706.1195833333335),
Row(Monthly_Inhand_Salary=1537.68),
Row(Monthly_Inhand_Salary=6620.053333333332),
Row(Monthly_Inhand_Salary=10367.67),
Row(Monthly_Inhand_Salary=1635.065833333333),
Row(Monthly_Inhand_Salary=956.1020833333333),
Row(Monthly_Inhand_Salary=5386.248333333333),
Row(Monthly_Inhand_Salary=817.0995833333333),
Row(Monthly_Inhand_Salary=5923.0583333333325),
Row(Monthly_Inhand_Salary=3419.99),
Row(Monthly_Inhand_Salary=5442.8975),
Row(Monthly_Inhand_Salary=3217.785),
Row(Monthly_Inhand_Salary=10124.405),
Row(Monthly_Inhand_Salary=1192.9283538967102),
Row(Monthly_Inhand_Salary=2676.953333333333),
Row(Monthly_Inhand_Salary=11841.143333333332),
Row(Monthly_Inhand_Salary=3123.0033333333336),
Row(Monthly_Inhand_Salary=1944.2458333333332),
Row(Monthly_Inhand_Salary=3553.0550000000007),
Row(Monthly_Inhand_Salary=1904.8108333333332),
Row(Monthly_Inhand_Salary=2999.918333333333),
Row(Monthly_Inhand_Salary=2150.4275),
Row(Monthly_Inhand_Salary=1527.569166666667),
Row(Monthly_Inhand_Salary=1626.0991666666666),
Row(Monthly_Inhand_Salary=2281.89),
Row(Monthly_Inhand_Salary=1248.6604166666666),
Row(Monthly_Inhand_Salary=4697.666666666667),
Row(Monthly_Inhand_Salary=1156.9358333333332),
Row(Monthly_Inhand_Salary=4689.145),
Row(Monthly_Inhand_Salary=3061.3441666666663),
Row(Monthly_Inhand_Salary=797.4995833333335),
Row(Monthly_Inhand_Salary=8401.093333333332),
Row(Monthly_Inhand_Salary=4592.12),
Row(Monthly_Inhand_Salary=13580.356666666668),
Row(Monthly_Inhand_Salary=3001.4300000000007),
Row(Monthly_Inhand_Salary=12087.763333333334),
Row(Monthly_Inhand_Salary=2675.255833333333),
Row(Monthly_Inhand_Salary=673.4704166666667),
Row(Monthly_Inhand_Salary=1056.8024999999998),
Row(Monthly_Inhand_Salary=10855.26),
Row(Monthly_Inhand_Salary=8167.47),
Row(Monthly_Inhand_Salary=4812.425),
Row(Monthly_Inhand_Salary=4891.05),
Row(Monthly_Inhand_Salary=1090.3529166666667),
Row(Monthly_Inhand_Salary=1506.8954166666665),
Row(Monthly_Inhand_Salary=3007.4906235681683),
Row(Monthly_Inhand_Salary=2086.1108333333336),
Row(Monthly_Inhand_Salary=5402.91),
Row(Monthly_Inhand_Salary=11322.9375),
Row(Monthly_Inhand_Salary=2044.2233990811048),
Row(Monthly_Inhand_Salary=3297.376666666666),
Row(Monthly_Inhand_Salary=1407.6175),
Row(Monthly_Inhand_Salary=1030.7091666666668),
Row(Monthly_Inhand_Salary=1289.16),
Row(Monthly_Inhand_Salary=5629.253333333332),
Row(Monthly_Inhand_Salary=1554.020833333333),
Row(Monthly_Inhand_Salary=4508.535),
Row(Monthly_Inhand_Salary=1092.0683333333334),
Row(Monthly_Inhand_Salary=1440.3241666666665),
Row(Monthly_Inhand_Salary=2222.806019052605),
Row(Monthly_Inhand_Salary=5191.81),
Row(Monthly_Inhand_Salary=4465.855000000001),
Row(Monthly_Inhand_Salary=1119.3325),
Row(Monthly_Inhand_Salary=431.73625),
Row(Monthly_Inhand_Salary=4142.458333333334),
Row(Monthly_Inhand_Salary=1401.694166666667),
Row(Monthly_Inhand_Salary=6319.495),
Row(Monthly_Inhand_Salary=3198.161666666667),
Row(Monthly_Inhand_Salary=2649.4841666666666),
Row(Monthly_Inhand_Salary=1728.003333333333),
Row(Monthly_Inhand_Salary=3500.88),
Row(Monthly_Inhand_Salary=1695.3908333333331),
Row(Monthly_Inhand_Salary=9454.036666666667),
Row(Monthly_Inhand_Salary=12059.723333333333),
Row(Monthly_Inhand_Salary=1830.7391666666665),
Row(Monthly_Inhand_Salary=4341.3925),
Row(Monthly_Inhand_Salary=1103.9975),
Row(Monthly_Inhand_Salary=10241.9),
Row(Monthly_Inhand_Salary=7934.017499999999),
Row(Monthly_Inhand_Salary=3569.73),
Row(Monthly_Inhand_Salary=1561.4391666666668),
Row(Monthly_Inhand_Salary=6995.1125),
Row(Monthly_Inhand_Salary=11360.608310250997),
Row(Monthly_Inhand_Salary=2986.5716666666667),
Row(Monthly_Inhand_Salary=6401.84),
Row(Monthly_Inhand_Salary=1115.2470833333332),
Row(Monthly_Inhand_Salary=2140.545816356962),
Row(Monthly_Inhand_Salary=6744.246666666668),
Row(Monthly_Inhand_Salary=1799.8725000000004),
Row(Monthly_Inhand_Salary=1527.6525),
Row(Monthly_Inhand_Salary=7471.013333333332),
Row(Monthly_Inhand_Salary=3678.505833333333),
Row(Monthly_Inhand_Salary=2929.541666666666),
Row(Monthly_Inhand_Salary=771.0804166666667),
Row(Monthly_Inhand_Salary=1662.6266666666668),
Row(Monthly_Inhand_Salary=10693.556666666664),
Row(Monthly_Inhand_Salary=2899.3841666666667),
Row(Monthly_Inhand_Salary=7231.61),
Row(Monthly_Inhand_Salary=1095.0725000000002),
Row(Monthly_Inhand_Salary=2529.1108333333336),
Row(Monthly_Inhand_Salary=2678.0425),
Row(Monthly_Inhand_Salary=6244.2625),
Row(Monthly_Inhand_Salary=2748.313333333333),
Row(Monthly_Inhand_Salary=2934.536666666667),
Row(Monthly_Inhand_Salary=8278.51),
Row(Monthly_Inhand_Salary=1039.4675000000002),
Row(Monthly_Inhand_Salary=2824.335),
Row(Monthly_Inhand_Salary=2514.2916666666665),
Row(Monthly_Inhand_Salary=4116.013333333333),
Row(Monthly_Inhand_Salary=3048.6625),
Row(Monthly_Inhand_Salary=2163.1565158798767),
Row(Monthly_Inhand_Salary=6309.995),
Row(Monthly_Inhand_Salary=5228.361666666667),
Row(Monthly_Inhand_Salary=8164.136666666666),
Row(Monthly_Inhand_Salary=8334.5),
Row(Monthly_Inhand_Salary=1269.0666666666666),
Row(Monthly_Inhand_Salary=1704.4616666666668),
Row(Monthly_Inhand_Salary=1671.7075000000002),
Row(Monthly_Inhand_Salary=4145.333091177216),
Row(Monthly_Inhand_Salary=2703.159166666667),
Row(Monthly_Inhand_Salary=561.7379166666666),
Row(Monthly_Inhand_Salary=2173.3441666666668),
Row(Monthly_Inhand_Salary=1766.8808333333334),
Row(Monthly_Inhand_Salary=7448.0325),
Row(Monthly_Inhand_Salary=3911.23),
Row(Monthly_Inhand_Salary=2684.8925),
Row(Monthly_Inhand_Salary=881.8533333333335),
Row(Monthly_Inhand_Salary=1012.48),
Row(Monthly_Inhand_Salary=1169.5795833333332),
Row(Monthly_Inhand_Salary=2903.82),
Row(Monthly_Inhand_Salary=1704.6016213914936),
Row(Monthly_Inhand_Salary=2506.57),
Row(Monthly_Inhand_Salary=2079.0616666666665),
Row(Monthly_Inhand_Salary=2230.8075),
Row(Monthly_Inhand_Salary=7080.216666666667),
Row(Monthly_Inhand_Salary=4656.141666666666),
Row(Monthly_Inhand_Salary=4406.49),
Row(Monthly_Inhand_Salary=7104.871666666668),
Row(Monthly_Inhand_Salary=1052.37375),
Row(Monthly_Inhand_Salary=1754.7658333333331),
Row(Monthly_Inhand_Salary=3757.369166666667),
Row(Monthly_Inhand_Salary=8744.8),
Row(Monthly_Inhand_Salary=2404.90261822173),
Row(Monthly_Inhand_Salary=1253.3783333333333),
Row(Monthly_Inhand_Salary=5691.490000000002),
Row(Monthly_Inhand_Salary=1984.8466666666666),
Row(Monthly_Inhand_Salary=599.99875),
Row(Monthly_Inhand_Salary=1867.9158333333332),
Row(Monthly_Inhand_Salary=1293.7866666666666),
Row(Monthly_Inhand_Salary=7227.8975),
Row(Monthly_Inhand_Salary=2679.4691666666668),
Row(Monthly_Inhand_Salary=2535.745),
Row(Monthly_Inhand_Salary=5208.8),
Row(Monthly_Inhand_Salary=1061.9116666666666),
Row(Monthly_Inhand_Salary=10210.52),
Row(Monthly_Inhand_Salary=672.6358333333334),
Row(Monthly_Inhand_Salary=1126.94875),
Row(Monthly_Inhand_Salary=6671.536666666668),
Row(Monthly_Inhand_Salary=8729.09),
Row(Monthly_Inhand_Salary=1654.878333333333),
Row(Monthly_Inhand_Salary=1456.634166666667),
Row(Monthly_Inhand_Salary=1623.729166666667),
Row(Monthly_Inhand_Salary=1620.5725),
Row(Monthly_Inhand_Salary=1461.7970833333331),
Row(Monthly_Inhand_Salary=4618.6375),
Row(Monthly_Inhand_Salary=598.4991666666666),
Row(Monthly_Inhand_Salary=1233.2158333333334),
Row(Monthly_Inhand_Salary=15090.076666666668),
Row(Monthly_Inhand_Salary=1368.2366666666667),
Row(Monthly_Inhand_Salary=11755.796666666667),
Row(Monthly_Inhand_Salary=2577.987997642031),
Row(Monthly_Inhand_Salary=7974.9575),
Row(Monthly_Inhand_Salary=1849.476666666667),
Row(Monthly_Inhand_Salary=1015.9879166666667),
Row(Monthly_Inhand_Salary=14104.516666666668),
Row(Monthly_Inhand_Salary=2888.395),
Row(Monthly_Inhand_Salary=7564.579999999999),
Row(Monthly_Inhand_Salary=3542.519166666667),
Row(Monthly_Inhand_Salary=2933.6366666666668),
Row(Monthly_Inhand_Salary=667.0524999999999),
Row(Monthly_Inhand_Salary=7187.456666666666),
Row(Monthly_Inhand_Salary=7079.4325),
Row(Monthly_Inhand_Salary=4640.715),
Row(Monthly_Inhand_Salary=3793.2425),
Row(Monthly_Inhand_Salary=2076.1366666666668),
Row(Monthly_Inhand_Salary=7775.935),
Row(Monthly_Inhand_Salary=5885.07),
Row(Monthly_Inhand_Salary=1292.9433333333334),
Row(Monthly_Inhand_Salary=949.4029166666667),
Row(Monthly_Inhand_Salary=4655.083333333333),
Row(Monthly_Inhand_Salary=1549.539166666667),
Row(Monthly_Inhand_Salary=1369.42),
Row(Monthly_Inhand_Salary=5228.0633333333335),
Row(Monthly_Inhand_Salary=774.7920833333333),
Row(Monthly_Inhand_Salary=2193.846666666667),
Row(Monthly_Inhand_Salary=6009.16),
Row(Monthly_Inhand_Salary=5841.3499999999985),
Row(Monthly_Inhand_Salary=2142.1383333333333),
Row(Monthly_Inhand_Salary=2828.643333333333),
Row(Monthly_Inhand_Salary=9838.366666666667),
Row(Monthly_Inhand_Salary=14289.176666666664),
Row(Monthly_Inhand_Salary=2163.1066666666666),
Row(Monthly_Inhand_Salary=531.8754166666666),
Row(Monthly_Inhand_Salary=6605.091666666667),
Row(Monthly_Inhand_Salary=2723.8975),
Row(Monthly_Inhand_Salary=7564.7175),
Row(Monthly_Inhand_Salary=5217.5425),
Row(Monthly_Inhand_Salary=1442.7341666666669),
Row(Monthly_Inhand_Salary=1167.4291666666666),
Row(Monthly_Inhand_Salary=5899.97),
Row(Monthly_Inhand_Salary=11526.983333333332),
Row(Monthly_Inhand_Salary=2659.4775),
Row(Monthly_Inhand_Salary=2696.835),
Row(Monthly_Inhand_Salary=9280.88),
Row(Monthly_Inhand_Salary=10071.6075),
Row(Monthly_Inhand_Salary=5738.733333333334),
Row(Monthly_Inhand_Salary=489.43602225137255),
Row(Monthly_Inhand_Salary=10356.946666666667),
Row(Monthly_Inhand_Salary=3306.16),
Row(Monthly_Inhand_Salary=872.96875),
Row(Monthly_Inhand_Salary=3580.4575),
Row(Monthly_Inhand_Salary=6315.618333333333),
Row(Monthly_Inhand_Salary=1350.437372182059),
Row(Monthly_Inhand_Salary=1932.664166666667),
Row(Monthly_Inhand_Salary=3946.1625),
Row(Monthly_Inhand_Salary=5202.193333333334),
Row(Monthly_Inhand_Salary=4813.717402541748),
Row(Monthly_Inhand_Salary=13943.246666666664),
Row(Monthly_Inhand_Salary=1421.2141666666666),
Row(Monthly_Inhand_Salary=1116.6916666666666),
Row(Monthly_Inhand_Salary=6074.2733333333335),
Row(Monthly_Inhand_Salary=2743.291312440571),
Row(Monthly_Inhand_Salary=10871.753333333332),
Row(Monthly_Inhand_Salary=2420.0033333333336),
Row(Monthly_Inhand_Salary=3611.72),
Row(Monthly_Inhand_Salary=7037.095),
Row(Monthly_Inhand_Salary=6170.9333333333325),
Row(Monthly_Inhand_Salary=2578.6575),
Row(Monthly_Inhand_Salary=1541.5158333333331),
Row(Monthly_Inhand_Salary=840.4516666666667),
Row(Monthly_Inhand_Salary=1209.7045833333334),
Row(Monthly_Inhand_Salary=1716.8791666666666),
Row(Monthly_Inhand_Salary=2271.2141666666666),
Row(Monthly_Inhand_Salary=1470.5625),
Row(Monthly_Inhand_Salary=2573.683333333333),
Row(Monthly_Inhand_Salary=1153.7183333333335),
Row(Monthly_Inhand_Salary=735.6691666666667),
Row(Monthly_Inhand_Salary=10121.365),
Row(Monthly_Inhand_Salary=924.77375),
Row(Monthly_Inhand_Salary=10126.533333333333),
Row(Monthly_Inhand_Salary=1664.535),
Row(Monthly_Inhand_Salary=2397.9483333333333),
Row(Monthly_Inhand_Salary=3076.465),
Row(Monthly_Inhand_Salary=1430.281666666667),
Row(Monthly_Inhand_Salary=3655.366666666667),
Row(Monthly_Inhand_Salary=12656.63),
Row(Monthly_Inhand_Salary=4247.721666666667),
Row(Monthly_Inhand_Salary=3780.988059572468),
Row(Monthly_Inhand_Salary=3280.7041666666664),
Row(Monthly_Inhand_Salary=2635.2016666666664),
Row(Monthly_Inhand_Salary=876.82375),
Row(Monthly_Inhand_Salary=5842.350694240866),
Row(Monthly_Inhand_Salary=1300.5929166666667),
Row(Monthly_Inhand_Salary=5883.703333333334),
Row(Monthly_Inhand_Salary=1348.7245833333334),
Row(Monthly_Inhand_Salary=9677.013333333334),
Row(Monthly_Inhand_Salary=8592.253333333332),
Row(Monthly_Inhand_Salary=5523.2523853841785),
Row(Monthly_Inhand_Salary=2254.9641666666666),
Row(Monthly_Inhand_Salary=1300.33),
Row(Monthly_Inhand_Salary=6421.81),
Row(Monthly_Inhand_Salary=4979.9225),
Row(Monthly_Inhand_Salary=1734.055833333333),
Row(Monthly_Inhand_Salary=1693.936666666667),
Row(Monthly_Inhand_Salary=2908.174166666666),
Row(Monthly_Inhand_Salary=3012.6650000000004),
Row(Monthly_Inhand_Salary=12547.563333333335),
Row(Monthly_Inhand_Salary=1167.0895833333334),
Row(Monthly_Inhand_Salary=4256.165),
Row(Monthly_Inhand_Salary=5114.113333333334),
Row(Monthly_Inhand_Salary=1740.013333333333),
Row(Monthly_Inhand_Salary=1479.8025),
Row(Monthly_Inhand_Salary=1570.695),
Row(Monthly_Inhand_Salary=1072.4420833333334),
Row(Monthly_Inhand_Salary=4662.7625),
Row(Monthly_Inhand_Salary=3938.193333333333),
Row(Monthly_Inhand_Salary=1185.275),
Row(Monthly_Inhand_Salary=11775.756666666664),
Row(Monthly_Inhand_Salary=9174.023333333333),
Row(Monthly_Inhand_Salary=3002.9731947568034),
Row(Monthly_Inhand_Salary=2969.4666666666667),
Row(Monthly_Inhand_Salary=2819.995),
Row(Monthly_Inhand_Salary=5279.0625),
Row(Monthly_Inhand_Salary=910.3375),
Row(Monthly_Inhand_Salary=2780.568333333333),
Row(Monthly_Inhand_Salary=1408.9345833333334),
Row(Monthly_Inhand_Salary=781.90125),
Row(Monthly_Inhand_Salary=3337.044166666666),
Row(Monthly_Inhand_Salary=2612.4908333333333),
Row(Monthly_Inhand_Salary=2611.115),
Row(Monthly_Inhand_Salary=1213.2833333333333),
Row(Monthly_Inhand_Salary=7795.8775),
Row(Monthly_Inhand_Salary=6383.793333333334),
Row(Monthly_Inhand_Salary=5263.57),
Row(Monthly_Inhand_Salary=1735.45),
Row(Monthly_Inhand_Salary=11455.193333333335),
Row(Monthly_Inhand_Salary=7056.861666666668),
Row(Monthly_Inhand_Salary=5229.463333333333),
Row(Monthly_Inhand_Salary=908.4325),
Row(Monthly_Inhand_Salary=1800.2595833333335),
Row(Monthly_Inhand_Salary=11388.913333333332),
Row(Monthly_Inhand_Salary=3663.845),
Row(Monthly_Inhand_Salary=5735.843333333332),
Row(Monthly_Inhand_Salary=5572.248968971794),
Row(Monthly_Inhand_Salary=817.8208333333333),
Row(Monthly_Inhand_Salary=8816.325),
Row(Monthly_Inhand_Salary=4715.0325),
Row(Monthly_Inhand_Salary=6595.488333333334),
Row(Monthly_Inhand_Salary=5593.536666666668),
Row(Monthly_Inhand_Salary=3439.42),
Row(Monthly_Inhand_Salary=13397.636666666667),
Row(Monthly_Inhand_Salary=3640.3964637286745),
Row(Monthly_Inhand_Salary=2643.8033333333333),
Row(Monthly_Inhand_Salary=8830.955),
Row(Monthly_Inhand_Salary=2011.5),
Row(Monthly_Inhand_Salary=7840.912500000001),
Row(Monthly_Inhand_Salary=3806.9483333333333),
Row(Monthly_Inhand_Salary=4570.92),
Row(Monthly_Inhand_Salary=4231.074999999999),
Row(Monthly_Inhand_Salary=4803.675),
Row(Monthly_Inhand_Salary=1454.6141666666665),
Row(Monthly_Inhand_Salary=10653.8675),
Row(Monthly_Inhand_Salary=11198.99),
Row(Monthly_Inhand_Salary=8037.8275),
Row(Monthly_Inhand_Salary=1288.8966666666668),
Row(Monthly_Inhand_Salary=668.4491666666668),
Row(Monthly_Inhand_Salary=8506.34),
Row(Monthly_Inhand_Salary=1703.69625),
Row(Monthly_Inhand_Salary=1071.8775),
Row(Monthly_Inhand_Salary=3798.0591666666655),
Row(Monthly_Inhand_Salary=1223.1333333333334),
Row(Monthly_Inhand_Salary=2146.1691666666666),
Row(Monthly_Inhand_Salary=794.3033333333333),
Row(Monthly_Inhand_Salary=1453.6825),
Row(Monthly_Inhand_Salary=3413.375),
Row(Monthly_Inhand_Salary=955.8158333333334),
Row(Monthly_Inhand_Salary=1610.9525),
Row(Monthly_Inhand_Salary=1112.0925),
Row(Monthly_Inhand_Salary=4875.395),
Row(Monthly_Inhand_Salary=1817.065833333333),
Row(Monthly_Inhand_Salary=5454.518333333333),
Row(Monthly_Inhand_Salary=2437.425),
Row(Monthly_Inhand_Salary=4279.69),
Row(Monthly_Inhand_Salary=8911.14),
Row(Monthly_Inhand_Salary=681.3975),
Row(Monthly_Inhand_Salary=3211.7816666666663),
Row(Monthly_Inhand_Salary=9095.8825),
Row(Monthly_Inhand_Salary=3821.7),
Row(Monthly_Inhand_Salary=7609.9375),
Row(Monthly_Inhand_Salary=1970.605),
Row(Monthly_Inhand_Salary=2394.03),
Row(Monthly_Inhand_Salary=11748.076666666668),
Row(Monthly_Inhand_Salary=11212.673333333332),
Row(Monthly_Inhand_Salary=2321.4500000000007),
Row(Monthly_Inhand_Salary=3214.3175),
Row(Monthly_Inhand_Salary=1623.5933333333335),
Row(Monthly_Inhand_Salary=4144.4775),
Row(Monthly_Inhand_Salary=9612.953333333333),
Row(Monthly_Inhand_Salary=5532.503333333332),
Row(Monthly_Inhand_Salary=2612.733333333333),
Row(Monthly_Inhand_Salary=1089.5629166666665),
Row(Monthly_Inhand_Salary=2501.5291666666667),
Row(Monthly_Inhand_Salary=9349.84),
Row(Monthly_Inhand_Salary=8671.055),
Row(Monthly_Inhand_Salary=2088.273333333333),
Row(Monthly_Inhand_Salary=1108.96),
Row(Monthly_Inhand_Salary=1853.720833333333),
Row(Monthly_Inhand_Salary=2521.596666666667),
Row(Monthly_Inhand_Salary=2345.980833333333),
Row(Monthly_Inhand_Salary=4939.635),
Row(Monthly_Inhand_Salary=13561.713333333333),
Row(Monthly_Inhand_Salary=1642.1308333333334),
Row(Monthly_Inhand_Salary=1322.0600000000004),
Row(Monthly_Inhand_Salary=7644.8875),
Row(Monthly_Inhand_Salary=3851.63),
Row(Monthly_Inhand_Salary=2389.204166666667),
Row(Monthly_Inhand_Salary=1178.8825),
Row(Monthly_Inhand_Salary=1628.9733333333334),
Row(Monthly_Inhand_Salary=2999.899166666666),
Row(Monthly_Inhand_Salary=5770.5225),
Row(Monthly_Inhand_Salary=5189.141666666666),
Row(Monthly_Inhand_Salary=14635.763333333334),
Row(Monthly_Inhand_Salary=1111.8608333333334),
Row(Monthly_Inhand_Salary=2262.4427560755803),
Row(Monthly_Inhand_Salary=614.62),
Row(Monthly_Inhand_Salary=2547.7866666666664),
Row(Monthly_Inhand_Salary=2550.4483333333333),
Row(Monthly_Inhand_Salary=3485.9516666666664),
Row(Monthly_Inhand_Salary=1119.9525),
Row(Monthly_Inhand_Salary=11929.053333333335),
Row(Monthly_Inhand_Salary=3337.8033333333333),
Row(Monthly_Inhand_Salary=578.6241533144276),
Row(Monthly_Inhand_Salary=3446.76),
Row(Monthly_Inhand_Salary=2917.7225),
Row(Monthly_Inhand_Salary=8779.1725),
Row(Monthly_Inhand_Salary=2939.166666666666),
Row(Monthly_Inhand_Salary=6667.25),
Row(Monthly_Inhand_Salary=7962.415000000001),
Row(Monthly_Inhand_Salary=7671.987699078777),
Row(Monthly_Inhand_Salary=5745.633333333334),
Row(Monthly_Inhand_Salary=4755.0999999999985),
Row(Monthly_Inhand_Salary=6123.373333333332),
Row(Monthly_Inhand_Salary=2922.7991666666667),
Row(Monthly_Inhand_Salary=1191.615),
Row(Monthly_Inhand_Salary=6173.6225),
Row(Monthly_Inhand_Salary=2664.0958333333333),
Row(Monthly_Inhand_Salary=6576.873333333332),
Row(Monthly_Inhand_Salary=3070.168333333333),
Row(Monthly_Inhand_Salary=3578.500833333333),
Row(Monthly_Inhand_Salary=1066.98875),
Row(Monthly_Inhand_Salary=5663.953333333334),
Row(Monthly_Inhand_Salary=6561.671666666666),
Row(Monthly_Inhand_Salary=651.7937499999998),
Row(Monthly_Inhand_Salary=3038.445),
Row(Monthly_Inhand_Salary=4254.0075),
Row(Monthly_Inhand_Salary=753.7220833333333),
Row(Monthly_Inhand_Salary=2333.188333333333),
Row(Monthly_Inhand_Salary=1077.1879166666668),
Row(Monthly_Inhand_Salary=5435.566666666667),
Row(Monthly_Inhand_Salary=1192.0341666666666),
Row(Monthly_Inhand_Salary=1068.9254166666665),
Row(Monthly_Inhand_Salary=4448.062323286613),
Row(Monthly_Inhand_Salary=3031.4933333333333),
Row(Monthly_Inhand_Salary=5743.573333333334),
Row(Monthly_Inhand_Salary=2249.4441666666667),
Row(Monthly_Inhand_Salary=1323.4558333333334),
Row(Monthly_Inhand_Salary=3823.2325),
Row(Monthly_Inhand_Salary=1191.2708333333333),
Row(Monthly_Inhand_Salary=1834.4391666666668),
Row(Monthly_Inhand_Salary=1497.4758333333332),
Row(Monthly_Inhand_Salary=13225.55),
Row(Monthly_Inhand_Salary=1922.539166666667),
Row(Monthly_Inhand_Salary=6183.897311926858),
Row(Monthly_Inhand_Salary=10336.3325),
Row(Monthly_Inhand_Salary=3007.461666666666),
Row(Monthly_Inhand_Salary=7886.52),
Row(Monthly_Inhand_Salary=8633.22),
Row(Monthly_Inhand_Salary=8249.1975),
Row(Monthly_Inhand_Salary=6431.71),
Row(Monthly_Inhand_Salary=2891.8291666666664),
Row(Monthly_Inhand_Salary=10209.926666666666),
Row(Monthly_Inhand_Salary=6151.513333333332),
Row(Monthly_Inhand_Salary=3084.106666666666),
Row(Monthly_Inhand_Salary=2192.4816666666666),
Row(Monthly_Inhand_Salary=1113.4533333333334),
Row(Monthly_Inhand_Salary=8420.935),
Row(Monthly_Inhand_Salary=8791.265),
Row(Monthly_Inhand_Salary=973.6366666666668),
Row(Monthly_Inhand_Salary=5159.18),
...]Annual Income and Montly In Hand Salary
It can be noted that Annual Income has the underscore problem but it has been addressed in the above cell, along with the proper datatype set.
Next, we would like to explore the difference between the annual income and the monthly in hand salary. Based on Kaggle, the description given for monthly in hand salary is 'Represents the monthly base salary of a person'. Initially, we thougth that it could be the salary left on hand after taxes and paying off neccessities such as debt, rent and other utilities fees. But because it could also just be monthly salary, annual income is just monthly income multiplied by 12.
We will also be using the Sample function. Based on the sample size calculator, with a population of 100000, we can use 383 rows of data to represent the population at the confidence level of 95% at margin of error of 5%.
salary_differences = credit_score.select('Customer_ID', 'Annual_Income', 'Monthly_Inhand_Salary')\
.filter(~col('Monthly_Inhand_Salary').isNull())\
.sample(False, 0.004, 100)\
.groupBy('Customer_ID', 'Annual_Income', 'Monthly_Inhand_Salary')\
.agg(
(col('Annual_Income') / 12).alias('Derived_Monthly_Income'),
(
F.abs(col('Monthly_Inhand_Salary') - (col('Annual_Income')/12))
/(col('Monthly_Inhand_Salary')+(col('Annual_Income')/12)/2) * 100
).alias('Difference %')
)
salary_differences.show()+-----------+-------------+---------------------+----------------------+-------------------+
|Customer_ID|Annual_Income|Monthly_Inhand_Salary|Derived_Monthly_Income| Difference %|
+-----------+-------------+---------------------+----------------------+-------------------+
| CUS_0x81bb| 13738| 1328.8945833333335| 1144.8333333333333| 9.68075321702326|
| CUS_0xbd2c| 29647| 2329.66| 2470.5833333333335| 3.953022270989189|
| CUS_0x1447| 9989| 653.4341666666667| 832.4166666666666| 16.732927122847116|
| CUS_0x30c5| 19170| 1510.5375| 1597.5| 3.765771910167101|
| CUS_0x4f2f| 49596| 4334.035| 4133.0| 3.1409093146119798|
| CUS_0x748| 71536| 5715.376666666668| 5961.333333333333| 2.828374436956559|
| CUS_0xb741| 97549| 8275.16| 8129.083333333333| 1.183794151695457|
| CUS_0x1630| 84721| 6943.133333333334| 7060.083333333333| 1.1166623301911685|
| CUS_0x45cb| 58170| 4861.5633333333335| 4847.5|0.19303676712143478|
| CUS_0x6619| 41131| 3589.6133333333332| 3427.5833333333335| 3.055206984946459|
| CUS_0xa2de| 137672| 11613.676666666664| 11472.666666666666| 0.8127372837248993|
| CUS_0x79a8| 106674| 8657.5425| 8889.5| 1.7703581262592059|
| CUS_0x2e31| 63206| 5309.2266666666665| 5267.166666666667| 0.5295355170273429|
| CUS_0x70b2| 38685| 3360.831666666667| 3223.75| 2.7566811367652275|
| CUS_0x63b1| 100686| 8680.51| 8390.5| 2.252371898823838|
| CUS_0xc6cb| 159958| 13161.86| 13329.833333333334| 0.8472044455704937|
| CUS_0x3530| 43200| 3807.075| 3600.0| 3.693102018432067|
| CUS_0x4469| 33475| 3033.6358333333333| 2789.5833333333335| 5.5110420120911945|
| CUS_0x4688| 15549| 1589.755| 1295.75| 13.139124877660743|
| CUS_0x5c81| 17497| 1409.1525| 1458.0833333333333| 2.288418614929343|
+-----------+-------------+---------------------+----------------------+-------------------+
only showing top 20 rows
salary_differences.agg(F.avg('Difference %')).show()+-----------------+
|avg(Difference %)|
+-----------------+
|4.339942821067325|
+-----------------+
We have sampled 400 rows to observe the percentage differences between the derived annual income and the Monthly In Hand Salary. Using the following formula, we were able to conclude that there are about 4.42% difference if we derived the monthly income from the annual income.
Therefore, for the column 'Montly_Inhand_Salary', we can drop the column to improve the performance of the model as the difference might not significantly improve, or worse, it may degrade the performance or overfit the model due to supplying similar information.
columns_to_drop.append('Monthly_Inhand_Salary')Type of Loan and Number of Loan
unique_value_dict['Type_of_Loan'][Row(Type_of_Loan='Credit-Builder Loan, Student Loan, and Home Equity Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Home Equity Loan, Mortgage Loan, Debt Consolidation Loan, Credit-Builder Loan, Personal Loan, and Mortgage Loan'),
Row(Type_of_Loan='Student Loan, Home Equity Loan, Auto Loan, Home Equity Loan, Debt Consolidation Loan, Personal Loan, Not Specified, Debt Consolidation Loan, and Not Specified'),
Row(Type_of_Loan='Debt Consolidation Loan, Debt Consolidation Loan, Personal Loan, Payday Loan, and Not Specified'),
Row(Type_of_Loan='Mortgage Loan, Home Equity Loan, Personal Loan, Home Equity Loan, Student Loan, Student Loan, Personal Loan, Debt Consolidation Loan, and Payday Loan'),
Row(Type_of_Loan='Personal Loan, Home Equity Loan, Home Equity Loan, Mortgage Loan, Personal Loan, Student Loan, Credit-Builder Loan, Mortgage Loan, and Mortgage Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Student Loan, Payday Loan, Not Specified, and Auto Loan'),
Row(Type_of_Loan='Auto Loan, Payday Loan, Student Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Home Equity Loan, and Auto Loan'),
Row(Type_of_Loan='Payday Loan, Credit-Builder Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Personal Loan, Home Equity Loan, Home Equity Loan, Not Specified, Mortgage Loan, and Payday Loan'),
Row(Type_of_Loan='Home Equity Loan, Not Specified, Auto Loan, and Not Specified'),
Row(Type_of_Loan='Personal Loan, Not Specified, Not Specified, Student Loan, Auto Loan, Home Equity Loan, Student Loan, and Student Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Student Loan, Home Equity Loan, Debt Consolidation Loan, Not Specified, Not Specified, Home Equity Loan, Student Loan, and Personal Loan'),
Row(Type_of_Loan='Not Specified, Personal Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Student Loan, Payday Loan, Credit-Builder Loan, Home Equity Loan, Personal Loan, Credit-Builder Loan, and Student Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Not Specified, Auto Loan, and Payday Loan'),
Row(Type_of_Loan='Not Specified, Debt Consolidation Loan, Not Specified, Credit-Builder Loan, Debt Consolidation Loan, Credit-Builder Loan, and Home Equity Loan'),
Row(Type_of_Loan='Personal Loan, Personal Loan, Credit-Builder Loan, Student Loan, and Auto Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Not Specified, Mortgage Loan, Auto Loan, Credit-Builder Loan, and Student Loan'),
Row(Type_of_Loan='Not Specified, Student Loan, Auto Loan, and Payday Loan'),
Row(Type_of_Loan='Personal Loan, Personal Loan, Credit-Builder Loan, and Student Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Credit-Builder Loan, Credit-Builder Loan, Credit-Builder Loan, Personal Loan, and Not Specified'),
Row(Type_of_Loan='Payday Loan, Payday Loan, Payday Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Not Specified, Payday Loan, Auto Loan, Mortgage Loan, and Mortgage Loan'),
Row(Type_of_Loan='Personal Loan, Payday Loan, Personal Loan, and Not Specified'),
Row(Type_of_Loan='Auto Loan, Personal Loan, Payday Loan, Auto Loan, Personal Loan, and Payday Loan'),
Row(Type_of_Loan='Personal Loan, Not Specified, Student Loan, and Mortgage Loan'),
Row(Type_of_Loan='Personal Loan, Personal Loan, Not Specified, and Mortgage Loan'),
Row(Type_of_Loan='Personal Loan, Debt Consolidation Loan, Personal Loan, Home Equity Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Not Specified, Credit-Builder Loan, and Student Loan'),
Row(Type_of_Loan='Mortgage Loan, Debt Consolidation Loan, Personal Loan, Auto Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Payday Loan, Personal Loan, Mortgage Loan, and Auto Loan'),
Row(Type_of_Loan='Student Loan, Payday Loan, Auto Loan, Auto Loan, Payday Loan, and Auto Loan'),
Row(Type_of_Loan='Student Loan, Auto Loan, Personal Loan, Auto Loan, Credit-Builder Loan, Payday Loan, Home Equity Loan, Auto Loan, and Personal Loan'),
Row(Type_of_Loan='Personal Loan, and Mortgage Loan'),
Row(Type_of_Loan='Personal Loan, Mortgage Loan, Home Equity Loan, Student Loan, Student Loan, Credit-Builder Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Auto Loan, Mortgage Loan, Personal Loan, and Not Specified'),
Row(Type_of_Loan='Personal Loan, Mortgage Loan, and Personal Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Payday Loan, Mortgage Loan, and Auto Loan'),
Row(Type_of_Loan='Payday Loan, Payday Loan, Personal Loan, Credit-Builder Loan, Payday Loan, Student Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Not Specified, Mortgage Loan, Debt Consolidation Loan, Mortgage Loan, Mortgage Loan, Mortgage Loan, Mortgage Loan, and Personal Loan'),
Row(Type_of_Loan='Auto Loan, Home Equity Loan, Credit-Builder Loan, Student Loan, Home Equity Loan, and Mortgage Loan'),
Row(Type_of_Loan='Not Specified, Credit-Builder Loan, Home Equity Loan, and Student Loan'),
Row(Type_of_Loan='Student Loan, Auto Loan, Mortgage Loan, Payday Loan, Home Equity Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Mortgage Loan, Credit-Builder Loan, Payday Loan, Not Specified, Personal Loan, Credit-Builder Loan, Debt Consolidation Loan, Student Loan, and Mortgage Loan'),
Row(Type_of_Loan='Auto Loan, Payday Loan, Mortgage Loan, and Auto Loan'),
Row(Type_of_Loan='Personal Loan, Credit-Builder Loan, Credit-Builder Loan, Personal Loan, Student Loan, and Not Specified'),
Row(Type_of_Loan='Debt Consolidation Loan, Credit-Builder Loan, Debt Consolidation Loan, Not Specified, Personal Loan, Mortgage Loan, and Student Loan'),
Row(Type_of_Loan='Personal Loan, Mortgage Loan, Not Specified, Auto Loan, Debt Consolidation Loan, Credit-Builder Loan, and Auto Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Debt Consolidation Loan, Debt Consolidation Loan, Auto Loan, Home Equity Loan, Student Loan, Not Specified, and Personal Loan'),
Row(Type_of_Loan='Not Specified, Debt Consolidation Loan, and Auto Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Debt Consolidation Loan, Not Specified, Credit-Builder Loan, Debt Consolidation Loan, and Auto Loan'),
Row(Type_of_Loan='Not Specified, Payday Loan, Mortgage Loan, Home Equity Loan, and Auto Loan'),
Row(Type_of_Loan='Student Loan, Not Specified, Debt Consolidation Loan, Debt Consolidation Loan, and Auto Loan'),
Row(Type_of_Loan='Home Equity Loan, Personal Loan, Mortgage Loan, and Mortgage Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Credit-Builder Loan, Home Equity Loan, and Personal Loan'),
Row(Type_of_Loan='Not Specified, Credit-Builder Loan, Home Equity Loan, and Payday Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Debt Consolidation Loan, Credit-Builder Loan, Auto Loan, Credit-Builder Loan, Mortgage Loan, and Mortgage Loan'),
Row(Type_of_Loan='Payday Loan, Payday Loan, Credit-Builder Loan, Personal Loan, Personal Loan, and Mortgage Loan'),
Row(Type_of_Loan='Auto Loan, Auto Loan, and Not Specified'),
Row(Type_of_Loan='Credit-Builder Loan, Home Equity Loan, and Payday Loan'),
Row(Type_of_Loan='Personal Loan, Not Specified, Not Specified, Personal Loan, Credit-Builder Loan, Personal Loan, and Mortgage Loan'),
Row(Type_of_Loan='Home Equity Loan, Not Specified, Debt Consolidation Loan, Debt Consolidation Loan, Mortgage Loan, Personal Loan, and Personal Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Student Loan, Home Equity Loan, and Personal Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Debt Consolidation Loan, Personal Loan, Mortgage Loan, Mortgage Loan, Auto Loan, and Personal Loan'),
Row(Type_of_Loan='Payday Loan, Credit-Builder Loan, Home Equity Loan, Credit-Builder Loan, Home Equity Loan, and Student Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Auto Loan, Auto Loan, Debt Consolidation Loan, and Payday Loan'),
Row(Type_of_Loan='Auto Loan, Payday Loan, Credit-Builder Loan, and Personal Loan'),
Row(Type_of_Loan='Student Loan, Personal Loan, Auto Loan, Debt Consolidation Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Payday Loan, Auto Loan, Debt Consolidation Loan, Debt Consolidation Loan, and Auto Loan'),
Row(Type_of_Loan='Auto Loan, Student Loan, Mortgage Loan, and Auto Loan'),
Row(Type_of_Loan='Not Specified, Mortgage Loan, Auto Loan, Not Specified, and Credit-Builder Loan'),
Row(Type_of_Loan='Home Equity Loan, Not Specified, Payday Loan, and Student Loan'),
Row(Type_of_Loan='Home Equity Loan, Student Loan, Credit-Builder Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Payday Loan, Mortgage Loan, Student Loan, Personal Loan, Home Equity Loan, Debt Consolidation Loan, and Student Loan'),
Row(Type_of_Loan='Mortgage Loan, Debt Consolidation Loan, Personal Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Credit-Builder Loan, Student Loan, Mortgage Loan, Personal Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Student Loan, Mortgage Loan, Home Equity Loan, and Home Equity Loan'),
Row(Type_of_Loan='Not Specified, Auto Loan, Auto Loan, and Student Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Mortgage Loan, Personal Loan, Personal Loan, Debt Consolidation Loan, Home Equity Loan, Debt Consolidation Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Payday Loan, Student Loan, Auto Loan, Payday Loan, Auto Loan, Student Loan, and Payday Loan'),
Row(Type_of_Loan='Payday Loan, Not Specified, Student Loan, Home Equity Loan, Debt Consolidation Loan, and Not Specified'),
Row(Type_of_Loan='Payday Loan, Payday Loan, Student Loan, Debt Consolidation Loan, Personal Loan, Payday Loan, Credit-Builder Loan, and Personal Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Credit-Builder Loan, Debt Consolidation Loan, Mortgage Loan, Student Loan, and Payday Loan'),
Row(Type_of_Loan='Auto Loan, Home Equity Loan, Not Specified, Not Specified, Student Loan, Mortgage Loan, and Mortgage Loan'),
Row(Type_of_Loan='Auto Loan, Mortgage Loan, Not Specified, Mortgage Loan, Student Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Not Specified, Student Loan, and Home Equity Loan'),
Row(Type_of_Loan='Not Specified, Credit-Builder Loan, Mortgage Loan, Home Equity Loan, Not Specified, and Personal Loan'),
Row(Type_of_Loan='Payday Loan, Auto Loan, Auto Loan, Credit-Builder Loan, Mortgage Loan, and Home Equity Loan'),
Row(Type_of_Loan='Student Loan, Mortgage Loan, Auto Loan, Home Equity Loan, Student Loan, Debt Consolidation Loan, Home Equity Loan, and Student Loan'),
Row(Type_of_Loan='Not Specified, Home Equity Loan, Personal Loan, and Home Equity Loan'),
Row(Type_of_Loan='Payday Loan, Debt Consolidation Loan, and Personal Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Not Specified, and Payday Loan'),
Row(Type_of_Loan='Auto Loan, Home Equity Loan, Mortgage Loan, Credit-Builder Loan, and Home Equity Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Mortgage Loan, Student Loan, Home Equity Loan, Student Loan, Auto Loan, and Personal Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Student Loan, Debt Consolidation Loan, Debt Consolidation Loan, Credit-Builder Loan, and Not Specified'),
Row(Type_of_Loan='Personal Loan, Payday Loan, Debt Consolidation Loan, Student Loan, Mortgage Loan, Mortgage Loan, and Not Specified'),
Row(Type_of_Loan='Not Specified, Mortgage Loan, Not Specified, Mortgage Loan, Payday Loan, and Personal Loan'),
Row(Type_of_Loan='Not Specified, Personal Loan, Payday Loan, Not Specified, Auto Loan, Not Specified, and Payday Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Payday Loan, Home Equity Loan, Credit-Builder Loan, Personal Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Not Specified, Auto Loan, Payday Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Home Equity Loan, Not Specified, Payday Loan, Payday Loan, Home Equity Loan, Mortgage Loan, and Home Equity Loan'),
Row(Type_of_Loan='Student Loan, Mortgage Loan, Personal Loan, Mortgage Loan, Home Equity Loan, and Payday Loan'),
Row(Type_of_Loan='Mortgage Loan, Not Specified, Not Specified, Personal Loan, Auto Loan, Not Specified, Payday Loan, Debt Consolidation Loan, and Mortgage Loan'),
Row(Type_of_Loan='Payday Loan, Home Equity Loan, Credit-Builder Loan, Student Loan, Debt Consolidation Loan, Payday Loan, and Payday Loan'),
Row(Type_of_Loan='Mortgage Loan, Mortgage Loan, Payday Loan, and Personal Loan'),
Row(Type_of_Loan='Payday Loan, Home Equity Loan, Payday Loan, Debt Consolidation Loan, Personal Loan, Debt Consolidation Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Payday Loan, Auto Loan, Debt Consolidation Loan, Payday Loan, Home Equity Loan, Credit-Builder Loan, Credit-Builder Loan, and Home Equity Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Payday Loan, and Personal Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Home Equity Loan, Mortgage Loan, Credit-Builder Loan, and Home Equity Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Payday Loan, Mortgage Loan, Home Equity Loan, Auto Loan, Credit-Builder Loan, Mortgage Loan, and Student Loan'),
Row(Type_of_Loan='Student Loan, Not Specified, Student Loan, Debt Consolidation Loan, Payday Loan, and Payday Loan'),
Row(Type_of_Loan='Auto Loan, Payday Loan, Mortgage Loan, Payday Loan, and Student Loan'),
Row(Type_of_Loan='Mortgage Loan, Student Loan, Payday Loan, Home Equity Loan, Credit-Builder Loan, Personal Loan, Student Loan, and Personal Loan'),
Row(Type_of_Loan='Not Specified, Debt Consolidation Loan, and Personal Loan'),
Row(Type_of_Loan='Not Specified, Credit-Builder Loan, Credit-Builder Loan, Credit-Builder Loan, Debt Consolidation Loan, and Student Loan'),
Row(Type_of_Loan='Student Loan, Credit-Builder Loan, Payday Loan, and Home Equity Loan'),
Row(Type_of_Loan='Mortgage Loan, Not Specified, and Auto Loan'),
Row(Type_of_Loan='Auto Loan, Personal Loan, Not Specified, Not Specified, Debt Consolidation Loan, Mortgage Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Mortgage Loan, Student Loan, Mortgage Loan, Home Equity Loan, and Payday Loan'),
Row(Type_of_Loan='Personal Loan, Home Equity Loan, Not Specified, Not Specified, Not Specified, Home Equity Loan, Mortgage Loan, Personal Loan, and Not Specified'),
Row(Type_of_Loan='Mortgage Loan, Mortgage Loan, and Personal Loan'),
Row(Type_of_Loan='Not Specified, Student Loan, Student Loan, Mortgage Loan, Payday Loan, Mortgage Loan, and Not Specified'),
Row(Type_of_Loan='Debt Consolidation Loan, Personal Loan, Mortgage Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Mortgage Loan, and Not Specified'),
Row(Type_of_Loan='Home Equity Loan, Debt Consolidation Loan, Not Specified, Payday Loan, Home Equity Loan, Personal Loan, Personal Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Personal Loan, Student Loan, Mortgage Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Not Specified, Personal Loan, Home Equity Loan, Payday Loan, Auto Loan, Student Loan, Payday Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Student Loan, Home Equity Loan, Personal Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Student Loan, Debt Consolidation Loan, Personal Loan, and Personal Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Not Specified, Home Equity Loan, Debt Consolidation Loan, Credit-Builder Loan, Debt Consolidation Loan, and Personal Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Credit-Builder Loan, Not Specified, and Payday Loan'),
Row(Type_of_Loan='Not Specified, Credit-Builder Loan, Home Equity Loan, Student Loan, Personal Loan, Payday Loan, and Home Equity Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Auto Loan, Debt Consolidation Loan, Debt Consolidation Loan, Credit-Builder Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Auto Loan, Personal Loan, Auto Loan, Student Loan, Credit-Builder Loan, and Personal Loan'),
Row(Type_of_Loan='Home Equity Loan, Home Equity Loan, Auto Loan, and Payday Loan'),
Row(Type_of_Loan='Not Specified, Personal Loan, Auto Loan, Credit-Builder Loan, and Personal Loan'),
Row(Type_of_Loan='Personal Loan, Personal Loan, Mortgage Loan, Home Equity Loan, Payday Loan, Personal Loan, Auto Loan, Debt Consolidation Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Payday Loan, Home Equity Loan, Mortgage Loan, Student Loan, and Personal Loan'),
Row(Type_of_Loan='Auto Loan, Payday Loan, Auto Loan, Student Loan, Student Loan, Student Loan, and Home Equity Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Mortgage Loan, Auto Loan, and Personal Loan'),
Row(Type_of_Loan='Student Loan, Credit-Builder Loan, Credit-Builder Loan, Mortgage Loan, Home Equity Loan, Home Equity Loan, Auto Loan, and Payday Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Personal Loan, Payday Loan, Mortgage Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Not Specified, Student Loan, Home Equity Loan, Credit-Builder Loan, and Home Equity Loan'),
Row(Type_of_Loan='Auto Loan, Payday Loan, Not Specified, Student Loan, and Home Equity Loan'),
Row(Type_of_Loan='Mortgage Loan, Personal Loan, and Auto Loan'),
Row(Type_of_Loan='Personal Loan, Personal Loan, and Payday Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Personal Loan, Mortgage Loan, Credit-Builder Loan, and Home Equity Loan'),
Row(Type_of_Loan='Student Loan, Debt Consolidation Loan, and Personal Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Credit-Builder Loan, Payday Loan, Personal Loan, Payday Loan, Not Specified, Not Specified, and Not Specified'),
Row(Type_of_Loan='Student Loan, Payday Loan, Payday Loan, Mortgage Loan, Credit-Builder Loan, Mortgage Loan, Debt Consolidation Loan, and Mortgage Loan'),
Row(Type_of_Loan='Student Loan, Payday Loan, and Mortgage Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Auto Loan, Auto Loan, Not Specified, Mortgage Loan, Home Equity Loan, Debt Consolidation Loan, and Auto Loan'),
Row(Type_of_Loan='Auto Loan, Student Loan, Debt Consolidation Loan, Credit-Builder Loan, Debt Consolidation Loan, and Payday Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Student Loan, Not Specified, and Student Loan'),
Row(Type_of_Loan='Student Loan, Mortgage Loan, Student Loan, Personal Loan, Not Specified, and Mortgage Loan'),
Row(Type_of_Loan='Payday Loan, Not Specified, Payday Loan, Not Specified, Mortgage Loan, Auto Loan, Debt Consolidation Loan, and Student Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Payday Loan, Home Equity Loan, and Payday Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Not Specified, Not Specified, Payday Loan, and Personal Loan'),
Row(Type_of_Loan='Not Specified, Debt Consolidation Loan, Home Equity Loan, Not Specified, Mortgage Loan, Personal Loan, and Personal Loan'),
Row(Type_of_Loan='Payday Loan, Mortgage Loan, Auto Loan, and Mortgage Loan'),
Row(Type_of_Loan='Payday Loan, Payday Loan, Payday Loan, and Auto Loan'),
Row(Type_of_Loan='Payday Loan, Mortgage Loan, Mortgage Loan, Credit-Builder Loan, and Not Specified'),
Row(Type_of_Loan='Not Specified, Payday Loan, Home Equity Loan, Mortgage Loan, Home Equity Loan, Home Equity Loan, Not Specified, and Home Equity Loan'),
Row(Type_of_Loan='Payday Loan, Debt Consolidation Loan, Debt Consolidation Loan, Debt Consolidation Loan, and Payday Loan'),
Row(Type_of_Loan='Auto Loan, Home Equity Loan, Credit-Builder Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Auto Loan, Mortgage Loan, Home Equity Loan, Student Loan, Debt Consolidation Loan, and Auto Loan'),
Row(Type_of_Loan='Payday Loan, Student Loan, Mortgage Loan, and Student Loan'),
Row(Type_of_Loan='Mortgage Loan, Credit-Builder Loan, Payday Loan, and Home Equity Loan'),
Row(Type_of_Loan='Payday Loan, Student Loan, Student Loan, and Payday Loan'),
Row(Type_of_Loan='Student Loan, Home Equity Loan, and Mortgage Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Student Loan, and Student Loan'),
Row(Type_of_Loan='Payday Loan, Payday Loan, Student Loan, Not Specified, Auto Loan, and Payday Loan'),
Row(Type_of_Loan='Mortgage Loan, Mortgage Loan, Credit-Builder Loan, Debt Consolidation Loan, Auto Loan, Student Loan, Payday Loan, Mortgage Loan, and Home Equity Loan'),
Row(Type_of_Loan='Home Equity Loan, Debt Consolidation Loan, Debt Consolidation Loan, Payday Loan, Payday Loan, and Home Equity Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Payday Loan, Auto Loan, and Auto Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Debt Consolidation Loan, Personal Loan, Payday Loan, and Student Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Payday Loan, Home Equity Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Personal Loan, and Student Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Auto Loan, Auto Loan, Not Specified, Personal Loan, Mortgage Loan, and Home Equity Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Home Equity Loan, Personal Loan, Mortgage Loan, Payday Loan, Not Specified, and Auto Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Mortgage Loan, Credit-Builder Loan, and Student Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Not Specified, Mortgage Loan, Home Equity Loan, Not Specified, Auto Loan, and Student Loan'),
Row(Type_of_Loan='Personal Loan, Credit-Builder Loan, and Not Specified'),
Row(Type_of_Loan='Student Loan, Payday Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Personal Loan, Not Specified, Mortgage Loan, Payday Loan, Home Equity Loan, Not Specified, and Mortgage Loan'),
Row(Type_of_Loan='Student Loan, Payday Loan, and Auto Loan'),
Row(Type_of_Loan='Home Equity Loan, Payday Loan, Student Loan, Student Loan, Credit-Builder Loan, and Auto Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Auto Loan, Home Equity Loan, and Not Specified'),
Row(Type_of_Loan='Personal Loan, Debt Consolidation Loan, Not Specified, Auto Loan, Not Specified, and Credit-Builder Loan'),
Row(Type_of_Loan='Not Specified, Not Specified, Mortgage Loan, Debt Consolidation Loan, Debt Consolidation Loan, Personal Loan, Personal Loan, Auto Loan, and Auto Loan'),
Row(Type_of_Loan='Personal Loan, Home Equity Loan, Payday Loan, and Student Loan'),
Row(Type_of_Loan='Payday Loan, Mortgage Loan, Credit-Builder Loan, and Personal Loan'),
Row(Type_of_Loan='Auto Loan, Student Loan, Mortgage Loan, and Student Loan'),
Row(Type_of_Loan='Home Equity Loan, Debt Consolidation Loan, Student Loan, and Personal Loan'),
Row(Type_of_Loan='Mortgage Loan, Student Loan, Payday Loan, Home Equity Loan, Auto Loan, Payday Loan, and Payday Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Mortgage Loan, Home Equity Loan, and Payday Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Credit-Builder Loan, Debt Consolidation Loan, Student Loan, Payday Loan, and Home Equity Loan'),
Row(Type_of_Loan='Mortgage Loan, Mortgage Loan, Home Equity Loan, Auto Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Not Specified, Credit-Builder Loan, Payday Loan, Debt Consolidation Loan, and Home Equity Loan'),
Row(Type_of_Loan='Auto Loan, Mortgage Loan, Student Loan, Home Equity Loan, Auto Loan, and Not Specified'),
Row(Type_of_Loan='Credit-Builder Loan, Auto Loan, Credit-Builder Loan, Payday Loan, Student Loan, and Payday Loan'),
Row(Type_of_Loan='Auto Loan, Debt Consolidation Loan, and Payday Loan'),
Row(Type_of_Loan='Not Specified, Mortgage Loan, Mortgage Loan, Debt Consolidation Loan, and Personal Loan'),
Row(Type_of_Loan='Personal Loan, Home Equity Loan, and Auto Loan'),
Row(Type_of_Loan='Not Specified, Auto Loan, Personal Loan, and Not Specified'),
Row(Type_of_Loan='Credit-Builder Loan, Student Loan, Debt Consolidation Loan, and Home Equity Loan'),
Row(Type_of_Loan='Auto Loan, Home Equity Loan, Not Specified, and Student Loan'),
Row(Type_of_Loan='Personal Loan, Personal Loan, and Home Equity Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Personal Loan, Auto Loan, and Personal Loan'),
Row(Type_of_Loan='Home Equity Loan, Debt Consolidation Loan, Personal Loan, Auto Loan, and Payday Loan'),
Row(Type_of_Loan='Student Loan, Not Specified, Auto Loan, Mortgage Loan, Auto Loan, Auto Loan, Auto Loan, Not Specified, and Debt Consolidation Loan'),
Row(Type_of_Loan='Home Equity Loan, Not Specified, Home Equity Loan, Credit-Builder Loan, Auto Loan, Auto Loan, and Personal Loan'),
Row(Type_of_Loan='Personal Loan, Not Specified, Mortgage Loan, Student Loan, Student Loan, Mortgage Loan, and Personal Loan'),
Row(Type_of_Loan='Student Loan, Credit-Builder Loan, Credit-Builder Loan, Debt Consolidation Loan, Not Specified, Student Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Student Loan, Home Equity Loan, Personal Loan, Auto Loan, and Personal Loan'),
Row(Type_of_Loan='Mortgage Loan, Credit-Builder Loan, Student Loan, Debt Consolidation Loan, Mortgage Loan, and Auto Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Mortgage Loan, Student Loan, and Not Specified'),
Row(Type_of_Loan='Home Equity Loan, Mortgage Loan, Payday Loan, Mortgage Loan, Mortgage Loan, and Payday Loan'),
Row(Type_of_Loan='Mortgage Loan, Credit-Builder Loan, and Student Loan'),
Row(Type_of_Loan='Personal Loan, Not Specified, Payday Loan, Auto Loan, Not Specified, Personal Loan, and Not Specified'),
Row(Type_of_Loan='Student Loan, Debt Consolidation Loan, Home Equity Loan, and Mortgage Loan'),
Row(Type_of_Loan='Not Specified, Home Equity Loan, Debt Consolidation Loan, Debt Consolidation Loan, Debt Consolidation Loan, Home Equity Loan, Auto Loan, Auto Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Home Equity Loan, Payday Loan, Student Loan, and Payday Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Personal Loan, Student Loan, Payday Loan, Auto Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Not Specified, Debt Consolidation Loan, Credit-Builder Loan, and Payday Loan'),
Row(Type_of_Loan='Payday Loan, Payday Loan, and Mortgage Loan'),
Row(Type_of_Loan='Personal Loan, Mortgage Loan, Auto Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Mortgage Loan, Mortgage Loan, Auto Loan, Student Loan, and Personal Loan'),
Row(Type_of_Loan='Not Specified, Auto Loan, Auto Loan, Home Equity Loan, Not Specified, Mortgage Loan, and Student Loan'),
Row(Type_of_Loan='Mortgage Loan, Personal Loan, Credit-Builder Loan, Mortgage Loan, Personal Loan, Payday Loan, Personal Loan, Not Specified, and Student Loan'),
Row(Type_of_Loan='Mortgage Loan, Debt Consolidation Loan, Not Specified, Debt Consolidation Loan, Not Specified, Mortgage Loan, and Mortgage Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Auto Loan, Mortgage Loan, Not Specified, Student Loan, and Student Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Personal Loan, Mortgage Loan, Home Equity Loan, Personal Loan, and Payday Loan'),
Row(Type_of_Loan='Student Loan, Personal Loan, Not Specified, Auto Loan, Payday Loan, Personal Loan, Payday Loan, Student Loan, and Not Specified'),
Row(Type_of_Loan='Mortgage Loan, Student Loan, Mortgage Loan, Not Specified, Auto Loan, Home Equity Loan, and Home Equity Loan'),
Row(Type_of_Loan='Not Specified, Credit-Builder Loan, Credit-Builder Loan, Credit-Builder Loan, Credit-Builder Loan, Mortgage Loan, Mortgage Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Payday Loan, Debt Consolidation Loan, Personal Loan, Mortgage Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Auto Loan, Student Loan, Student Loan, Personal Loan, Personal Loan, and Auto Loan'),
Row(Type_of_Loan='Payday Loan, Home Equity Loan, Not Specified, and Credit-Builder Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Debt Consolidation Loan, Personal Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Not Specified, Personal Loan, Not Specified, and Mortgage Loan'),
Row(Type_of_Loan='Mortgage Loan, Student Loan, Mortgage Loan, Student Loan, Payday Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Auto Loan, Mortgage Loan, Credit-Builder Loan, Mortgage Loan, and Student Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Not Specified, Home Equity Loan, Not Specified, Student Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Student Loan, Student Loan, Not Specified, Payday Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Personal Loan, Debt Consolidation Loan, and Home Equity Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Credit-Builder Loan, Personal Loan, Auto Loan, Credit-Builder Loan, and Home Equity Loan'),
Row(Type_of_Loan='Payday Loan, Payday Loan, Not Specified, and Credit-Builder Loan'),
Row(Type_of_Loan='Auto Loan, Home Equity Loan, Payday Loan, and Mortgage Loan'),
Row(Type_of_Loan='Not Specified, Payday Loan, Personal Loan, Auto Loan, and Student Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Debt Consolidation Loan, Home Equity Loan, Auto Loan, Payday Loan, Home Equity Loan, Debt Consolidation Loan, Home Equity Loan, and Payday Loan'),
Row(Type_of_Loan='Home Equity Loan, Mortgage Loan, Not Specified, and Home Equity Loan'),
Row(Type_of_Loan='Personal Loan, Mortgage Loan, Debt Consolidation Loan, Auto Loan, Mortgage Loan, and Student Loan'),
Row(Type_of_Loan='Auto Loan, Mortgage Loan, Not Specified, Payday Loan, and Mortgage Loan'),
Row(Type_of_Loan='Auto Loan, Not Specified, Payday Loan, Debt Consolidation Loan, Auto Loan, Mortgage Loan, Credit-Builder Loan, Not Specified, and Student Loan'),
Row(Type_of_Loan='Not Specified, Home Equity Loan, Debt Consolidation Loan, and Student Loan'),
Row(Type_of_Loan='Mortgage Loan, Not Specified, Mortgage Loan, and Home Equity Loan'),
Row(Type_of_Loan='Payday Loan, Auto Loan, Student Loan, Credit-Builder Loan, Personal Loan, and Home Equity Loan'),
Row(Type_of_Loan='Home Equity Loan, Credit-Builder Loan, Auto Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Not Specified, Payday Loan, Debt Consolidation Loan, and Payday Loan'),
Row(Type_of_Loan='Mortgage Loan, Not Specified, Auto Loan, Auto Loan, Home Equity Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Not Specified, Home Equity Loan, Mortgage Loan, and Not Specified'),
Row(Type_of_Loan='Personal Loan, Credit-Builder Loan, Student Loan, Mortgage Loan, Not Specified, Debt Consolidation Loan, Auto Loan, Not Specified, and Student Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Student Loan, Credit-Builder Loan, Mortgage Loan, Credit-Builder Loan, and Not Specified'),
Row(Type_of_Loan='Home Equity Loan, Mortgage Loan, Debt Consolidation Loan, Personal Loan, Credit-Builder Loan, Debt Consolidation Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Student Loan, Mortgage Loan, Credit-Builder Loan, Payday Loan, Personal Loan, and Student Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Debt Consolidation Loan, Payday Loan, Auto Loan, Auto Loan, Credit-Builder Loan, Mortgage Loan, Debt Consolidation Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Home Equity Loan, Auto Loan, Not Specified, Payday Loan, Personal Loan, Debt Consolidation Loan, and Mortgage Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Home Equity Loan, Not Specified, Home Equity Loan, Debt Consolidation Loan, Debt Consolidation Loan, Mortgage Loan, and Mortgage Loan'),
Row(Type_of_Loan='Home Equity Loan, Debt Consolidation Loan, Credit-Builder Loan, and Home Equity Loan'),
Row(Type_of_Loan='Not Specified, Personal Loan, Student Loan, Home Equity Loan, Credit-Builder Loan, Mortgage Loan, Debt Consolidation Loan, and Personal Loan'),
Row(Type_of_Loan='Personal Loan, Mortgage Loan, Home Equity Loan, Auto Loan, Personal Loan, Debt Consolidation Loan, Credit-Builder Loan, and Student Loan'),
Row(Type_of_Loan='Mortgage Loan, and Student Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Payday Loan, Debt Consolidation Loan, Credit-Builder Loan, Auto Loan, and Auto Loan'),
Row(Type_of_Loan='Payday Loan, Personal Loan, Not Specified, Not Specified, and Personal Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Payday Loan, Student Loan, Personal Loan, Debt Consolidation Loan, Payday Loan, Credit-Builder Loan, Personal Loan, and Mortgage Loan'),
Row(Type_of_Loan='Not Specified, Personal Loan, Auto Loan, Payday Loan, Not Specified, Student Loan, and Mortgage Loan'),
Row(Type_of_Loan='Mortgage Loan, Mortgage Loan, Home Equity Loan, and Personal Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Credit-Builder Loan, Mortgage Loan, Home Equity Loan, Personal Loan, Mortgage Loan, Home Equity Loan, Debt Consolidation Loan, and Payday Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Not Specified, Auto Loan, Not Specified, and Credit-Builder Loan'),
Row(Type_of_Loan='Personal Loan, Student Loan, Auto Loan, Mortgage Loan, Auto Loan, and Personal Loan'),
Row(Type_of_Loan='Mortgage Loan, Mortgage Loan, Home Equity Loan, Home Equity Loan, Credit-Builder Loan, Not Specified, Home Equity Loan, Payday Loan, and Not Specified'),
Row(Type_of_Loan='Auto Loan, Payday Loan, Student Loan, Home Equity Loan, Payday Loan, and Home Equity Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Not Specified, Credit-Builder Loan, Debt Consolidation Loan, Auto Loan, Mortgage Loan, Payday Loan, and Mortgage Loan'),
Row(Type_of_Loan='Payday Loan, Payday Loan, Not Specified, Student Loan, Mortgage Loan, Payday Loan, Mortgage Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Debt Consolidation Loan, Payday Loan, Personal Loan, Not Specified, and Payday Loan'),
Row(Type_of_Loan='Not Specified, Auto Loan, Home Equity Loan, Payday Loan, Mortgage Loan, Student Loan, Student Loan, Auto Loan, and Auto Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Auto Loan, Home Equity Loan, Home Equity Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Auto Loan, Payday Loan, Debt Consolidation Loan, and Home Equity Loan'),
Row(Type_of_Loan='Auto Loan, Student Loan, Personal Loan, Payday Loan, Payday Loan, and Home Equity Loan'),
Row(Type_of_Loan='Payday Loan, Student Loan, Credit-Builder Loan, Personal Loan, Debt Consolidation Loan, Payday Loan, and Home Equity Loan'),
Row(Type_of_Loan='Not Specified, Payday Loan, Not Specified, Student Loan, Student Loan, Student Loan, Mortgage Loan, Mortgage Loan, and Student Loan'),
Row(Type_of_Loan='Payday Loan, Not Specified, Home Equity Loan, Student Loan, Home Equity Loan, Home Equity Loan, and Not Specified'),
Row(Type_of_Loan='Student Loan, Auto Loan, Credit-Builder Loan, Debt Consolidation Loan, Not Specified, Not Specified, Payday Loan, Payday Loan, and Personal Loan'),
Row(Type_of_Loan='Payday Loan, Payday Loan, Student Loan, and Auto Loan'),
Row(Type_of_Loan='Mortgage Loan, Debt Consolidation Loan, Payday Loan, Home Equity Loan, Home Equity Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Mortgage Loan, Not Specified, Not Specified, and Payday Loan'),
Row(Type_of_Loan='Student Loan, Credit-Builder Loan, Student Loan, Home Equity Loan, and Student Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Credit-Builder Loan, Payday Loan, and Auto Loan'),
Row(Type_of_Loan='Home Equity Loan, Student Loan, Debt Consolidation Loan, Auto Loan, Student Loan, Auto Loan, and Payday Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Home Equity Loan, Not Specified, and Mortgage Loan'),
Row(Type_of_Loan='Auto Loan, Debt Consolidation Loan, Debt Consolidation Loan, Auto Loan, Not Specified, Payday Loan, and Not Specified'),
Row(Type_of_Loan='Home Equity Loan, Not Specified, Credit-Builder Loan, Auto Loan, Student Loan, and Mortgage Loan'),
Row(Type_of_Loan='Personal Loan, Mortgage Loan, Mortgage Loan, Not Specified, Payday Loan, and Not Specified'),
Row(Type_of_Loan='Payday Loan, Auto Loan, and Personal Loan'),
Row(Type_of_Loan='Student Loan, Personal Loan, Debt Consolidation Loan, Payday Loan, Student Loan, Auto Loan, Credit-Builder Loan, Payday Loan, and Student Loan'),
Row(Type_of_Loan='Payday Loan, Student Loan, Auto Loan, Credit-Builder Loan, Debt Consolidation Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Personal Loan, Payday Loan, Mortgage Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Auto Loan, Payday Loan, and Home Equity Loan'),
Row(Type_of_Loan='Student Loan, Credit-Builder Loan, Home Equity Loan, Mortgage Loan, and Student Loan'),
Row(Type_of_Loan='Mortgage Loan, Mortgage Loan, Auto Loan, Debt Consolidation Loan, and Mortgage Loan'),
Row(Type_of_Loan='Mortgage Loan, Home Equity Loan, Credit-Builder Loan, Credit-Builder Loan, Credit-Builder Loan, and Payday Loan'),
Row(Type_of_Loan='Personal Loan, Personal Loan, Debt Consolidation Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Home Equity Loan, Credit-Builder Loan, Credit-Builder Loan, Payday Loan, and Student Loan'),
Row(Type_of_Loan='Personal Loan, Student Loan, Debt Consolidation Loan, Mortgage Loan, Debt Consolidation Loan, Home Equity Loan, and Payday Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Auto Loan, Auto Loan, Student Loan, Auto Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Auto Loan, Student Loan, Auto Loan, Home Equity Loan, Mortgage Loan, Not Specified, and Not Specified'),
Row(Type_of_Loan='Payday Loan, Debt Consolidation Loan, Auto Loan, and Not Specified'),
Row(Type_of_Loan='Credit-Builder Loan, Student Loan, Not Specified, Mortgage Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, and Not Specified'),
Row(Type_of_Loan='Not Specified, Auto Loan, Debt Consolidation Loan, Home Equity Loan, Student Loan, Mortgage Loan, Student Loan, and Not Specified'),
Row(Type_of_Loan='Credit-Builder Loan, Credit-Builder Loan, and Payday Loan'),
Row(Type_of_Loan='Auto Loan, Payday Loan, Credit-Builder Loan, Auto Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Not Specified, Home Equity Loan, and Home Equity Loan'),
Row(Type_of_Loan='Payday Loan, Debt Consolidation Loan, Debt Consolidation Loan, Mortgage Loan, and Personal Loan'),
Row(Type_of_Loan='Mortgage Loan, Home Equity Loan, Personal Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Payday Loan, Student Loan, Personal Loan, Auto Loan, Payday Loan, and Not Specified'),
Row(Type_of_Loan='Debt Consolidation Loan, Personal Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Not Specified, Personal Loan, Home Equity Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Personal Loan, Auto Loan, Auto Loan, Home Equity Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Auto Loan, Payday Loan, and Not Specified'),
Row(Type_of_Loan='Auto Loan, Personal Loan, and Home Equity Loan'),
Row(Type_of_Loan='Payday Loan, Personal Loan, Auto Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Personal Loan, Home Equity Loan, Credit-Builder Loan, Not Specified, Home Equity Loan, Personal Loan, and Personal Loan'),
Row(Type_of_Loan='Mortgage Loan, Payday Loan, Mortgage Loan, and Payday Loan'),
Row(Type_of_Loan='Student Loan, Auto Loan, Student Loan, and Home Equity Loan'),
Row(Type_of_Loan='Student Loan, Payday Loan, Debt Consolidation Loan, and Home Equity Loan'),
Row(Type_of_Loan='Student Loan, Credit-Builder Loan, Debt Consolidation Loan, Mortgage Loan, Not Specified, Auto Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Home Equity Loan, Debt Consolidation Loan, Debt Consolidation Loan, Home Equity Loan, Personal Loan, and Home Equity Loan'),
Row(Type_of_Loan='Not Specified, Not Specified, Auto Loan, Mortgage Loan, and Student Loan'),
Row(Type_of_Loan='Personal Loan, Student Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Not Specified, Debt Consolidation Loan, Student Loan, Payday Loan, Mortgage Loan, and Not Specified'),
Row(Type_of_Loan='Mortgage Loan, Payday Loan, Mortgage Loan, Auto Loan, and Auto Loan'),
Row(Type_of_Loan='Not Specified, Payday Loan, Personal Loan, Home Equity Loan, and Mortgage Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Mortgage Loan, Student Loan, and Payday Loan'),
Row(Type_of_Loan='Home Equity Loan, Payday Loan, Credit-Builder Loan, Not Specified, Personal Loan, Auto Loan, Not Specified, Student Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Personal Loan, Personal Loan, Not Specified, Payday Loan, and Payday Loan'),
Row(Type_of_Loan='Auto Loan, Debt Consolidation Loan, Payday Loan, and Payday Loan'),
Row(Type_of_Loan='Personal Loan, Debt Consolidation Loan, Student Loan, Mortgage Loan, and Personal Loan'),
Row(Type_of_Loan='Home Equity Loan, Debt Consolidation Loan, Debt Consolidation Loan, Not Specified, Payday Loan, Student Loan, Credit-Builder Loan, Personal Loan, and Payday Loan'),
Row(Type_of_Loan='Home Equity Loan, Payday Loan, Auto Loan, Credit-Builder Loan, Payday Loan, Payday Loan, and Mortgage Loan'),
Row(Type_of_Loan='Home Equity Loan, Home Equity Loan, Mortgage Loan, and Payday Loan'),
Row(Type_of_Loan='Student Loan, Credit-Builder Loan, Personal Loan, and Payday Loan'),
Row(Type_of_Loan='Auto Loan, Not Specified, Not Specified, Payday Loan, Not Specified, Not Specified, and Personal Loan'),
Row(Type_of_Loan='Personal Loan, and Home Equity Loan'),
Row(Type_of_Loan='Personal Loan, Auto Loan, and Payday Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Debt Consolidation Loan, and Personal Loan'),
Row(Type_of_Loan='Not Specified, Payday Loan, Mortgage Loan, Payday Loan, Debt Consolidation Loan, and Personal Loan'),
Row(Type_of_Loan='Payday Loan, Credit-Builder Loan, Student Loan, and Personal Loan'),
Row(Type_of_Loan='Student Loan, Home Equity Loan, Credit-Builder Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Home Equity Loan, Home Equity Loan, Student Loan, and Personal Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Auto Loan, Personal Loan, Credit-Builder Loan, Home Equity Loan, Mortgage Loan, and Auto Loan'),
Row(Type_of_Loan='Mortgage Loan, Home Equity Loan, Personal Loan, and Personal Loan'),
Row(Type_of_Loan='Student Loan, Credit-Builder Loan, Mortgage Loan, Home Equity Loan, Not Specified, and Auto Loan'),
Row(Type_of_Loan='Personal Loan, Personal Loan, Home Equity Loan, Payday Loan, Personal Loan, Debt Consolidation Loan, and Payday Loan'),
Row(Type_of_Loan='Student Loan, Home Equity Loan, Not Specified, Debt Consolidation Loan, and Home Equity Loan'),
Row(Type_of_Loan='Not Specified, Credit-Builder Loan, Auto Loan, Personal Loan, Student Loan, Home Equity Loan, and Home Equity Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Home Equity Loan, Debt Consolidation Loan, Not Specified, Credit-Builder Loan, Mortgage Loan, and Personal Loan'),
Row(Type_of_Loan='Student Loan, Payday Loan, Debt Consolidation Loan, Student Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Home Equity Loan, Credit-Builder Loan, Credit-Builder Loan, and Personal Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Mortgage Loan, Not Specified, and Mortgage Loan'),
Row(Type_of_Loan='Personal Loan, Payday Loan, Personal Loan, Auto Loan, Auto Loan, Debt Consolidation Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Student Loan, Home Equity Loan, Credit-Builder Loan, Debt Consolidation Loan, and Student Loan'),
Row(Type_of_Loan='Home Equity Loan, Not Specified, Payday Loan, and Auto Loan'),
Row(Type_of_Loan='Mortgage Loan, Not Specified, Debt Consolidation Loan, Not Specified, Personal Loan, and Mortgage Loan'),
Row(Type_of_Loan='Personal Loan, Not Specified, Personal Loan, Debt Consolidation Loan, Debt Consolidation Loan, and Payday Loan'),
Row(Type_of_Loan='Auto Loan, Home Equity Loan, Mortgage Loan, Auto Loan, Home Equity Loan, Credit-Builder Loan, Mortgage Loan, Student Loan, and Student Loan'),
Row(Type_of_Loan='Student Loan, Auto Loan, Payday Loan, Student Loan, Not Specified, Home Equity Loan, and Personal Loan'),
Row(Type_of_Loan='Student Loan, Payday Loan, and Personal Loan'),
Row(Type_of_Loan='Payday Loan, Credit-Builder Loan, Debt Consolidation Loan, and Mortgage Loan'),
Row(Type_of_Loan='Not Specified, Mortgage Loan, Mortgage Loan, Home Equity Loan, and Personal Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Student Loan, Not Specified, Not Specified, Student Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Auto Loan, Not Specified, Mortgage Loan, Credit-Builder Loan, and Payday Loan'),
Row(Type_of_Loan='Student Loan, Not Specified, and Student Loan'),
Row(Type_of_Loan='Student Loan, Payday Loan, Credit-Builder Loan, Credit-Builder Loan, Debt Consolidation Loan, Credit-Builder Loan, Credit-Builder Loan, and Payday Loan'),
Row(Type_of_Loan='Payday Loan, Debt Consolidation Loan, and Payday Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Mortgage Loan, and Home Equity Loan'),
Row(Type_of_Loan='Auto Loan, Home Equity Loan, Not Specified, Home Equity Loan, Credit-Builder Loan, Student Loan, Student Loan, and Home Equity Loan'),
Row(Type_of_Loan='Home Equity Loan, Debt Consolidation Loan, Not Specified, and Personal Loan'),
Row(Type_of_Loan='Personal Loan, Not Specified, Auto Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Personal Loan, Mortgage Loan, Not Specified, and Payday Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Home Equity Loan, Payday Loan, Not Specified, Payday Loan, Auto Loan, and Auto Loan'),
Row(Type_of_Loan='Home Equity Loan, Not Specified, Not Specified, and Personal Loan'),
Row(Type_of_Loan='Auto Loan, Debt Consolidation Loan, Payday Loan, and Not Specified'),
Row(Type_of_Loan='Personal Loan, Credit-Builder Loan, Mortgage Loan, Student Loan, Mortgage Loan, Credit-Builder Loan, Auto Loan, Mortgage Loan, and Personal Loan'),
Row(Type_of_Loan='Auto Loan, Student Loan, Not Specified, Student Loan, Payday Loan, and Student Loan'),
Row(Type_of_Loan='Payday Loan, Not Specified, and Payday Loan'),
Row(Type_of_Loan='Home Equity Loan, Mortgage Loan, Payday Loan, and Mortgage Loan'),
Row(Type_of_Loan='Student Loan, Credit-Builder Loan, Credit-Builder Loan, and Mortgage Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Auto Loan, Mortgage Loan, Not Specified, Personal Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Auto Loan, Payday Loan, Debt Consolidation Loan, Home Equity Loan, Student Loan, and Student Loan'),
Row(Type_of_Loan='Auto Loan, Personal Loan, Personal Loan, Credit-Builder Loan, Auto Loan, Auto Loan, and Home Equity Loan'),
Row(Type_of_Loan='Auto Loan, Home Equity Loan, Student Loan, Auto Loan, Payday Loan, Credit-Builder Loan, Credit-Builder Loan, and Payday Loan'),
Row(Type_of_Loan='Mortgage Loan, Mortgage Loan, Not Specified, Debt Consolidation Loan, and Home Equity Loan'),
Row(Type_of_Loan='Payday Loan, Debt Consolidation Loan, Student Loan, Auto Loan, Student Loan, and Personal Loan'),
Row(Type_of_Loan='Student Loan, Personal Loan, Debt Consolidation Loan, and Not Specified'),
Row(Type_of_Loan='Auto Loan, Auto Loan, Not Specified, Personal Loan, Payday Loan, and Student Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Mortgage Loan, Debt Consolidation Loan, Payday Loan, Credit-Builder Loan, Debt Consolidation Loan, and Mortgage Loan'),
Row(Type_of_Loan='Payday Loan, Auto Loan, Credit-Builder Loan, Debt Consolidation Loan, Credit-Builder Loan, Auto Loan, and Personal Loan'),
Row(Type_of_Loan='Student Loan, Debt Consolidation Loan, and Payday Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Auto Loan, Home Equity Loan, Not Specified, Debt Consolidation Loan, and Student Loan'),
Row(Type_of_Loan='Not Specified, and Debt Consolidation Loan'),
Row(Type_of_Loan='Student Loan, Personal Loan, Auto Loan, and Auto Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Student Loan, Home Equity Loan, and Payday Loan'),
Row(Type_of_Loan='Payday Loan, Personal Loan, Payday Loan, Home Equity Loan, Student Loan, Home Equity Loan, and Mortgage Loan'),
Row(Type_of_Loan='Home Equity Loan, Personal Loan, and Not Specified'),
Row(Type_of_Loan='Home Equity Loan, Debt Consolidation Loan, Home Equity Loan, Home Equity Loan, Personal Loan, and Mortgage Loan'),
Row(Type_of_Loan='Personal Loan, Not Specified, Debt Consolidation Loan, Mortgage Loan, Auto Loan, Student Loan, and Payday Loan'),
Row(Type_of_Loan='Home Equity Loan, Credit-Builder Loan, Student Loan, Auto Loan, and Payday Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Auto Loan, Personal Loan, Auto Loan, Payday Loan, Debt Consolidation Loan, and Personal Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Personal Loan, Not Specified, Debt Consolidation Loan, and Personal Loan'),
Row(Type_of_Loan='Mortgage Loan, Home Equity Loan, Student Loan, Credit-Builder Loan, Credit-Builder Loan, Personal Loan, Auto Loan, Mortgage Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Mortgage Loan, Debt Consolidation Loan, Auto Loan, and Auto Loan'),
Row(Type_of_Loan='Auto Loan, Mortgage Loan, Personal Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Debt Consolidation Loan, Home Equity Loan, Auto Loan, Payday Loan, Personal Loan, and Home Equity Loan'),
Row(Type_of_Loan='Student Loan, Personal Loan, Mortgage Loan, Credit-Builder Loan, and Mortgage Loan'),
Row(Type_of_Loan='Personal Loan, Mortgage Loan, Not Specified, Payday Loan, and Auto Loan'),
Row(Type_of_Loan='Payday Loan, Not Specified, Student Loan, Not Specified, Personal Loan, Credit-Builder Loan, Payday Loan, Personal Loan, and Auto Loan'),
Row(Type_of_Loan='Payday Loan, Credit-Builder Loan, Personal Loan, and Student Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Student Loan, Not Specified, Payday Loan, Payday Loan, Auto Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Home Equity Loan, Student Loan, Payday Loan, Home Equity Loan, and Not Specified'),
Row(Type_of_Loan='Credit-Builder Loan, Personal Loan, Personal Loan, Not Specified, Mortgage Loan, Mortgage Loan, Credit-Builder Loan, Home Equity Loan, and Auto Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Auto Loan, Personal Loan, Student Loan, Auto Loan, Personal Loan, and Student Loan'),
Row(Type_of_Loan='Not Specified, Credit-Builder Loan, Payday Loan, Mortgage Loan, and Home Equity Loan'),
Row(Type_of_Loan='Payday Loan, Mortgage Loan, Debt Consolidation Loan, Personal Loan, Not Specified, and Auto Loan'),
Row(Type_of_Loan='Not Specified, Debt Consolidation Loan, Personal Loan, Credit-Builder Loan, Home Equity Loan, and Home Equity Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Debt Consolidation Loan, Payday Loan, and Payday Loan'),
Row(Type_of_Loan='Student Loan, Credit-Builder Loan, Personal Loan, and Student Loan'),
Row(Type_of_Loan='Student Loan, Personal Loan, Credit-Builder Loan, Mortgage Loan, Debt Consolidation Loan, Auto Loan, and Personal Loan'),
Row(Type_of_Loan='Not Specified, Home Equity Loan, Payday Loan, Payday Loan, Home Equity Loan, and Mortgage Loan'),
Row(Type_of_Loan='Auto Loan, Debt Consolidation Loan, Home Equity Loan, and Payday Loan'),
Row(Type_of_Loan='Student Loan, Personal Loan, Mortgage Loan, and Student Loan'),
Row(Type_of_Loan='Not Specified, Personal Loan, Not Specified, Personal Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Auto Loan, Mortgage Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Student Loan, Debt Consolidation Loan, Not Specified, Credit-Builder Loan, and Personal Loan'),
Row(Type_of_Loan='Home Equity Loan, Mortgage Loan, Personal Loan, Mortgage Loan, and Student Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Credit-Builder Loan, Credit-Builder Loan, Credit-Builder Loan, and Payday Loan'),
Row(Type_of_Loan='Auto Loan, Personal Loan, Not Specified, Credit-Builder Loan, and Student Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Student Loan, Payday Loan, Home Equity Loan, Auto Loan, Credit-Builder Loan, and Not Specified'),
Row(Type_of_Loan='Credit-Builder Loan, Student Loan, Debt Consolidation Loan, Auto Loan, Not Specified, and Personal Loan'),
Row(Type_of_Loan='Home Equity Loan, Debt Consolidation Loan, Personal Loan, Payday Loan, Personal Loan, Student Loan, Home Equity Loan, Personal Loan, and Personal Loan'),
Row(Type_of_Loan='Student Loan, Debt Consolidation Loan, Payday Loan, Not Specified, Payday Loan, and Student Loan'),
Row(Type_of_Loan='Home Equity Loan, Mortgage Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Home Equity Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Mortgage Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Auto Loan, Credit-Builder Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Payday Loan, Mortgage Loan, Credit-Builder Loan, Mortgage Loan, Not Specified, and Auto Loan'),
Row(Type_of_Loan='Home Equity Loan, Not Specified, Student Loan, Debt Consolidation Loan, Credit-Builder Loan, Student Loan, Auto Loan, and Auto Loan'),
Row(Type_of_Loan='Payday Loan, Student Loan, and Mortgage Loan'),
Row(Type_of_Loan='Personal Loan, Payday Loan, Student Loan, Mortgage Loan, and Not Specified'),
Row(Type_of_Loan='Credit-Builder Loan, Student Loan, and Payday Loan'),
Row(Type_of_Loan='Not Specified, Home Equity Loan, Student Loan, and Payday Loan'),
Row(Type_of_Loan='Personal Loan, Debt Consolidation Loan, Home Equity Loan, Debt Consolidation Loan, Not Specified, Debt Consolidation Loan, Credit-Builder Loan, and Mortgage Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Mortgage Loan, Not Specified, Payday Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Home Equity Loan, Credit-Builder Loan, Mortgage Loan, Mortgage Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Student Loan, Not Specified, Not Specified, Credit-Builder Loan, Mortgage Loan, and Mortgage Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Auto Loan, Student Loan, Not Specified, Auto Loan, Student Loan, Personal Loan, and Home Equity Loan'),
Row(Type_of_Loan='Not Specified, Home Equity Loan, Student Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Student Loan, Home Equity Loan, Debt Consolidation Loan, and Payday Loan'),
Row(Type_of_Loan='Auto Loan, Auto Loan, Payday Loan, Home Equity Loan, Not Specified, Credit-Builder Loan, Auto Loan, and Payday Loan'),
Row(Type_of_Loan='Personal Loan, Not Specified, Payday Loan, Payday Loan, Student Loan, and Student Loan'),
Row(Type_of_Loan='Mortgage Loan, Student Loan, Auto Loan, Student Loan, Not Specified, Mortgage Loan, and Student Loan'),
Row(Type_of_Loan='Payday Loan, Debt Consolidation Loan, Not Specified, and Personal Loan'),
Row(Type_of_Loan='Auto Loan, Payday Loan, Personal Loan, Credit-Builder Loan, Student Loan, Payday Loan, Credit-Builder Loan, Not Specified, and Personal Loan'),
Row(Type_of_Loan='Student Loan, Student Loan, Credit-Builder Loan, Student Loan, Not Specified, Payday Loan, Home Equity Loan, and Student Loan'),
Row(Type_of_Loan='Mortgage Loan, Auto Loan, Student Loan, Student Loan, Mortgage Loan, Payday Loan, and Home Equity Loan'),
Row(Type_of_Loan='Not Specified, Mortgage Loan, Not Specified, Debt Consolidation Loan, Auto Loan, and Student Loan'),
Row(Type_of_Loan='Not Specified, Home Equity Loan, Not Specified, and Personal Loan'),
Row(Type_of_Loan='Mortgage Loan, Mortgage Loan, Auto Loan, Mortgage Loan, Personal Loan, Auto Loan, Personal Loan, and Auto Loan'),
Row(Type_of_Loan='Not Specified, Auto Loan, Mortgage Loan, and Payday Loan'),
Row(Type_of_Loan='Mortgage Loan, Credit-Builder Loan, Home Equity Loan, Auto Loan, Mortgage Loan, Mortgage Loan, and Mortgage Loan'),
Row(Type_of_Loan='Not Specified, Personal Loan, Student Loan, Mortgage Loan, Student Loan, Payday Loan, and Home Equity Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Payday Loan, Auto Loan, and Payday Loan'),
Row(Type_of_Loan='Auto Loan, Personal Loan, Payday Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Mortgage Loan, Credit-Builder Loan, Debt Consolidation Loan, Student Loan, Credit-Builder Loan, and Personal Loan'),
Row(Type_of_Loan='Home Equity Loan, Home Equity Loan, Mortgage Loan, Payday Loan, and Mortgage Loan'),
Row(Type_of_Loan='Personal Loan, Credit-Builder Loan, Payday Loan, Mortgage Loan, and Personal Loan'),
Row(Type_of_Loan='Not Specified, Home Equity Loan, Auto Loan, Payday Loan, Student Loan, Personal Loan, Mortgage Loan, Not Specified, and Auto Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Credit-Builder Loan, and Auto Loan'),
Row(Type_of_Loan='Mortgage Loan, Debt Consolidation Loan, Mortgage Loan, Mortgage Loan, Not Specified, and Mortgage Loan'),
Row(Type_of_Loan='Student Loan, Payday Loan, Student Loan, Mortgage Loan, and Mortgage Loan'),
Row(Type_of_Loan='Student Loan, Auto Loan, Payday Loan, and Mortgage Loan'),
Row(Type_of_Loan='Student Loan, Debt Consolidation Loan, and Mortgage Loan'),
Row(Type_of_Loan='Student Loan, Mortgage Loan, Home Equity Loan, Debt Consolidation Loan, Home Equity Loan, Debt Consolidation Loan, Auto Loan, and Student Loan'),
Row(Type_of_Loan='Mortgage Loan, Auto Loan, Student Loan, Student Loan, Personal Loan, Credit-Builder Loan, Auto Loan, Credit-Builder Loan, and Payday Loan'),
Row(Type_of_Loan='Personal Loan, Home Equity Loan, Credit-Builder Loan, Credit-Builder Loan, and Auto Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Mortgage Loan, Auto Loan, and Home Equity Loan'),
Row(Type_of_Loan='Payday Loan, Auto Loan, Not Specified, and Credit-Builder Loan'),
Row(Type_of_Loan='Auto Loan, Payday Loan, Personal Loan, Auto Loan, Payday Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Student Loan, Not Specified, Not Specified, and Mortgage Loan'),
Row(Type_of_Loan='Home Equity Loan, Debt Consolidation Loan, Auto Loan, Auto Loan, Credit-Builder Loan, Mortgage Loan, Home Equity Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Home Equity Loan, Credit-Builder Loan, Auto Loan, Auto Loan, and Payday Loan'),
Row(Type_of_Loan='Not Specified, Payday Loan, Not Specified, Credit-Builder Loan, Mortgage Loan, Payday Loan, Student Loan, Home Equity Loan, and Payday Loan'),
Row(Type_of_Loan='Payday Loan, Home Equity Loan, Debt Consolidation Loan, and Personal Loan'),
Row(Type_of_Loan='Personal Loan, Payday Loan, Home Equity Loan, Debt Consolidation Loan, and Payday Loan'),
Row(Type_of_Loan='Not Specified, Student Loan, Not Specified, and Auto Loan'),
Row(Type_of_Loan='Payday Loan, Home Equity Loan, Auto Loan, Mortgage Loan, Auto Loan, and Personal Loan'),
Row(Type_of_Loan='Student Loan, Not Specified, Mortgage Loan, and Personal Loan'),
Row(Type_of_Loan='Home Equity Loan, Payday Loan, Student Loan, Student Loan, Credit-Builder Loan, Student Loan, Not Specified, Personal Loan, and Home Equity Loan'),
Row(Type_of_Loan='Student Loan, Debt Consolidation Loan, Not Specified, Student Loan, Student Loan, and Mortgage Loan'),
Row(Type_of_Loan='Personal Loan, Auto Loan, Student Loan, Home Equity Loan, Student Loan, Payday Loan, and Not Specified'),
Row(Type_of_Loan='Auto Loan, Student Loan, Student Loan, Not Specified, Not Specified, Personal Loan, and Personal Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Home Equity Loan, Not Specified, and Payday Loan'),
Row(Type_of_Loan='Auto Loan, Payday Loan, Credit-Builder Loan, Credit-Builder Loan, Debt Consolidation Loan, Auto Loan, and Home Equity Loan'),
Row(Type_of_Loan='Mortgage Loan, Credit-Builder Loan, Home Equity Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Auto Loan, Debt Consolidation Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Personal Loan, Mortgage Loan, Not Specified, Payday Loan, Personal Loan, Not Specified, Not Specified, Home Equity Loan, and Not Specified'),
Row(Type_of_Loan='Payday Loan, Debt Consolidation Loan, Debt Consolidation Loan, Student Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Mortgage Loan, Payday Loan, Student Loan, Debt Consolidation Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Auto Loan, Personal Loan, Debt Consolidation Loan, Home Equity Loan, Credit-Builder Loan, and Not Specified'),
Row(Type_of_Loan='Mortgage Loan, Home Equity Loan, and Personal Loan'),
Row(Type_of_Loan='Mortgage Loan, Personal Loan, Not Specified, and Not Specified'),
Row(Type_of_Loan='Debt Consolidation Loan, Payday Loan, Personal Loan, and Personal Loan'),
Row(Type_of_Loan='Auto Loan, Not Specified, Home Equity Loan, Debt Consolidation Loan, Personal Loan, Auto Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Debt Consolidation Loan, Student Loan, Not Specified, and Credit-Builder Loan'),
Row(Type_of_Loan='Not Specified, Payday Loan, Student Loan, Home Equity Loan, Credit-Builder Loan, Debt Consolidation Loan, Home Equity Loan, and Personal Loan'),
Row(Type_of_Loan='Auto Loan, Personal Loan, Credit-Builder Loan, Credit-Builder Loan, Mortgage Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Not Specified, Credit-Builder Loan, Home Equity Loan, Debt Consolidation Loan, Home Equity Loan, Personal Loan, Debt Consolidation Loan, and Not Specified'),
Row(Type_of_Loan='Student Loan, Debt Consolidation Loan, Credit-Builder Loan, Not Specified, Home Equity Loan, and Home Equity Loan'),
Row(Type_of_Loan='Home Equity Loan, Home Equity Loan, Credit-Builder Loan, and Personal Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Payday Loan, Personal Loan, Credit-Builder Loan, Home Equity Loan, Home Equity Loan, and Personal Loan'),
Row(Type_of_Loan='Not Specified, Mortgage Loan, Payday Loan, Mortgage Loan, Mortgage Loan, and Student Loan'),
Row(Type_of_Loan='Auto Loan, Debt Consolidation Loan, Student Loan, Student Loan, Payday Loan, Credit-Builder Loan, and Auto Loan'),
Row(Type_of_Loan='Not Specified, Student Loan, Payday Loan, Payday Loan, Credit-Builder Loan, Personal Loan, Not Specified, and Payday Loan'),
Row(Type_of_Loan='Student Loan, Payday Loan, Student Loan, Debt Consolidation Loan, Auto Loan, Student Loan, Home Equity Loan, and Home Equity Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Payday Loan, Student Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Student Loan, Mortgage Loan, Not Specified, Mortgage Loan, and Personal Loan'),
Row(Type_of_Loan='Student Loan, Auto Loan, Debt Consolidation Loan, and Payday Loan'),
Row(Type_of_Loan='Payday Loan, Auto Loan, Mortgage Loan, Auto Loan, Debt Consolidation Loan, Not Specified, Not Specified, Student Loan, and Student Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Mortgage Loan, Not Specified, Debt Consolidation Loan, Auto Loan, and Mortgage Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Payday Loan, Debt Consolidation Loan, and Personal Loan'),
Row(Type_of_Loan='Personal Loan, Not Specified, Mortgage Loan, Home Equity Loan, Mortgage Loan, Payday Loan, Payday Loan, Payday Loan, and Home Equity Loan'),
Row(Type_of_Loan='Mortgage Loan, Payday Loan, and Not Specified'),
Row(Type_of_Loan='Not Specified, Student Loan, Payday Loan, Not Specified, Home Equity Loan, Home Equity Loan, and Home Equity Loan'),
Row(Type_of_Loan='Not Specified, Student Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Student Loan, Mortgage Loan, Auto Loan, and Not Specified'),
Row(Type_of_Loan='Student Loan, Mortgage Loan, Payday Loan, Mortgage Loan, Payday Loan, and Student Loan'),
Row(Type_of_Loan='Auto Loan, Student Loan, Personal Loan, Auto Loan, Mortgage Loan, Auto Loan, and Home Equity Loan'),
Row(Type_of_Loan='Not Specified, Mortgage Loan, and Not Specified'),
Row(Type_of_Loan='Debt Consolidation Loan, Payday Loan, and Student Loan'),
Row(Type_of_Loan='Home Equity Loan, Payday Loan, and Home Equity Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Not Specified, Home Equity Loan, and Auto Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Credit-Builder Loan, Payday Loan, Not Specified, Payday Loan, Mortgage Loan, Home Equity Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Auto Loan, Credit-Builder Loan, Payday Loan, Credit-Builder Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Personal Loan, Payday Loan, Student Loan, Payday Loan, and Personal Loan'),
Row(Type_of_Loan='Not Specified, Debt Consolidation Loan, Payday Loan, Home Equity Loan, Credit-Builder Loan, and Payday Loan'),
Row(Type_of_Loan='Student Loan, Student Loan, Personal Loan, Mortgage Loan, Auto Loan, Debt Consolidation Loan, Not Specified, Student Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Student Loan, Personal Loan, Personal Loan, Personal Loan, Not Specified, Debt Consolidation Loan, and Auto Loan'),
Row(Type_of_Loan='Home Equity Loan, Mortgage Loan, Home Equity Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Student Loan, Home Equity Loan, Auto Loan, and Student Loan'),
Row(Type_of_Loan='Personal Loan, Student Loan, Auto Loan, Mortgage Loan, and Mortgage Loan'),
Row(Type_of_Loan='Personal Loan, Personal Loan, Personal Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Personal Loan, Student Loan, Mortgage Loan, Home Equity Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Home Equity Loan, Home Equity Loan, Student Loan, and Personal Loan'),
Row(Type_of_Loan='Auto Loan, Payday Loan, Home Equity Loan, Home Equity Loan, Not Specified, and Debt Consolidation Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Mortgage Loan, and Student Loan'),
Row(Type_of_Loan='Mortgage Loan, Mortgage Loan, Auto Loan, and Student Loan'),
Row(Type_of_Loan='Payday Loan, Payday Loan, Debt Consolidation Loan, Credit-Builder Loan, Not Specified, Personal Loan, Home Equity Loan, and Personal Loan'),
Row(Type_of_Loan='Mortgage Loan, Payday Loan, Debt Consolidation Loan, Personal Loan, Personal Loan, Not Specified, Payday Loan, Home Equity Loan, and Personal Loan'),
Row(Type_of_Loan='Not Specified, Auto Loan, and Student Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, and Auto Loan'),
Row(Type_of_Loan='Payday Loan, and Auto Loan'),
Row(Type_of_Loan='Mortgage Loan, Auto Loan, Home Equity Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Credit-Builder Loan, Debt Consolidation Loan, and Not Specified'),
Row(Type_of_Loan='Personal Loan, Credit-Builder Loan, Personal Loan, Credit-Builder Loan, and Auto Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Credit-Builder Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Mortgage Loan, Debt Consolidation Loan, Student Loan, and Auto Loan'),
Row(Type_of_Loan='Payday Loan, Not Specified, and Not Specified'),
Row(Type_of_Loan='Auto Loan, Student Loan, Credit-Builder Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Debt Consolidation Loan, and Mortgage Loan'),
Row(Type_of_Loan='Auto Loan, Payday Loan, Payday Loan, Credit-Builder Loan, Credit-Builder Loan, Home Equity Loan, Personal Loan, Mortgage Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Mortgage Loan, Auto Loan, Mortgage Loan, Not Specified, Home Equity Loan, Mortgage Loan, and Mortgage Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Student Loan, Personal Loan, Not Specified, Debt Consolidation Loan, Mortgage Loan, and Student Loan'),
Row(Type_of_Loan='Auto Loan, Not Specified, Credit-Builder Loan, Mortgage Loan, and Not Specified'),
Row(Type_of_Loan='Credit-Builder Loan, Credit-Builder Loan, Not Specified, and Auto Loan'),
Row(Type_of_Loan='Mortgage Loan, Payday Loan, Student Loan, Payday Loan, Credit-Builder Loan, and Student Loan'),
Row(Type_of_Loan='Not Specified, Not Specified, Personal Loan, Personal Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Credit-Builder Loan, Debt Consolidation Loan, Debt Consolidation Loan, Payday Loan, Payday Loan, Credit-Builder Loan, and Payday Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Personal Loan, Student Loan, Debt Consolidation Loan, Auto Loan, and Personal Loan'),
Row(Type_of_Loan='Payday Loan, Mortgage Loan, Personal Loan, Auto Loan, Not Specified, Debt Consolidation Loan, and Personal Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Personal Loan, Home Equity Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Personal Loan, Mortgage Loan, Mortgage Loan, and Personal Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Personal Loan, Home Equity Loan, Auto Loan, and Auto Loan'),
Row(Type_of_Loan='Personal Loan, Auto Loan, Debt Consolidation Loan, Credit-Builder Loan, and Payday Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Credit-Builder Loan, Credit-Builder Loan, Home Equity Loan, Student Loan, Home Equity Loan, and Home Equity Loan'),
Row(Type_of_Loan='Home Equity Loan, Mortgage Loan, Mortgage Loan, Home Equity Loan, Credit-Builder Loan, and Mortgage Loan'),
Row(Type_of_Loan='Not Specified, Credit-Builder Loan, Mortgage Loan, Credit-Builder Loan, Credit-Builder Loan, Student Loan, Mortgage Loan, Debt Consolidation Loan, and Mortgage Loan'),
Row(Type_of_Loan='Student Loan, Home Equity Loan, Mortgage Loan, and Payday Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Credit-Builder Loan, Mortgage Loan, Student Loan, Credit-Builder Loan, Mortgage Loan, and Payday Loan'),
Row(Type_of_Loan='Student Loan, Debt Consolidation Loan, Credit-Builder Loan, and Payday Loan'),
Row(Type_of_Loan='Home Equity Loan, Home Equity Loan, Debt Consolidation Loan, Payday Loan, and Mortgage Loan'),
Row(Type_of_Loan='Personal Loan, Personal Loan, Not Specified, and Payday Loan'),
Row(Type_of_Loan='Auto Loan, Not Specified, Auto Loan, Credit-Builder Loan, Personal Loan, Home Equity Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Student Loan, Home Equity Loan, Auto Loan, and Home Equity Loan'),
Row(Type_of_Loan='Personal Loan, Credit-Builder Loan, Mortgage Loan, Personal Loan, Credit-Builder Loan, and Home Equity Loan'),
Row(Type_of_Loan='Student Loan, Not Specified, Mortgage Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Home Equity Loan, Not Specified, Payday Loan, Auto Loan, and Personal Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Debt Consolidation Loan, Not Specified, and Personal Loan'),
Row(Type_of_Loan='Not Specified, Not Specified, Payday Loan, Debt Consolidation Loan, Home Equity Loan, and Payday Loan'),
Row(Type_of_Loan='Student Loan, Debt Consolidation Loan, Not Specified, Credit-Builder Loan, Debt Consolidation Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Auto Loan, Debt Consolidation Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Student Loan, Mortgage Loan, Home Equity Loan, Home Equity Loan, and Personal Loan'),
Row(Type_of_Loan='Not Specified, Home Equity Loan, Personal Loan, Not Specified, Not Specified, Auto Loan, Auto Loan, Debt Consolidation Loan, and Not Specified'),
Row(Type_of_Loan='Payday Loan, Not Specified, Not Specified, Payday Loan, and Auto Loan'),
Row(Type_of_Loan='Payday Loan, Auto Loan, Not Specified, and Debt Consolidation Loan'),
Row(Type_of_Loan='Not Specified, Home Equity Loan, Not Specified, Student Loan, Student Loan, and Auto Loan'),
Row(Type_of_Loan='Mortgage Loan, Student Loan, and Mortgage Loan'),
Row(Type_of_Loan='Personal Loan, Personal Loan, and Mortgage Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Personal Loan, Debt Consolidation Loan, Auto Loan, Home Equity Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Credit-Builder Loan, Student Loan, Home Equity Loan, and Student Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Credit-Builder Loan, Home Equity Loan, Payday Loan, Auto Loan, and Personal Loan'),
Row(Type_of_Loan='Personal Loan, Auto Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Personal Loan, Home Equity Loan, Debt Consolidation Loan, and Auto Loan'),
Row(Type_of_Loan='Student Loan, Auto Loan, Payday Loan, and Student Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Not Specified, Home Equity Loan, Auto Loan, Home Equity Loan, Payday Loan, Mortgage Loan, and Personal Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Payday Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Student Loan, Personal Loan, Mortgage Loan, Auto Loan, Student Loan, Not Specified, Payday Loan, and Auto Loan'),
Row(Type_of_Loan='Student Loan, Personal Loan, Auto Loan, Home Equity Loan, and Home Equity Loan'),
Row(Type_of_Loan='Not Specified, Credit-Builder Loan, Debt Consolidation Loan, Home Equity Loan, Payday Loan, and Not Specified'),
Row(Type_of_Loan='Credit-Builder Loan, Payday Loan, and Payday Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Debt Consolidation Loan, Home Equity Loan, Home Equity Loan, Credit-Builder Loan, and Personal Loan'),
Row(Type_of_Loan='Mortgage Loan, Auto Loan, and Mortgage Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Debt Consolidation Loan, Mortgage Loan, Home Equity Loan, and Personal Loan'),
Row(Type_of_Loan='Not Specified, Credit-Builder Loan, Payday Loan, Home Equity Loan, Home Equity Loan, Payday Loan, Not Specified, and Auto Loan'),
Row(Type_of_Loan='Personal Loan, Not Specified, Not Specified, Auto Loan, Home Equity Loan, Not Specified, and Payday Loan'),
Row(Type_of_Loan='Auto Loan, Student Loan, Home Equity Loan, Payday Loan, Home Equity Loan, and Personal Loan'),
Row(Type_of_Loan='Mortgage Loan, Payday Loan, and Personal Loan'),
Row(Type_of_Loan='Not Specified, Student Loan, Student Loan, and Personal Loan'),
Row(Type_of_Loan='Auto Loan, Credit-Builder Loan, Payday Loan, Home Equity Loan, Payday Loan, Mortgage Loan, Home Equity Loan, and Home Equity Loan'),
Row(Type_of_Loan='Personal Loan, Credit-Builder Loan, Home Equity Loan, Student Loan, Credit-Builder Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Not Specified, Student Loan, Home Equity Loan, Personal Loan, and Personal Loan'),
Row(Type_of_Loan='Mortgage Loan, Not Specified, Not Specified, Payday Loan, Not Specified, and Student Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Auto Loan, Credit-Builder Loan, Personal Loan, Auto Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, and Payday Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Payday Loan, and Mortgage Loan'),
Row(Type_of_Loan='Home Equity Loan, Debt Consolidation Loan, Not Specified, and Home Equity Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Not Specified, and Auto Loan'),
Row(Type_of_Loan='Personal Loan, Credit-Builder Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Auto Loan, Home Equity Loan, and Payday Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Not Specified, and Debt Consolidation Loan'),
Row(Type_of_Loan='Payday Loan, Mortgage Loan, Not Specified, Home Equity Loan, Credit-Builder Loan, Credit-Builder Loan, and Student Loan'),
Row(Type_of_Loan='Not Specified, Student Loan, and Payday Loan'),
Row(Type_of_Loan='Student Loan, Auto Loan, Personal Loan, and Mortgage Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Payday Loan, Credit-Builder Loan, and Not Specified'),
Row(Type_of_Loan='Credit-Builder Loan, Home Equity Loan, Home Equity Loan, Not Specified, and Not Specified'),
Row(Type_of_Loan='Home Equity Loan, Mortgage Loan, Home Equity Loan, Auto Loan, Student Loan, Not Specified, and Mortgage Loan'),
Row(Type_of_Loan='Personal Loan, Debt Consolidation Loan, Personal Loan, Payday Loan, Personal Loan, and Student Loan'),
Row(Type_of_Loan='Not Specified, Personal Loan, Auto Loan, Credit-Builder Loan, Mortgage Loan, and Home Equity Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Payday Loan, Student Loan, Student Loan, Debt Consolidation Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Personal Loan, Debt Consolidation Loan, Not Specified, Personal Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Mortgage Loan, Mortgage Loan, Payday Loan, Home Equity Loan, Student Loan, and Mortgage Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Debt Consolidation Loan, Not Specified, Not Specified, Credit-Builder Loan, Payday Loan, and Not Specified'),
Row(Type_of_Loan='Auto Loan, Debt Consolidation Loan, Not Specified, and Student Loan'),
Row(Type_of_Loan='Payday Loan, Home Equity Loan, Payday Loan, and Home Equity Loan'),
Row(Type_of_Loan='Not Specified, Home Equity Loan, Mortgage Loan, Student Loan, and Mortgage Loan'),
Row(Type_of_Loan='Mortgage Loan, Student Loan, Mortgage Loan, Personal Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Auto Loan, Student Loan, Mortgage Loan, and Personal Loan'),
Row(Type_of_Loan='Payday Loan, Mortgage Loan, Home Equity Loan, Student Loan, Auto Loan, and Not Specified'),
Row(Type_of_Loan='Debt Consolidation Loan, Personal Loan, Payday Loan, Personal Loan, Student Loan, Debt Consolidation Loan, Mortgage Loan, Credit-Builder Loan, and Personal Loan'),
Row(Type_of_Loan='Not Specified, Payday Loan, Mortgage Loan, Debt Consolidation Loan, Auto Loan, Credit-Builder Loan, Personal Loan, Debt Consolidation Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Payday Loan, Personal Loan, Credit-Builder Loan, Payday Loan, Home Equity Loan, Payday Loan, and Auto Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Mortgage Loan, Mortgage Loan, and Personal Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Auto Loan, and Mortgage Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Personal Loan, Mortgage Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Mortgage Loan, Student Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Mortgage Loan, Home Equity Loan, Not Specified, Home Equity Loan, Debt Consolidation Loan, Credit-Builder Loan, and Home Equity Loan'),
Row(Type_of_Loan='Mortgage Loan, Mortgage Loan, and Student Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Student Loan, Personal Loan, Personal Loan, Payday Loan, Mortgage Loan, Mortgage Loan, Student Loan, and Personal Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Personal Loan, Auto Loan, Home Equity Loan, Auto Loan, Student Loan, Payday Loan, and Payday Loan'),
Row(Type_of_Loan='Not Specified, Personal Loan, Student Loan, Not Specified, Payday Loan, Mortgage Loan, Mortgage Loan, Not Specified, and Debt Consolidation Loan'),
Row(Type_of_Loan='Auto Loan, Personal Loan, Home Equity Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Student Loan, Home Equity Loan, Mortgage Loan, and Mortgage Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Mortgage Loan, Not Specified, Payday Loan, Auto Loan, Not Specified, Payday Loan, Home Equity Loan, and Mortgage Loan'),
Row(Type_of_Loan='Personal Loan, Student Loan, Payday Loan, and Not Specified'),
Row(Type_of_Loan='Credit-Builder Loan, Student Loan, Debt Consolidation Loan, Student Loan, Student Loan, Home Equity Loan, Credit-Builder Loan, and Not Specified'),
Row(Type_of_Loan='Mortgage Loan, Credit-Builder Loan, Not Specified, and Not Specified'),
Row(Type_of_Loan='Not Specified, Student Loan, Debt Consolidation Loan, and Student Loan'),
Row(Type_of_Loan='Not Specified, Personal Loan, Auto Loan, Not Specified, and Debt Consolidation Loan'),
Row(Type_of_Loan='Auto Loan, Mortgage Loan, Not Specified, Auto Loan, Debt Consolidation Loan, Credit-Builder Loan, and Home Equity Loan'),
Row(Type_of_Loan='Personal Loan, Auto Loan, Mortgage Loan, Personal Loan, Debt Consolidation Loan, Personal Loan, Student Loan, Home Equity Loan, and Payday Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Debt Consolidation Loan, Payday Loan, Home Equity Loan, Personal Loan, Payday Loan, Payday Loan, Home Equity Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Personal Loan, Home Equity Loan, Mortgage Loan, Student Loan, Student Loan, and Student Loan'),
Row(Type_of_Loan='Auto Loan, Auto Loan, Debt Consolidation Loan, Payday Loan, Debt Consolidation Loan, Debt Consolidation Loan, and Not Specified'),
Row(Type_of_Loan='Debt Consolidation Loan, Not Specified, Debt Consolidation Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Student Loan, Student Loan, Payday Loan, and Home Equity Loan'),
Row(Type_of_Loan='Mortgage Loan, Student Loan, Debt Consolidation Loan, Payday Loan, and Home Equity Loan'),
Row(Type_of_Loan='Payday Loan, Auto Loan, Payday Loan, Credit-Builder Loan, Home Equity Loan, and Home Equity Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Auto Loan, Personal Loan, Debt Consolidation Loan, Debt Consolidation Loan, and Payday Loan'),
Row(Type_of_Loan='Payday Loan, Payday Loan, Credit-Builder Loan, Student Loan, Home Equity Loan, Auto Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Auto Loan, Payday Loan, Debt Consolidation Loan, Mortgage Loan, Credit-Builder Loan, Credit-Builder Loan, and Student Loan'),
Row(Type_of_Loan='Personal Loan, Student Loan, Not Specified, Debt Consolidation Loan, and Student Loan'),
Row(Type_of_Loan='Student Loan, Payday Loan, Debt Consolidation Loan, Not Specified, and Payday Loan'),
Row(Type_of_Loan='Auto Loan, Auto Loan, Credit-Builder Loan, and Personal Loan'),
Row(Type_of_Loan='Mortgage Loan, Not Specified, Home Equity Loan, Auto Loan, Auto Loan, Home Equity Loan, Debt Consolidation Loan, Auto Loan, and Personal Loan'),
Row(Type_of_Loan='Auto Loan, Mortgage Loan, Personal Loan, Home Equity Loan, and Mortgage Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Auto Loan, Credit-Builder Loan, Not Specified, Student Loan, Student Loan, Auto Loan, Home Equity Loan, and Home Equity Loan'),
Row(Type_of_Loan='Home Equity Loan, Mortgage Loan, Mortgage Loan, Home Equity Loan, Personal Loan, Home Equity Loan, Auto Loan, Credit-Builder Loan, and Home Equity Loan'),
Row(Type_of_Loan='Auto Loan, Credit-Builder Loan, Mortgage Loan, Debt Consolidation Loan, Debt Consolidation Loan, Not Specified, and Debt Consolidation Loan'),
Row(Type_of_Loan='Home Equity Loan, Auto Loan, and Home Equity Loan'),
Row(Type_of_Loan='Payday Loan, Student Loan, Auto Loan, Mortgage Loan, Auto Loan, Payday Loan, Mortgage Loan, and Payday Loan'),
Row(Type_of_Loan='Auto Loan, Payday Loan, Not Specified, Auto Loan, Home Equity Loan, and Payday Loan'),
Row(Type_of_Loan='Personal Loan, Payday Loan, Debt Consolidation Loan, and Mortgage Loan'),
Row(Type_of_Loan='Payday Loan, Auto Loan, Student Loan, and Not Specified'),
Row(Type_of_Loan='Student Loan, Payday Loan, Mortgage Loan, Not Specified, Auto Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Personal Loan, Mortgage Loan, Debt Consolidation Loan, Debt Consolidation Loan, Auto Loan, Not Specified, Student Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Student Loan, Auto Loan, Auto Loan, and Not Specified'),
Row(Type_of_Loan='Payday Loan, Debt Consolidation Loan, and Student Loan'),
Row(Type_of_Loan='Auto Loan, Student Loan, Student Loan, and Home Equity Loan'),
Row(Type_of_Loan='Mortgage Loan, Not Specified, Home Equity Loan, Mortgage Loan, Debt Consolidation Loan, Student Loan, and Personal Loan'),
Row(Type_of_Loan='Home Equity Loan, Mortgage Loan, Personal Loan, and Student Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Payday Loan, Payday Loan, and Mortgage Loan'),
Row(Type_of_Loan='Home Equity Loan, Student Loan, Home Equity Loan, Payday Loan, Student Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Home Equity Loan, Student Loan, Auto Loan, and Not Specified'),
Row(Type_of_Loan='Credit-Builder Loan, Home Equity Loan, Not Specified, Mortgage Loan, Home Equity Loan, and Student Loan'),
Row(Type_of_Loan='Home Equity Loan, Home Equity Loan, Credit-Builder Loan, Student Loan, and Mortgage Loan'),
Row(Type_of_Loan='Personal Loan, Payday Loan, Debt Consolidation Loan, Auto Loan, Credit-Builder Loan, Not Specified, and Payday Loan'),
Row(Type_of_Loan='Auto Loan, Mortgage Loan, Personal Loan, Not Specified, Mortgage Loan, Mortgage Loan, Not Specified, Mortgage Loan, and Student Loan'),
Row(Type_of_Loan='Personal Loan, Credit-Builder Loan, Credit-Builder Loan, Auto Loan, Mortgage Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Mortgage Loan, Credit-Builder Loan, Auto Loan, and Personal Loan'),
Row(Type_of_Loan='Student Loan, Not Specified, Payday Loan, Credit-Builder Loan, Credit-Builder Loan, Personal Loan, Not Specified, and Personal Loan'),
Row(Type_of_Loan='Home Equity Loan, Credit-Builder Loan, Personal Loan, Home Equity Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Home Equity Loan, Credit-Builder Loan, Credit-Builder Loan, Credit-Builder Loan, Credit-Builder Loan, and Payday Loan'),
Row(Type_of_Loan='Personal Loan, Debt Consolidation Loan, Student Loan, Personal Loan, Auto Loan, Debt Consolidation Loan, Home Equity Loan, and Not Specified'),
Row(Type_of_Loan='Home Equity Loan, Personal Loan, Home Equity Loan, Personal Loan, Payday Loan, Credit-Builder Loan, Auto Loan, Mortgage Loan, and Not Specified'),
Row(Type_of_Loan='Personal Loan, Home Equity Loan, Home Equity Loan, and Not Specified'),
Row(Type_of_Loan='Debt Consolidation Loan, Home Equity Loan, Payday Loan, Not Specified, Credit-Builder Loan, Credit-Builder Loan, and Auto Loan'),
Row(Type_of_Loan='Credit-Builder Loan, and Auto Loan'),
Row(Type_of_Loan='Mortgage Loan, Not Specified, Home Equity Loan, and Home Equity Loan'),
Row(Type_of_Loan='Home Equity Loan, Debt Consolidation Loan, Auto Loan, Auto Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Auto Loan, Credit-Builder Loan, Not Specified, Mortgage Loan, Personal Loan, and Payday Loan'),
Row(Type_of_Loan='Payday Loan, Debt Consolidation Loan, Debt Consolidation Loan, Mortgage Loan, Payday Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Auto Loan, Auto Loan, and Auto Loan'),
Row(Type_of_Loan='Home Equity Loan, Mortgage Loan, Mortgage Loan, Student Loan, and Not Specified'),
Row(Type_of_Loan='Home Equity Loan, Not Specified, Home Equity Loan, Student Loan, Not Specified, Auto Loan, and Personal Loan'),
Row(Type_of_Loan='Not Specified, Payday Loan, Credit-Builder Loan, Home Equity Loan, Mortgage Loan, and Mortgage Loan'),
Row(Type_of_Loan='Student Loan, Auto Loan, Auto Loan, Auto Loan, and Student Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Home Equity Loan, Mortgage Loan, Not Specified, Home Equity Loan, and Home Equity Loan'),
Row(Type_of_Loan='Student Loan, Auto Loan, Payday Loan, Not Specified, Mortgage Loan, Auto Loan, Personal Loan, Debt Consolidation Loan, and Payday Loan'),
Row(Type_of_Loan='Payday Loan, Personal Loan, Not Specified, and Debt Consolidation Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Student Loan, Mortgage Loan, Home Equity Loan, Student Loan, Personal Loan, Mortgage Loan, and Home Equity Loan'),
Row(Type_of_Loan='Mortgage Loan, Not Specified, Credit-Builder Loan, Debt Consolidation Loan, Not Specified, Mortgage Loan, and Student Loan'),
Row(Type_of_Loan='Home Equity Loan, Mortgage Loan, Personal Loan, Student Loan, Mortgage Loan, Debt Consolidation Loan, Debt Consolidation Loan, Student Loan, and Not Specified'),
Row(Type_of_Loan='Not Specified, Personal Loan, Mortgage Loan, and Personal Loan'),
Row(Type_of_Loan='Mortgage Loan, Home Equity Loan, and Student Loan'),
Row(Type_of_Loan='Mortgage Loan, Credit-Builder Loan, Credit-Builder Loan, and Not Specified'),
Row(Type_of_Loan='Mortgage Loan, Home Equity Loan, Student Loan, Auto Loan, and Personal Loan'),
Row(Type_of_Loan='Student Loan, Home Equity Loan, Personal Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Mortgage Loan, Home Equity Loan, Student Loan, Home Equity Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Not Specified, Credit-Builder Loan, Personal Loan, and Personal Loan'),
Row(Type_of_Loan='Auto Loan, Not Specified, Not Specified, Auto Loan, Mortgage Loan, Home Equity Loan, Payday Loan, and Personal Loan'),
Row(Type_of_Loan='Student Loan, Auto Loan, Not Specified, Credit-Builder Loan, Auto Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Not Specified, Mortgage Loan, and Payday Loan'),
Row(Type_of_Loan='Auto Loan, Payday Loan, Debt Consolidation Loan, and Student Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Student Loan, Debt Consolidation Loan, Mortgage Loan, Student Loan, and Home Equity Loan'),
Row(Type_of_Loan='Home Equity Loan, Student Loan, Credit-Builder Loan, and Home Equity Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Auto Loan, Payday Loan, Credit-Builder Loan, and Student Loan'),
Row(Type_of_Loan='Auto Loan, Not Specified, Payday Loan, Mortgage Loan, Personal Loan, Payday Loan, and Personal Loan'),
Row(Type_of_Loan='Student Loan, Personal Loan, Not Specified, Not Specified, Debt Consolidation Loan, Debt Consolidation Loan, and Auto Loan'),
Row(Type_of_Loan='Payday Loan, Mortgage Loan, and Auto Loan'),
Row(Type_of_Loan='Payday Loan, Credit-Builder Loan, Personal Loan, Auto Loan, Personal Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Personal Loan, Personal Loan, Debt Consolidation Loan, Personal Loan, and Not Specified'),
Row(Type_of_Loan='Mortgage Loan, Credit-Builder Loan, Personal Loan, Mortgage Loan, Personal Loan, Payday Loan, Payday Loan, Not Specified, and Credit-Builder Loan'),
Row(Type_of_Loan='Auto Loan, Payday Loan, Credit-Builder Loan, Personal Loan, Not Specified, and Auto Loan'),
Row(Type_of_Loan='Student Loan, Home Equity Loan, Student Loan, and Auto Loan'),
Row(Type_of_Loan='Student Loan, Debt Consolidation Loan, Not Specified, Mortgage Loan, Personal Loan, Home Equity Loan, and Home Equity Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Auto Loan, Debt Consolidation Loan, and Payday Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Debt Consolidation Loan, Debt Consolidation Loan, Mortgage Loan, Home Equity Loan, and Personal Loan'),
Row(Type_of_Loan='Personal Loan, Auto Loan, Not Specified, and Student Loan'),
Row(Type_of_Loan='Mortgage Loan, Home Equity Loan, Auto Loan, Not Specified, Not Specified, and Debt Consolidation Loan'),
Row(Type_of_Loan='Not Specified, Mortgage Loan, Auto Loan, Mortgage Loan, Mortgage Loan, Personal Loan, Payday Loan, Home Equity Loan, and Student Loan'),
Row(Type_of_Loan='Payday Loan, Not Specified, Auto Loan, Payday Loan, Home Equity Loan, Personal Loan, and Personal Loan'),
Row(Type_of_Loan='Personal Loan, Home Equity Loan, Student Loan, Student Loan, Personal Loan, and Student Loan'),
Row(Type_of_Loan='Not Specified, Payday Loan, Not Specified, Mortgage Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Auto Loan, Student Loan, Debt Consolidation Loan, Credit-Builder Loan, Debt Consolidation Loan, Mortgage Loan, Student Loan, Debt Consolidation Loan, and Student Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Credit-Builder Loan, Student Loan, Mortgage Loan, Auto Loan, and Personal Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Mortgage Loan, Auto Loan, Home Equity Loan, and Student Loan'),
Row(Type_of_Loan='Payday Loan, Payday Loan, Mortgage Loan, Mortgage Loan, Debt Consolidation Loan, Student Loan, and Auto Loan'),
Row(Type_of_Loan='Student Loan, Not Specified, Auto Loan, Mortgage Loan, Auto Loan, Mortgage Loan, and Student Loan'),
Row(Type_of_Loan='Personal Loan, Mortgage Loan, Not Specified, Personal Loan, Not Specified, Mortgage Loan, Not Specified, and Personal Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Personal Loan, Payday Loan, Mortgage Loan, Mortgage Loan, Home Equity Loan, Credit-Builder Loan, Not Specified, and Student Loan'),
Row(Type_of_Loan='Personal Loan, Auto Loan, Auto Loan, Personal Loan, and Student Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Mortgage Loan, Student Loan, Not Specified, and Mortgage Loan'),
Row(Type_of_Loan='Auto Loan, Student Loan, Home Equity Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Auto Loan, Auto Loan, Mortgage Loan, Payday Loan, Home Equity Loan, and Not Specified'),
Row(Type_of_Loan='Not Specified, Credit-Builder Loan, Home Equity Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Home Equity Loan, Mortgage Loan, Payday Loan, and Student Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Mortgage Loan, Home Equity Loan, and Not Specified'),
Row(Type_of_Loan='Student Loan, Personal Loan, and Auto Loan'),
Row(Type_of_Loan='Auto Loan, Auto Loan, Payday Loan, Not Specified, Auto Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Debt Consolidation Loan, Auto Loan, Not Specified, Payday Loan, Not Specified, and Credit-Builder Loan'),
Row(Type_of_Loan='Home Equity Loan, Payday Loan, Credit-Builder Loan, Personal Loan, Debt Consolidation Loan, Home Equity Loan, Debt Consolidation Loan, and Student Loan'),
Row(Type_of_Loan='Home Equity Loan, Student Loan, Mortgage Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Home Equity Loan, Auto Loan, and Not Specified'),
Row(Type_of_Loan='Home Equity Loan, Payday Loan, and Payday Loan'),
Row(Type_of_Loan='Personal Loan, Credit-Builder Loan, Not Specified, and Personal Loan'),
Row(Type_of_Loan='Not Specified, Personal Loan, and Home Equity Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Personal Loan, and Personal Loan'),
Row(Type_of_Loan='Auto Loan, Debt Consolidation Loan, Student Loan, Not Specified, Credit-Builder Loan, Debt Consolidation Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Personal Loan, Not Specified, Not Specified, Student Loan, and Not Specified'),
Row(Type_of_Loan='Home Equity Loan, Payday Loan, Personal Loan, and Auto Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Not Specified, Credit-Builder Loan, Payday Loan, Debt Consolidation Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Mortgage Loan, Personal Loan, Debt Consolidation Loan, Payday Loan, Home Equity Loan, Payday Loan, Not Specified, Mortgage Loan, and Auto Loan'),
Row(Type_of_Loan='Home Equity Loan, Auto Loan, Not Specified, Mortgage Loan, Not Specified, and Personal Loan'),
Row(Type_of_Loan='Payday Loan, Auto Loan, and Mortgage Loan'),
Row(Type_of_Loan='Not Specified, Home Equity Loan, Personal Loan, Student Loan, and Personal Loan'),
Row(Type_of_Loan='Home Equity Loan, Personal Loan, Debt Consolidation Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Not Specified, Personal Loan, Not Specified, Not Specified, Payday Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Home Equity Loan, Mortgage Loan, Student Loan, and Student Loan'),
Row(Type_of_Loan='Auto Loan, Payday Loan, Home Equity Loan, Payday Loan, and Not Specified'),
Row(Type_of_Loan='Auto Loan, Debt Consolidation Loan, Mortgage Loan, and Not Specified'),
Row(Type_of_Loan='Student Loan, Personal Loan, Personal Loan, and Payday Loan'),
Row(Type_of_Loan='Personal Loan, Personal Loan, Not Specified, Auto Loan, and Personal Loan'),
Row(Type_of_Loan='Personal Loan, Payday Loan, Not Specified, Not Specified, Credit-Builder Loan, Personal Loan, and Payday Loan'),
Row(Type_of_Loan='Home Equity Loan, Payday Loan, Personal Loan, Personal Loan, Not Specified, Payday Loan, Credit-Builder Loan, and Mortgage Loan'),
Row(Type_of_Loan='Mortgage Loan, Credit-Builder Loan, Payday Loan, Payday Loan, Student Loan, Auto Loan, Home Equity Loan, and Auto Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Credit-Builder Loan, Not Specified, Home Equity Loan, Student Loan, Mortgage Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Home Equity Loan, Not Specified, Home Equity Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Student Loan, Mortgage Loan, Credit-Builder Loan, and Student Loan'),
Row(Type_of_Loan='Not Specified, Debt Consolidation Loan, Auto Loan, Auto Loan, Personal Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Personal Loan, Personal Loan, Debt Consolidation Loan, Not Specified, Debt Consolidation Loan, and Payday Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Credit-Builder Loan, Student Loan, Home Equity Loan, Payday Loan, and Mortgage Loan'),
Row(Type_of_Loan='Mortgage Loan, Home Equity Loan, Auto Loan, Auto Loan, Home Equity Loan, Not Specified, and Personal Loan'),
Row(Type_of_Loan='Mortgage Loan, Student Loan, Not Specified, Student Loan, Credit-Builder Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Credit-Builder Loan, Personal Loan, Student Loan, Credit-Builder Loan, Not Specified, and Payday Loan'),
Row(Type_of_Loan='Auto Loan, Credit-Builder Loan, Credit-Builder Loan, Not Specified, Auto Loan, and Personal Loan'),
Row(Type_of_Loan='Auto Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Payday Loan, Home Equity Loan, Personal Loan, and Student Loan'),
Row(Type_of_Loan='Auto Loan, Debt Consolidation Loan, Personal Loan, and Not Specified'),
Row(Type_of_Loan='Personal Loan, Home Equity Loan, Student Loan, Home Equity Loan, Payday Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Mortgage Loan, Credit-Builder Loan, and Home Equity Loan'),
Row(Type_of_Loan='Student Loan, and Mortgage Loan'),
Row(Type_of_Loan='Not Specified, Mortgage Loan, Not Specified, and Mortgage Loan'),
Row(Type_of_Loan='Payday Loan, Not Specified, Student Loan, Credit-Builder Loan, Credit-Builder Loan, and Payday Loan'),
Row(Type_of_Loan='Not Specified, Student Loan, Auto Loan, Home Equity Loan, and Mortgage Loan'),
Row(Type_of_Loan='Mortgage Loan, Auto Loan, Mortgage Loan, Not Specified, Payday Loan, and Personal Loan'),
Row(Type_of_Loan='Home Equity Loan, Student Loan, Personal Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Student Loan, Payday Loan, and Payday Loan'),
Row(Type_of_Loan='Mortgage Loan, Auto Loan, Payday Loan, and Student Loan'),
Row(Type_of_Loan='Payday Loan, Auto Loan, Student Loan, Payday Loan, Personal Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Credit-Builder Loan, Student Loan, Credit-Builder Loan, Auto Loan, Not Specified, Personal Loan, Home Equity Loan, and Home Equity Loan'),
Row(Type_of_Loan='Personal Loan, Mortgage Loan, and Home Equity Loan'),
Row(Type_of_Loan='Home Equity Loan, Payday Loan, and Personal Loan'),
Row(Type_of_Loan='Mortgage Loan, Not Specified, Student Loan, and Not Specified'),
Row(Type_of_Loan='Payday Loan, Student Loan, Home Equity Loan, and Mortgage Loan'),
Row(Type_of_Loan='Student Loan, Debt Consolidation Loan, Not Specified, Debt Consolidation Loan, Home Equity Loan, and Home Equity Loan'),
Row(Type_of_Loan='Not Specified, Student Loan, Mortgage Loan, and Student Loan'),
Row(Type_of_Loan='Student Loan, Debt Consolidation Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Home Equity Loan, Auto Loan, Student Loan, Payday Loan, Not Specified, Home Equity Loan, and Mortgage Loan'),
Row(Type_of_Loan='Auto Loan, Not Specified, Payday Loan, Credit-Builder Loan, and Student Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Payday Loan, Mortgage Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Mortgage Loan, Not Specified, Credit-Builder Loan, Not Specified, and Auto Loan'),
Row(Type_of_Loan='Auto Loan, Credit-Builder Loan, and Payday Loan'),
Row(Type_of_Loan='Auto Loan, Mortgage Loan, Auto Loan, Payday Loan, and Not Specified'),
Row(Type_of_Loan='Debt Consolidation Loan, Auto Loan, Student Loan, Mortgage Loan, Not Specified, Credit-Builder Loan, and Not Specified'),
Row(Type_of_Loan='Not Specified, Auto Loan, Home Equity Loan, Payday Loan, Payday Loan, Student Loan, Mortgage Loan, and Not Specified'),
Row(Type_of_Loan='Payday Loan, Payday Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Home Equity Loan, Home Equity Loan, Personal Loan, Home Equity Loan, Auto Loan, Debt Consolidation Loan, Auto Loan, and Payday Loan'),
Row(Type_of_Loan='Auto Loan, Not Specified, Mortgage Loan, and Mortgage Loan'),
Row(Type_of_Loan='Home Equity Loan, Home Equity Loan, Auto Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Not Specified, Debt Consolidation Loan, and Payday Loan'),
Row(Type_of_Loan='Student Loan, Debt Consolidation Loan, Personal Loan, and Payday Loan'),
Row(Type_of_Loan='Home Equity Loan, Payday Loan, Payday Loan, Payday Loan, and Payday Loan'),
Row(Type_of_Loan='Not Specified, Mortgage Loan, Debt Consolidation Loan, Personal Loan, and Auto Loan'),
Row(Type_of_Loan='Home Equity Loan, Home Equity Loan, Home Equity Loan, Not Specified, and Mortgage Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Mortgage Loan, Home Equity Loan, and Mortgage Loan'),
Row(Type_of_Loan='Mortgage Loan, Debt Consolidation Loan, and Mortgage Loan'),
Row(Type_of_Loan='Mortgage Loan, Credit-Builder Loan, Payday Loan, Credit-Builder Loan, Auto Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Personal Loan, Auto Loan, Not Specified, Home Equity Loan, Payday Loan, Auto Loan, and Not Specified'),
Row(Type_of_Loan='Payday Loan, Home Equity Loan, and Student Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Credit-Builder Loan, Home Equity Loan, and Home Equity Loan'),
Row(Type_of_Loan='Home Equity Loan'),
Row(Type_of_Loan='Personal Loan, Personal Loan, Credit-Builder Loan, and Not Specified'),
Row(Type_of_Loan='Payday Loan, Personal Loan, Personal Loan, and Payday Loan'),
Row(Type_of_Loan='Home Equity Loan, Credit-Builder Loan, Mortgage Loan, Student Loan, Student Loan, and Payday Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Not Specified, Payday Loan, Mortgage Loan, Debt Consolidation Loan, Not Specified, Not Specified, Home Equity Loan, and Home Equity Loan'),
Row(Type_of_Loan='Student Loan, Debt Consolidation Loan, Student Loan, and Mortgage Loan'),
Row(Type_of_Loan='Payday Loan, Mortgage Loan, Student Loan, and Auto Loan'),
Row(Type_of_Loan='Home Equity Loan, Payday Loan, Not Specified, Auto Loan, Auto Loan, Payday Loan, and Not Specified'),
Row(Type_of_Loan='Student Loan, Personal Loan, Student Loan, and Mortgage Loan'),
Row(Type_of_Loan='Student Loan, Not Specified, Not Specified, and Personal Loan'),
Row(Type_of_Loan='Not Specified, Auto Loan, and Auto Loan'),
Row(Type_of_Loan='Personal Loan, Credit-Builder Loan, Auto Loan, Mortgage Loan, Student Loan, Debt Consolidation Loan, Home Equity Loan, and Student Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Credit-Builder Loan, Student Loan, Mortgage Loan, and Home Equity Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Not Specified, Mortgage Loan, Mortgage Loan, Not Specified, Mortgage Loan, and Home Equity Loan'),
Row(Type_of_Loan='Personal Loan, Auto Loan, Home Equity Loan, and Auto Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Credit-Builder Loan, and Personal Loan'),
Row(Type_of_Loan='Personal Loan, Payday Loan, Credit-Builder Loan, and Mortgage Loan'),
Row(Type_of_Loan='Auto Loan, Home Equity Loan, Mortgage Loan, Credit-Builder Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Payday Loan, Mortgage Loan, Payday Loan, Debt Consolidation Loan, Home Equity Loan, and Home Equity Loan'),
Row(Type_of_Loan='Mortgage Loan, Auto Loan, Debt Consolidation Loan, and Auto Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Mortgage Loan, Personal Loan, Home Equity Loan, and Student Loan'),
Row(Type_of_Loan='Student Loan, Payday Loan, Personal Loan, Not Specified, Mortgage Loan, Student Loan, Debt Consolidation Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Not Specified, Not Specified, Not Specified, Mortgage Loan, Student Loan, and Auto Loan'),
Row(Type_of_Loan='Payday Loan, Not Specified, Not Specified, Not Specified, and Student Loan'),
Row(Type_of_Loan='Payday Loan, Mortgage Loan, Not Specified, Personal Loan, Not Specified, and Home Equity Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Personal Loan, Student Loan, Personal Loan, and Auto Loan'),
Row(Type_of_Loan='Student Loan, Debt Consolidation Loan, Auto Loan, Not Specified, and Credit-Builder Loan'),
Row(Type_of_Loan='Payday Loan, Auto Loan, Not Specified, Home Equity Loan, Credit-Builder Loan, Mortgage Loan, Not Specified, and Not Specified'),
Row(Type_of_Loan='Not Specified, Personal Loan, Auto Loan, and Home Equity Loan'),
Row(Type_of_Loan='Payday Loan, Auto Loan, Auto Loan, and Auto Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Payday Loan, Personal Loan, and Payday Loan'),
Row(Type_of_Loan='Mortgage Loan, Not Specified, and Student Loan'),
Row(Type_of_Loan='Home Equity Loan, Credit-Builder Loan, Auto Loan, Not Specified, Payday Loan, and Mortgage Loan'),
Row(Type_of_Loan='Personal Loan, Credit-Builder Loan, Auto Loan, and Payday Loan'),
Row(Type_of_Loan='Mortgage Loan, Personal Loan, Payday Loan, and Not Specified'),
Row(Type_of_Loan='Debt Consolidation Loan, Mortgage Loan, Payday Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Payday Loan, Student Loan, Debt Consolidation Loan, and Not Specified'),
Row(Type_of_Loan='Credit-Builder Loan, Personal Loan, Credit-Builder Loan, Mortgage Loan, Personal Loan, Payday Loan, Payday Loan, Payday Loan, and Student Loan'),
Row(Type_of_Loan='Not Specified, Payday Loan, Mortgage Loan, Credit-Builder Loan, Personal Loan, Payday Loan, Debt Consolidation Loan, and Payday Loan'),
Row(Type_of_Loan='Personal Loan, Student Loan, and Not Specified'),
Row(Type_of_Loan='Auto Loan, Student Loan, Credit-Builder Loan, and Personal Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Credit-Builder Loan, and Not Specified'),
Row(Type_of_Loan='Student Loan, Auto Loan, Home Equity Loan, Home Equity Loan, Student Loan, Credit-Builder Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Home Equity Loan, Personal Loan, Personal Loan, Debt Consolidation Loan, Mortgage Loan, Payday Loan, and Student Loan'),
Row(Type_of_Loan='Payday Loan, Home Equity Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Mortgage Loan, and Auto Loan'),
Row(Type_of_Loan='Student Loan, Credit-Builder Loan, Not Specified, Mortgage Loan, Auto Loan, and Payday Loan'),
Row(Type_of_Loan='Auto Loan, Mortgage Loan, Credit-Builder Loan, Home Equity Loan, Credit-Builder Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Home Equity Loan, Home Equity Loan, Student Loan, Not Specified, Home Equity Loan, Student Loan, and Payday Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Not Specified, Auto Loan, Payday Loan, Payday Loan, Mortgage Loan, Auto Loan, Debt Consolidation Loan, and Payday Loan'),
Row(Type_of_Loan='Student Loan, Debt Consolidation Loan, Personal Loan, and Mortgage Loan'),
Row(Type_of_Loan='Payday Loan, Credit-Builder Loan, Credit-Builder Loan, and Auto Loan'),
Row(Type_of_Loan='Mortgage Loan, Debt Consolidation Loan, Payday Loan, Mortgage Loan, Home Equity Loan, Mortgage Loan, Credit-Builder Loan, Credit-Builder Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Not Specified, Mortgage Loan, and Auto Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Mortgage Loan, and Not Specified'),
Row(Type_of_Loan='Mortgage Loan, Payday Loan, Not Specified, Home Equity Loan, Personal Loan, Personal Loan, Debt Consolidation Loan, Personal Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Home Equity Loan, Not Specified, Home Equity Loan, Home Equity Loan, Home Equity Loan, Student Loan, and Student Loan'),
Row(Type_of_Loan='Personal Loan, Student Loan, Credit-Builder Loan, Not Specified, and Auto Loan'),
Row(Type_of_Loan='Student Loan, Debt Consolidation Loan, Home Equity Loan, Personal Loan, Not Specified, Credit-Builder Loan, and Student Loan'),
Row(Type_of_Loan='Personal Loan, Payday Loan, Credit-Builder Loan, Credit-Builder Loan, Student Loan, Auto Loan, and Not Specified'),
Row(Type_of_Loan='Auto Loan, Home Equity Loan, Payday Loan, Mortgage Loan, Payday Loan, and Student Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Home Equity Loan, Not Specified, Auto Loan, Student Loan, Debt Consolidation Loan, Not Specified, Payday Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Personal Loan, Credit-Builder Loan, Credit-Builder Loan, Payday Loan, and Home Equity Loan'),
Row(Type_of_Loan='Personal Loan, Auto Loan, Payday Loan, Not Specified, Payday Loan, Student Loan, Not Specified, and Student Loan'),
Row(Type_of_Loan='Not Specified, Credit-Builder Loan, Mortgage Loan, Not Specified, Mortgage Loan, Not Specified, Auto Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Auto Loan, Home Equity Loan, Payday Loan, Credit-Builder Loan, Auto Loan, Auto Loan, and Student Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Debt Consolidation Loan, Home Equity Loan, Not Specified, Home Equity Loan, Not Specified, Home Equity Loan, and Student Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Personal Loan, Mortgage Loan, Auto Loan, Student Loan, Auto Loan, and Home Equity Loan'),
Row(Type_of_Loan='Auto Loan, Not Specified, Debt Consolidation Loan, and Student Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Auto Loan, Payday Loan, and Not Specified'),
Row(Type_of_Loan='Auto Loan, Mortgage Loan, Not Specified, Debt Consolidation Loan, and Payday Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Payday Loan, and Not Specified'),
Row(Type_of_Loan='Mortgage Loan, Home Equity Loan, Home Equity Loan, and Personal Loan'),
Row(Type_of_Loan='Home Equity Loan, Home Equity Loan, Student Loan, Payday Loan, Not Specified, Student Loan, Mortgage Loan, Student Loan, and Not Specified'),
Row(Type_of_Loan='Debt Consolidation Loan, Auto Loan, Credit-Builder Loan, and Student Loan'),
Row(Type_of_Loan='Home Equity Loan, Personal Loan, Debt Consolidation Loan, Personal Loan, Credit-Builder Loan, Home Equity Loan, Mortgage Loan, and Personal Loan'),
Row(Type_of_Loan='Not Specified, Personal Loan, Home Equity Loan, Personal Loan, Home Equity Loan, Not Specified, and Home Equity Loan'),
Row(Type_of_Loan='Mortgage Loan, Student Loan, Student Loan, Home Equity Loan, Personal Loan, Auto Loan, and Mortgage Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Auto Loan, Personal Loan, Debt Consolidation Loan, Auto Loan, Home Equity Loan, and Student Loan'),
Row(Type_of_Loan='Auto Loan, Credit-Builder Loan, Debt Consolidation Loan, Not Specified, Payday Loan, and Auto Loan'),
Row(Type_of_Loan='Payday Loan, Credit-Builder Loan, Student Loan, and Home Equity Loan'),
Row(Type_of_Loan='Payday Loan, Home Equity Loan, and Personal Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Home Equity Loan, Auto Loan, Payday Loan, Debt Consolidation Loan, Mortgage Loan, Personal Loan, and Payday Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Mortgage Loan, Auto Loan, Mortgage Loan, and Auto Loan'),
Row(Type_of_Loan='Personal Loan, Debt Consolidation Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Home Equity Loan, Credit-Builder Loan, Home Equity Loan, and Student Loan'),
Row(Type_of_Loan='Personal Loan, Mortgage Loan, Home Equity Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Personal Loan, Payday Loan, Debt Consolidation Loan, Mortgage Loan, Personal Loan, and Auto Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Personal Loan, Home Equity Loan, and Not Specified'),
Row(Type_of_Loan='Credit-Builder Loan, Student Loan, Credit-Builder Loan, Student Loan, Debt Consolidation Loan, Personal Loan, Not Specified, Mortgage Loan, and Home Equity Loan'),
Row(Type_of_Loan='Auto Loan, Credit-Builder Loan, Auto Loan, Mortgage Loan, Not Specified, Personal Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Not Specified, Credit-Builder Loan, Debt Consolidation Loan, and Student Loan'),
Row(Type_of_Loan='Mortgage Loan, Payday Loan, Student Loan, and Personal Loan'),
Row(Type_of_Loan='Mortgage Loan, Personal Loan, Not Specified, Debt Consolidation Loan, Credit-Builder Loan, Mortgage Loan, and Payday Loan'),
Row(Type_of_Loan='Mortgage Loan, Student Loan, Payday Loan, Personal Loan, Credit-Builder Loan, Auto Loan, and Student Loan'),
Row(Type_of_Loan='Debt Consolidation Loan, Credit-Builder Loan, Debt Consolidation Loan, and Home Equity Loan'),
Row(Type_of_Loan='Home Equity Loan, Personal Loan, Debt Consolidation Loan, Auto Loan, Not Specified, Not Specified, and Debt Consolidation Loan'),
Row(Type_of_Loan='Student Loan, Mortgage Loan, Debt Consolidation Loan, and Personal Loan'),
Row(Type_of_Loan='Student Loan, Auto Loan, Not Specified, and Personal Loan'),
Row(Type_of_Loan='Not Specified, Student Loan, and Student Loan'),
Row(Type_of_Loan='Personal Loan, Home Equity Loan, Mortgage Loan, and Personal Loan'),
Row(Type_of_Loan='Auto Loan, Home Equity Loan, Student Loan, Credit-Builder Loan, Personal Loan, and Debt Consolidation Loan'),
Row(Type_of_Loan='Student Loan, Student Loan, Debt Consolidation Loan, Credit-Builder Loan, and Not Specified'),
Row(Type_of_Loan='Credit-Builder Loan, Personal Loan, Mortgage Loan, Personal Loan, Not Specified, Auto Loan, and Mortgage Loan'),
Row(Type_of_Loan='Auto Loan, Auto Loan, Credit-Builder Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Credit-Builder Loan, Home Equity Loan, Student Loan, Credit-Builder Loan, and Not Specified'),
Row(Type_of_Loan='Debt Consolidation Loan, Student Loan, Home Equity Loan, Payday Loan, Payday Loan, Debt Consolidation Loan, and Student Loan'),
Row(Type_of_Loan='Mortgage Loan, Credit-Builder Loan, Debt Consolidation Loan, Student Loan, Student Loan, Mortgage Loan, Student Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Personal Loan, Payday Loan, Not Specified, and Personal Loan'),
Row(Type_of_Loan='Home Equity Loan, Personal Loan, and Credit-Builder Loan'),
Row(Type_of_Loan='Not Specified, Auto Loan, Credit-Builder Loan, Personal Loan, Auto Loan, and Auto Loan'),
Row(Type_of_Loan='Payday Loan, Debt Consolidation Loan, Debt Consolidation Loan, and Auto Loan'),
Row(Type_of_Loan='Auto Loan, Mortgage Loan, and Student Loan'),
Row(Type_of_Loan='Not Specified, Personal Loan, Auto Loan, Personal Loan, and Mortgage Loan'),
Row(Type_of_Loan='Mortgage Loan, Debt Consolidation Loan, Not Specified, Personal Loan, Mortgage Loan, Personal Loan, Auto Loan, Debt Consolidation Loan, and Payday Loan'),
Row(Type_of_Loan='Home Equity Loan, Debt Consolidation Loan, Credit-Builder Loan, Student Loan, Home Equity Loan, and Mortgage Loan'),
Row(Type_of_Loan='Auto Loan, Debt Consolidation Loan, Payday Loan, Mortgage Loan, Mortgage Loan, Not Specified, and Student Loan'),
Row(Type_of_Loan='Mortgage Loan, Credit-Builder Loan, Home Equity Loan, Personal Loan, and Payday Loan'),
...]unique_value_dict['Num_of_Loan'][Row(Num_of_Loan='1159'),
Row(Num_of_Loan='1372'),
Row(Num_of_Loan='1241'),
Row(Num_of_Loan='926'),
Row(Num_of_Loan='1265'),
Row(Num_of_Loan='7'),
Row(Num_of_Loan='447'),
Row(Num_of_Loan='1_'),
Row(Num_of_Loan='613'),
Row(Num_of_Loan='574'),
Row(Num_of_Loan='581'),
Row(Num_of_Loan='1485'),
Row(Num_of_Loan='462'),
Row(Num_of_Loan='1171_'),
Row(Num_of_Loan='54'),
Row(Num_of_Loan='1008'),
Row(Num_of_Loan='282'),
Row(Num_of_Loan='940'),
Row(Num_of_Loan='1412'),
Row(Num_of_Loan='1496'),
Row(Num_of_Loan='635'),
Row(Num_of_Loan='132'),
Row(Num_of_Loan='1236'),
Row(Num_of_Loan='1259'),
Row(Num_of_Loan='101'),
Row(Num_of_Loan='1318'),
Row(Num_of_Loan='433'),
Row(Num_of_Loan='415'),
Row(Num_of_Loan='1112'),
Row(Num_of_Loan='323'),
Row(Num_of_Loan='138'),
Row(Num_of_Loan='961'),
Row(Num_of_Loan='351'),
Row(Num_of_Loan='387'),
Row(Num_of_Loan='29'),
Row(Num_of_Loan='991'),
Row(Num_of_Loan='863'),
Row(Num_of_Loan='1470'),
Row(Num_of_Loan='424'),
Row(Num_of_Loan='235_'),
Row(Num_of_Loan='686'),
Row(Num_of_Loan='1135'),
Row(Num_of_Loan='87'),
Row(Num_of_Loan='348'),
Row(Num_of_Loan='3'),
Row(Num_of_Loan='1365'),
Row(Num_of_Loan='1298'),
Row(Num_of_Loan='910'),
Row(Num_of_Loan='652'),
Row(Num_of_Loan='924'),
Row(Num_of_Loan='1300'),
Row(Num_of_Loan='966'),
Row(Num_of_Loan='737'),
Row(Num_of_Loan='995'),
Row(Num_of_Loan='895'),
Row(Num_of_Loan='365'),
Row(Num_of_Loan='146'),
Row(Num_of_Loan='352'),
Row(Num_of_Loan='8'),
Row(Num_of_Loan='1296'),
Row(Num_of_Loan='1227'),
Row(Num_of_Loan='1054'),
Row(Num_of_Loan='1345'),
Row(Num_of_Loan='1482'),
Row(Num_of_Loan='843'),
Row(Num_of_Loan='636'),
Row(Num_of_Loan='628'),
Row(Num_of_Loan='663'),
Row(Num_of_Loan='917'),
Row(Num_of_Loan='1070'),
Row(Num_of_Loan='597'),
Row(Num_of_Loan='1074'),
Row(Num_of_Loan='1027_'),
Row(Num_of_Loan='52'),
Row(Num_of_Loan='251'),
Row(Num_of_Loan='742'),
Row(Num_of_Loan='8_'),
Row(Num_of_Loan='868'),
Row(Num_of_Loan='0'),
Row(Num_of_Loan='1457'),
Row(Num_of_Loan='1416'),
Row(Num_of_Loan='785_'),
Row(Num_of_Loan='1371'),
Row(Num_of_Loan='1340'),
Row(Num_of_Loan='466'),
Row(Num_of_Loan='629'),
Row(Num_of_Loan='697'),
Row(Num_of_Loan='372'),
Row(Num_of_Loan='1185_'),
Row(Num_of_Loan='3_'),
Row(Num_of_Loan='1129_'),
Row(Num_of_Loan='1039'),
Row(Num_of_Loan='2_'),
Row(Num_of_Loan='1228'),
Row(Num_of_Loan='527'),
Row(Num_of_Loan='1387'),
Row(Num_of_Loan='656'),
Row(Num_of_Loan='267'),
Row(Num_of_Loan='284'),
Row(Num_of_Loan='520'),
Row(Num_of_Loan='484'),
Row(Num_of_Loan='1006'),
Row(Num_of_Loan='873'),
Row(Num_of_Loan='897'),
Row(Num_of_Loan='300'),
Row(Num_of_Loan='1030'),
Row(Num_of_Loan='633'),
Row(Num_of_Loan='5'),
Row(Num_of_Loan='1152'),
Row(Num_of_Loan='31'),
Row(Num_of_Loan='1307'),
Row(Num_of_Loan='1106'),
Row(Num_of_Loan='100'),
Row(Num_of_Loan='7_'),
Row(Num_of_Loan='143_'),
Row(Num_of_Loan='18'),
Row(Num_of_Loan='359'),
Row(Num_of_Loan='617'),
Row(Num_of_Loan='70'),
Row(Num_of_Loan='733'),
Row(Num_of_Loan='1354'),
Row(Num_of_Loan='174'),
Row(Num_of_Loan='745'),
Row(Num_of_Loan='302'),
Row(Num_of_Loan='684'),
Row(Num_of_Loan='1182'),
Row(Num_of_Loan='649'),
Row(Num_of_Loan='1424'),
Row(Num_of_Loan='449'),
Row(Num_of_Loan='274'),
Row(Num_of_Loan='639'),
Row(Num_of_Loan='999'),
Row(Num_of_Loan='1294'),
Row(Num_of_Loan='801'),
Row(Num_of_Loan='614'),
Row(Num_of_Loan='601'),
Row(Num_of_Loan='596'),
Row(Num_of_Loan='659'),
Row(Num_of_Loan='9_'),
Row(Num_of_Loan='126'),
Row(Num_of_Loan='17'),
Row(Num_of_Loan='640'),
Row(Num_of_Loan='1433'),
Row(Num_of_Loan='905'),
Row(Num_of_Loan='1131'),
Row(Num_of_Loan='227'),
Row(Num_of_Loan='492'),
Row(Num_of_Loan='889'),
Row(Num_of_Loan='1384'),
Row(Num_of_Loan='548'),
Row(Num_of_Loan='1046'),
Row(Num_of_Loan='1257'),
Row(Num_of_Loan='773'),
Row(Num_of_Loan='1419'),
Row(Num_of_Loan='716'),
Row(Num_of_Loan='621'),
Row(Num_of_Loan='1053'),
Row(Num_of_Loan='1040'),
Row(Num_of_Loan='1137'),
Row(Num_of_Loan='455'),
Row(Num_of_Loan='1444'),
Row(Num_of_Loan='164'),
Row(Num_of_Loan='802'),
Row(Num_of_Loan='147'),
Row(Num_of_Loan='1017'),
Row(Num_of_Loan='208'),
Row(Num_of_Loan='78'),
Row(Num_of_Loan='501'),
Row(Num_of_Loan='1271'),
Row(Num_of_Loan='1196'),
Row(Num_of_Loan='904'),
Row(Num_of_Loan='89'),
Row(Num_of_Loan='228'),
Row(Num_of_Loan='290'),
Row(Num_of_Loan='227_'),
Row(Num_of_Loan='136'),
Row(Num_of_Loan='198'),
Row(Num_of_Loan='943'),
Row(Num_of_Loan='6'),
Row(Num_of_Loan='1216'),
Row(Num_of_Loan='1439'),
Row(Num_of_Loan='935'),
Row(Num_of_Loan='1464'),
Row(Num_of_Loan='841'),
Row(Num_of_Loan='341'),
Row(Num_of_Loan='753'),
Row(Num_of_Loan='653'),
Row(Num_of_Loan='1023'),
Row(Num_of_Loan='1187'),
Row(Num_of_Loan='329'),
Row(Num_of_Loan='967'),
Row(Num_of_Loan='201'),
Row(Num_of_Loan='799'),
Row(Num_of_Loan='344'),
Row(Num_of_Loan='1110'),
Row(Num_of_Loan='229'),
Row(Num_of_Loan='657'),
Row(Num_of_Loan='978'),
Row(Num_of_Loan='1391'),
Row(Num_of_Loan='418'),
Row(Num_of_Loan='1382'),
Row(Num_of_Loan='404'),
Row(Num_of_Loan='19'),
Row(Num_of_Loan='-100'),
Row(Num_of_Loan='464'),
Row(Num_of_Loan='630_'),
Row(Num_of_Loan='23'),
Row(Num_of_Loan='280'),
Row(Num_of_Loan='439'),
Row(Num_of_Loan='41'),
Row(Num_of_Loan='1302'),
Row(Num_of_Loan='1210'),
Row(Num_of_Loan='931'),
Row(Num_of_Loan='55'),
Row(Num_of_Loan='1459_'),
Row(Num_of_Loan='319'),
Row(Num_of_Loan='238'),
Row(Num_of_Loan='696_'),
Row(Num_of_Loan='349'),
Row(Num_of_Loan='719'),
Row(Num_of_Loan='983'),
Row(Num_of_Loan='606'),
Row(Num_of_Loan='507'),
Row(Num_of_Loan='545'),
Row(Num_of_Loan='891'),
Row(Num_of_Loan='1131_'),
Row(Num_of_Loan='936'),
Row(Num_of_Loan='95'),
Row(Num_of_Loan='927'),
Row(Num_of_Loan='1451'),
Row(Num_of_Loan='1312'),
Row(Num_of_Loan='819'),
Row(Num_of_Loan='1461'),
Row(Num_of_Loan='103'),
Row(Num_of_Loan='1297'),
Row(Num_of_Loan='1348'),
Row(Num_of_Loan='1441'),
Row(Num_of_Loan='1465'),
Row(Num_of_Loan='292'),
Row(Num_of_Loan='190'),
Row(Num_of_Loan='288'),
Row(Num_of_Loan='1320_'),
Row(Num_of_Loan='728'),
Row(Num_of_Loan='597_'),
Row(Num_of_Loan='241'),
Row(Num_of_Loan='1225_'),
Row(Num_of_Loan='1393'),
Row(Num_of_Loan='1400'),
Row(Num_of_Loan='193'),
Row(Num_of_Loan='638'),
Row(Num_of_Loan='1209'),
Row(Num_of_Loan='285'),
Row(Num_of_Loan='231'),
Row(Num_of_Loan='834'),
Row(Num_of_Loan='869'),
Row(Num_of_Loan='1077'),
Row(Num_of_Loan='968'),
Row(Num_of_Loan='6_'),
Row(Num_of_Loan='58'),
Row(Num_of_Loan='816'),
Row(Num_of_Loan='1219_'),
Row(Num_of_Loan='394'),
Row(Num_of_Loan='416'),
Row(Num_of_Loan='437'),
Row(Num_of_Loan='1129'),
Row(Num_of_Loan='1363'),
Row(Num_of_Loan='1096'),
Row(Num_of_Loan='5_'),
Row(Num_of_Loan='1181'),
Row(Num_of_Loan='1035'),
Row(Num_of_Loan='832'),
Row(Num_of_Loan='33'),
Row(Num_of_Loan='430'),
Row(Num_of_Loan='242'),
Row(Num_of_Loan='778'),
Row(Num_of_Loan='350'),
Row(Num_of_Loan='622'),
Row(Num_of_Loan='540'),
Row(Num_of_Loan='359_'),
Row(Num_of_Loan='291'),
Row(Num_of_Loan='1127'),
Row(Num_of_Loan='679'),
Row(Num_of_Loan='958'),
Row(Num_of_Loan='952'),
Row(Num_of_Loan='526'),
Row(Num_of_Loan='1478'),
Row(Num_of_Loan='654'),
Row(Num_of_Loan='860'),
Row(Num_of_Loan='1202'),
Row(Num_of_Loan='153'),
Row(Num_of_Loan='1319'),
Row(Num_of_Loan='1430'),
Row(Num_of_Loan='217'),
Row(Num_of_Loan='833'),
Row(Num_of_Loan='1225'),
Row(Num_of_Loan='141'),
Row(Num_of_Loan='515'),
Row(Num_of_Loan='1217'),
Row(Num_of_Loan='243'),
Row(Num_of_Loan='148'),
Row(Num_of_Loan='1320'),
Row(Num_of_Loan='867'),
Row(Num_of_Loan='1204'),
Row(Num_of_Loan='316'),
Row(Num_of_Loan='457'),
Row(Num_of_Loan='1406'),
Row(Num_of_Loan='1313'),
Row(Num_of_Loan='1274'),
Row(Num_of_Loan='838'),
Row(Num_of_Loan='1289'),
Row(Num_of_Loan='84'),
Row(Num_of_Loan='497'),
Row(Num_of_Loan='0_'),
Row(Num_of_Loan='143'),
Row(Num_of_Loan='777'),
Row(Num_of_Loan='1048'),
Row(Num_of_Loan='1447'),
Row(Num_of_Loan='494'),
Row(Num_of_Loan='9'),
Row(Num_of_Loan='701'),
Row(Num_of_Loan='444'),
Row(Num_of_Loan='313'),
Row(Num_of_Loan='562'),
Row(Num_of_Loan='336'),
Row(Num_of_Loan='1495'),
Row(Num_of_Loan='757'),
Row(Num_of_Loan='1353'),
Row(Num_of_Loan='405'),
Row(Num_of_Loan='781'),
Row(Num_of_Loan='32'),
Row(Num_of_Loan='186'),
Row(Num_of_Loan='27_'),
Row(Num_of_Loan='945'),
Row(Num_of_Loan='1484'),
Row(Num_of_Loan='1015'),
Row(Num_of_Loan='538'),
Row(Num_of_Loan='1'),
Row(Num_of_Loan='1150'),
Row(Num_of_Loan='1085'),
Row(Num_of_Loan='289'),
Row(Num_of_Loan='237'),
Row(Num_of_Loan='1088'),
Row(Num_of_Loan='1014'),
Row(Num_of_Loan='378_'),
Row(Num_of_Loan='472'),
Row(Num_of_Loan='859'),
Row(Num_of_Loan='131_'),
Row(Num_of_Loan='571'),
Row(Num_of_Loan='463'),
Row(Num_of_Loan='1474'),
Row(Num_of_Loan='1160'),
Row(Num_of_Loan='56'),
Row(Num_of_Loan='1463'),
Row(Num_of_Loan='295'),
Row(Num_of_Loan='1347_'),
Row(Num_of_Loan='420'),
Row(Num_of_Loan='546'),
Row(Num_of_Loan='563'),
Row(Num_of_Loan='955'),
Row(Num_of_Loan='1036'),
Row(Num_of_Loan='49'),
Row(Num_of_Loan='1359'),
Row(Num_of_Loan='275'),
Row(Num_of_Loan='911'),
Row(Num_of_Loan='172'),
Row(Num_of_Loan='1214'),
Row(Num_of_Loan='65'),
Row(Num_of_Loan='752'),
Row(Num_of_Loan='4'),
Row(Num_of_Loan='1019'),
Row(Num_of_Loan='855'),
Row(Num_of_Loan='39'),
Row(Num_of_Loan='795'),
Row(Num_of_Loan='252'),
Row(Num_of_Loan='510'),
Row(Num_of_Loan='1189'),
Row(Num_of_Loan='720'),
Row(Num_of_Loan='1094'),
Row(Num_of_Loan='696'),
Row(Num_of_Loan='83'),
Row(Num_of_Loan='875'),
Row(Num_of_Loan='4_'),
Row(Num_of_Loan='123'),
Row(Num_of_Loan='1103'),
Row(Num_of_Loan='215'),
Row(Num_of_Loan='1151'),
Row(Num_of_Loan='996'),
Row(Num_of_Loan='157'),
Row(Num_of_Loan='191'),
Row(Num_of_Loan='831'),
Row(Num_of_Loan='182'),
Row(Num_of_Loan='939'),
Row(Num_of_Loan='662'),
Row(Num_of_Loan='1279'),
Row(Num_of_Loan='1132_'),
Row(Num_of_Loan='137'),
Row(Num_of_Loan='1311_'),
Row(Num_of_Loan='392'),
Row(Num_of_Loan='661'),
Row(Num_of_Loan='321'),
Row(Num_of_Loan='1178'),
Row(Num_of_Loan='809'),
Row(Num_of_Loan='1480'),
Row(Num_of_Loan='92_'),
Row(Num_of_Loan='1047'),
Row(Num_of_Loan='579'),
Row(Num_of_Loan='529'),
Row(Num_of_Loan='2'),
Row(Num_of_Loan='1154'),
Row(Num_of_Loan='1002'),
Row(Num_of_Loan='196'),
Row(Num_of_Loan='254'),
Row(Num_of_Loan='848'),
Row(Num_of_Loan='590'),
Row(Num_of_Loan='311'),
Row(Num_of_Loan='192'),
Row(Num_of_Loan='1091'),
Row(Num_of_Loan='814'),
Row(Num_of_Loan='504'),
Row(Num_of_Loan='1369'),
Row(Num_of_Loan='330'),
Row(Num_of_Loan='50'),
Row(Num_of_Loan='1222'),
Row(Num_of_Loan='332'),
Row(Num_of_Loan='820'),
Row(Num_of_Loan='881'),
Row(Num_of_Loan='527_'),
Row(Num_of_Loan='216'),
Row(Num_of_Loan='898'),
Row(Num_of_Loan='119'),
Row(Num_of_Loan='1001'),
Row(Num_of_Loan='699'),
Row(Num_of_Loan='438'),
Row(Num_of_Loan='1329')]Based on the above, it can be seen that Type of Loan has repeated categorial values shown. A customer can have 'Personal Loan' and 'Student Loan', but the value shown is in text/string format. Furthermore, there are instances where the same type of loan is repeated, such as one of the unique value shown is 'Payday Loan, Payday Loan, Payday Loan, and Debt Consolidation Loan'. Does this mean that the customer have 3 Payday Loan or is it just another mistake or error in the input. The unique value dictionary does not fully reflect the updated value as the dictionary was processed before the preprocessing.
The code below is epxlores handling the column 'Type_of_Loan' and also explore the relationship between these two columns.
# Select only the Customer_ID and Type_of_Loan
typeOfLoans = credit_score.select('Customer_ID','Type_of_Loan')
typeOfLoans.show(5, truncate = False)+-----------+-------------------------------------------------+
|Customer_ID|Type_of_Loan |
+-----------+-------------------------------------------------+
|CUS_0x1844 |Not Specified, Student Loan, and Home Equity Loan|
|CUS_0x1844 |Not Specified, Student Loan, and Home Equity Loan|
|CUS_0x1844 |Not Specified, Student Loan, and Home Equity Loan|
|CUS_0x1844 |Not Specified, Student Loan, and Home Equity Loan|
|CUS_0x1844 |Not Specified, Student Loan, and Home Equity Loan|
+-----------+-------------------------------------------------+
only showing top 5 rows
Noted that because it is stored as a string, the last type of loan in the string, consist of the word 'and', which we will be remove. This is because when we split the column into individual values of type of loan with the split function in pyspark, when we split in based on the ',', the value 'and' will be included and that will create another set of unique value.
# Repalce the ' and' with '', an empty value
typeOfLoans = typeOfLoans.withColumn('Type_of_Loan',
F.regexp_replace('Type_of_Loan', ' and', ''))
print('Removed the " and" from the string values')
typeOfLoans.show(5, truncate = False)
# Split the values in 'Type_of_Loan' based on ',' as separator
# Store into column 'Loan_List'
typeOfLoans = typeOfLoans.withColumn('Loan_List',
F.split('Type_of_Loan', ', '))
print('Split the values into a list as shown in with the ' +
'as the square bracket surrounds the values.')
typeOfLoans.select('Customer_ID', 'Loan_List').show(5, truncate = False)
# Create another column to store the exploded value
typeOfLoans = typeOfLoans.withColumn(
'ex_Loan_List',
F.explode('Loan_List')
)
# Print to show result
typeOfLoans.select('Customer_ID', 'ex_Loan_List').show(truncate = False)
typeOfLoans.select('ex_Loan_List').distinct().show(truncate = False)
print('The .explode function has increased the number of rows from 100000 to',
typeOfLoans.count())
# Checkpoint the Dataset
typeOfLoans = typeOfLoans.checkpoint()Removed the " and" from the string values
+-----------+---------------------------------------------+
|Customer_ID|Type_of_Loan |
+-----------+---------------------------------------------+
|CUS_0x1844 |Not Specified, Student Loan, Home Equity Loan|
|CUS_0x1844 |Not Specified, Student Loan, Home Equity Loan|
|CUS_0x1844 |Not Specified, Student Loan, Home Equity Loan|
|CUS_0x1844 |Not Specified, Student Loan, Home Equity Loan|
|CUS_0x1844 |Not Specified, Student Loan, Home Equity Loan|
+-----------+---------------------------------------------+
only showing top 5 rows
Split the values into a list as shown in with the as the square bracket surrounds the values.
+-----------+-----------------------------------------------+
|Customer_ID|Loan_List |
+-----------+-----------------------------------------------+
|CUS_0x1844 |[Not Specified, Student Loan, Home Equity Loan]|
|CUS_0x1844 |[Not Specified, Student Loan, Home Equity Loan]|
|CUS_0x1844 |[Not Specified, Student Loan, Home Equity Loan]|
|CUS_0x1844 |[Not Specified, Student Loan, Home Equity Loan]|
|CUS_0x1844 |[Not Specified, Student Loan, Home Equity Loan]|
+-----------+-----------------------------------------------+
only showing top 5 rows
+-----------+----------------+
|Customer_ID|ex_Loan_List |
+-----------+----------------+
|CUS_0x1844 |Not Specified |
|CUS_0x1844 |Student Loan |
|CUS_0x1844 |Home Equity Loan|
|CUS_0x1844 |Not Specified |
|CUS_0x1844 |Student Loan |
|CUS_0x1844 |Home Equity Loan|
|CUS_0x1844 |Not Specified |
|CUS_0x1844 |Student Loan |
|CUS_0x1844 |Home Equity Loan|
|CUS_0x1844 |Not Specified |
|CUS_0x1844 |Student Loan |
|CUS_0x1844 |Home Equity Loan|
|CUS_0x1844 |Not Specified |
|CUS_0x1844 |Student Loan |
|CUS_0x1844 |Home Equity Loan|
|CUS_0x1844 |Not Specified |
|CUS_0x1844 |Student Loan |
|CUS_0x1844 |Home Equity Loan|
|CUS_0x1844 |Not Specified |
|CUS_0x1844 |Student Loan |
+-----------+----------------+
only showing top 20 rows
+-----------------------+
|ex_Loan_List |
+-----------------------+
|Home Equity Loan |
|Payday Loan |
|Personal Loan |
|Debt Consolidation Loan|
|Mortgage Loan |
|Student Loan |
|Credit-Builder Loan |
|Auto Loan |
|Not Specified |
+-----------------------+
The .explode function has increased the number of rows from 100000 to 353288Now that the type of loan string was split into several values and stored into a list. The explode function will represent one value in the list as one row. Hence, our dataset grew from 100000 to . With all the next steps are right, we should get back 100000 rows of data.
For the next cell of code, it is no better time than now to count how many types of loan is a customer having. This is to check if we need to have the column 'Num_of_Loan', or to drop it from the main dataset.
# Select the Customer ID and Exploded Loan List
# Group them based on Customer ID
# Get count for how many loans that appear in the column 'ex_Loan_List
number_of_loans_derived = typeOfLoans.select('Customer_ID', 'ex_Loan_List')\
.groupBy('Customer_ID')\
.agg((F.count('ex_Loan_List')/8)
.alias('Derived_Num_of_Loan'))
number_of_loans_derived.show()
# Select Customer ID and Number of Loan Column
# Group them based on both columns, and get count
number_of_loans = credit_score.select('Customer_ID', 'Num_of_Loan')\
.groupBy('Customer_ID','Num_of_Loan').count()
number_of_loans.show()
# Join both the tables to have a side by side comparison
joined_num_of_loan = number_of_loans.join(
number_of_loans_derived,
on = 'Customer_ID',
how = 'left'
)
# Show the table, drop the count, as we do not need it
joined_num_of_loan.drop('count').show()+-----------+-------------------+
|Customer_ID|Derived_Num_of_Loan|
+-----------+-------------------+
| CUS_0x1844| 3.0|
| CUS_0x1b0f| 3.0|
| CUS_0x1eae| 4.0|
| CUS_0x1ed5| 3.0|
| CUS_0x2444| 3.0|
| CUS_0x3061| 6.0|
| CUS_0x33d2| 2.0|
| CUS_0x36ab| 6.0|
| CUS_0x3e17| 7.0|
| CUS_0x3f38| 4.0|
| CUS_0x42fb| 6.0|
| CUS_0x4b6b| 3.0|
| CUS_0x4e0d| 2.0|
| CUS_0x5479| 1.0|
| CUS_0x566d| 1.0|
| CUS_0x5a8b| 2.0|
| CUS_0x5d29| 5.0|
| CUS_0x5e1f| 1.0|
| CUS_0x6371| 9.0|
| CUS_0x65b1| 9.0|
+-----------+-------------------+
only showing top 20 rows
+-----------+-----------+-----+
|Customer_ID|Num_of_Loan|count|
+-----------+-----------+-----+
| CUS_0x1844| 3| 8|
| CUS_0x1b0f| 3| 8|
| CUS_0x1eae| 4| 8|
| CUS_0x1ed5| 3| 8|
| CUS_0x2444| 3| 8|
| CUS_0x3061| 6| 8|
| CUS_0x33d2| 2| 8|
| CUS_0x36ab| 6| 8|
| CUS_0x3c41| 0| 8|
| CUS_0x3c95| 0| 8|
| CUS_0x3e17| 7| 8|
| CUS_0x3f38| 4| 8|
| CUS_0x42fb| 6| 8|
| CUS_0x4b6b| 3| 8|
| CUS_0x4e0d| 2| 8|
| CUS_0x5479| 1| 8|
| CUS_0x566d| 1| 8|
| CUS_0x5a8b| 2| 8|
| CUS_0x5d29| 5| 8|
| CUS_0x5e1f| 1| 8|
+-----------+-----------+-----+
only showing top 20 rows
+-----------+-----------+-------------------+
|Customer_ID|Num_of_Loan|Derived_Num_of_Loan|
+-----------+-----------+-------------------+
| CUS_0x1844| 3| 3.0|
| CUS_0x1b0f| 3| 3.0|
| CUS_0x1eae| 4| 4.0|
| CUS_0x1ed5| 3| 3.0|
| CUS_0x2444| 3| 3.0|
| CUS_0x3061| 6| 6.0|
| CUS_0x33d2| 2| 2.0|
| CUS_0x36ab| 6| 6.0|
| CUS_0x3c41| 0| null|
| CUS_0x3c95| 0| null|
| CUS_0x3e17| 7| 7.0|
| CUS_0x3f38| 4| 4.0|
| CUS_0x42fb| 6| 6.0|
| CUS_0x4b6b| 3| 3.0|
| CUS_0x4e0d| 2| 2.0|
| CUS_0x5479| 1| 1.0|
| CUS_0x566d| 1| 1.0|
| CUS_0x5a8b| 2| 2.0|
| CUS_0x5d29| 5| 5.0|
| CUS_0x5e1f| 1| 1.0|
+-----------+-----------+-------------------+
only showing top 20 rows
Based on the result, we noted that the column 'Num_of_Loan' is the same as the amount of occurence of in the type of loan. It is written multiple times to represent the number of the same loan taken. Also, when we group the customer ID and number of loan together, and get the count of how many rows are there with that particular customer ID and number of loan, the count is consistently 8. This is because all the customer entry repeats 8 times. Therefore, when we count the number of loans in the 'number_of_loans_derived' variable, we need to divide by 8 to accurately depict the number of loans the customer has.
Then, the following code will be creating more columns, in which they represent each of the loan. This will reduce the row count back to 100000, if all goes well.
# Create a column and store the default value as 1
exploded_types_of_loan = typeOfLoans.withColumn(
'constant_val',
F.lit(1))
exploded_types_of_loan.show()
# Pivot the unique values from 'ex_Loan_List' into individual columns
pivoted_types_of_loan = exploded_types_of_loan\
.groupBy('Customer_ID')\
.pivot('ex_Loan_List')\
.agg(coalesce(F.first('constant_val')))
# Drop the unneeded columns
pivoted_types_of_loan = pivoted_types_of_loan.drop(
'Type_of_Loan',
'Loan_List',
'ex_Loan_List'
)
pivoted_types_of_loan.show()
# Filling up the null values
pivoted_types_of_loan = pivoted_types_of_loan.fillna(0, subset=pivoted_types_of_loan.columns)
pivoted_types_of_loan.show()
# Joining the pivoted dataset to the main dataset
credit_score = credit_score.join(
pivoted_types_of_loan,
on = 'Customer_ID',
how = 'left'
)
# Drop Type of Loan
credit_score = credit_score.drop('Type_of_Loan')
credit_score = credit_score.checkpoint()
credit_score.show(2, vertical=True)+-----------+--------------------+--------------------+----------------+------------+
|Customer_ID| Type_of_Loan| Loan_List| ex_Loan_List|constant_val|
+-----------+--------------------+--------------------+----------------+------------+
| CUS_0x1844|Not Specified, St...|[Not Specified, S...| Not Specified| 1|
| CUS_0x1844|Not Specified, St...|[Not Specified, S...| Student Loan| 1|
| CUS_0x1844|Not Specified, St...|[Not Specified, S...|Home Equity Loan| 1|
| CUS_0x1844|Not Specified, St...|[Not Specified, S...| Not Specified| 1|
| CUS_0x1844|Not Specified, St...|[Not Specified, S...| Student Loan| 1|
| CUS_0x1844|Not Specified, St...|[Not Specified, S...|Home Equity Loan| 1|
| CUS_0x1844|Not Specified, St...|[Not Specified, S...| Not Specified| 1|
| CUS_0x1844|Not Specified, St...|[Not Specified, S...| Student Loan| 1|
| CUS_0x1844|Not Specified, St...|[Not Specified, S...|Home Equity Loan| 1|
| CUS_0x1844|Not Specified, St...|[Not Specified, S...| Not Specified| 1|
| CUS_0x1844|Not Specified, St...|[Not Specified, S...| Student Loan| 1|
| CUS_0x1844|Not Specified, St...|[Not Specified, S...|Home Equity Loan| 1|
| CUS_0x1844|Not Specified, St...|[Not Specified, S...| Not Specified| 1|
| CUS_0x1844|Not Specified, St...|[Not Specified, S...| Student Loan| 1|
| CUS_0x1844|Not Specified, St...|[Not Specified, S...|Home Equity Loan| 1|
| CUS_0x1844|Not Specified, St...|[Not Specified, S...| Not Specified| 1|
| CUS_0x1844|Not Specified, St...|[Not Specified, S...| Student Loan| 1|
| CUS_0x1844|Not Specified, St...|[Not Specified, S...|Home Equity Loan| 1|
| CUS_0x1844|Not Specified, St...|[Not Specified, S...| Not Specified| 1|
| CUS_0x1844|Not Specified, St...|[Not Specified, S...| Student Loan| 1|
+-----------+--------------------+--------------------+----------------+------------+
only showing top 20 rows
+-----------+---------+-------------------+-----------------------+----------------+-------------+-------------+-----------+-------------+------------+
|Customer_ID|Auto Loan|Credit-Builder Loan|Debt Consolidation Loan|Home Equity Loan|Mortgage Loan|Not Specified|Payday Loan|Personal Loan|Student Loan|
+-----------+---------+-------------------+-----------------------+----------------+-------------+-------------+-----------+-------------+------------+
| CUS_0x1844| null| null| null| 1| null| 1| null| null| 1|
| CUS_0x1b0f| null| null| null| null| 1| null| null| 1| null|
| CUS_0x1eae| null| 1| null| 1| 1| null| null| null| null|
| CUS_0x1ed5| null| null| 1| null| null| null| null| null| 1|
| CUS_0x2444| 1| null| 1| null| null| null| 1| null| null|
| CUS_0x3061| null| null| null| 1| null| 1| 1| null| 1|
| CUS_0x33d2| null| null| null| 1| null| null| 1| null| null|
| CUS_0x36ab| 1| 1| null| 1| 1| 1| null| null| null|
| CUS_0x3e17| 1| 1| null| null| null| 1| 1| null| 1|
| CUS_0x3f38| null| null| null| 1| null| 1| null| 1| 1|
| CUS_0x42fb| null| 1| null| 1| null| null| 1| 1| null|
| CUS_0x4b6b| null| null| null| null| 1| null| 1| null| null|
| CUS_0x4e0d| null| null| null| null| null| 1| 1| null| null|
| CUS_0x5479| null| null| null| 1| null| null| null| null| null|
| CUS_0x566d| null| 1| null| null| null| null| null| null| null|
| CUS_0x5a8b| null| 1| null| null| null| null| 1| null| null|
| CUS_0x5d29| null| null| 1| null| 1| 1| 1| null| null|
| CUS_0x5e1f| null| null| null| null| null| null| 1| null| null|
| CUS_0x6371| 1| null| 1| 1| 1| null| 1| 1| 1|
| CUS_0x65b1| null| null| 1| null| 1| null| 1| 1| 1|
+-----------+---------+-------------------+-----------------------+----------------+-------------+-------------+-----------+-------------+------------+
only showing top 20 rows
+-----------+---------+-------------------+-----------------------+----------------+-------------+-------------+-----------+-------------+------------+
|Customer_ID|Auto Loan|Credit-Builder Loan|Debt Consolidation Loan|Home Equity Loan|Mortgage Loan|Not Specified|Payday Loan|Personal Loan|Student Loan|
+-----------+---------+-------------------+-----------------------+----------------+-------------+-------------+-----------+-------------+------------+
| CUS_0x1844| 0| 0| 0| 1| 0| 1| 0| 0| 1|
| CUS_0x1b0f| 0| 0| 0| 0| 1| 0| 0| 1| 0|
| CUS_0x1eae| 0| 1| 0| 1| 1| 0| 0| 0| 0|
| CUS_0x1ed5| 0| 0| 1| 0| 0| 0| 0| 0| 1|
| CUS_0x2444| 1| 0| 1| 0| 0| 0| 1| 0| 0|
| CUS_0x3061| 0| 0| 0| 1| 0| 1| 1| 0| 1|
| CUS_0x33d2| 0| 0| 0| 1| 0| 0| 1| 0| 0|
| CUS_0x36ab| 1| 1| 0| 1| 1| 1| 0| 0| 0|
| CUS_0x3e17| 1| 1| 0| 0| 0| 1| 1| 0| 1|
| CUS_0x3f38| 0| 0| 0| 1| 0| 1| 0| 1| 1|
| CUS_0x42fb| 0| 1| 0| 1| 0| 0| 1| 1| 0|
| CUS_0x4b6b| 0| 0| 0| 0| 1| 0| 1| 0| 0|
| CUS_0x4e0d| 0| 0| 0| 0| 0| 1| 1| 0| 0|
| CUS_0x5479| 0| 0| 0| 1| 0| 0| 0| 0| 0|
| CUS_0x566d| 0| 1| 0| 0| 0| 0| 0| 0| 0|
| CUS_0x5a8b| 0| 1| 0| 0| 0| 0| 1| 0| 0|
| CUS_0x5d29| 0| 0| 1| 0| 1| 1| 1| 0| 0|
| CUS_0x5e1f| 0| 0| 0| 0| 0| 0| 1| 0| 0|
| CUS_0x6371| 1| 0| 1| 1| 1| 0| 1| 1| 1|
| CUS_0x65b1| 0| 0| 1| 0| 1| 0| 1| 1| 1|
+-----------+---------+-------------------+-----------------------+----------------+-------------+-------------+-----------+-------------+------------+
only showing top 20 rows
-RECORD 0----------------------------------------
Customer_ID | CUS_0x1844
ID | 0x1648e
Month | January
Name | Anthony Deutscha
SSN | 638-11-3367
Credit_Score | Standard
Age | 38
Occupation | Writer
Annual_Income | 9728
Monthly_Inhand_Salary | 636.715
Num_Bank_Accounts | 6
Num_Credit_Card | 6
Interest_Rate | 5
Num_of_Loan | 3
Delay_from_due_date | 12
Num_of_Delayed_Payment | 13
Changed_Credit_Limit | 15
Num_Credit_Inquiries | 6.0
Credit_Mix | Standard
Outstanding_Debt | 1382.42
Credit_Utilization_Ratio | 30.21115362763025
Credit_History_Age | 5 Years and 3 Months
Payment_of_Min_Amount | Yes
Total_EMI_per_month | 23.637195867727538
Amount_invested_monthly | 44.57156941035435
Payment_Behaviour | Low_spent_Small_v...
Monthly_Balance | 285.4627347219181
Auto Loan | 0
Credit-Builder Loan | 0
Debt Consolidation Loan | 0
Home Equity Loan | 1
Mortgage Loan | 0
Not Specified | 1
Payday Loan | 0
Personal Loan | 0
Student Loan | 1
-RECORD 1----------------------------------------
Customer_ID | CUS_0x1844
ID | 0x1648f
Month | February
Name | Anthony Deutscha
SSN | 638-11-3367
Credit_Score | Standard
Age | 38
Occupation | Writer
Annual_Income | 9728
Monthly_Inhand_Salary | 636.715
Num_Bank_Accounts | 6
Num_Credit_Card | 6
Interest_Rate | 5
Num_of_Loan | 3
Delay_from_due_date | 12
Num_of_Delayed_Payment | 13
Changed_Credit_Limit | 15
Num_Credit_Inquiries | 6.0
Credit_Mix | Standard
Outstanding_Debt | 1382.42
Credit_Utilization_Ratio | 30.21115362763025
Credit_History_Age | 5 Years and 3 Months
Payment_of_Min_Amount | Yes
Total_EMI_per_month | 23.637195867727538
Amount_invested_monthly | 44.57156941035435
Payment_Behaviour | Low_spent_Small_v...
Monthly_Balance | 285.4627347219181
Auto Loan | 0
Credit-Builder Loan | 0
Debt Consolidation Loan | 0
Home Equity Loan | 1
Mortgage Loan | 0
Not Specified | 1
Payday Loan | 0
Personal Loan | 0
Student Loan | 1
only showing top 2 rows
columns_to_drop.append('Not Specified')Because there is column called Not Specified, if we drop it, it might not represent 'Num of Loan' as well it could have. Therefore, we will not drop Num_of_Loan but will drop the 'Not Specified' as the it does not represent any type of loan and only represent having 1 more loan or not. Furthermore, the values of all the loans that were pivoted, only consisted of 0 and 1 and do not present any information about the number of loan it has.
Payment Behaviour
Next we will look into 'Payment_Behaviour', which is actually having two column worth of information, placed into one.
unique_value_dict['Payment_Behaviour'][Row(Payment_Behaviour='Low_spent_Small_value_payments'),
Row(Payment_Behaviour='High_spent_Medium_value_payments'),
Row(Payment_Behaviour='High_spent_Small_value_payments'),
Row(Payment_Behaviour='Low_spent_Large_value_payments'),
Row(Payment_Behaviour='Low_spent_Medium_value_payments'),
Row(Payment_Behaviour='High_spent_Large_value_payments'),
Row(Payment_Behaviour='!@9#%8')]First, we need need to deal with the last type of value, '!@9#%8'.
credit_score.select('Payment_Behaviour')\
.groupBy('Payment_Behaviour')\
.count()\
.show()+--------------------+-----+
| Payment_Behaviour|count|
+--------------------+-----+
|Low_spent_Small_v...|36008|
|High_spent_Medium...|20832|
|High_spent_Small_...| 7712|
|Low_spent_Large_v...| 6592|
|Low_spent_Medium_...|10792|
|High_spent_Large_...|15024|
| !@9#%8| 3040|
+--------------------+-----+
We can see that there are about 3072 rows of the unknown input. We can try to run it with the fill_with_most_occured and see what happens.
credit_score = fill_with_most_occured(credit_score, 'Payment_Behaviour')
credit_score = credit_score.checkpoint()GroupData of Payment_Behaviour created.
GroupData of Payment_Behaviour's "Customer_ID" duplicates dropped.
GroupData columns renamed.# Check the Payment Behaviour column
credit_score.select('Payment_Behaviour')\
.groupBy('Payment_Behaviour')\
.count()\
.show()
credit_score.select('Customer_ID', 'Payment_Behaviour')\
.groupBy('Customer_ID','Payment_Behaviour')\
.count()\
.show()
credit_score.select('Customer_ID', 'Payment_Behaviour')\
.groupBy('Customer_ID','Payment_Behaviour')\
.count()\
.filter(col('Payment_Behaviour') == '!@9#%8')\
.show()+--------------------+-----+
| Payment_Behaviour|count|
+--------------------+-----+
|Low_spent_Small_v...|36008|
|High_spent_Medium...|20832|
|High_spent_Small_...| 7712|
|Low_spent_Large_v...| 6592|
|Low_spent_Medium_...|10792|
|High_spent_Large_...|15024|
| !@9#%8| 3040|
+--------------------+-----+
+-----------+--------------------+-----+
|Customer_ID| Payment_Behaviour|count|
+-----------+--------------------+-----+
| CUS_0x1844|Low_spent_Small_v...| 8|
| CUS_0x1b0f|Low_spent_Large_v...| 8|
| CUS_0x1eae|Low_spent_Small_v...| 8|
| CUS_0x1ed5|Low_spent_Small_v...| 8|
| CUS_0x2444|High_spent_Large_...| 8|
| CUS_0x3061|Low_spent_Small_v...| 8|
| CUS_0x33d2|Low_spent_Medium_...| 8|
| CUS_0x36ab|Low_spent_Small_v...| 8|
| CUS_0x3c41|High_spent_Medium...| 8|
| CUS_0x3c95| !@9#%8| 8|
| CUS_0x3e17|High_spent_Medium...| 8|
| CUS_0x3f38|Low_spent_Small_v...| 8|
| CUS_0x42fb|Low_spent_Small_v...| 8|
| CUS_0x4b6b|Low_spent_Small_v...| 8|
| CUS_0x4e0d|Low_spent_Small_v...| 8|
| CUS_0x5479|Low_spent_Small_v...| 8|
| CUS_0x566d|High_spent_Large_...| 8|
| CUS_0x5a8b|High_spent_Medium...| 8|
| CUS_0x5d29|Low_spent_Medium_...| 8|
| CUS_0x5e1f| !@9#%8| 8|
+-----------+--------------------+-----+
only showing top 20 rows
+-----------+-----------------+-----+
|Customer_ID|Payment_Behaviour|count|
+-----------+-----------------+-----+
| CUS_0x3c95| !@9#%8| 8|
| CUS_0x5e1f| !@9#%8| 8|
| CUS_0x63e0| !@9#%8| 8|
| CUS_0x10c0| !@9#%8| 8|
| CUS_0x6f0a| !@9#%8| 8|
| CUS_0x7a8e| !@9#%8| 8|
| CUS_0x51d4| !@9#%8| 8|
| CUS_0x81c3| !@9#%8| 8|
| CUS_0xa4c6| !@9#%8| 8|
| CUS_0x1948| !@9#%8| 8|
| CUS_0x69c6| !@9#%8| 8|
| CUS_0x72e3| !@9#%8| 8|
| CUS_0xa20f| !@9#%8| 8|
| CUS_0xa57| !@9#%8| 8|
| CUS_0x14f5| !@9#%8| 8|
| CUS_0xb362| !@9#%8| 8|
| CUS_0x6b88| !@9#%8| 8|
| CUS_0x9885| !@9#%8| 8|
| CUS_0x1232| !@9#%8| 8|
| CUS_0x28ef| !@9#%8| 8|
+-----------+-----------------+-----+
only showing top 20 rows
Based on the results above, the fill_with_most_occured function did not work because the value of '!@9#%8' is the majority value for 3072 rows of data. Hence, these might rows of data might need to be dropped.
# Filter out the rows that meet the requirement
credit_score = credit_score.filter(~(col('Payment_Behaviour') == '!@9#%8'))
credit_score = credit_score.checkpoint()
# Print count to verify if the rows have been dropped.
credit_score.count()96960split_pb = credit_score.select(
'Customer_ID',
'Payment_Behaviour')
# Split based on '_'
split_pb = split_pb.withColumn(
'Payment_Behaviour',
F.split('Payment_Behaviour', '_'))
split_pb.show(truncate = False)
# Get Item Spent
split_pb = split_pb.withColumn(
'Spending Frequency',
col('Payment_Behaviour').getItem(0))
split_pb.show(truncate = False)
# Get Item Value Payment
split_pb = split_pb.withColumn(
'Average Size of Payment',
col('Payment_Behaviour').getItem(2))
split_pb.show(truncate = False)
# Drop Payment_Behaviour
split_pb = split_pb.drop('Payment_Behaviour')
columns_to_drop.append('Payment_Behaviour')
# Show split_pb
split_pb.show()+-----------+------------------------------------+
|Customer_ID|Payment_Behaviour |
+-----------+------------------------------------+
|CUS_0x1844 |[Low, spent, Small, value, payments]|
|CUS_0x1844 |[Low, spent, Small, value, payments]|
|CUS_0x1844 |[Low, spent, Small, value, payments]|
|CUS_0x1844 |[Low, spent, Small, value, payments]|
|CUS_0x1844 |[Low, spent, Small, value, payments]|
|CUS_0x1844 |[Low, spent, Small, value, payments]|
|CUS_0x1844 |[Low, spent, Small, value, payments]|
|CUS_0x1844 |[Low, spent, Small, value, payments]|
|CUS_0x1b0f |[Low, spent, Large, value, payments]|
|CUS_0x1b0f |[Low, spent, Large, value, payments]|
|CUS_0x1b0f |[Low, spent, Large, value, payments]|
|CUS_0x1b0f |[Low, spent, Large, value, payments]|
|CUS_0x1b0f |[Low, spent, Large, value, payments]|
|CUS_0x1b0f |[Low, spent, Large, value, payments]|
|CUS_0x1b0f |[Low, spent, Large, value, payments]|
|CUS_0x1b0f |[Low, spent, Large, value, payments]|
|CUS_0x1eae |[Low, spent, Small, value, payments]|
|CUS_0x1eae |[Low, spent, Small, value, payments]|
|CUS_0x1eae |[Low, spent, Small, value, payments]|
|CUS_0x1eae |[Low, spent, Small, value, payments]|
+-----------+------------------------------------+
only showing top 20 rows
+-----------+------------------------------------+------------------+
|Customer_ID|Payment_Behaviour |Spending Frequency|
+-----------+------------------------------------+------------------+
|CUS_0x1844 |[Low, spent, Small, value, payments]|Low |
|CUS_0x1844 |[Low, spent, Small, value, payments]|Low |
|CUS_0x1844 |[Low, spent, Small, value, payments]|Low |
|CUS_0x1844 |[Low, spent, Small, value, payments]|Low |
|CUS_0x1844 |[Low, spent, Small, value, payments]|Low |
|CUS_0x1844 |[Low, spent, Small, value, payments]|Low |
|CUS_0x1844 |[Low, spent, Small, value, payments]|Low |
|CUS_0x1844 |[Low, spent, Small, value, payments]|Low |
|CUS_0x1b0f |[Low, spent, Large, value, payments]|Low |
|CUS_0x1b0f |[Low, spent, Large, value, payments]|Low |
|CUS_0x1b0f |[Low, spent, Large, value, payments]|Low |
|CUS_0x1b0f |[Low, spent, Large, value, payments]|Low |
|CUS_0x1b0f |[Low, spent, Large, value, payments]|Low |
|CUS_0x1b0f |[Low, spent, Large, value, payments]|Low |
|CUS_0x1b0f |[Low, spent, Large, value, payments]|Low |
|CUS_0x1b0f |[Low, spent, Large, value, payments]|Low |
|CUS_0x1eae |[Low, spent, Small, value, payments]|Low |
|CUS_0x1eae |[Low, spent, Small, value, payments]|Low |
|CUS_0x1eae |[Low, spent, Small, value, payments]|Low |
|CUS_0x1eae |[Low, spent, Small, value, payments]|Low |
+-----------+------------------------------------+------------------+
only showing top 20 rows
+-----------+------------------------------------+------------------+-----------------------+
|Customer_ID|Payment_Behaviour |Spending Frequency|Average Size of Payment|
+-----------+------------------------------------+------------------+-----------------------+
|CUS_0x1844 |[Low, spent, Small, value, payments]|Low |Small |
|CUS_0x1844 |[Low, spent, Small, value, payments]|Low |Small |
|CUS_0x1844 |[Low, spent, Small, value, payments]|Low |Small |
|CUS_0x1844 |[Low, spent, Small, value, payments]|Low |Small |
|CUS_0x1844 |[Low, spent, Small, value, payments]|Low |Small |
|CUS_0x1844 |[Low, spent, Small, value, payments]|Low |Small |
|CUS_0x1844 |[Low, spent, Small, value, payments]|Low |Small |
|CUS_0x1844 |[Low, spent, Small, value, payments]|Low |Small |
|CUS_0x1b0f |[Low, spent, Large, value, payments]|Low |Large |
|CUS_0x1b0f |[Low, spent, Large, value, payments]|Low |Large |
|CUS_0x1b0f |[Low, spent, Large, value, payments]|Low |Large |
|CUS_0x1b0f |[Low, spent, Large, value, payments]|Low |Large |
|CUS_0x1b0f |[Low, spent, Large, value, payments]|Low |Large |
|CUS_0x1b0f |[Low, spent, Large, value, payments]|Low |Large |
|CUS_0x1b0f |[Low, spent, Large, value, payments]|Low |Large |
|CUS_0x1b0f |[Low, spent, Large, value, payments]|Low |Large |
|CUS_0x1eae |[Low, spent, Small, value, payments]|Low |Small |
|CUS_0x1eae |[Low, spent, Small, value, payments]|Low |Small |
|CUS_0x1eae |[Low, spent, Small, value, payments]|Low |Small |
|CUS_0x1eae |[Low, spent, Small, value, payments]|Low |Small |
+-----------+------------------------------------+------------------+-----------------------+
only showing top 20 rows
+-----------+------------------+-----------------------+
|Customer_ID|Spending Frequency|Average Size of Payment|
+-----------+------------------+-----------------------+
| CUS_0x1844| Low| Small|
| CUS_0x1844| Low| Small|
| CUS_0x1844| Low| Small|
| CUS_0x1844| Low| Small|
| CUS_0x1844| Low| Small|
| CUS_0x1844| Low| Small|
| CUS_0x1844| Low| Small|
| CUS_0x1844| Low| Small|
| CUS_0x1b0f| Low| Large|
| CUS_0x1b0f| Low| Large|
| CUS_0x1b0f| Low| Large|
| CUS_0x1b0f| Low| Large|
| CUS_0x1b0f| Low| Large|
| CUS_0x1b0f| Low| Large|
| CUS_0x1b0f| Low| Large|
| CUS_0x1b0f| Low| Large|
| CUS_0x1eae| Low| Small|
| CUS_0x1eae| Low| Small|
| CUS_0x1eae| Low| Small|
| CUS_0x1eae| Low| Small|
+-----------+------------------+-----------------------+
only showing top 20 rows
# Group the columns based on Customer ID
# spending Frequency and Average Size of Payment to
# get single line of data.
split_pb.show()
split_pb = split_pb\
.groupBy('Customer_ID',
'Spending Frequency',
'Average Size of Payment')\
.count()
# Dropping the count
split_pb = split_pb.drop('count')
split_pb.show()
# Joining the result
credit_score = credit_score.join(
split_pb,
on = 'Customer_ID',
)
# Print schema and print to check result
credit_score.printSchema()
credit_score.show(1, vertical = True, truncate=False)
credit_score.count()+-----------+------------------+-----------------------+
|Customer_ID|Spending Frequency|Average Size of Payment|
+-----------+------------------+-----------------------+
| CUS_0x1844| Low| Small|
| CUS_0x1844| Low| Small|
| CUS_0x1844| Low| Small|
| CUS_0x1844| Low| Small|
| CUS_0x1844| Low| Small|
| CUS_0x1844| Low| Small|
| CUS_0x1844| Low| Small|
| CUS_0x1844| Low| Small|
| CUS_0x1b0f| Low| Large|
| CUS_0x1b0f| Low| Large|
| CUS_0x1b0f| Low| Large|
| CUS_0x1b0f| Low| Large|
| CUS_0x1b0f| Low| Large|
| CUS_0x1b0f| Low| Large|
| CUS_0x1b0f| Low| Large|
| CUS_0x1b0f| Low| Large|
| CUS_0x1eae| Low| Small|
| CUS_0x1eae| Low| Small|
| CUS_0x1eae| Low| Small|
| CUS_0x1eae| Low| Small|
+-----------+------------------+-----------------------+
only showing top 20 rows
+-----------+------------------+-----------------------+
|Customer_ID|Spending Frequency|Average Size of Payment|
+-----------+------------------+-----------------------+
| CUS_0x1844| Low| Small|
| CUS_0x1b0f| Low| Large|
| CUS_0x1eae| Low| Small|
| CUS_0x1ed5| Low| Small|
| CUS_0x2444| High| Large|
| CUS_0x3061| Low| Small|
| CUS_0x33d2| Low| Medium|
| CUS_0x36ab| Low| Small|
| CUS_0x3c41| High| Medium|
| CUS_0x3e17| High| Medium|
| CUS_0x3f38| Low| Small|
| CUS_0x42fb| Low| Small|
| CUS_0x4b6b| Low| Small|
| CUS_0x4e0d| Low| Small|
| CUS_0x5479| Low| Small|
| CUS_0x566d| High| Large|
| CUS_0x5a8b| High| Medium|
| CUS_0x5d29| Low| Medium|
| CUS_0x6320| Low| Large|
| CUS_0x6371| Low| Small|
+-----------+------------------+-----------------------+
only showing top 20 rows
root
|-- Customer_ID: string (nullable = true)
|-- ID: string (nullable = true)
|-- Month: string (nullable = true)
|-- Name: string (nullable = true)
|-- SSN: string (nullable = true)
|-- Credit_Score: string (nullable = true)
|-- Age: integer (nullable = true)
|-- Occupation: string (nullable = true)
|-- Annual_Income: integer (nullable = true)
|-- Monthly_Inhand_Salary: double (nullable = true)
|-- Num_Bank_Accounts: integer (nullable = true)
|-- Num_Credit_Card: integer (nullable = true)
|-- Interest_Rate: integer (nullable = true)
|-- Num_of_Loan: integer (nullable = true)
|-- Delay_from_due_date: integer (nullable = true)
|-- Num_of_Delayed_Payment: integer (nullable = true)
|-- Changed_Credit_Limit: integer (nullable = true)
|-- Num_Credit_Inquiries: double (nullable = true)
|-- Credit_Mix: string (nullable = true)
|-- Outstanding_Debt: double (nullable = true)
|-- Credit_Utilization_Ratio: double (nullable = true)
|-- Credit_History_Age: string (nullable = true)
|-- Payment_of_Min_Amount: string (nullable = true)
|-- Total_EMI_per_month: double (nullable = true)
|-- Amount_invested_monthly: double (nullable = true)
|-- Monthly_Balance: double (nullable = true)
|-- Auto Loan: integer (nullable = true)
|-- Credit-Builder Loan: integer (nullable = true)
|-- Debt Consolidation Loan: integer (nullable = true)
|-- Home Equity Loan: integer (nullable = true)
|-- Mortgage Loan: integer (nullable = true)
|-- Not Specified: integer (nullable = true)
|-- Payday Loan: integer (nullable = true)
|-- Personal Loan: integer (nullable = true)
|-- Student Loan: integer (nullable = true)
|-- Payment_Behaviour: string (nullable = true)
|-- Spending Frequency: string (nullable = true)
|-- Average Size of Payment: string (nullable = true)
-RECORD 0--------------------------------------------------
Customer_ID | CUS_0x1844
ID | 0x1648e
Month | January
Name | Anthony Deutscha
SSN | 638-11-3367
Credit_Score | Standard
Age | 38
Occupation | Writer
Annual_Income | 9728
Monthly_Inhand_Salary | 636.715
Num_Bank_Accounts | 6
Num_Credit_Card | 6
Interest_Rate | 5
Num_of_Loan | 3
Delay_from_due_date | 12
Num_of_Delayed_Payment | 13
Changed_Credit_Limit | 15
Num_Credit_Inquiries | 6.0
Credit_Mix | Standard
Outstanding_Debt | 1382.42
Credit_Utilization_Ratio | 30.21115362763025
Credit_History_Age | 5 Years and 3 Months
Payment_of_Min_Amount | Yes
Total_EMI_per_month | 23.637195867727538
Amount_invested_monthly | 44.57156941035435
Monthly_Balance | 285.4627347219181
Auto Loan | 0
Credit-Builder Loan | 0
Debt Consolidation Loan | 0
Home Equity Loan | 1
Mortgage Loan | 0
Not Specified | 1
Payday Loan | 0
Personal Loan | 0
Student Loan | 1
Payment_Behaviour | Low_spent_Small_value_payments
Spending Frequency | Low
Average Size of Payment | Small
only showing top 1 row
96960Credit History Age
Next we will be looking into column 'Credit_History_Age'.
unique_value_dict['Credit_History_Age'][Row(Credit_History_Age='5 Years and 11 Months'),
Row(Credit_History_Age='19 Years and 5 Months'),
Row(Credit_History_Age='27 Years and 0 Months'),
Row(Credit_History_Age='0 Years and 8 Months'),
Row(Credit_History_Age='13 Years and 2 Months'),
Row(Credit_History_Age='10 Years and 1 Months'),
Row(Credit_History_Age='22 Years and 8 Months'),
Row(Credit_History_Age='23 Years and 4 Months'),
Row(Credit_History_Age='24 Years and 4 Months'),
Row(Credit_History_Age='9 Years and 11 Months'),
Row(Credit_History_Age='11 Years and 10 Months'),
Row(Credit_History_Age='26 Years and 2 Months'),
Row(Credit_History_Age='27 Years and 10 Months'),
Row(Credit_History_Age='14 Years and 10 Months'),
Row(Credit_History_Age='20 Years and 1 Months'),
Row(Credit_History_Age='32 Years and 11 Months'),
Row(Credit_History_Age='2 Years and 7 Months'),
Row(Credit_History_Age='22 Years and 4 Months'),
Row(Credit_History_Age='8 Years and 7 Months'),
Row(Credit_History_Age='33 Years and 3 Months'),
Row(Credit_History_Age='26 Years and 5 Months'),
Row(Credit_History_Age='25 Years and 4 Months'),
Row(Credit_History_Age='22 Years and 3 Months'),
Row(Credit_History_Age='16 Years and 9 Months'),
Row(Credit_History_Age='18 Years and 2 Months'),
Row(Credit_History_Age='30 Years and 2 Months'),
Row(Credit_History_Age='13 Years and 8 Months'),
Row(Credit_History_Age='28 Years and 3 Months'),
Row(Credit_History_Age='5 Years and 10 Months'),
Row(Credit_History_Age='31 Years and 8 Months'),
Row(Credit_History_Age='22 Years and 2 Months'),
Row(Credit_History_Age='31 Years and 0 Months'),
Row(Credit_History_Age='32 Years and 3 Months'),
Row(Credit_History_Age='19 Years and 7 Months'),
Row(Credit_History_Age='22 Years and 6 Months'),
Row(Credit_History_Age='12 Years and 11 Months'),
Row(Credit_History_Age='2 Years and 2 Months'),
Row(Credit_History_Age='29 Years and 8 Months'),
Row(Credit_History_Age='4 Years and 4 Months'),
Row(Credit_History_Age='12 Years and 1 Months'),
Row(Credit_History_Age='18 Years and 7 Months'),
Row(Credit_History_Age='19 Years and 9 Months'),
Row(Credit_History_Age='21 Years and 9 Months'),
Row(Credit_History_Age='10 Years and 7 Months'),
Row(Credit_History_Age='5 Years and 4 Months'),
Row(Credit_History_Age='9 Years and 5 Months'),
Row(Credit_History_Age='6 Years and 10 Months'),
Row(Credit_History_Age='6 Years and 0 Months'),
Row(Credit_History_Age='32 Years and 2 Months'),
Row(Credit_History_Age='19 Years and 2 Months'),
Row(Credit_History_Age='8 Years and 10 Months'),
Row(Credit_History_Age='20 Years and 2 Months'),
Row(Credit_History_Age='5 Years and 2 Months'),
Row(Credit_History_Age='4 Years and 6 Months'),
Row(Credit_History_Age='7 Years and 2 Months'),
Row(Credit_History_Age='10 Years and 3 Months'),
Row(Credit_History_Age='24 Years and 6 Months'),
Row(Credit_History_Age='10 Years and 8 Months'),
Row(Credit_History_Age='9 Years and 8 Months'),
Row(Credit_History_Age='30 Years and 1 Months'),
Row(Credit_History_Age='17 Years and 10 Months'),
Row(Credit_History_Age='8 Years and 8 Months'),
Row(Credit_History_Age='21 Years and 1 Months'),
Row(Credit_History_Age='24 Years and 11 Months'),
Row(Credit_History_Age='23 Years and 3 Months'),
Row(Credit_History_Age='26 Years and 9 Months'),
Row(Credit_History_Age='10 Years and 10 Months'),
Row(Credit_History_Age='23 Years and 7 Months'),
Row(Credit_History_Age='25 Years and 7 Months'),
Row(Credit_History_Age='32 Years and 7 Months'),
Row(Credit_History_Age='30 Years and 9 Months'),
Row(Credit_History_Age='18 Years and 3 Months'),
Row(Credit_History_Age='32 Years and 10 Months'),
Row(Credit_History_Age='14 Years and 11 Months'),
Row(Credit_History_Age='0 Years and 6 Months'),
Row(Credit_History_Age='24 Years and 2 Months'),
Row(Credit_History_Age='10 Years and 0 Months'),
Row(Credit_History_Age=None),
Row(Credit_History_Age='9 Years and 0 Months'),
Row(Credit_History_Age='24 Years and 9 Months'),
Row(Credit_History_Age='2 Years and 8 Months'),
Row(Credit_History_Age='9 Years and 6 Months'),
Row(Credit_History_Age='23 Years and 10 Months'),
Row(Credit_History_Age='23 Years and 9 Months'),
Row(Credit_History_Age='9 Years and 1 Months'),
Row(Credit_History_Age='3 Years and 8 Months'),
Row(Credit_History_Age='25 Years and 9 Months'),
Row(Credit_History_Age='13 Years and 9 Months'),
Row(Credit_History_Age='20 Years and 0 Months'),
Row(Credit_History_Age='18 Years and 10 Months'),
Row(Credit_History_Age='11 Years and 1 Months'),
Row(Credit_History_Age='17 Years and 8 Months'),
Row(Credit_History_Age='28 Years and 5 Months'),
Row(Credit_History_Age='1 Years and 2 Months'),
Row(Credit_History_Age='9 Years and 2 Months'),
Row(Credit_History_Age='11 Years and 8 Months'),
Row(Credit_History_Age='26 Years and 3 Months'),
Row(Credit_History_Age='6 Years and 3 Months'),
Row(Credit_History_Age='20 Years and 11 Months'),
Row(Credit_History_Age='21 Years and 5 Months'),
Row(Credit_History_Age='7 Years and 10 Months'),
Row(Credit_History_Age='24 Years and 8 Months'),
Row(Credit_History_Age='3 Years and 7 Months'),
Row(Credit_History_Age='3 Years and 10 Months'),
Row(Credit_History_Age='31 Years and 9 Months'),
Row(Credit_History_Age='7 Years and 7 Months'),
Row(Credit_History_Age='2 Years and 3 Months'),
Row(Credit_History_Age='26 Years and 10 Months'),
Row(Credit_History_Age='7 Years and 8 Months'),
Row(Credit_History_Age='30 Years and 7 Months'),
Row(Credit_History_Age='22 Years and 7 Months'),
Row(Credit_History_Age='21 Years and 10 Months'),
Row(Credit_History_Age='19 Years and 10 Months'),
Row(Credit_History_Age='12 Years and 7 Months'),
Row(Credit_History_Age='31 Years and 6 Months'),
Row(Credit_History_Age='12 Years and 3 Months'),
Row(Credit_History_Age='16 Years and 10 Months'),
Row(Credit_History_Age='28 Years and 7 Months'),
Row(Credit_History_Age='13 Years and 3 Months'),
Row(Credit_History_Age='16 Years and 1 Months'),
Row(Credit_History_Age='21 Years and 3 Months'),
Row(Credit_History_Age='15 Years and 10 Months'),
Row(Credit_History_Age='21 Years and 8 Months'),
Row(Credit_History_Age='13 Years and 6 Months'),
Row(Credit_History_Age='11 Years and 11 Months'),
Row(Credit_History_Age='18 Years and 9 Months'),
Row(Credit_History_Age='10 Years and 6 Months'),
Row(Credit_History_Age='17 Years and 7 Months'),
Row(Credit_History_Age='13 Years and 4 Months'),
Row(Credit_History_Age='20 Years and 8 Months'),
Row(Credit_History_Age='31 Years and 5 Months'),
Row(Credit_History_Age='0 Years and 11 Months'),
Row(Credit_History_Age='13 Years and 11 Months'),
Row(Credit_History_Age='21 Years and 0 Months'),
Row(Credit_History_Age='19 Years and 4 Months'),
Row(Credit_History_Age='28 Years and 0 Months'),
Row(Credit_History_Age='25 Years and 0 Months'),
Row(Credit_History_Age='20 Years and 3 Months'),
Row(Credit_History_Age='11 Years and 4 Months'),
Row(Credit_History_Age='4 Years and 3 Months'),
Row(Credit_History_Age='0 Years and 1 Months'),
Row(Credit_History_Age='17 Years and 0 Months'),
Row(Credit_History_Age='18 Years and 4 Months'),
Row(Credit_History_Age='16 Years and 11 Months'),
Row(Credit_History_Age='14 Years and 1 Months'),
Row(Credit_History_Age='7 Years and 4 Months'),
Row(Credit_History_Age='30 Years and 11 Months'),
Row(Credit_History_Age='9 Years and 3 Months'),
Row(Credit_History_Age='10 Years and 4 Months'),
Row(Credit_History_Age='18 Years and 11 Months'),
Row(Credit_History_Age='29 Years and 3 Months'),
Row(Credit_History_Age='8 Years and 6 Months'),
Row(Credit_History_Age='1 Years and 4 Months'),
Row(Credit_History_Age='4 Years and 10 Months'),
Row(Credit_History_Age='9 Years and 10 Months'),
Row(Credit_History_Age='18 Years and 1 Months'),
Row(Credit_History_Age='1 Years and 7 Months'),
Row(Credit_History_Age='13 Years and 7 Months'),
Row(Credit_History_Age='6 Years and 11 Months'),
Row(Credit_History_Age='10 Years and 2 Months'),
Row(Credit_History_Age='33 Years and 0 Months'),
Row(Credit_History_Age='25 Years and 1 Months'),
Row(Credit_History_Age='30 Years and 0 Months'),
Row(Credit_History_Age='12 Years and 0 Months'),
Row(Credit_History_Age='6 Years and 7 Months'),
Row(Credit_History_Age='2 Years and 9 Months'),
Row(Credit_History_Age='3 Years and 11 Months'),
Row(Credit_History_Age='5 Years and 8 Months'),
Row(Credit_History_Age='29 Years and 11 Months'),
Row(Credit_History_Age='22 Years and 11 Months'),
Row(Credit_History_Age='17 Years and 11 Months'),
Row(Credit_History_Age='14 Years and 9 Months'),
Row(Credit_History_Age='31 Years and 3 Months'),
Row(Credit_History_Age='29 Years and 2 Months'),
Row(Credit_History_Age='1 Years and 9 Months'),
Row(Credit_History_Age='5 Years and 1 Months'),
Row(Credit_History_Age='24 Years and 0 Months'),
Row(Credit_History_Age='1 Years and 5 Months'),
Row(Credit_History_Age='15 Years and 7 Months'),
Row(Credit_History_Age='26 Years and 7 Months'),
Row(Credit_History_Age='17 Years and 9 Months'),
Row(Credit_History_Age='25 Years and 5 Months'),
Row(Credit_History_Age='14 Years and 3 Months'),
Row(Credit_History_Age='31 Years and 7 Months'),
Row(Credit_History_Age='8 Years and 11 Months'),
Row(Credit_History_Age='7 Years and 9 Months'),
Row(Credit_History_Age='26 Years and 1 Months'),
Row(Credit_History_Age='25 Years and 10 Months'),
Row(Credit_History_Age='12 Years and 8 Months'),
Row(Credit_History_Age='22 Years and 5 Months'),
Row(Credit_History_Age='27 Years and 9 Months'),
Row(Credit_History_Age='33 Years and 8 Months'),
Row(Credit_History_Age='21 Years and 11 Months'),
Row(Credit_History_Age='33 Years and 7 Months'),
Row(Credit_History_Age='7 Years and 5 Months'),
Row(Credit_History_Age='16 Years and 8 Months'),
Row(Credit_History_Age='32 Years and 8 Months'),
Row(Credit_History_Age='31 Years and 2 Months'),
Row(Credit_History_Age='28 Years and 6 Months'),
Row(Credit_History_Age='6 Years and 1 Months'),
Row(Credit_History_Age='1 Years and 0 Months'),
Row(Credit_History_Age='20 Years and 7 Months'),
Row(Credit_History_Age='28 Years and 4 Months'),
Row(Credit_History_Age='4 Years and 11 Months'),
Row(Credit_History_Age='29 Years and 0 Months'),
Row(Credit_History_Age='7 Years and 1 Months'),
Row(Credit_History_Age='0 Years and 7 Months'),
Row(Credit_History_Age='4 Years and 1 Months'),
Row(Credit_History_Age='21 Years and 4 Months'),
Row(Credit_History_Age='12 Years and 10 Months'),
Row(Credit_History_Age='11 Years and 3 Months'),
Row(Credit_History_Age='24 Years and 3 Months'),
Row(Credit_History_Age='8 Years and 5 Months'),
Row(Credit_History_Age='27 Years and 6 Months'),
Row(Credit_History_Age='18 Years and 0 Months'),
Row(Credit_History_Age='23 Years and 1 Months'),
Row(Credit_History_Age='19 Years and 8 Months'),
Row(Credit_History_Age='15 Years and 8 Months'),
Row(Credit_History_Age='26 Years and 8 Months'),
Row(Credit_History_Age='5 Years and 5 Months'),
Row(Credit_History_Age='28 Years and 9 Months'),
Row(Credit_History_Age='21 Years and 2 Months'),
Row(Credit_History_Age='27 Years and 1 Months'),
Row(Credit_History_Age='18 Years and 5 Months'),
Row(Credit_History_Age='28 Years and 2 Months'),
Row(Credit_History_Age='20 Years and 10 Months'),
Row(Credit_History_Age='29 Years and 7 Months'),
Row(Credit_History_Age='9 Years and 4 Months'),
Row(Credit_History_Age='6 Years and 8 Months'),
Row(Credit_History_Age='6 Years and 6 Months'),
Row(Credit_History_Age='20 Years and 9 Months'),
Row(Credit_History_Age='6 Years and 2 Months'),
Row(Credit_History_Age='12 Years and 5 Months'),
Row(Credit_History_Age='14 Years and 7 Months'),
Row(Credit_History_Age='25 Years and 8 Months'),
Row(Credit_History_Age='3 Years and 1 Months'),
Row(Credit_History_Age='21 Years and 6 Months'),
Row(Credit_History_Age='7 Years and 3 Months'),
Row(Credit_History_Age='12 Years and 2 Months'),
Row(Credit_History_Age='12 Years and 6 Months'),
Row(Credit_History_Age='14 Years and 6 Months'),
Row(Credit_History_Age='27 Years and 8 Months'),
Row(Credit_History_Age='17 Years and 2 Months'),
Row(Credit_History_Age='30 Years and 4 Months'),
Row(Credit_History_Age='14 Years and 0 Months'),
Row(Credit_History_Age='8 Years and 9 Months'),
Row(Credit_History_Age='31 Years and 4 Months'),
Row(Credit_History_Age='1 Years and 8 Months'),
Row(Credit_History_Age='15 Years and 5 Months'),
Row(Credit_History_Age='32 Years and 5 Months'),
Row(Credit_History_Age='16 Years and 5 Months'),
Row(Credit_History_Age='19 Years and 11 Months'),
Row(Credit_History_Age='28 Years and 11 Months'),
Row(Credit_History_Age='8 Years and 4 Months'),
Row(Credit_History_Age='28 Years and 10 Months'),
Row(Credit_History_Age='8 Years and 3 Months'),
Row(Credit_History_Age='22 Years and 9 Months'),
Row(Credit_History_Age='22 Years and 0 Months'),
Row(Credit_History_Age='4 Years and 9 Months'),
Row(Credit_History_Age='7 Years and 6 Months'),
Row(Credit_History_Age='11 Years and 5 Months'),
Row(Credit_History_Age='11 Years and 6 Months'),
Row(Credit_History_Age='28 Years and 8 Months'),
Row(Credit_History_Age='27 Years and 5 Months'),
Row(Credit_History_Age='16 Years and 3 Months'),
Row(Credit_History_Age='2 Years and 1 Months'),
Row(Credit_History_Age='15 Years and 9 Months'),
Row(Credit_History_Age='17 Years and 3 Months'),
Row(Credit_History_Age='8 Years and 2 Months'),
Row(Credit_History_Age='16 Years and 0 Months'),
Row(Credit_History_Age='1 Years and 11 Months'),
Row(Credit_History_Age='0 Years and 3 Months'),
Row(Credit_History_Age='17 Years and 4 Months'),
Row(Credit_History_Age='24 Years and 7 Months'),
Row(Credit_History_Age='4 Years and 5 Months'),
Row(Credit_History_Age='20 Years and 5 Months'),
Row(Credit_History_Age='0 Years and 2 Months'),
Row(Credit_History_Age='23 Years and 2 Months'),
Row(Credit_History_Age='18 Years and 6 Months'),
Row(Credit_History_Age='8 Years and 1 Months'),
Row(Credit_History_Age='23 Years and 8 Months'),
Row(Credit_History_Age='30 Years and 6 Months'),
Row(Credit_History_Age='5 Years and 3 Months'),
Row(Credit_History_Age='27 Years and 2 Months'),
Row(Credit_History_Age='14 Years and 8 Months'),
Row(Credit_History_Age='1 Years and 3 Months'),
Row(Credit_History_Age='11 Years and 7 Months'),
Row(Credit_History_Age='13 Years and 10 Months'),
Row(Credit_History_Age='16 Years and 4 Months'),
Row(Credit_History_Age='24 Years and 1 Months'),
Row(Credit_History_Age='27 Years and 4 Months'),
Row(Credit_History_Age='2 Years and 11 Months'),
Row(Credit_History_Age='29 Years and 4 Months'),
Row(Credit_History_Age='29 Years and 10 Months'),
Row(Credit_History_Age='15 Years and 4 Months'),
Row(Credit_History_Age='2 Years and 6 Months'),
Row(Credit_History_Age='13 Years and 5 Months'),
Row(Credit_History_Age='17 Years and 1 Months'),
Row(Credit_History_Age='0 Years and 9 Months'),
Row(Credit_History_Age='20 Years and 6 Months'),
Row(Credit_History_Age='28 Years and 1 Months'),
Row(Credit_History_Age='3 Years and 3 Months'),
Row(Credit_History_Age='19 Years and 0 Months'),
Row(Credit_History_Age='26 Years and 4 Months'),
Row(Credit_History_Age='4 Years and 0 Months'),
Row(Credit_History_Age='13 Years and 1 Months'),
Row(Credit_History_Age='29 Years and 6 Months'),
Row(Credit_History_Age='10 Years and 11 Months'),
Row(Credit_History_Age='9 Years and 9 Months'),
Row(Credit_History_Age='10 Years and 5 Months'),
Row(Credit_History_Age='24 Years and 5 Months'),
Row(Credit_History_Age='0 Years and 10 Months'),
Row(Credit_History_Age='20 Years and 4 Months'),
Row(Credit_History_Age='33 Years and 5 Months'),
Row(Credit_History_Age='25 Years and 6 Months'),
Row(Credit_History_Age='11 Years and 9 Months'),
Row(Credit_History_Age='4 Years and 7 Months'),
Row(Credit_History_Age='31 Years and 10 Months'),
Row(Credit_History_Age='13 Years and 0 Months'),
Row(Credit_History_Age='4 Years and 2 Months'),
Row(Credit_History_Age='6 Years and 5 Months'),
Row(Credit_History_Age='33 Years and 2 Months'),
Row(Credit_History_Age='30 Years and 8 Months'),
Row(Credit_History_Age='1 Years and 6 Months'),
Row(Credit_History_Age='4 Years and 8 Months'),
Row(Credit_History_Age='14 Years and 2 Months'),
Row(Credit_History_Age='17 Years and 5 Months'),
Row(Credit_History_Age='25 Years and 3 Months'),
Row(Credit_History_Age='32 Years and 4 Months'),
Row(Credit_History_Age='30 Years and 3 Months'),
Row(Credit_History_Age='15 Years and 11 Months'),
Row(Credit_History_Age='15 Years and 2 Months'),
Row(Credit_History_Age='2 Years and 10 Months'),
Row(Credit_History_Age='27 Years and 7 Months'),
Row(Credit_History_Age='14 Years and 4 Months'),
Row(Credit_History_Age='19 Years and 1 Months'),
Row(Credit_History_Age='29 Years and 9 Months'),
Row(Credit_History_Age='23 Years and 0 Months'),
Row(Credit_History_Age='32 Years and 9 Months'),
Row(Credit_History_Age='33 Years and 4 Months'),
Row(Credit_History_Age='16 Years and 7 Months'),
Row(Credit_History_Age='23 Years and 5 Months'),
Row(Credit_History_Age='15 Years and 3 Months'),
Row(Credit_History_Age='31 Years and 11 Months'),
Row(Credit_History_Age='32 Years and 1 Months'),
Row(Credit_History_Age='19 Years and 6 Months'),
Row(Credit_History_Age='6 Years and 4 Months'),
Row(Credit_History_Age='3 Years and 2 Months'),
Row(Credit_History_Age='14 Years and 5 Months'),
Row(Credit_History_Age='25 Years and 11 Months'),
Row(Credit_History_Age='27 Years and 3 Months'),
Row(Credit_History_Age='22 Years and 10 Months'),
Row(Credit_History_Age='15 Years and 6 Months'),
Row(Credit_History_Age='3 Years and 9 Months'),
Row(Credit_History_Age='21 Years and 7 Months'),
Row(Credit_History_Age='3 Years and 5 Months'),
Row(Credit_History_Age='17 Years and 6 Months'),
Row(Credit_History_Age='23 Years and 6 Months'),
Row(Credit_History_Age='1 Years and 10 Months'),
Row(Credit_History_Age='26 Years and 6 Months'),
Row(Credit_History_Age='19 Years and 3 Months'),
Row(Credit_History_Age='11 Years and 0 Months'),
Row(Credit_History_Age='0 Years and 5 Months'),
Row(Credit_History_Age='15 Years and 0 Months'),
Row(Credit_History_Age='3 Years and 4 Months'),
Row(Credit_History_Age='2 Years and 5 Months'),
Row(Credit_History_Age='31 Years and 1 Months'),
Row(Credit_History_Age='33 Years and 6 Months'),
Row(Credit_History_Age='6 Years and 9 Months'),
Row(Credit_History_Age='32 Years and 6 Months'),
Row(Credit_History_Age='0 Years and 4 Months'),
Row(Credit_History_Age='3 Years and 0 Months'),
Row(Credit_History_Age='29 Years and 1 Months'),
Row(Credit_History_Age='30 Years and 10 Months'),
Row(Credit_History_Age='33 Years and 1 Months'),
Row(Credit_History_Age='8 Years and 0 Months'),
Row(Credit_History_Age='1 Years and 1 Months'),
Row(Credit_History_Age='12 Years and 4 Months'),
Row(Credit_History_Age='23 Years and 11 Months'),
Row(Credit_History_Age='24 Years and 10 Months'),
Row(Credit_History_Age='12 Years and 9 Months'),
Row(Credit_History_Age='7 Years and 11 Months'),
Row(Credit_History_Age='10 Years and 9 Months'),
Row(Credit_History_Age='5 Years and 0 Months'),
Row(Credit_History_Age='32 Years and 0 Months'),
Row(Credit_History_Age='15 Years and 1 Months'),
Row(Credit_History_Age='7 Years and 0 Months'),
Row(Credit_History_Age='5 Years and 9 Months'),
Row(Credit_History_Age='25 Years and 2 Months'),
Row(Credit_History_Age='29 Years and 5 Months'),
Row(Credit_History_Age='5 Years and 6 Months'),
Row(Credit_History_Age='27 Years and 11 Months'),
Row(Credit_History_Age='5 Years and 7 Months'),
Row(Credit_History_Age='26 Years and 0 Months'),
Row(Credit_History_Age='16 Years and 6 Months'),
Row(Credit_History_Age='16 Years and 2 Months'),
Row(Credit_History_Age='9 Years and 7 Months'),
Row(Credit_History_Age='2 Years and 4 Months'),
Row(Credit_History_Age='26 Years and 11 Months'),
Row(Credit_History_Age='18 Years and 8 Months'),
Row(Credit_History_Age='3 Years and 6 Months'),
Row(Credit_History_Age='2 Years and 0 Months'),
Row(Credit_History_Age='30 Years and 5 Months'),
Row(Credit_History_Age='22 Years and 1 Months'),
Row(Credit_History_Age='11 Years and 2 Months')]# Selecting Customer_ID, and Credit History Age
credit_his_age = credit_score.select('Customer_ID','Credit_History_Age')
# Splitting the string values based on ' ' as a seperator
credit_his_age = credit_his_age.withColumn(
'Credit_History_Age',
F.split('Credit_History_Age', ' ')
)
# Converting years into months and get the total
credit_his_age = credit_his_age.withColumn(
'Credit_History_Age_in_Months',
((col('Credit_History_Age').getItem(0)*12) +
(col('Credit_History_Age').getItem(3)))
)
# Show to check the results
credit_his_age = credit_his_age\
.groupBy('Customer_ID',
'Credit_History_Age_in_Months')\
.count()
credit_his_age = credit_his_age.drop('count')
credit_his_age.show()
# Drop unneeded columns
credit_his_age = credit_his_age.drop('Credit_History_Age')
columns_to_drop.append('Credit_History_Age')
# Join with the main dataset
credit_score = credit_score.join(
credit_his_age,
on = 'Customer_ID',
how = 'inner'
)
# Print the following to check the results
credit_score.printSchema()
credit_score.show(1, vertical = True)
print(credit_score.count())
credit_score = credit_score.checkpoint()+-----------+----------------------------+
|Customer_ID|Credit_History_Age_in_Months|
+-----------+----------------------------+
| CUS_0x1844| 63.0|
| CUS_0x1b0f| 101.0|
| CUS_0x1eae| 259.0|
| CUS_0x1ed5| 89.0|
| CUS_0x2444| 273.0|
| CUS_0x3061| 86.0|
| CUS_0x33d2| 202.0|
| CUS_0x36ab| 146.0|
| CUS_0x3c41| 323.0|
| CUS_0x3e17| 225.0|
| CUS_0x3f38| 88.0|
| CUS_0x42fb| null|
| CUS_0x4b6b| null|
| CUS_0x4e0d| 157.0|
| CUS_0x5479| null|
| CUS_0x566d| 332.0|
| CUS_0x5a8b| 142.0|
| CUS_0x5d29| 131.0|
| CUS_0x6320| null|
| CUS_0x6371| null|
+-----------+----------------------------+
only showing top 20 rows
root
|-- Customer_ID: string (nullable = true)
|-- ID: string (nullable = true)
|-- Month: string (nullable = true)
|-- Name: string (nullable = true)
|-- SSN: string (nullable = true)
|-- Credit_Score: string (nullable = true)
|-- Age: integer (nullable = true)
|-- Occupation: string (nullable = true)
|-- Annual_Income: integer (nullable = true)
|-- Monthly_Inhand_Salary: double (nullable = true)
|-- Num_Bank_Accounts: integer (nullable = true)
|-- Num_Credit_Card: integer (nullable = true)
|-- Interest_Rate: integer (nullable = true)
|-- Num_of_Loan: integer (nullable = true)
|-- Delay_from_due_date: integer (nullable = true)
|-- Num_of_Delayed_Payment: integer (nullable = true)
|-- Changed_Credit_Limit: integer (nullable = true)
|-- Num_Credit_Inquiries: double (nullable = true)
|-- Credit_Mix: string (nullable = true)
|-- Outstanding_Debt: double (nullable = true)
|-- Credit_Utilization_Ratio: double (nullable = true)
|-- Credit_History_Age: string (nullable = true)
|-- Payment_of_Min_Amount: string (nullable = true)
|-- Total_EMI_per_month: double (nullable = true)
|-- Amount_invested_monthly: double (nullable = true)
|-- Monthly_Balance: double (nullable = true)
|-- Auto Loan: integer (nullable = true)
|-- Credit-Builder Loan: integer (nullable = true)
|-- Debt Consolidation Loan: integer (nullable = true)
|-- Home Equity Loan: integer (nullable = true)
|-- Mortgage Loan: integer (nullable = true)
|-- Not Specified: integer (nullable = true)
|-- Payday Loan: integer (nullable = true)
|-- Personal Loan: integer (nullable = true)
|-- Student Loan: integer (nullable = true)
|-- Payment_Behaviour: string (nullable = true)
|-- Spending Frequency: string (nullable = true)
|-- Average Size of Payment: string (nullable = true)
|-- Credit_History_Age_in_Months: double (nullable = true)
-RECORD 0--------------------------------------------
Customer_ID | CUS_0x1844
ID | 0x1648e
Month | January
Name | Anthony Deutscha
SSN | 638-11-3367
Credit_Score | Standard
Age | 38
Occupation | Writer
Annual_Income | 9728
Monthly_Inhand_Salary | 636.715
Num_Bank_Accounts | 6
Num_Credit_Card | 6
Interest_Rate | 5
Num_of_Loan | 3
Delay_from_due_date | 12
Num_of_Delayed_Payment | 13
Changed_Credit_Limit | 15
Num_Credit_Inquiries | 6.0
Credit_Mix | Standard
Outstanding_Debt | 1382.42
Credit_Utilization_Ratio | 30.21115362763025
Credit_History_Age | 5 Years and 3 Months
Payment_of_Min_Amount | Yes
Total_EMI_per_month | 23.637195867727538
Amount_invested_monthly | 44.57156941035435
Monthly_Balance | 285.4627347219181
Auto Loan | 0
Credit-Builder Loan | 0
Debt Consolidation Loan | 0
Home Equity Loan | 1
Mortgage Loan | 0
Not Specified | 1
Payday Loan | 0
Personal Loan | 0
Student Loan | 1
Payment_Behaviour | Low_spent_Small_v...
Spending Frequency | Low
Average Size of Payment | Small
Credit_History_Age_in_Months | 63.0
only showing top 1 row
96960We noted that there are null values contained in the column 'Credit_Hisotry_Age'. We will need to drop them as well.
credit_score = credit_score.filter(~(col('Credit_History_Age_in_Months').isNull()))
credit_score = credit_score.checkpoint()
credit_score.count()81472credit_score.groupBy('Occupation').count().show()+-------------+-----+
| Occupation|count|
+-------------+-----+
| Scientist| 5552|
|Media_Manager| 5440|
| Musician| 5160|
| Lawyer| 5640|
| Teacher| 5640|
| Developer| 5472|
| Writer| 4960|
| Architect| 5488|
| Mechanic| 5656|
| Entrepreneur| 5400|
| Journalist| 5240|
| Doctor| 5368|
| Engineer| 5424|
| Accountant| 5608|
| Manager| 5200|
| _______| 224|
+-------------+-----+
That should be all the required columns that may need attention to explore. Now we need to look into the remaining preprocessing required. Based on the show above, the Spending Frequency, Average Sizes of Payment and Occupation are categorical. Credit score, the target variable or label, is also a categorical data.
from pyspark.ml.feature import OneHotEncoder, StringIndexer# Columns that need to be converted
columns_to_process = [
'Spending Frequency',
'Average Size of Payment',
'Occupation',
'Credit_Score']
# Function to turn categoric data into numeric
def category_to_numeric(data, column):
# Name of the columns
column_indexed = column + '_indexed'
column_encoded = column + '_encoded'
# Initialize the String Indexer
string_indexer = StringIndexer(
inputCol = column,
outputCol = (column_indexed)
)
# Fit data to the string indexer to be fitted and transform
model = string_indexer.fit(data)
indexed = model.transform(data)
# Initialize the one hot encoder
encoder = OneHotEncoder(
inputCol = column_indexed,
outputCol = column_encoded
)
# Using the one hot encoder, fitting and transforming the desired data
data = encoder.fit(indexed).transform(indexed)
return data
# Print schema before the conversion
credit_score.printSchema()
# Loop through the list to be processed
for column in columns_to_process:
# Convert the desired column into numeric
credit_score = category_to_numeric(credit_score, column)
# Print schema after the conversion
credit_score.printSchema()
credit_score = credit_score.checkpoint()root
|-- Customer_ID: string (nullable = true)
|-- ID: string (nullable = true)
|-- Month: string (nullable = true)
|-- Name: string (nullable = true)
|-- SSN: string (nullable = true)
|-- Credit_Score: string (nullable = true)
|-- Age: integer (nullable = true)
|-- Occupation: string (nullable = true)
|-- Annual_Income: integer (nullable = true)
|-- Monthly_Inhand_Salary: double (nullable = true)
|-- Num_Bank_Accounts: integer (nullable = true)
|-- Num_Credit_Card: integer (nullable = true)
|-- Interest_Rate: integer (nullable = true)
|-- Num_of_Loan: integer (nullable = true)
|-- Delay_from_due_date: integer (nullable = true)
|-- Num_of_Delayed_Payment: integer (nullable = true)
|-- Changed_Credit_Limit: integer (nullable = true)
|-- Num_Credit_Inquiries: double (nullable = true)
|-- Credit_Mix: string (nullable = true)
|-- Outstanding_Debt: double (nullable = true)
|-- Credit_Utilization_Ratio: double (nullable = true)
|-- Credit_History_Age: string (nullable = true)
|-- Payment_of_Min_Amount: string (nullable = true)
|-- Total_EMI_per_month: double (nullable = true)
|-- Amount_invested_monthly: double (nullable = true)
|-- Monthly_Balance: double (nullable = true)
|-- Auto Loan: integer (nullable = true)
|-- Credit-Builder Loan: integer (nullable = true)
|-- Debt Consolidation Loan: integer (nullable = true)
|-- Home Equity Loan: integer (nullable = true)
|-- Mortgage Loan: integer (nullable = true)
|-- Not Specified: integer (nullable = true)
|-- Payday Loan: integer (nullable = true)
|-- Personal Loan: integer (nullable = true)
|-- Student Loan: integer (nullable = true)
|-- Payment_Behaviour: string (nullable = true)
|-- Spending Frequency: string (nullable = true)
|-- Average Size of Payment: string (nullable = true)
|-- Credit_History_Age_in_Months: double (nullable = true)
root
|-- Customer_ID: string (nullable = true)
|-- ID: string (nullable = true)
|-- Month: string (nullable = true)
|-- Name: string (nullable = true)
|-- SSN: string (nullable = true)
|-- Credit_Score: string (nullable = true)
|-- Age: integer (nullable = true)
|-- Occupation: string (nullable = true)
|-- Annual_Income: integer (nullable = true)
|-- Monthly_Inhand_Salary: double (nullable = true)
|-- Num_Bank_Accounts: integer (nullable = true)
|-- Num_Credit_Card: integer (nullable = true)
|-- Interest_Rate: integer (nullable = true)
|-- Num_of_Loan: integer (nullable = true)
|-- Delay_from_due_date: integer (nullable = true)
|-- Num_of_Delayed_Payment: integer (nullable = true)
|-- Changed_Credit_Limit: integer (nullable = true)
|-- Num_Credit_Inquiries: double (nullable = true)
|-- Credit_Mix: string (nullable = true)
|-- Outstanding_Debt: double (nullable = true)
|-- Credit_Utilization_Ratio: double (nullable = true)
|-- Credit_History_Age: string (nullable = true)
|-- Payment_of_Min_Amount: string (nullable = true)
|-- Total_EMI_per_month: double (nullable = true)
|-- Amount_invested_monthly: double (nullable = true)
|-- Monthly_Balance: double (nullable = true)
|-- Auto Loan: integer (nullable = true)
|-- Credit-Builder Loan: integer (nullable = true)
|-- Debt Consolidation Loan: integer (nullable = true)
|-- Home Equity Loan: integer (nullable = true)
|-- Mortgage Loan: integer (nullable = true)
|-- Not Specified: integer (nullable = true)
|-- Payday Loan: integer (nullable = true)
|-- Personal Loan: integer (nullable = true)
|-- Student Loan: integer (nullable = true)
|-- Payment_Behaviour: string (nullable = true)
|-- Spending Frequency: string (nullable = true)
|-- Average Size of Payment: string (nullable = true)
|-- Credit_History_Age_in_Months: double (nullable = true)
|-- Spending Frequency_indexed: double (nullable = false)
|-- Spending Frequency_encoded: vector (nullable = true)
|-- Average Size of Payment_indexed: double (nullable = false)
|-- Average Size of Payment_encoded: vector (nullable = true)
|-- Occupation_indexed: double (nullable = false)
|-- Occupation_encoded: vector (nullable = true)
|-- Credit_Score_indexed: double (nullable = false)
|-- Credit_Score_encoded: vector (nullable = true)
The string indexer converts categorical columns into numeric ones as shown in the intended columns but with the '_indexed'. If there are three unique values, the string indexer will transform it into 0, 1 or 2. Then the one hot encoder, will vectorize the output of the string indexer. There are sources online that mentioned having only string indexed columns, such as the example given, a column having a values of 0, 1 and 2, is that some machine learning model might assume the meaning that 0 is not having any value, and 2 is 2 times more than 1, when in fact the numbers are only used to represent category. Therefore, vectorizing it will help with that.
The following code are to drop all the unnecesary columns before we continue with the machine learning models.
columns_to_drop['Credit_Mix',
'Monthly_Inhand_Salary',
'Not Specified',
'Payment_Behaviour',
'Credit_History_Age']credit_score = credit_score.drop(*columns_to_drop)
credit_score = credit_score.drop(*columns_to_process)
credit_score = credit_score.drop(*id_features)
credit_score = credit_score.checkpoint()
credit_score.printSchema()
credit_score.show(1, vertical=True)root
|-- Age: integer (nullable = true)
|-- Annual_Income: integer (nullable = true)
|-- Num_Bank_Accounts: integer (nullable = true)
|-- Num_Credit_Card: integer (nullable = true)
|-- Interest_Rate: integer (nullable = true)
|-- Num_of_Loan: integer (nullable = true)
|-- Delay_from_due_date: integer (nullable = true)
|-- Num_of_Delayed_Payment: integer (nullable = true)
|-- Changed_Credit_Limit: integer (nullable = true)
|-- Num_Credit_Inquiries: double (nullable = true)
|-- Outstanding_Debt: double (nullable = true)
|-- Credit_Utilization_Ratio: double (nullable = true)
|-- Payment_of_Min_Amount: string (nullable = true)
|-- Total_EMI_per_month: double (nullable = true)
|-- Amount_invested_monthly: double (nullable = true)
|-- Monthly_Balance: double (nullable = true)
|-- Auto Loan: integer (nullable = true)
|-- Credit-Builder Loan: integer (nullable = true)
|-- Debt Consolidation Loan: integer (nullable = true)
|-- Home Equity Loan: integer (nullable = true)
|-- Mortgage Loan: integer (nullable = true)
|-- Payday Loan: integer (nullable = true)
|-- Personal Loan: integer (nullable = true)
|-- Student Loan: integer (nullable = true)
|-- Credit_History_Age_in_Months: double (nullable = true)
|-- Spending Frequency_indexed: double (nullable = false)
|-- Spending Frequency_encoded: vector (nullable = true)
|-- Average Size of Payment_indexed: double (nullable = false)
|-- Average Size of Payment_encoded: vector (nullable = true)
|-- Occupation_indexed: double (nullable = false)
|-- Occupation_encoded: vector (nullable = true)
|-- Credit_Score_indexed: double (nullable = false)
|-- Credit_Score_encoded: vector (nullable = true)
-RECORD 0---------------------------------------------
Age | 38
Annual_Income | 9728
Num_Bank_Accounts | 6
Num_Credit_Card | 6
Interest_Rate | 5
Num_of_Loan | 3
Delay_from_due_date | 12
Num_of_Delayed_Payment | 13
Changed_Credit_Limit | 15
Num_Credit_Inquiries | 6.0
Outstanding_Debt | 1382.42
Credit_Utilization_Ratio | 30.21115362763025
Payment_of_Min_Amount | Yes
Total_EMI_per_month | 23.637195867727538
Amount_invested_monthly | 44.57156941035435
Monthly_Balance | 285.4627347219181
Auto Loan | 0
Credit-Builder Loan | 0
Debt Consolidation Loan | 0
Home Equity Loan | 1
Mortgage Loan | 0
Payday Loan | 0
Personal Loan | 0
Student Loan | 1
Credit_History_Age_in_Months | 63.0
Spending Frequency_indexed | 0.0
Spending Frequency_encoded | (1,[0],[1.0])
Average Size of Payment_indexed | 0.0
Average Size of Payment_encoded | (2,[0],[1.0])
Occupation_indexed | 14.0
Occupation_encoded | (15,[14],[1.0])
Credit_Score_indexed | 0.0
Credit_Score_encoded | (2,[0],[1.0])
only showing top 1 row
columns_left_to_explore = []
for column in credit_score.columns:
count = credit_score.filter(col(column).isNull()).count()
if count != 0:
print(column + ' has ' + str(count) + ' missing values')
columns_left_to_explore.append(column)Num_of_Delayed_Payment has 440 missing values
Changed_Credit_Limit has 8 missing values
Num_Credit_Inquiries has 24 missing values
Amount_invested_monthly has 3800 missing values
Monthly_Balance has 1304 missing values
Auto Loan has 9336 missing values
Credit-Builder Loan has 9336 missing values
Debt Consolidation Loan has 9336 missing values
Home Equity Loan has 9336 missing values
Mortgage Loan has 9336 missing values
Payday Loan has 9336 missing values
Personal Loan has 9336 missing values
Student Loan has 9336 missing valuesBased on the above, we noted that are still missing values in the dataset that need to be handled and also a column that have been missed out which is still a text based column. The 'Payment_of_Min_Amount'.
# Check Unique values
print(unique_value_dict['Payment_of_Min_Amount'])
# Check for missing values
print(credit_score.groupBy('Payment_of_Min_Amount').count().show())[Row(Payment_of_Min_Amount='NM'), Row(Payment_of_Min_Amount='No'), Row(Payment_of_Min_Amount='Yes')]
+---------------------+-----+
|Payment_of_Min_Amount|count|
+---------------------+-----+
| NM| 568|
| No|32776|
| Yes|48128|
+---------------------+-----+
NoneWe noted that there are three distinct values for this column, 'Yes', 'No', and 'NM', and there are only 528 rows that are in the 'NM' value. Therefore, we can drop those rows as well.
print('Number of Rows before dropping "NM": ', credit_score.count())
credit_score = credit_score.filter(~(col('Payment_of_Min_Amount') == 'NM'))
print('Number of Rows after dropping "NM": ', credit_score.count())Number of Rows before dropping "NM": 81472
Number of Rows after dropping "NM": 80904Because this column only has yes and no value, we can use 0 and 1, without using the string indexer and one hot encoder to do this.
credit_score = credit_score.withColumn(
'Payment_of_Min_Amount',
F.when(col('Payment_of_Min_Amount') == 'No', 0)\
.when(col('Payment_of_Min_Amount') == 'Yes', 1)\
.otherwise(col('Payment_of_Min_Amount'))\
.cast(IntegerType())
)
credit_score.select('Payment_of_Min_Amount').groupBy('Payment_of_Min_Amount').count().show()
print(credit_score.select('Payment_of_Min_Amount'))
credit_score = credit_score.checkpoint()+---------------------+-----+
|Payment_of_Min_Amount|count|
+---------------------+-----+
| 1|48128|
| 0|32776|
+---------------------+-----+
DataFrame[Payment_of_Min_Amount: int]Now to address the remaining missing values that was proccessed above.
# Print the distinct values and their count
for column in columns_left_to_explore:
credit_score.groupBy(column).count().show(100)
# Filter the Loan Type
loan_type_columns = [col for col in columns_left_to_explore if 'Loan' in col]
# Remove Loan Type columns from list
for column in loan_type_columns:
columns_left_to_explore.remove(column)+----------------------+-----+
|Num_of_Delayed_Payment|count|
+----------------------+-----+
| -1| 48|
| 28| 24|
| 27| 24|
| 26| 16|
| 12| 4720|
| 22| 1648|
| null| 432|
| 1| 1584|
| 13| 3064|
| 16| 4920|
| 6| 1728|
| 3| 1632|
| 20| 5032|
| 5| 1704|
| 19| 5032|
| 15| 4864|
| 9| 4416|
| 17| 4592|
| 4| 1536|
| 8| 4704|
| 23| 1800|
| 7| 1568|
| 10| 4968|
| -2| 40|
| 25| 1744|
| 24| 1640|
| 21| 1848|
| 11| 4288|
| 14| 3168|
| 2| 1744|
| 0| 1704|
| 18| 4672|
+----------------------+-----+
+--------------------+-----+
|Changed_Credit_Limit|count|
+--------------------+-----+
| 28| 624|
| 26| 584|
| 27| 608|
| 12| 2344|
| 22| 592|
| null| 8|
| 1| 4008|
| 13| 1992|
| 6| 3824|
| 16| 2744|
| 3| 4080|
| 20| 608|
| 5| 3768|
| 19| 2832|
| 15| 2800|
| 9| 6248|
| 17| 2768|
| 4| 4392|
| 8| 6160|
| 23| 632|
| 7| 5808|
| 10| 4904|
| 25| 624|
| 24| 648|
| 29| 544|
| 21| 560|
| 11| 5640|
| 14| 1896|
| 2| 3960|
| 30| 8|
| 0| 2032|
| 18| 2664|
+--------------------+-----+
+--------------------+-----+
|Num_Credit_Inquiries|count|
+--------------------+-----+
| 8.0| 6472|
| 0.0| 6024|
| 7.0| 6840|
| 1282.0| 8|
| null| 24|
| 86.0| 8|
| 1.0| 6496|
| 2405.0| 8|
| 1487.0| 8|
| 4.0| 9616|
| 11.0| 4288|
| 14.0| 768|
| 1213.0| 8|
| 3.0| 7600|
| 2.0| 6816|
| 17.0| 192|
| 2254.0| 8|
| 10.0| 4000|
| 13.0| 1040|
| 6.0| 6720|
| 1941.0| 8|
| 15.0| 640|
| 5.0| 4760|
| 9.0| 4424|
| 16.0| 360|
| 12.0| 3768|
+--------------------+-----+
+-----------------------+-----+
|Amount_invested_monthly|count|
+-----------------------+-----+
| 153.48160759357242| 8|
| 178.7583307684732| 8|
| 352.6424257998038| 8|
| 51.082159638816265| 8|
| 182.93896788042431| 8|
| 120.02643718809227| 8|
| 89.52411045264235| 8|
| 292.12432475776643| 8|
| 46.941123028868226| 8|
| 68.47356529471752| 8|
| 136.27314317172969| 8|
| 346.71118729239896| 8|
| 681.0142821962519| 8|
| 384.43249455327225| 8|
| 170.0257925333507| 8|
| 145.72185286549808| 8|
| 100.6156935391274| 8|
| 124.48053052023023| 8|
| 358.2300011872085| 8|
| 690.7448752339978| 8|
| 522.1365541307312| 8|
| 66.12818710334099| 8|
| 195.316849708674| 8|
| 61.73669850349335| 8|
| 27.529069681486007| 8|
| 109.52270941076556| 8|
| 127.9396927730949| 8|
| 389.15885983817344| 8|
| 62.51017268626197| 8|
| 45.73027466888289| 8|
| 64.09278219121839| 8|
| 48.11205865768198| 8|
| 275.93146198016456| 8|
| 344.5508610555433| 8|
| 118.84562266733371| 8|
| 43.07411744780003| 8|
| 252.95054546375218| 8|
| 219.65620147447814| 8|
| 49.482587276104596| 8|
| 64.14915718393657| 8|
| 53.67129496577199| 8|
| 121.70960852931113| 8|
| 110.08545170643114| 8|
| 95.11035308057676| 8|
| 299.2892697876012| 8|
| 158.94947116123458| 8|
| 53.54621289052261| 8|
| 78.44415423803042| 8|
| 164.19895657130922| 8|
| 145.74703179968142| 8|
| 114.06570938349688| 8|
| 108.25756608960023| 8|
| 178.12107670637363| 8|
| 132.24604758254608| 8|
| 245.06179783238517| 8|
| 531.1960999473007| 8|
| 140.55288701361968| 8|
| 448.1938446536375| 8|
| 85.04662516606308| 8|
| 38.15801921804493| 8|
| 61.58997800711112| 8|
| 604.6377840289732| 8|
| 838.6232195344513| 8|
| 333.57177925268087| 8|
| 111.18838621311487| 8|
| 87.89558145110071| 8|
| 269.28582065995397| 8|
| 439.6776590630765| 8|
| 54.235382478842716| 8|
| 110.19964611638822| 8|
| 115.09385252155731| 8|
| 47.39569208681922| 8|
| 39.285312331230685| 8|
| 48.639066286637174| 8|
| 143.57755646899196| 8|
| 236.9247044788289| 8|
| 135.55329730302088| 8|
| 829.2754594811537| 8|
| 152.28206446530797| 8|
| 132.91787152104058| 8|
| 128.70367707542636| 8|
| 238.9823421186261| 8|
| 105.52361769736166| 8|
| 80.49028629515327| 8|
| 106.92663734464995| 8|
| 112.38023935018174| 8|
| 117.50516334362518| 8|
| 194.3616097155128| 8|
| 83.7978875356769| 8|
| 591.3782051636166| 8|
| 96.85329420648186| 8|
| 338.796788967333| 8|
| 163.02106052457668| 8|
| 86.84316266301785| 8|
| 30.29315144345136| 8|
| 227.6187415383298| 8|
| 115.82811476822474| 8|
| 162.02271557560178| 8|
| 105.57421462606571| 8|
| 165.94963024940168| 8|
+-----------------------+-----+
only showing top 100 rows
+------------------+-----+
| Monthly_Balance|count|
+------------------+-----+
| 703.1293738021684| 8|
|446.37292180431336| 8|
| 249.8070181253751| 8|
|235.35964776363116| 8|
| 760.3908430269906| 8|
| 396.6921091694071| 8|
| 568.5451545058462| 8|
| 356.5451513244941| 8|
| 310.3351448517185| 8|
|336.33036540273645| 8|
| 614.4444284524145| 8|
| 427.0508256562877| 8|
|166.45264182914457| 8|
| 490.1721773566514| 8|
| 734.8471639321957| 8|
| 647.9571317515059| 8|
| 309.2469330945158| 8|
| 504.8804997587358| 8|
|1025.8390552339765| 8|
| 345.2808509731348| 8|
|496.15277244614083| 8|
| 323.1772437366338| 8|
|267.10556926428217| 8|
| 553.5445922847618| 8|
| 370.9437168529345| 8|
| 992.5469750072273| 8|
| 293.9700516260998| 8|
| 330.0250182981825| 8|
| 272.9109087386877| 8|
|171.80838330065643| 8|
| 278.4755891506759| 8|
| 602.6436239095223| 8|
| 316.9640364039031| 8|
| 363.3204151435986| 8|
| 306.1473105594705| 8|
| 260.1255919429688| 8|
| 457.7797392106829| 8|
|1436.8205541223278| 8|
|299.50112427005587| 8|
|314.95505626681006| 8|
| 362.0998736619049| 8|
|430.77486334879205| 8|
|458.49073258120234| 8|
| 89.0250774233926| 8|
|306.74396969300966| 8|
| 448.3453713968449| 8|
|287.99473294811787| 8|
| 963.2994074282477| 8|
|445.18887837844085| 8|
|340.36589617591136| 8|
| 727.5323964695247| 8|
| 737.4714012015828| 8|
|227.43365119907529| 8|
| 360.3433327137839| 8|
| 290.8495242480392| 8|
|215.23453299507327| 8|
| 413.4049735995066| 8|
|276.93658904313617| 8|
|288.57200426658227| 8|
|1038.2885013078567| 8|
| 242.4833607258564| 8|
| 622.8589499816667| 8|
| 258.799696826076| 8|
| 512.9579383182709| 8|
| 309.7733487279136| 8|
|224.72585965590923| 8|
|105.18831364180151| 8|
| 461.2024949525658| 8|
| 511.4266783999017| 8|
|303.60252786232104| 8|
| 567.7856667241547| 8|
| 934.8188687047067| 8|
| 654.600004223394| 8|
|1097.0639332540227| 8|
| 388.0122830106935| 8|
| 1079.712860417668| 8|
| 353.1631934346814| 8|
| 460.1009115893087| 8|
|236.63450698430813| 8|
| 912.0593291175868| 8|
|432.66815995771987| 8|
|250.03547315135827| 8|
| 540.7038198941706| 8|
|189.02679858570497| 8|
|384.60593839715966| 8|
| 295.7229030493955| 8|
| 296.6936300498122| 8|
|395.73286939620573| 8|
| 257.3525864196911| 8|
| 323.1234403999585| 8|
|292.76103558404265| 8|
|435.91560728133277| 8|
| 234.4226531475108| 8|
| 275.6103465774071| 8|
| 386.0240533569049| 8|
|390.39673788028864| 8|
| 443.2654272869336| 8|
| 278.0822609755249| 8|
|276.52840880226967| 8|
| 246.4366655904365| 8|
+------------------+-----+
only showing top 100 rows
+---------+-----+
|Auto Loan|count|
+---------+-----+
| null| 9280|
| 1|24968|
| 0|46656|
+---------+-----+
+-------------------+-----+
|Credit-Builder Loan|count|
+-------------------+-----+
| null| 9280|
| 1|25664|
| 0|45960|
+-------------------+-----+
+-----------------------+-----+
|Debt Consolidation Loan|count|
+-----------------------+-----+
| null| 9280|
| 1|25144|
| 0|46480|
+-----------------------+-----+
+----------------+-----+
|Home Equity Loan|count|
+----------------+-----+
| null| 9280|
| 1|25400|
| 0|46224|
+----------------+-----+
+-------------+-----+
|Mortgage Loan|count|
+-------------+-----+
| null| 9280|
| 1|25376|
| 0|46248|
+-------------+-----+
+-----------+-----+
|Payday Loan|count|
+-----------+-----+
| null| 9280|
| 1|26016|
| 0|45608|
+-----------+-----+
+-------------+-----+
|Personal Loan|count|
+-------------+-----+
| null| 9280|
| 1|25384|
| 0|46240|
+-------------+-----+
+------------+-----+
|Student Loan|count|
+------------+-----+
| null| 9280|
| 1|25232|
| 0|46392|
+------------+-----+
Based on the above, we noted that number of delayed payment is fine and the null values can be dropped. For the column Number of Credit Inquiries, there are some outliers that should be dropped as well. For column amount invested monthly and monthly balance, there seem to be a lot of unique values due to it being considerably continuious data, because it measures money, and the rest of the loan type data, null values will be dropped as well
print(loan_type_columns)
credit_score.select('Num_of_Loan', *loan_type_columns)\
.filter(F.col('Auto Loan').isNull()).show()['Auto Loan', 'Credit-Builder Loan', 'Debt Consolidation Loan', 'Home Equity Loan', 'Mortgage Loan', 'Payday Loan', 'Personal Loan', 'Student Loan']
+-----------+---------+-------------------+-----------------------+----------------+-------------+-----------+-------------+------------+
|Num_of_Loan|Auto Loan|Credit-Builder Loan|Debt Consolidation Loan|Home Equity Loan|Mortgage Loan|Payday Loan|Personal Loan|Student Loan|
+-----------+---------+-------------------+-----------------------+----------------+-------------+-----------+-------------+------------+
| 0| null| null| null| null| null| null| null| null|
| 0| null| null| null| null| null| null| null| null|
| 0| null| null| null| null| null| null| null| null|
| 0| null| null| null| null| null| null| null| null|
| 0| null| null| null| null| null| null| null| null|
| 0| null| null| null| null| null| null| null| null|
| 0| null| null| null| null| null| null| null| null|
| 0| null| null| null| null| null| null| null| null|
| 0| null| null| null| null| null| null| null| null|
| 0| null| null| null| null| null| null| null| null|
| 0| null| null| null| null| null| null| null| null|
| 0| null| null| null| null| null| null| null| null|
| 0| null| null| null| null| null| null| null| null|
| 0| null| null| null| null| null| null| null| null|
| 0| null| null| null| null| null| null| null| null|
| 0| null| null| null| null| null| null| null| null|
| 0| null| null| null| null| null| null| null| null|
| 0| null| null| null| null| null| null| null| null|
| 0| null| null| null| null| null| null| null| null|
| 0| null| null| null| null| null| null| null| null|
+-----------+---------+-------------------+-----------------------+----------------+-------------+-----------+-------------+------------+
only showing top 20 rows
Based on the above, all of the null values is because of there are no loans taken by these customers. Therefore, we will be replacing these the null values with 0.
for column in loan_type_columns:
credit_score = credit_score.withColumn(
column,
F.when(col(column) == 0, 0)\
.when(col(column) == 1, 1)\
.otherwise(0))
credit_score = credit_score.checkpoint()# Drop rows of nulls from the selected columns
print('Before dropping columns: ', credit_score.count())
for column in columns_left_to_explore:
credit_score = credit_score.filter(~(col(column).isNull()))
print('Column ' + column +
' dropped. Current count: ' +
str(credit_score.count()))
print('Afer dropping columns: ' + str(credit_score.count()))
# Drop rows for Number of Credit Inquiries outliers
credit_score = credit_score.filter(~(col('Num_Credit_Inquiries') > 17))
print('After dropping Num_Credit_Inquiries Outliers: ', credit_score.count())
credit_score = credit_score.checkpoint()Before dropping columns: 80904
Column Num_of_Delayed_Payment dropped. Current count: 80472
Column Changed_Credit_Limit dropped. Current count: 80464
Column Num_Credit_Inquiries dropped. Current count: 80440
Column Amount_invested_monthly dropped. Current count: 76696
Column Monthly_Balance dropped. Current count: 75448
Afer dropping columns: 75448
After dropping Num_Credit_Inquiries Outliers: 75400Dropping Duplicates
We noted that there are each customer has repeated rows of input, this might be because it was also initially a timeframe related dataset, with only minor differences in data throughout, which indicated the changes over time. Removing the identification and time related column, with additionally filling missing information with the most occuring, we essentially lessen the amount of data we can use to build this model.
print('Before Dropping Duplicates: ', credit_score.count())
credit_score = credit_score.dropDuplicates()
print('After Dropping Duplicates: ', credit_score.count())
credit_score = credit_score.checkpoint()Before Dropping Duplicates: 75400
After Dropping Duplicates: 14905Machine Learning Implementation
Now we will be implementing the different machine learning models. Because we will first implement Random Forest Regressor and Random Forest Regressors. It is known that for these models, we need not over process the data for it to work. Therefore, normalization will not be applied yet to the data.
Preparing list of columns
We have prepared the columns for the different models as some might require different type of inputs.
credit_score_columns = credit_score.columns
columns_to_remove = []
credit_score_columns_indexed = []
credit_score_columns_encoded = []
output_columns = []
for column in credit_score_columns:
if 'indexed' in column and not('Credit_Score' in column):
columns_to_remove.append(column)
credit_score_columns_indexed.append(column)
if 'encoded' in column and not('Credit_Score' in column):
columns_to_remove.append(column)
credit_score_columns_encoded.append(column)
if 'Credit_Score' in column:
columns_to_remove.append(column)
output_columns.append(column)
for column in columns_to_remove:
credit_score_columns.remove(column)
print('This is Credit Score Columns: ', credit_score_columns)
print('This is Credit Score Indexed Columns: ', credit_score_columns_indexed)
print('This is Credit Score Encoded Columns: ', credit_score_columns_encoded)
print('This is Credit Score Output Columns: ', output_columns)This is Credit Score Columns: ['Age', 'Annual_Income', 'Num_Bank_Accounts', 'Num_Credit_Card', 'Interest_Rate', 'Num_of_Loan', 'Delay_from_due_date', 'Num_of_Delayed_Payment', 'Changed_Credit_Limit', 'Num_Credit_Inquiries', 'Outstanding_Debt', 'Credit_Utilization_Ratio', 'Payment_of_Min_Amount', 'Total_EMI_per_month', 'Amount_invested_monthly', 'Monthly_Balance', 'Auto Loan', 'Credit-Builder Loan', 'Debt Consolidation Loan', 'Home Equity Loan', 'Mortgage Loan', 'Payday Loan', 'Personal Loan', 'Student Loan', 'Credit_History_Age_in_Months']
This is Credit Score Indexed Columns: ['Spending Frequency_indexed', 'Average Size of Payment_indexed', 'Occupation_indexed']
This is Credit Score Encoded Columns: ['Spending Frequency_encoded', 'Average Size of Payment_encoded', 'Occupation_encoded']
This is Credit Score Output Columns: ['Credit_Score_indexed', 'Credit_Score_encoded']for column in credit_score.columns:
count = credit_score.select(column).filter(col(column).isNull()).count()
if count != 0:
print(column + " " + str(count))Vector Assembler
We will need to store the feature into one column. This needs to be done on a model to model basis. So the following code is for the Random Forest Regressor.
from pyspark.ml.feature import VectorAssembler
input_columns = credit_score_columns + credit_score_columns_indexed
print(input_columns)
vector_assembler = VectorAssembler(
inputCols = input_columns,
outputCol = 'features'
)
print(output_columns[0])
dataset = vector_assembler.transform(credit_score)
dataset = dataset.checkpoint()['Age', 'Annual_Income', 'Num_Bank_Accounts', 'Num_Credit_Card', 'Interest_Rate', 'Num_of_Loan', 'Delay_from_due_date', 'Num_of_Delayed_Payment', 'Changed_Credit_Limit', 'Num_Credit_Inquiries', 'Outstanding_Debt', 'Credit_Utilization_Ratio', 'Payment_of_Min_Amount', 'Total_EMI_per_month', 'Amount_invested_monthly', 'Monthly_Balance', 'Auto Loan', 'Credit-Builder Loan', 'Debt Consolidation Loan', 'Home Equity Loan', 'Mortgage Loan', 'Payday Loan', 'Personal Loan', 'Student Loan', 'Credit_History_Age_in_Months', 'Spending Frequency_indexed', 'Average Size of Payment_indexed', 'Occupation_indexed']
Credit_Score_indexedNormalizing Data for Multilayer Perceptron
As it is said that keep values between 0 and 1, would be beneficial for perceptrons as having larger values could cause many issues such as vanishing or exploding weights (when 0.1 _ 0.1 multiple times until the values is almost 0, or 10 _ 10 multiple times while the other weights are of values between 0 - 1) and placing emphasis on certain features only due to the magnitude of its value (annual income being in the 100000s while age is only within 2 digits, emphasize on annual income feature will be given by the model), etc.
Before normalizing, we will check all column values once again, because after a round of testing all the models and normalizing the values, it is noted that there are still outliers in the data.
for column in credit_score:
credit_score.select(column).groupBy(column).count().orderBy(column).show(100)+----+-----+
| Age|count|
+----+-----+
|-500| 1|
| 14| 184|
| 15| 207|
| 16| 216|
| 17| 238|
| 18| 365|
| 19| 447|
| 20| 408|
| 21| 426|
| 22| 445|
| 23| 408|
| 24| 405|
| 25| 444|
| 26| 450|
| 27| 418|
| 28| 451|
| 29| 416|
| 30| 418|
| 31| 474|
| 32| 430|
| 33| 378|
| 34| 448|
| 35| 427|
| 36| 439|
| 37| 424|
| 38| 456|
| 39| 439|
| 40| 402|
| 41| 413|
| 42| 392|
| 43| 426|
| 44| 415|
| 45| 381|
| 46| 257|
| 47| 188|
| 48| 204|
| 49| 206|
| 50| 200|
| 51| 228|
| 52| 217|
| 53| 225|
| 54| 217|
| 55| 211|
| 56| 52|
|1792| 2|
|2318| 1|
|2471| 2|
|3734| 2|
|4775| 1|
|8553| 1|
+----+-----+
+-------------+-----+
|Annual_Income|count|
+-------------+-----+
| 7005| 1|
| 7006| 4|
| 7011| 2|
| 7019| 1|
| 7020| 1|
| 7021| 2|
| 7023| 1|
| 7039| 1|
| 7046| 2|
| 7055| 2|
| 7056| 2|
| 7059| 2|
| 7064| 1|
| 7077| 1|
| 7079| 1|
| 7084| 2|
| 7085| 2|
| 7087| 2|
| 7091| 2|
| 7097| 2|
| 7103| 1|
| 7106| 1|
| 7110| 1|
| 7112| 1|
| 7123| 2|
| 7127| 1|
| 7136| 2|
| 7152| 2|
| 7153| 2|
| 7156| 2|
| 7160| 3|
| 7161| 2|
| 7166| 1|
| 7168| 2|
| 7171| 1|
| 7174| 1|
| 7184| 2|
| 7186| 1|
| 7187| 2|
| 7200| 4|
| 7201| 1|
| 7206| 2|
| 7207| 1|
| 7225| 2|
| 7230| 2|
| 7233| 1|
| 7252| 2|
| 7261| 2|
| 7269| 2|
| 7290| 2|
| 7295| 2|
| 7296| 1|
| 7299| 2|
| 7304| 2|
| 7309| 3|
| 7314| 2|
| 7326| 1|
| 7330| 2|
| 7361| 2|
| 7369| 1|
| 7371| 4|
| 7377| 2|
| 7379| 1|
| 7388| 2|
| 7423| 2|
| 7424| 1|
| 7427| 2|
| 7435| 2|
| 7441| 2|
| 7448| 2|
| 7453| 1|
| 7457| 1|
| 7465| 1|
| 7467| 2|
| 7471| 1|
| 7472| 2|
| 7476| 2|
| 7477| 2|
| 7493| 2|
| 7495| 1|
| 7499| 2|
| 7506| 2|
| 7512| 1|
| 7517| 2|
| 7518| 1|
| 7526| 2|
| 7531| 1|
| 7534| 2|
| 7536| 2|
| 7542| 1|
| 7546| 2|
| 7555| 2|
| 7558| 2|
| 7567| 4|
| 7569| 2|
| 7588| 2|
| 7596| 2|
| 7598| 1|
| 7599| 2|
| 7604| 2|
+-------------+-----+
only showing top 100 rows
+-----------------+-----+
|Num_Bank_Accounts|count|
+-----------------+-----+
| -1| 3|
| 0| 689|
| 1| 735|
| 2| 724|
| 3| 1787|
| 4| 1799|
| 5| 1803|
| 6| 1919|
| 7| 1888|
| 8| 1868|
| 9| 848|
| 10| 829|
| 103| 2|
| 724| 2|
| 795| 2|
| 1255| 1|
| 1268| 2|
| 1321| 2|
| 1443| 1|
| 1774| 1|
+-----------------+-----+
+---------------+-----+
|Num_Credit_Card|count|
+---------------+-----+
| 1| 346|
| 2| 366|
| 3| 1950|
| 4| 2096|
| 5| 2831|
| 6| 2488|
| 7| 2522|
| 8| 773|
| 9| 703|
| 10| 798|
| 11| 10|
| 98| 1|
| 163| 1|
| 270| 2|
| 305| 2|
| 357| 2|
| 422| 2|
| 514| 1|
| 616| 2|
| 664| 2|
| 848| 2|
| 870| 1|
| 1271| 1|
| 1375| 2|
| 1426| 1|
+---------------+-----+
+-------------+-----+
|Interest_Rate|count|
+-------------+-----+
| 1| 444|
| 2| 429|
| 3| 443|
| 4| 431|
| 5| 760|
| 6| 685|
| 7| 675|
| 8| 735|
| 9| 664|
| 10| 663|
| 11| 706|
| 12| 661|
| 13| 294|
| 14| 282|
| 15| 587|
| 16| 540|
| 17| 550|
| 18| 604|
| 19| 547|
| 20| 532|
| 21| 250|
| 22| 249|
| 23| 276|
| 24| 291|
| 25| 228|
| 26| 228|
| 27| 271|
| 28| 277|
| 29| 287|
| 30| 269|
| 31| 244|
| 32| 279|
| 33| 239|
| 34| 257|
| 92| 1|
| 197| 1|
| 208| 2|
| 243| 1|
| 520| 2|
| 679| 2|
| 1115| 2|
| 1277| 2|
| 1313| 2|
| 1384| 2|
| 2129| 2|
| 2226| 2|
| 3217| 1|
| 3467| 2|
| 4360| 2|
| 4805| 1|
| 5418| 1|
+-------------+-----+
+-----------+-----+
|Num_of_Loan|count|
+-----------+-----+
| -100| 14|
| 0| 1739|
| 1| 1640|
| 2| 2332|
| 3| 2347|
| 4| 2216|
| 5| 1201|
| 6| 1227|
| 7| 1144|
| 8| 481|
| 9| 562|
| 1030| 2|
+-----------+-----+
+-------------------+-----+
|Delay_from_due_date|count|
+-------------------+-----+
| -3| 2|
| -2| 5|
| -1| 2|
| 0| 211|
| 1| 213|
| 2| 207|
| 3| 257|
| 4| 255|
| 5| 509|
| 6| 500|
| 7| 500|
| 8| 535|
| 9| 485|
| 10| 480|
| 11| 489|
| 12| 445|
| 13| 532|
| 14| 516|
| 15| 581|
| 16| 384|
| 17| 342|
| 18| 367|
| 19| 386|
| 20| 359|
| 21| 320|
| 22| 308|
| 23| 322|
| 24| 362|
| 25| 365|
| 26| 344|
| 27| 378|
| 28| 360|
| 29| 357|
| 30| 344|
| 31| 78|
| 32| 90|
| 33| 87|
| 34| 82|
| 35| 86|
| 36| 98|
| 37| 86|
| 38| 93|
| 39| 79|
| 40| 79|
| 41| 90|
| 42| 79|
| 43| 84|
| 44| 91|
| 45| 88|
| 46| 86|
| 47| 95|
| 48| 113|
| 49| 94|
| 50| 94|
| 51| 82|
| 52| 85|
| 53| 95|
| 54| 113|
| 55| 102|
| 56| 90|
| 57| 97|
| 58| 87|
| 59| 92|
| 60| 73|
| 61| 88|
| 62| 107|
+-------------------+-----+
+----------------------+-----+
|Num_of_Delayed_Payment|count|
+----------------------+-----+
| -2| 9|
| -1| 10|
| 0| 348|
| 1| 327|
| 2| 361|
| 3| 335|
| 4| 307|
| 5| 353|
| 6| 339|
| 7| 302|
| 8| 859|
| 9| 796|
| 10| 921|
| 11| 773|
| 12| 860|
| 13| 524|
| 14| 540|
| 15| 874|
| 16| 893|
| 17| 828|
| 18| 819|
| 19| 911|
| 20| 924|
| 21| 350|
| 22| 315|
| 23| 346|
| 24| 321|
| 25| 347|
| 26| 3|
| 27| 5|
| 28| 5|
+----------------------+-----+
+--------------------+-----+
|Changed_Credit_Limit|count|
+--------------------+-----+
| 0| 386|
| 1| 763|
| 2| 770|
| 3| 779|
| 4| 823|
| 5| 737|
| 6| 758|
| 7| 1090|
| 8| 1181|
| 9| 1149|
| 10| 889|
| 11| 1048|
| 12| 410|
| 13| 337|
| 14| 323|
| 15| 504|
| 16| 490|
| 17| 470|
| 18| 456|
| 19| 472|
| 20| 105|
| 21| 94|
| 22| 109|
| 23| 117|
| 24| 120|
| 25| 110|
| 26| 100|
| 27| 115|
| 28| 102|
| 29| 97|
| 30| 1|
+--------------------+-----+
+--------------------+-----+
|Num_Credit_Inquiries|count|
+--------------------+-----+
| 0.0| 1104|
| 1.0| 1234|
| 2.0| 1269|
| 3.0| 1414|
| 4.0| 1691|
| 5.0| 837|
| 6.0| 1216|
| 7.0| 1224|
| 8.0| 1164|
| 9.0| 838|
| 10.0| 752|
| 11.0| 829|
| 12.0| 731|
| 13.0| 204|
| 14.0| 160|
| 15.0| 128|
| 16.0| 73|
| 17.0| 37|
+--------------------+-----+
+----------------+-----+
|Outstanding_Debt|count|
+----------------+-----+
| 0.23| 2|
| 0.34| 1|
| 0.54| 2|
| 0.56| 2|
| 0.77| 2|
| 0.95| 2|
| 1.23| 1|
| 1.3| 2|
| 1.33| 1|
| 1.37| 1|
| 1.42| 1|
| 1.48| 2|
| 2.04| 1|
| 2.13| 1|
| 2.43| 1|
| 3.31| 1|
| 3.5| 2|
| 3.74| 2|
| 4.5| 2|
| 4.61| 1|
| 4.64| 2|
| 5.28| 2|
| 5.57| 2|
| 5.67| 1|
| 5.8| 2|
| 6.41| 2|
| 6.49| 2|
| 6.84| 2|
| 7.24| 1|
| 7.44| 2|
| 7.51| 1|
| 7.54| 2|
| 7.64| 2|
| 7.87| 2|
| 8.07| 2|
| 8.11| 1|
| 9.32| 1|
| 9.35| 2|
| 9.55| 1|
| 9.65| 2|
| 9.7| 1|
| 10.29| 3|
| 10.52| 1|
| 10.55| 2|
| 10.77| 2|
| 10.89| 2|
| 11.02| 1|
| 12.41| 2|
| 12.65| 2|
| 12.9| 1|
| 13.24| 2|
| 13.57| 2|
| 13.59| 1|
| 13.72| 2|
| 14.34| 2|
| 14.56| 2|
| 15.03| 1|
| 15.18| 1|
| 15.47| 2|
| 15.58| 2|
| 15.74| 2|
| 16.3| 1|
| 16.36| 1|
| 16.42| 2|
| 16.45| 2|
| 16.88| 2|
| 17.72| 2|
| 17.81| 2|
| 17.87| 1|
| 18.31| 1|
| 18.55| 1|
| 18.93| 2|
| 18.99| 1|
| 19.11| 1|
| 19.36| 2|
| 19.43| 1|
| 19.94| 1|
| 19.96| 1|
| 20.09| 2|
| 20.94| 1|
| 21.07| 1|
| 21.75| 2|
| 22.45| 1|
| 22.71| 1|
| 22.88| 2|
| 23.2| 1|
| 23.64| 1|
| 23.7| 2|
| 23.79| 2|
| 24.1| 2|
| 24.57| 1|
| 24.73| 2|
| 25.16| 1|
| 25.62| 2|
| 25.78| 2|
| 26.42| 2|
| 26.47| 1|
| 27.63| 2|
| 27.94| 2|
| 28.15| 1|
+----------------+-----+
only showing top 100 rows
+------------------------+-----+
|Credit_Utilization_Ratio|count|
+------------------------+-----+
| 21.02766450595043| 1|
| 21.542891624957218| 2|
| 21.630213876760216| 1|
| 21.70335230812595| 2|
| 21.705928473763276| 1|
| 21.722347888735534| 1|
| 21.768190492431412| 1|
| 21.781802308909477| 1|
| 21.800502171646148| 1|
| 21.82087345917348| 1|
| 21.8279903822023| 2|
| 21.829727285787573| 2|
| 21.86247740478445| 2|
| 21.864235214355393| 2|
| 21.881204553979494| 1|
| 21.881606781214447| 1|
| 21.901401749767214| 2|
| 21.92215443228629| 2|
| 21.930961180439933| 2|
| 21.950659110594646| 1|
| 21.979065904729108| 2|
| 21.983017752769676| 2|
| 21.984370378609952| 1|
| 22.0430685878679| 2|
| 22.069423223792143| 2|
| 22.072571318844773| 2|
| 22.10467933981442| 2|
| 22.105740540901323| 1|
| 22.15154126135888| 1|
| 22.160533919546403| 2|
| 22.196721405407445| 2|
| 22.207508244445645| 2|
| 22.24476313537557| 1|
| 22.267574010817704| 1|
| 22.27244731001976| 1|
| 22.292537903746094| 2|
| 22.29762931125713| 1|
| 22.31268014682543| 2|
| 22.316101786461925| 2|
| 22.33176850208251| 2|
| 22.341378455897626| 1|
| 22.356040976575713| 2|
| 22.36553000878052| 1|
| 22.371671983769854| 1|
| 22.3737446755288| 2|
| 22.37898903557043| 1|
| 22.380398869829754| 2|
| 22.39042839242095| 2|
| 22.393534714716235| 1|
| 22.397021185742307| 1|
| 22.418271365757263| 2|
| 22.421900490041764| 1|
| 22.443160558432627| 2|
| 22.44756288603193| 1|
| 22.453006568236102| 2|
| 22.462063150591035| 1|
| 22.46330892741706| 1|
| 22.46784278224068| 2|
| 22.484412659366694| 2|
| 22.492852612979497| 1|
| 22.50450693679105| 1|
| 22.511478166287283| 2|
| 22.521090968594827| 1|
| 22.54319357361861| 2|
| 22.545766595288118| 2|
| 22.565522450844046| 2|
| 22.579465175593675| 1|
| 22.589717929187003| 2|
| 22.591787758905237| 1|
| 22.60538961789712| 1|
| 22.605985127190266| 1|
| 22.620430287902103| 1|
| 22.62071532157298| 2|
| 22.64697180483743| 1|
| 22.647399287043505| 1|
| 22.6499383573388| 2|
| 22.65553735805397| 2|
| 22.660870811848078| 2|
| 22.682539521549355| 2|
| 22.68841242825795| 2|
| 22.70210060975084| 2|
| 22.705344755850696| 2|
| 22.70558946172973| 1|
| 22.71265776614702| 3|
| 22.7263982616485| 1|
| 22.72931698610209| 2|
| 22.772919978848854| 1|
| 22.7831499572201| 2|
| 22.784842755890594| 1|
| 22.792364450392927| 1|
| 22.794775422212552| 2|
| 22.83673871162875| 2|
| 22.852138433125628| 2|
| 22.857379810137747| 2|
| 22.861782392308783| 2|
| 22.86585394877776| 2|
| 22.87576370156097| 1|
| 22.888204455018894| 1|
| 22.893717849699488| 2|
| 22.893907479137106| 2|
+------------------------+-----+
only showing top 100 rows
+---------------------+-----+
|Payment_of_Min_Amount|count|
+---------------------+-----+
| 0| 6267|
| 1| 8638|
+---------------------+-----+
+-------------------+-----+
|Total_EMI_per_month|count|
+-------------------+-----+
| 0.0| 1675|
| 4.4628374669131645| 1|
| 4.713183571733377| 2|
| 4.865689677072079| 1|
| 4.916138542370655| 1|
| 5.138484695591384| 1|
| 5.218466358633885| 2|
| 5.262291048154371| 2|
| 5.351086151020351| 2|
| 5.463308977561259| 2|
| 5.629824416938626| 2|
| 5.711416878860573| 2|
| 5.748475833624722| 1|
| 5.766275880264306| 1|
| 5.913472082013276| 1|
| 5.968634608828611| 1|
| 6.047450347381079| 2|
| 6.29857321686096| 1|
| 6.412118995076589| 2|
| 6.4878675261176335| 2|
| 6.518271070705215| 1|
| 6.524757595186792| 1|
| 6.6065179827057605| 1|
| 6.637556691814388| 2|
| 6.706015137932544| 1|
| 6.71953494058182| 2|
| 6.7501194879651925| 2|
| 6.814611210325142| 2|
| 6.898288998100544| 1|
| 6.9819930191464366| 1|
| 7.049634750496763| 2|
| 7.05443635523817| 2|
| 7.067810341481343| 2|
| 7.167790767928642| 1|
| 7.180053892226407| 2|
| 7.183338098170633| 1|
| 7.188037221560094| 1|
| 7.247942505883222| 2|
| 7.249926181887131| 1|
| 7.288523415735337| 1|
| 7.293280162361606| 1|
| 7.303131514583107| 1|
| 7.327678460882679| 2|
| 7.334973367345464| 2|
| 7.3401274994922705| 2|
| 7.348140838048644| 2|
| 7.375661122441943| 1|
| 7.403524777057425| 2|
| 7.511182287951912| 1|
| 7.6379557514141885| 1|
| 7.642056540954449| 1|
| 7.648423558909102| 2|
| 7.737807248837968| 2|
| 7.7678943918962675| 2|
| 7.771075085382389| 1|
| 7.847698736792763| 1|
| 7.8970740737019645| 2|
| 7.904920536954126| 2|
| 7.913043411570557| 2|
| 7.9258761282951795| 2|
| 7.954928158129438| 2|
| 7.981570049242603| 1|
| 7.991650369121829| 1|
| 8.025107606573853| 2|
| 8.036609620229202| 1|
| 8.039939020263716| 2|
| 8.140792415105551| 1|
| 8.157936038864184| 1|
| 8.245353566398231| 1|
| 8.32457870219988| 2|
| 8.350875465140536| 2|
| 8.367989377877612| 1|
| 8.39085635551636| 1|
| 8.439815424520496| 2|
| 8.47408555938318| 1|
| 8.485266863383051| 2|
| 8.521817034400451| 1|
| 8.540130456032621| 1|
| 8.561280959665341| 1|
| 8.562244720862807| 2|
| 8.593567256269756| 2|
| 8.616123307996686| 1|
| 8.647233303107| 1|
| 8.693717318052272| 1|
| 8.724970589613072| 2|
| 8.733919706404741| 1|
| 8.740465074824666| 2|
| 8.821659718564948| 2|
| 8.862377138762078| 2|
| 8.897017222603756| 1|
| 8.961406105567454| 1|
| 8.970576328687951| 2|
| 8.996502339506062| 1|
| 9.012222642080221| 1|
| 9.060348682889094| 1|
| 9.091012303737477| 1|
| 9.143908457799562| 2|
| 9.168931261835741| 2|
| 9.175797471274404| 2|
| 9.22840565157338| 1|
+-------------------+-----+
only showing top 100 rows
+-----------------------+-----+
|Amount_invested_monthly|count|
+-----------------------+-----+
| 0.0| 39|
| 10.010194262612963| 1|
| 10.46159759179635| 2|
| 10.47500745842986| 2|
| 10.672831399078632| 2|
| 10.682540064142273| 1|
| 10.805861169293614| 2|
| 10.880617234145971| 1|
| 10.887483303378731| 2|
| 10.895046988254046| 2|
| 11.164843206368538| 1|
| 11.306434035208731| 2|
| 11.337555886943655| 1|
| 11.348913391667185| 2|
| 11.624031592911289| 2|
| 12.240127244955804| 2|
| 12.376379808932716| 2|
| 12.524733410478834| 2|
| 12.569601035339| 1|
| 12.63100304789831| 2|
| 12.661153413512125| 2|
| 12.716530247025554| 1|
| 12.846632047897995| 2|
| 12.920005493867414| 2|
| 12.925146181050325| 2|
| 13.066209919444336| 1|
| 13.133014949335914| 2|
| 13.21008348074107| 1|
| 13.37459506391507| 2|
| 13.389043428386884| 1|
| 13.457706122932773| 1|
| 13.496482302873144| 2|
| 13.613838353844136| 2|
| 13.616761364811072| 1|
| 13.637805792124846| 2|
| 13.837497135735585| 2|
| 13.86776101753593| 1|
| 13.921215446856117| 2|
| 13.964737101670892| 2|
| 13.978475440768257| 2|
| 13.983644722319632| 1|
| 14.091449809848001| 1|
| 14.222500068398581| 1|
| 14.265286906327455| 1|
| 14.278716004049285| 2|
| 14.285252654836466| 1|
| 14.622739235117402| 2|
| 14.68129323406641| 2|
| 14.909474165347852| 2|
| 14.931128583674884| 2|
| 14.960539934848855| 1|
| 14.963945622835851| 1|
| 14.990202053079958| 1|
| 15.06966258486371| 2|
| 15.127041730944063| 1|
| 15.157326531814814| 2|
| 15.206733513024965| 2|
| 15.27318449481906| 2|
| 15.344954474358435| 1|
| 15.361496149255565| 1|
| 15.370842940423275| 2|
| 15.3943175874297| 2|
| 15.41083847206666| 2|
| 15.557184586282592| 2|
| 15.558120579103527| 2|
| 15.573409363717232| 1|
| 15.649026661609211| 2|
| 15.826087405455725| 2|
| 15.859610701243147| 2|
| 15.953354953294161| 1|
| 16.042198639572| 1|
| 16.069107401645933| 2|
| 16.106524668995963| 1|
| 16.139833844406766| 2|
| 16.14929645805267| 2|
| 16.159623599384016| 1|
| 16.164806051375315| 2|
| 16.17451414922814| 2|
| 16.286719355483015| 1|
| 16.397054112739124| 1|
| 16.49603915447353| 2|
| 16.552914131735964| 1|
| 16.59127918616869| 2|
| 16.73697365096827| 2|
| 16.776174776332873| 1|
| 16.796633080905572| 2|
| 16.947556445487617| 2|
| 16.971890206610276| 2|
| 16.987344794088585| 2|
| 17.038740519062443| 1|
| 17.125298610245732| 1|
| 17.154118266507837| 2|
| 17.30791586852336| 2|
| 17.32913269499249| 2|
| 17.334376222608338| 2|
| 17.36428972480781| 2|
| 17.421053041936613| 2|
| 17.44053158497596| 2|
| 17.498241811557797| 1|
| 17.51026476749946| 1|
+-----------------------+-----+
only showing top 100 rows
+-------------------+-----+
| Monthly_Balance|count|
+-------------------+-----+
|0.08862786534905354| 1|
| 0.5035823529403842| 1|
| 0.9081458437026412| 2|
| 1.7054929984553835| 2|
| 1.987138164398857| 2|
| 2.0207122933654773| 2|
| 2.4783517490499776| 1|
| 2.661540771565342| 1|
| 3.5128075871649003| 1|
| 4.1289513724424864| 2|
| 4.557246160962677| 2|
| 4.605698751634009| 2|
| 5.204521752694519| 1|
| 5.238707185797921| 2|
| 5.387081669385567| 3|
| 6.738319085435081| 2|
| 7.562479838793705| 2|
| 8.923133036344325| 2|
| 9.11879568846632| 2|
| 9.582461201749993| 2|
| 11.691132272434402| 2|
| 12.698958018084795| 2|
| 15.450914052143046| 1|
| 15.649017084929085| 2|
| 16.926107637259804| 1|
| 17.340081894114288| 2|
| 17.59303115992111| 1|
| 19.25146987266237| 2|
| 19.260026858751413| 1|
| 20.055994575434735| 1|
| 21.55314295536385| 1|
| 22.384101436516747| 1|
| 22.666007091769416| 1|
| 22.824368663599216| 1|
| 24.294490242928987| 2|
| 25.091618133651767| 1|
| 26.317125983088545| 2|
| 26.742007496468943| 1|
| 27.30636253170809| 1|
| 27.504875806534532| 2|
| 28.83467580154911| 1|
| 29.266943649688983| 1|
| 29.280302837318803| 1|
| 29.812201767928173| 2|
| 30.223896308509442| 2|
| 30.278365564444126| 2|
| 30.461678731855606| 2|
| 30.76582279442169| 1|
| 30.882521922168394| 2|
| 31.534533961569768| 1|
| 31.95558041714571| 2|
| 33.05305454414884| 1|
| 33.16636620108557| 2|
| 34.345513612273635| 1|
| 34.546589097892365| 1|
| 37.37953938357782| 2|
| 37.55704272438885| 1|
| 38.009576700774225| 2|
| 38.61179351122365| 1|
| 38.935523118553185| 2|
| 39.26880692497525| 1|
| 39.95336468734564| 2|
| 40.19842747519692| 1|
| 40.39917891050095| 1|
| 40.43063442294374| 2|
| 41.087225482398594| 1|
| 43.70378292319845| 2|
| 43.849570478422095| 2|
| 43.865337330375674| 2|
| 44.191583211436644| 2|
| 44.48871463899286| 2|
| 45.015573189532574| 1|
| 45.62434483788118| 1|
| 45.91328725295449| 1|
| 45.9915541351904| 2|
| 46.33221464520162| 1|
| 46.36581616001399| 2|
| 46.573819825604744| 1|
| 46.894620617361106| 1|
| 47.40643980471469| 2|
| 48.08866420135212| 1|
| 48.55290317696382| 2|
| 49.505817424674255| 2|
| 50.0340539738942| 2|
| 50.90006749704091| 1|
| 51.086885954493944| 1|
| 51.2148323909969| 2|
| 53.139197398397634| 2|
| 53.25968388966203| 2|
| 53.332266984875275| 1|
| 53.75438369984539| 2|
| 54.517425088172786| 2|
| 54.91346208515722| 1|
| 56.28141921257532| 2|
| 56.39229886455421| 2|
| 57.167053381278954| 2|
| 57.54575219216883| 2|
| 58.38547176188649| 1|
| 58.78319870768622| 2|
| 58.84470284157919| 2|
+-------------------+-----+
only showing top 100 rows
+---------+-----+
|Auto Loan|count|
+---------+-----+
| 0|10354|
| 1| 4551|
+---------+-----+
+-------------------+-----+
|Credit-Builder Loan|count|
+-------------------+-----+
| 0|10200|
| 1| 4705|
+-------------------+-----+
+-----------------------+-----+
|Debt Consolidation Loan|count|
+-----------------------+-----+
| 0|10319|
| 1| 4586|
+-----------------------+-----+
+----------------+-----+
|Home Equity Loan|count|
+----------------+-----+
| 0|10277|
| 1| 4628|
+----------------+-----+
+-------------+-----+
|Mortgage Loan|count|
+-------------+-----+
| 0|10247|
| 1| 4658|
+-------------+-----+
+-----------+-----+
|Payday Loan|count|
+-----------+-----+
| 0|10085|
| 1| 4820|
+-----------+-----+
+-------------+-----+
|Personal Loan|count|
+-------------+-----+
| 0|10282|
| 1| 4623|
+-------------+-----+
+------------+-----+
|Student Loan|count|
+------------+-----+
| 0|10240|
| 1| 4665|
+------------+-----+
+----------------------------+-----+
|Credit_History_Age_in_Months|count|
+----------------------------+-----+
| 1.0| 2|
| 2.0| 16|
| 3.0| 10|
| 4.0| 23|
| 5.0| 6|
| 6.0| 2|
| 7.0| 7|
| 8.0| 14|
| 9.0| 15|
| 10.0| 21|
| 11.0| 13|
| 12.0| 3|
| 13.0| 11|
| 14.0| 12|
| 15.0| 20|
| 16.0| 19|
| 17.0| 12|
| 18.0| 2|
| 19.0| 23|
| 20.0| 15|
| 21.0| 14|
| 22.0| 18|
| 23.0| 12|
| 24.0| 4|
| 25.0| 25|
| 26.0| 18|
| 27.0| 11|
| 28.0| 6|
| 29.0| 17|
| 31.0| 7|
| 32.0| 13|
| 33.0| 13|
| 34.0| 12|
| 35.0| 22|
| 37.0| 11|
| 38.0| 14|
| 39.0| 13|
| 40.0| 16|
| 41.0| 9|
| 43.0| 9|
| 44.0| 2|
| 45.0| 5|
| 46.0| 21|
| 47.0| 17|
| 49.0| 24|
| 50.0| 12|
| 51.0| 7|
| 52.0| 9|
| 53.0| 11|
| 55.0| 17|
| 56.0| 19|
| 57.0| 9|
| 58.0| 10|
| 59.0| 25|
| 61.0| 18|
| 62.0| 47|
| 63.0| 38|
| 64.0| 50|
| 65.0| 52|
| 66.0| 2|
| 67.0| 40|
| 68.0| 57|
| 69.0| 45|
| 70.0| 46|
| 71.0| 65|
| 72.0| 2|
| 73.0| 51|
| 74.0| 62|
| 75.0| 42|
| 76.0| 51|
| 77.0| 66|
| 78.0| 3|
| 79.0| 58|
| 80.0| 41|
| 81.0| 41|
| 82.0| 22|
| 83.0| 43|
| 85.0| 42|
| 86.0| 45|
| 87.0| 34|
| 88.0| 43|
| 89.0| 44|
| 90.0| 1|
| 91.0| 38|
| 92.0| 54|
| 93.0| 41|
| 94.0| 48|
| 95.0| 56|
| 96.0| 7|
| 97.0| 38|
| 98.0| 38|
| 99.0| 44|
| 100.0| 39|
| 101.0| 64|
| 102.0| 4|
| 103.0| 39|
| 104.0| 26|
| 105.0| 47|
| 106.0| 50|
| 107.0| 48|
+----------------------------+-----+
only showing top 100 rows
+--------------------------+-----+
|Spending Frequency_indexed|count|
+--------------------------+-----+
| 0.0| 8265|
| 1.0| 6640|
+--------------------------+-----+
+--------------------------+-----+
|Spending Frequency_encoded|count|
+--------------------------+-----+
| (1,[],[])| 6640|
| (1,[0],[1.0])| 8265|
+--------------------------+-----+
+-------------------------------+-----+
|Average Size of Payment_indexed|count|
+-------------------------------+-----+
| 0.0| 6825|
| 1.0| 4847|
| 2.0| 3233|
+-------------------------------+-----+
+-------------------------------+-----+
|Average Size of Payment_encoded|count|
+-------------------------------+-----+
| (2,[],[])| 3233|
| (2,[0],[1.0])| 6825|
| (2,[1],[1.0])| 4847|
+-------------------------------+-----+
+------------------+-----+
|Occupation_indexed|count|
+------------------+-----+
| 0.0| 1038|
| 1.0| 1055|
| 2.0| 1038|
| 3.0| 1023|
| 4.0| 1033|
| 5.0| 1005|
| 6.0| 1017|
| 7.0| 1006|
| 8.0| 1001|
| 9.0| 970|
| 10.0| 959|
| 11.0| 919|
| 12.0| 974|
| 13.0| 932|
| 14.0| 892|
| 15.0| 43|
+------------------+-----+
+------------------+-----+
|Occupation_encoded|count|
+------------------+-----+
| (15,[],[])| 43|
| (15,[0],[1.0])| 1038|
| (15,[1],[1.0])| 1055|
| (15,[2],[1.0])| 1038|
| (15,[3],[1.0])| 1023|
| (15,[4],[1.0])| 1033|
| (15,[5],[1.0])| 1005|
| (15,[6],[1.0])| 1017|
| (15,[7],[1.0])| 1006|
| (15,[8],[1.0])| 1001|
| (15,[9],[1.0])| 970|
| (15,[10],[1.0])| 959|
| (15,[11],[1.0])| 919|
| (15,[12],[1.0])| 974|
| (15,[13],[1.0])| 932|
| (15,[14],[1.0])| 892|
+------------------+-----+
+--------------------+-----+
|Credit_Score_indexed|count|
+--------------------+-----+
| 0.0| 8381|
| 1.0| 3874|
| 2.0| 2650|
+--------------------+-----+
+--------------------+-----+
|Credit_Score_encoded|count|
+--------------------+-----+
| (2,[],[])| 2650|
| (2,[0],[1.0])| 8381|
| (2,[1],[1.0])| 3874|
+--------------------+-----+
for column in credit_score:
credit_score.select(column).groupBy(column).count().orderBy('count').show(100)+----+-----+
| Age|count|
+----+-----+
|2318| 1|
|-500| 1|
|8553| 1|
|4775| 1|
|2471| 2|
|1792| 2|
|3734| 2|
| 56| 52|
| 14| 184|
| 47| 188|
| 50| 200|
| 48| 204|
| 49| 206|
| 15| 207|
| 55| 211|
| 16| 216|
| 54| 217|
| 52| 217|
| 53| 225|
| 51| 228|
| 17| 238|
| 46| 257|
| 18| 365|
| 33| 378|
| 45| 381|
| 42| 392|
| 40| 402|
| 24| 405|
| 20| 408|
| 23| 408|
| 41| 413|
| 44| 415|
| 29| 416|
| 27| 418|
| 30| 418|
| 37| 424|
| 43| 426|
| 21| 426|
| 35| 427|
| 32| 430|
| 39| 439|
| 36| 439|
| 25| 444|
| 22| 445|
| 19| 447|
| 34| 448|
| 26| 450|
| 28| 451|
| 38| 456|
| 31| 474|
+----+-----+
+-------------+-----+
|Annual_Income|count|
+-------------+-----+
| 71746| 1|
| 30547| 1|
| 91432| 1|
| 89221| 1|
| 111940| 1|
| 58820| 1|
| 66978| 1|
| 47013| 1|
| 14958| 1|
| 22609| 1|
| 71732| 1|
| 30519| 1|
| 30128| 1|
| 36237| 1|
| 123306| 1|
| 55197| 1|
| 67857| 1|
| 33337| 1|
| 142277| 1|
| 63197| 1|
| 50847| 1|
| 17775| 1|
| 126982| 1|
| 25355| 1|
| 67556| 1|
| 19180| 1|
| 36366| 1|
| 58853| 1|
| 71508| 1|
| 59641| 1|
| 90487| 1|
| 35235| 1|
| 15604| 1|
| 8779| 1|
| 37788| 1|
| 30802| 1|
| 29827| 1|
| 41037| 1|
| 66289| 1|
| 17172| 1|
| 18759| 1|
| 54231| 1|
| 19526| 1|
| 34435| 1|
| 73436| 1|
| 20134| 1|
| 114128| 1|
| 25628| 1|
| 26921| 1|
| 8701| 1|
| 122618| 1|
| 24873| 1|
| 29960| 1|
| 67863| 1|
| 75354| 1|
| 47268| 1|
| 103755| 1|
| 65300| 1|
| 32473| 1|
| 71565| 1|
| 128349| 1|
| 16574| 1|
| 75881| 1|
| 19758| 1|
| 39460| 1|
| 18979| 1|
| 56687| 1|
| 101453| 1|
| 80815| 1|
| 65454| 1|
| 80669| 1|
| 8928| 1|
| 15382| 1|
| 48254| 1|
| 78113| 1|
| 15957| 1|
| 40332| 1|
| 11458| 1|
| 20497| 1|
| 70097| 1|
| 29228| 1|
| 13840| 1|
| 33868| 1|
| 44822| 1|
| 19200| 1|
| 38868| 1|
| 73683| 1|
| 66176| 1|
| 36783| 1|
| 23336| 1|
| 42373| 1|
| 74820| 1|
| 18221| 1|
| 102594| 1|
| 35694| 1|
| 69478| 1|
| 43270| 1|
| 69637| 1|
| 93131| 1|
| 60965| 1|
+-------------+-----+
only showing top 100 rows
+-----------------+-----+
|Num_Bank_Accounts|count|
+-----------------+-----+
| 1774| 1|
| 1443| 1|
| 1255| 1|
| 1321| 2|
| 103| 2|
| 795| 2|
| 724| 2|
| 1268| 2|
| -1| 3|
| 0| 689|
| 2| 724|
| 1| 735|
| 10| 829|
| 9| 848|
| 3| 1787|
| 4| 1799|
| 5| 1803|
| 8| 1868|
| 7| 1888|
| 6| 1919|
+-----------------+-----+
+---------------+-----+
|Num_Credit_Card|count|
+---------------+-----+
| 1426| 1|
| 163| 1|
| 514| 1|
| 98| 1|
| 1271| 1|
| 870| 1|
| 1375| 2|
| 616| 2|
| 305| 2|
| 664| 2|
| 848| 2|
| 270| 2|
| 357| 2|
| 422| 2|
| 11| 10|
| 1| 346|
| 2| 366|
| 9| 703|
| 8| 773|
| 10| 798|
| 3| 1950|
| 4| 2096|
| 6| 2488|
| 7| 2522|
| 5| 2831|
+---------------+-----+
+-------------+-----+
|Interest_Rate|count|
+-------------+-----+
| 5418| 1|
| 243| 1|
| 4805| 1|
| 92| 1|
| 3217| 1|
| 197| 1|
| 3467| 2|
| 679| 2|
| 520| 2|
| 1313| 2|
| 2129| 2|
| 2226| 2|
| 4360| 2|
| 1115| 2|
| 1384| 2|
| 1277| 2|
| 208| 2|
| 25| 228|
| 26| 228|
| 33| 239|
| 31| 244|
| 22| 249|
| 21| 250|
| 34| 257|
| 30| 269|
| 27| 271|
| 23| 276|
| 28| 277|
| 32| 279|
| 14| 282|
| 29| 287|
| 24| 291|
| 13| 294|
| 2| 429|
| 4| 431|
| 3| 443|
| 1| 444|
| 20| 532|
| 16| 540|
| 19| 547|
| 17| 550|
| 15| 587|
| 18| 604|
| 12| 661|
| 10| 663|
| 9| 664|
| 7| 675|
| 6| 685|
| 11| 706|
| 8| 735|
| 5| 760|
+-------------+-----+
+-----------+-----+
|Num_of_Loan|count|
+-----------+-----+
| 1030| 2|
| -100| 14|
| 8| 481|
| 9| 562|
| 7| 1144|
| 5| 1201|
| 6| 1227|
| 1| 1640|
| 0| 1739|
| 4| 2216|
| 2| 2332|
| 3| 2347|
+-----------+-----+
+-------------------+-----+
|Delay_from_due_date|count|
+-------------------+-----+
| -1| 2|
| -3| 2|
| -2| 5|
| 60| 73|
| 31| 78|
| 39| 79|
| 40| 79|
| 42| 79|
| 51| 82|
| 34| 82|
| 43| 84|
| 52| 85|
| 37| 86|
| 46| 86|
| 35| 86|
| 58| 87|
| 33| 87|
| 45| 88|
| 61| 88|
| 32| 90|
| 56| 90|
| 41| 90|
| 44| 91|
| 59| 92|
| 38| 93|
| 49| 94|
| 50| 94|
| 47| 95|
| 53| 95|
| 57| 97|
| 36| 98|
| 55| 102|
| 62| 107|
| 54| 113|
| 48| 113|
| 2| 207|
| 0| 211|
| 1| 213|
| 4| 255|
| 3| 257|
| 22| 308|
| 21| 320|
| 23| 322|
| 17| 342|
| 26| 344|
| 30| 344|
| 29| 357|
| 20| 359|
| 28| 360|
| 24| 362|
| 25| 365|
| 18| 367|
| 27| 378|
| 16| 384|
| 19| 386|
| 12| 445|
| 10| 480|
| 9| 485|
| 11| 489|
| 7| 500|
| 6| 500|
| 5| 509|
| 14| 516|
| 13| 532|
| 8| 535|
| 15| 581|
+-------------------+-----+
+----------------------+-----+
|Num_of_Delayed_Payment|count|
+----------------------+-----+
| 26| 3|
| 28| 5|
| 27| 5|
| -2| 9|
| -1| 10|
| 7| 302|
| 4| 307|
| 22| 315|
| 24| 321|
| 1| 327|
| 3| 335|
| 6| 339|
| 23| 346|
| 25| 347|
| 0| 348|
| 21| 350|
| 5| 353|
| 2| 361|
| 13| 524|
| 14| 540|
| 11| 773|
| 9| 796|
| 18| 819|
| 17| 828|
| 8| 859|
| 12| 860|
| 15| 874|
| 16| 893|
| 19| 911|
| 10| 921|
| 20| 924|
+----------------------+-----+
+--------------------+-----+
|Changed_Credit_Limit|count|
+--------------------+-----+
| 30| 1|
| 21| 94|
| 29| 97|
| 26| 100|
| 28| 102|
| 20| 105|
| 22| 109|
| 25| 110|
| 27| 115|
| 23| 117|
| 24| 120|
| 14| 323|
| 13| 337|
| 0| 386|
| 12| 410|
| 18| 456|
| 17| 470|
| 19| 472|
| 16| 490|
| 15| 504|
| 5| 737|
| 6| 758|
| 1| 763|
| 2| 770|
| 3| 779|
| 4| 823|
| 10| 889|
| 11| 1048|
| 7| 1090|
| 9| 1149|
| 8| 1181|
+--------------------+-----+
+--------------------+-----+
|Num_Credit_Inquiries|count|
+--------------------+-----+
| 17.0| 37|
| 16.0| 73|
| 15.0| 128|
| 14.0| 160|
| 13.0| 204|
| 12.0| 731|
| 10.0| 752|
| 11.0| 829|
| 5.0| 837|
| 9.0| 838|
| 0.0| 1104|
| 8.0| 1164|
| 6.0| 1216|
| 7.0| 1224|
| 1.0| 1234|
| 2.0| 1269|
| 3.0| 1414|
| 4.0| 1691|
+--------------------+-----+
+----------------+-----+
|Outstanding_Debt|count|
+----------------+-----+
| 830.63| 1|
| 1027.64| 1|
| 839.77| 1|
| 976.94| 1|
| 3189.7| 1|
| 1287.76| 1|
| 430.39| 1|
| 2145.42| 1|
| 767.91| 1|
| 320.07| 1|
| 347.93| 1|
| 1078.95| 1|
| 1137.64| 1|
| 819.81| 1|
| 4720.99| 1|
| 792.73| 1|
| 1224.04| 1|
| 1457.03| 1|
| 179.1| 1|
| 203.21| 1|
| 2958.46| 1|
| 2289.03| 1|
| 1375.36| 1|
| 374.7| 1|
| 4367.85| 1|
| 1109.1| 1|
| 328.05| 1|
| 630.62| 1|
| 715.19| 1|
| 3991.34| 1|
| 786.55| 1|
| 1210.87| 1|
| 1285.23| 1|
| 1030.14| 1|
| 1350.08| 1|
| 1229.33| 1|
| 1911.65| 1|
| 1469.17| 1|
| 1284.31| 1|
| 1283.78| 1|
| 1342.14| 1|
| 3051.99| 1|
| 884.52| 1|
| 1037.68| 1|
| 2989.13| 1|
| 242.96| 1|
| 82.11| 1|
| 124.1| 1|
| 510.55| 1|
| 662.86| 1|
| 3804.76| 1|
| 1086.65| 1|
| 2439.06| 1|
| 261.93| 1|
| 1389.91| 1|
| 3103.97| 1|
| 355.39| 1|
| 818.5| 1|
| 1434.54| 1|
| 1276.97| 1|
| 664.62| 1|
| 1334.8| 1|
| 1079.55| 1|
| 2061.66| 1|
| 3607.96| 1|
| 746.19| 1|
| 1341.25| 1|
| 1141.72| 1|
| 668.14| 1|
| 2136.31| 1|
| 455.22| 1|
| 914.82| 1|
| 3698.45| 1|
| 2589.93| 1|
| 1210.4| 1|
| 2930.71| 1|
| 1292.5| 1|
| 201.94| 1|
| 9.55| 1|
| 315.42| 1|
| 153.99| 1|
| 1102.41| 1|
| 203.33| 1|
| 2225.58| 1|
| 1484.58| 1|
| 100.49| 1|
| 900.26| 1|
| 1945.68| 1|
| 4397.24| 1|
| 759.58| 1|
| 3683.98| 1|
| 19.96| 1|
| 2748.17| 1|
| 1476.36| 1|
| 838.05| 1|
| 929.51| 1|
| 506.3| 1|
| 1439.29| 1|
| 349.88| 1|
| 2268.36| 1|
+----------------+-----+
only showing top 100 rows
+------------------------+-----+
|Credit_Utilization_Ratio|count|
+------------------------+-----+
| 31.929524177481| 1|
| 31.642330133136173| 1|
| 38.854476457781| 1|
| 29.39985346478011| 1|
| 25.778423413582892| 1|
| 36.869838603029145| 1|
| 33.909376887126434| 1|
| 36.443103367878145| 1|
| 36.29148976123147| 1|
| 24.20960780406837| 1|
| 31.585383030644078| 1|
| 34.37013432043272| 1|
| 32.758941156652625| 1|
| 33.56472508290697| 1|
| 29.827791718614048| 1|
| 32.34271827438348| 1|
| 35.41178781126481| 1|
| 30.57862476154433| 1|
| 27.408907201599234| 1|
| 27.793973668939465| 1|
| 39.78199034858991| 1|
| 27.761530558236718| 1|
| 26.82916036150625| 1|
| 35.21233440012586| 1|
| 38.11978822502434| 1|
| 30.023499694611026| 1|
| 23.989260948042716| 1|
| 41.575611084136355| 1|
| 30.271518487769704| 1|
| 28.755837748910498| 1|
| 37.911510774266006| 1|
| 33.888388001815535| 1|
| 35.44381514425191| 1|
| 38.922847227430495| 1|
| 37.27994208338172| 1|
| 40.04719655295394| 1|
| 25.70561655256136| 1|
| 35.65711811434618| 1|
| 28.90722310941793| 1|
| 36.206109490532434| 1|
| 24.55870446030809| 1|
| 32.27308981733626| 1|
| 36.178322326087326| 1|
| 39.02043252769608| 1|
| 28.61673885106348| 1|
| 39.68116676700739| 1|
| 25.899609257429663| 1|
| 33.51092487063549| 1|
| 26.75755632872441| 1|
| 30.042113694486385| 1|
| 29.860517991892237| 1|
| 40.118691226042344| 1|
| 30.524172010556818| 1|
| 33.027375634671046| 1|
| 34.514558465971874| 1|
| 29.139873302817172| 1|
| 22.87576370156097| 1|
| 34.19228134960661| 1|
| 36.71110818053104| 1|
| 31.48865346118935| 1|
| 32.326516652860974| 1|
| 21.800502171646148| 1|
| 45.03107074220409| 1|
| 41.963673334726536| 1|
| 36.48536854182144| 1|
| 41.292827395478895| 1|
| 33.241409764816076| 1|
| 32.74153148658421| 1|
| 32.74489087056402| 1|
| 38.77469003722636| 1|
| 32.102666110027144| 1|
| 36.916451883229264| 1|
| 26.407303291486517| 1|
| 37.25547264927663| 1|
| 34.55417890338729| 1|
| 36.017742446631544| 1|
| 27.55005132255407| 1|
| 26.08939562765427| 1|
| 29.274043151276132| 1|
| 31.58564144066153| 1|
| 26.202478173317946| 1|
| 44.69630957186141| 1|
| 25.039045665389384| 1|
| 29.347371552381937| 1|
| 36.02920864834289| 1|
| 27.984253790493284| 1|
| 23.193465389190784| 1|
| 35.43572031918311| 1|
| 34.97271476782981| 1|
| 28.103834105655192| 1|
| 36.872573744716156| 1|
| 34.345621685787826| 1|
| 35.34261196142779| 1|
| 37.763810846979254| 1|
| 35.86262280381679| 1|
| 23.931113860611767| 1|
| 28.940892588545452| 1|
| 29.1106732174476| 1|
| 33.787287053887894| 1|
| 42.177064038016965| 1|
+------------------------+-----+
only showing top 100 rows
+---------------------+-----+
|Payment_of_Min_Amount|count|
+---------------------+-----+
| 0| 6267|
| 1| 8638|
+---------------------+-----+
+-------------------+-----+
|Total_EMI_per_month|count|
+-------------------+-----+
| 37.473474457512175| 1|
| 65.36923331459585| 1|
| 250.4172459569628| 1|
| 145.47549261096216| 1|
| 133.68868684473466| 1|
| 30.30549812001825| 1|
| 64.63369949838587| 1|
| 250.10899938647282| 1|
| 302.9162402277047| 1|
| 87.1462147142287| 1|
| 27.519588144245194| 1|
| 22.194088626628766| 1|
| 94.46358890600919| 1|
| 473.1944773799017| 1|
| 44.60716114646277| 1|
| 165.51000075402303| 1|
| 147.0690962890094| 1|
| 45.2646813787989| 1|
| 28.40229704201295| 1|
| 10.962584704325865| 1|
| 85.02935949376669| 1|
| 203.27952130139252| 1|
| 48.47441488517351| 1|
| 21.189696963670034| 1|
| 372.7950058240231| 1|
| 79.85401928431752| 1|
| 52.999514064558774| 1|
| 69.88827520495059| 1|
| 29.14796235594895| 1|
| 52.52158963126021| 1|
| 42.35061760310256| 1|
| 153.39499394571286| 1|
| 127.89861427518109| 1|
| 69.72084239010081| 1|
| 115.04758491554756| 1|
| 18.997238259885574| 1|
| 140.20993380921036| 1|
| 12.03182073160791| 1|
| 59.16549863768918| 1|
| 57.181987988783185| 1|
| 195.8564065116201| 1|
| 35.23571968511521| 1|
| 265.3379077795067| 1|
| 73.67019025318037| 1|
| 223.40820068628773| 1|
| 174.81884849726933| 1|
| 27.29487715493764| 1|
| 74.85037187731447| 1|
| 15.684761106563904| 1|
| 48.844132086716755| 1|
| 119.92649037461531| 1|
| 178.69366876789874| 1|
| 16.904100749323593| 1|
| 41.72758325369589| 1|
| 48.935271886060725| 1|
| 33.81955602684455| 1|
| 25.46799855634962| 1|
| 284.40446981296964| 1|
| 40.98279994086803| 1|
| 16.01410495975805| 1|
| 241.11316100558412| 1|
| 28.064296618865253| 1|
| 227.3018600172955| 1|
| 24.53485516137741| 1|
| 10.552437529398258| 1|
| 65.88958759409584| 1|
| 75.71692855733535| 1|
| 58.996574535646076| 1|
| 130.63491905089842| 1|
| 51.17896890976082| 1|
| 7.511182287951912| 1|
| 135.2703961897122| 1|
| 200.38615492102997| 1|
| 192.81087769599893| 1|
| 15.359696785723465| 1|
| 180.10079118369708| 1|
| 169.2558027710161| 1|
| 194.5173530345591| 1|
| 127.79070025910565| 1|
| 51.56522935796982| 1|
| 33.977334001759175| 1|
| 187.46432294878502| 1|
| 75.5226388676993| 1|
| 31.30713069585225| 1|
| 25.742071947871217| 1|
| 27.026782070694672| 1|
| 11.69835833250137| 1|
| 68.55642939971186| 1|
| 19.90951245535901| 1|
| 160.53930016722137| 1|
| 62.4939254673283| 1|
| 13.369253820088865| 1|
| 129.16175806802985| 1|
| 103.03756035536594| 1|
| 243.94796786695633| 1|
| 171.16569750568982| 1|
| 595.3609382602646| 1|
| 143.63639380798568| 1|
| 78.74861888701788| 1|
| 28.008171703377663| 1|
+-------------------+-----+
only showing top 100 rows
+-----------------------+-----+
|Amount_invested_monthly|count|
+-----------------------+-----+
| 218.43611575001339| 1|
| 55.52850567240079| 1|
| 317.9129512125796| 1|
| 165.47076910687122| 1|
| 193.85308957303317| 1|
| 362.1320797841125| 1|
| 86.9391929215641| 1|
| 322.46551050893385| 1|
| 33.57514249989692| 1|
| 59.22545962350342| 1|
| 104.21569600886814| 1|
| 165.13394166392774| 1|
| 49.73750846417072| 1|
| 204.14518004092582| 1|
| 78.448670403986| 1|
| 105.57421462606571| 1|
| 375.7392000988502| 1|
| 86.84316266301785| 1|
| 175.84833807674354| 1|
| 89.13843747051655| 1|
| 51.10329233930394| 1|
| 143.81240235979868| 1|
| 731.3784436932382| 1|
| 75.2494765978132| 1|
| 207.43647477239938| 1|
| 142.59320910038926| 1|
| 53.627217893834704| 1|
| 159.4845687372489| 1|
| 69.27750494252564| 1|
| 18.320456469292047| 1|
| 133.0386446726332| 1|
| 152.28206446530797| 1|
| 104.07221467073113| 1|
| 48.639066286637174| 1|
| 33.11489417677804| 1|
| 158.94947116123458| 1|
| 338.796788967333| 1|
| 299.2892697876012| 1|
| 62.953444496105355| 1|
| 105.52361769736166| 1|
| 162.02271557560178| 1|
| 61.0520135535276| 1|
| 122.90193000314001| 1|
| 104.58801807642655| 1|
| 65.51302104395508| 1|
| 184.3790481609256| 1|
| 54.91550465161602| 1|
| 57.835489532555066| 1|
| 210.21942692839053| 1|
| 358.59877044352334| 1|
| 37.43490474827333| 1|
| 117.50516334362518| 1|
| 70.71343062953899| 1|
| 132.24604758254608| 1|
| 118.84562266733371| 1|
| 194.3616097155128| 1|
| 58.33573529688074| 1|
| 604.6377840289732| 1|
| 208.9859169462516| 1|
| 128.70367707542636| 1|
| 1056.2635238946168| 1|
| 138.8259567553315| 1|
| 81.52004072422156| 1|
| 110.19964611638822| 1|
| 68.47356529471752| 1|
| 132.91787152104058| 1|
| 275.93146198016456| 1|
| 136.27314317172969| 1|
| 195.316849708674| 1|
| 38.15801921804493| 1|
| 64.14915718393657| 1|
| 681.0142821962519| 1|
| 66.12818710334099| 1|
| 531.1960999473007| 1|
| 61.73669850349335| 1|
| 127.9396927730949| 1|
| 120.02643718809227| 1|
| 134.35881563664088| 1|
| 89.52411045264235| 1|
| 448.1938446536375| 1|
| 178.7583307684732| 1|
| 238.9823421186261| 1|
| 27.529069681486007| 1|
| 439.6776590630765| 1|
| 170.0257925333507| 1|
| 168.33069480725962| 1|
| 364.6490050350761| 1|
| 108.25756608960023| 1|
| 1092.7097309020658| 1|
| 164.19895657130922| 1|
| 431.12743599773626| 1|
| 245.06179783238517| 1|
| 317.25445507202863| 1|
| 164.21291703691497| 1|
| 123.0719222324176| 1|
| 140.55288701361968| 1|
| 152.3194100323595| 1|
| 54.235382478842716| 1|
| 99.56989485985778| 1|
| 145.74703179968142| 1|
+-----------------------+-----+
only showing top 100 rows
+------------------+-----+
| Monthly_Balance|count|
+------------------+-----+
|328.77349805774577| 1|
| 84.84061127772313| 1|
|276.35773236989456| 1|
| 464.9102025274546| 1|
| 799.0311420559128| 1|
| 193.7429654077217| 1|
| 703.1016234359572| 1|
|306.49655066306343| 1|
| 265.1289243629135| 1|
| 340.2201294861163| 1|
| 290.8325898723405| 1|
| 397.7719791024859| 1|
| 364.1999201609816| 1|
|349.08074798613035| 1|
| 433.6047729627723| 1|
|289.44322754389117| 1|
| 546.4395301303758| 1|
| 720.7609370963188| 1|
|370.37061221613146| 1|
| 216.1965118641349| 1|
| 672.0205622636665| 1|
| 257.6665528790783| 1|
|508.45402422738886| 1|
|457.13363572321543| 1|
|373.88112840800574| 1|
|172.37280649041958| 1|
|397.33914899173294| 1|
|300.02161044813124| 1|
| 704.0836956883193| 1|
|432.64009337679715| 1|
| 370.5154653466386| 1|
|279.26102977395874| 1|
| 309.7746085829013| 1|
| 406.0848871626909| 1|
| 690.7982433981722| 1|
|348.54982237062416| 1|
| 443.2654272869336| 1|
| 435.6228854566873| 1|
|252.53173128701812| 1|
| 912.0593291175868| 1|
| 242.4833607258564| 1|
|325.78227082708264| 1|
| 267.6255348018871| 1|
|330.41582568556686| 1|
|215.23453299507327| 1|
| 666.7241794238229| 1|
|429.60102187774606| 1|
| 313.4079414131567| 1|
| 255.0757089253637| 1|
| 802.1835921808723| 1|
| 485.0252941011462| 1|
| 388.0122830106935| 1|
| 604.0596866449949| 1|
| 540.7038198941706| 1|
|294.53409329225366| 1|
| 512.9579383182709| 1|
| 320.2130311317271| 1|
| 460.1009115893087| 1|
|166.72263589712037| 1|
|189.02679858570497| 1|
| 714.4125463377462| 1|
| 293.9700516260998| 1|
| 341.6317650115592| 1|
| 461.2024949525658| 1|
| 296.6936300498122| 1|
| 992.5469750072273| 1|
|384.60593839715966| 1|
| 654.600004223394| 1|
| 658.2822836263151| 1|
| 275.6103465774071| 1|
| 420.7130711705748| 1|
| 310.3351448517185| 1|
| 727.5323964695247| 1|
| 703.1293738021684| 1|
| 249.8070181253751| 1|
|166.45264182914457| 1|
|250.03547315135827| 1|
|306.74396969300966| 1|
| 345.2808509731348| 1|
| 647.9571317515059| 1|
| 360.3433327137839| 1|
| 323.1772437366338| 1|
| 760.3908430269906| 1|
| 306.1473105594705| 1|
|395.73286939620573| 1|
| 490.1721773566514| 1|
| 260.1255919429688| 1|
|458.49073258120234| 1|
| 622.8589499816667| 1|
| 89.0250774233926| 1|
| 272.9109087386877| 1|
| 278.4755891506759| 1|
|276.52840880226967| 1|
|353.60745621133657| 1|
| 368.4489817820763| 1|
| 258.799696826076| 1|
| 263.3833958037833| 1|
| 386.0240533569049| 1|
| 322.252492803916| 1|
|303.60252786232104| 1|
+------------------+-----+
only showing top 100 rows
+---------+-----+
|Auto Loan|count|
+---------+-----+
| 1| 4551|
| 0|10354|
+---------+-----+
+-------------------+-----+
|Credit-Builder Loan|count|
+-------------------+-----+
| 1| 4705|
| 0|10200|
+-------------------+-----+
+-----------------------+-----+
|Debt Consolidation Loan|count|
+-----------------------+-----+
| 1| 4586|
| 0|10319|
+-----------------------+-----+
+----------------+-----+
|Home Equity Loan|count|
+----------------+-----+
| 1| 4628|
| 0|10277|
+----------------+-----+
+-------------+-----+
|Mortgage Loan|count|
+-------------+-----+
| 1| 4658|
| 0|10247|
+-------------+-----+
+-----------+-----+
|Payday Loan|count|
+-----------+-----+
| 1| 4820|
| 0|10085|
+-----------+-----+
+-------------+-----+
|Personal Loan|count|
+-------------+-----+
| 1| 4623|
| 0|10282|
+-------------+-----+
+------------+-----+
|Student Loan|count|
+------------+-----+
| 1| 4665|
| 0|10240|
+------------+-----+
+----------------------------+-----+
|Credit_History_Age_in_Months|count|
+----------------------------+-----+
| 162.0| 1|
| 330.0| 1|
| 144.0| 1|
| 324.0| 1|
| 246.0| 1|
| 126.0| 1|
| 90.0| 1|
| 168.0| 2|
| 348.0| 2|
| 372.0| 2|
| 1.0| 2|
| 198.0| 2|
| 6.0| 2|
| 240.0| 2|
| 66.0| 2|
| 306.0| 2|
| 72.0| 2|
| 108.0| 2|
| 44.0| 2|
| 288.0| 2|
| 282.0| 2|
| 258.0| 2|
| 18.0| 2|
| 216.0| 2|
| 276.0| 3|
| 354.0| 3|
| 12.0| 3|
| 390.0| 3|
| 150.0| 3|
| 156.0| 3|
| 180.0| 3|
| 312.0| 3|
| 396.0| 3|
| 78.0| 3|
| 384.0| 3|
| 270.0| 4|
| 252.0| 4|
| 132.0| 4|
| 102.0| 4|
| 342.0| 4|
| 24.0| 4|
| 378.0| 4|
| 192.0| 4|
| 366.0| 4|
| 45.0| 5|
| 234.0| 5|
| 204.0| 5|
| 336.0| 6|
| 28.0| 6|
| 5.0| 6|
| 210.0| 6|
| 51.0| 7|
| 222.0| 7|
| 31.0| 7|
| 7.0| 7|
| 228.0| 7|
| 186.0| 7|
| 96.0| 7|
| 52.0| 9|
| 43.0| 9|
| 41.0| 9|
| 57.0| 9|
| 58.0| 10|
| 3.0| 10|
| 13.0| 11|
| 53.0| 11|
| 37.0| 11|
| 27.0| 11|
| 17.0| 12|
| 14.0| 12|
| 34.0| 12|
| 50.0| 12|
| 23.0| 12|
| 32.0| 13|
| 33.0| 13|
| 11.0| 13|
| 39.0| 13|
| 8.0| 14|
| 38.0| 14|
| 21.0| 14|
| 9.0| 15|
| 20.0| 15|
| 40.0| 16|
| 2.0| 16|
| 29.0| 17|
| 55.0| 17|
| 47.0| 17|
| 26.0| 18|
| 301.0| 18|
| 22.0| 18|
| 61.0| 18|
| 56.0| 19|
| 16.0| 19|
| 15.0| 20|
| 46.0| 21|
| 10.0| 21|
| 350.0| 22|
| 35.0| 22|
| 82.0| 22|
| 4.0| 23|
+----------------------------+-----+
only showing top 100 rows
+--------------------------+-----+
|Spending Frequency_indexed|count|
+--------------------------+-----+
| 1.0| 6640|
| 0.0| 8265|
+--------------------------+-----+
+--------------------------+-----+
|Spending Frequency_encoded|count|
+--------------------------+-----+
| (1,[],[])| 6640|
| (1,[0],[1.0])| 8265|
+--------------------------+-----+
+-------------------------------+-----+
|Average Size of Payment_indexed|count|
+-------------------------------+-----+
| 2.0| 3233|
| 1.0| 4847|
| 0.0| 6825|
+-------------------------------+-----+
+-------------------------------+-----+
|Average Size of Payment_encoded|count|
+-------------------------------+-----+
| (2,[],[])| 3233|
| (2,[1],[1.0])| 4847|
| (2,[0],[1.0])| 6825|
+-------------------------------+-----+
+------------------+-----+
|Occupation_indexed|count|
+------------------+-----+
| 15.0| 43|
| 14.0| 892|
| 11.0| 919|
| 13.0| 932|
| 10.0| 959|
| 9.0| 970|
| 12.0| 974|
| 8.0| 1001|
| 5.0| 1005|
| 7.0| 1006|
| 6.0| 1017|
| 3.0| 1023|
| 4.0| 1033|
| 0.0| 1038|
| 2.0| 1038|
| 1.0| 1055|
+------------------+-----+
+------------------+-----+
|Occupation_encoded|count|
+------------------+-----+
| (15,[],[])| 43|
| (15,[14],[1.0])| 892|
| (15,[11],[1.0])| 919|
| (15,[13],[1.0])| 932|
| (15,[10],[1.0])| 959|
| (15,[9],[1.0])| 970|
| (15,[12],[1.0])| 974|
| (15,[8],[1.0])| 1001|
| (15,[5],[1.0])| 1005|
| (15,[7],[1.0])| 1006|
| (15,[6],[1.0])| 1017|
| (15,[3],[1.0])| 1023|
| (15,[4],[1.0])| 1033|
| (15,[0],[1.0])| 1038|
| (15,[2],[1.0])| 1038|
| (15,[1],[1.0])| 1055|
+------------------+-----+
+--------------------+-----+
|Credit_Score_indexed|count|
+--------------------+-----+
| 2.0| 2650|
| 1.0| 3874|
| 0.0| 8381|
+--------------------+-----+
+--------------------+-----+
|Credit_Score_encoded|count|
+--------------------+-----+
| (2,[],[])| 2650|
| (2,[1],[1.0])| 3874|
| (2,[0],[1.0])| 8381|
+--------------------+-----+
As shown in the printed tables, it is noted that there are still outliers in our data and it needs to be removed. We will have to go through with them individually accordingly.
# Removing Outliers for
print('Before dropping outliers: ', credit_score.count())
print()
credit_score = credit_score.filter(~(col('Age') > 56))
credit_score = credit_score.filter(~(col('Age') < 14))
print('After dropping Age outliers: ', credit_score.count())
credit_score = credit_score.filter(~(col('Num_Bank_Accounts') > 10))
credit_score = credit_score.filter(~(col('Num_Bank_Accounts') < 0))
print('After dropping "Num_Bank_Accounts" outliers: ', credit_score.count())
credit_score = credit_score.filter(~(col('Num_Credit_Card') > 11))
print('After dropping "Num_Credit_Card" outliers: ', credit_score.count())
credit_score = credit_score.filter(~(col('Interest_Rate') > 34))
print('After dropping "Interest_Rate" outliers: ', credit_score.count())
credit_score = credit_score.filter(~(col('Num_of_Loan') < 0))
print('After dropping "Num_of_Loan" outliers: ', credit_score.count())
credit_score = credit_score.filter(~(col('Delay_from_due_date') < 0))
print('After dropping "Delay_from_due_date" outliers: ', credit_score.count())
credit_score = credit_score.filter(~(col('Num_of_Delayed_Payment') < 0))
print('After dropping "Num_of_Delayed_Payment" outliers: ', credit_score.count())
credit_score = credit_score.filter(~(col('Num_of_Delayed_Payment') < 0))
print('After dropping "Num_of_Delayed_Payment" outliers: ', credit_score.count())
credit_score = credit_score.checkpoint()Before dropping outliers: 14905
After dropping Age outliers: 14895
After dropping "Num_Bank_Accounts" outliers: 14879
After dropping "Num_Credit_Card" outliers: 14857
After dropping "Interest_Rate" outliers: 14829
After dropping "Num_of_Loan" outliers: 14815
After dropping "Delay_from_due_date" outliers: 14806
After dropping "Num_of_Delayed_Payment" outliers: 14787
After dropping "Num_of_Delayed_Payment" outliers: 14787from pyspark.mllib.feature import Normalizer
normalizer = Normalizer(float('inf'))
normalized_credit_score = credit_score
normalizing_columns = credit_score_columns + credit_score_columns_indexed
for column in normalizing_columns:
column_max = normalized_credit_score.agg(F.max(column))
column_min = normalized_credit_score.agg(F.min(column))
min_max_for_print = column_min.join(column_max)
min_max_for_print.show()
max_column = ('max ' + column)
min_column = ('min ' + column)
normalized_column = ('normalized ' + column)
normalized_credit_score = normalized_credit_score.select(
F.max(column).alias(max_column),
F.min(column).alias(min_column))\
.crossJoin(normalized_credit_score)\
.withColumn(normalized_column,
(col(column) - col(min_column))/(col(max_column) - col(min_column))
)
normalized_credit_score = normalized_credit_score.checkpoint()
normalized_credit_score.show(4,truncate=False,vertical=True)+--------+--------+
|min(Age)|max(Age)|
+--------+--------+
| 14| 56|
+--------+--------+
+------------------+------------------+
|min(Annual_Income)|max(Annual_Income)|
+------------------+------------------+
| 7005| 18265510|
+------------------+------------------+
+----------------------+----------------------+
|min(Num_Bank_Accounts)|max(Num_Bank_Accounts)|
+----------------------+----------------------+
| 0| 10|
+----------------------+----------------------+
+--------------------+--------------------+
|min(Num_Credit_Card)|max(Num_Credit_Card)|
+--------------------+--------------------+
| 1| 11|
+--------------------+--------------------+
+------------------+------------------+
|min(Interest_Rate)|max(Interest_Rate)|
+------------------+------------------+
| 1| 34|
+------------------+------------------+
+----------------+----------------+
|min(Num_of_Loan)|max(Num_of_Loan)|
+----------------+----------------+
| 0| 1030|
+----------------+----------------+
+------------------------+------------------------+
|min(Delay_from_due_date)|max(Delay_from_due_date)|
+------------------------+------------------------+
| 0| 62|
+------------------------+------------------------+
+---------------------------+---------------------------+
|min(Num_of_Delayed_Payment)|max(Num_of_Delayed_Payment)|
+---------------------------+---------------------------+
| 0| 28|
+---------------------------+---------------------------+
+-------------------------+-------------------------+
|min(Changed_Credit_Limit)|max(Changed_Credit_Limit)|
+-------------------------+-------------------------+
| 0| 30|
+-------------------------+-------------------------+
+-------------------------+-------------------------+
|min(Num_Credit_Inquiries)|max(Num_Credit_Inquiries)|
+-------------------------+-------------------------+
| 0.0| 17.0|
+-------------------------+-------------------------+
+---------------------+---------------------+
|min(Outstanding_Debt)|max(Outstanding_Debt)|
+---------------------+---------------------+
| 0.23| 4997.1|
+---------------------+---------------------+
+-----------------------------+-----------------------------+
|min(Credit_Utilization_Ratio)|max(Credit_Utilization_Ratio)|
+-----------------------------+-----------------------------+
| 21.02766450595043| 49.56451934738699|
+-----------------------------+-----------------------------+
+--------------------------+--------------------------+
|min(Payment_of_Min_Amount)|max(Payment_of_Min_Amount)|
+--------------------------+--------------------------+
| 0| 1|
+--------------------------+--------------------------+
+------------------------+------------------------+
|min(Total_EMI_per_month)|max(Total_EMI_per_month)|
+------------------------+------------------------+
| 0.0| 82178.0|
+------------------------+------------------------+
+----------------------------+----------------------------+
|min(Amount_invested_monthly)|max(Amount_invested_monthly)|
+----------------------------+----------------------------+
| 0.0| 10000.0|
+----------------------------+----------------------------+
+--------------------+--------------------+
|min(Monthly_Balance)|max(Monthly_Balance)|
+--------------------+--------------------+
| 0.08862786534905354| 1602.0405189622518|
+--------------------+--------------------+
+--------------+--------------+
|min(Auto Loan)|max(Auto Loan)|
+--------------+--------------+
| 0| 1|
+--------------+--------------+
+------------------------+------------------------+
|min(Credit-Builder Loan)|max(Credit-Builder Loan)|
+------------------------+------------------------+
| 0| 1|
+------------------------+------------------------+
+----------------------------+----------------------------+
|min(Debt Consolidation Loan)|max(Debt Consolidation Loan)|
+----------------------------+----------------------------+
| 0| 1|
+----------------------------+----------------------------+
+---------------------+---------------------+
|min(Home Equity Loan)|max(Home Equity Loan)|
+---------------------+---------------------+
| 0| 1|
+---------------------+---------------------+
+------------------+------------------+
|min(Mortgage Loan)|max(Mortgage Loan)|
+------------------+------------------+
| 0| 1|
+------------------+------------------+
+----------------+----------------+
|min(Payday Loan)|max(Payday Loan)|
+----------------+----------------+
| 0| 1|
+----------------+----------------+
+------------------+------------------+
|min(Personal Loan)|max(Personal Loan)|
+------------------+------------------+
| 0| 1|
+------------------+------------------+
+-----------------+-----------------+
|min(Student Loan)|max(Student Loan)|
+-----------------+-----------------+
| 0| 1|
+-----------------+-----------------+
+---------------------------------+---------------------------------+
|min(Credit_History_Age_in_Months)|max(Credit_History_Age_in_Months)|
+---------------------------------+---------------------------------+
| 1.0| 397.0|
+---------------------------------+---------------------------------+
+-------------------------------+-------------------------------+
|min(Spending Frequency_indexed)|max(Spending Frequency_indexed)|
+-------------------------------+-------------------------------+
| 0.0| 1.0|
+-------------------------------+-------------------------------+
+------------------------------------+------------------------------------+
|min(Average Size of Payment_indexed)|max(Average Size of Payment_indexed)|
+------------------------------------+------------------------------------+
| 0.0| 2.0|
+------------------------------------+------------------------------------+
+-----------------------+-----------------------+
|min(Occupation_indexed)|max(Occupation_indexed)|
+-----------------------+-----------------------+
| 0.0| 15.0|
+-----------------------+-----------------------+
-RECORD 0-----------------------------------------------------------
max Occupation_indexed | 15.0
min Occupation_indexed | 0.0
max Average Size of Payment_indexed | 2.0
min Average Size of Payment_indexed | 0.0
max Spending Frequency_indexed | 1.0
min Spending Frequency_indexed | 0.0
max Credit_History_Age_in_Months | 397.0
min Credit_History_Age_in_Months | 1.0
max Student Loan | 1
min Student Loan | 0
max Personal Loan | 1
min Personal Loan | 0
max Payday Loan | 1
min Payday Loan | 0
max Mortgage Loan | 1
min Mortgage Loan | 0
max Home Equity Loan | 1
min Home Equity Loan | 0
max Debt Consolidation Loan | 1
min Debt Consolidation Loan | 0
max Credit-Builder Loan | 1
min Credit-Builder Loan | 0
max Auto Loan | 1
min Auto Loan | 0
max Monthly_Balance | 1602.0405189622518
min Monthly_Balance | 0.08862786534905354
max Amount_invested_monthly | 10000.0
min Amount_invested_monthly | 0.0
max Total_EMI_per_month | 82178.0
min Total_EMI_per_month | 0.0
max Payment_of_Min_Amount | 1
min Payment_of_Min_Amount | 0
max Credit_Utilization_Ratio | 49.56451934738699
min Credit_Utilization_Ratio | 21.02766450595043
max Outstanding_Debt | 4997.1
min Outstanding_Debt | 0.23
max Num_Credit_Inquiries | 17.0
min Num_Credit_Inquiries | 0.0
max Changed_Credit_Limit | 30
min Changed_Credit_Limit | 0
max Num_of_Delayed_Payment | 28
min Num_of_Delayed_Payment | 0
max Delay_from_due_date | 62
min Delay_from_due_date | 0
max Num_of_Loan | 1030
min Num_of_Loan | 0
max Interest_Rate | 34
min Interest_Rate | 1
max Num_Credit_Card | 11
min Num_Credit_Card | 1
max Num_Bank_Accounts | 10
min Num_Bank_Accounts | 0
max Annual_Income | 18265510
min Annual_Income | 7005
max Age | 56
min Age | 14
Age | 23
Annual_Income | 20940
Num_Bank_Accounts | 9
Num_Credit_Card | 10
Interest_Rate | 15
Num_of_Loan | 5
Delay_from_due_date | 54
Num_of_Delayed_Payment | 20
Changed_Credit_Limit | 1
Num_Credit_Inquiries | 7.0
Outstanding_Debt | 2554.48
Credit_Utilization_Ratio | 29.577221854075194
Payment_of_Min_Amount | 1
Total_EMI_per_month | 47.16396888167924
Amount_invested_monthly | 49.33189198577
Monthly_Balance | 346.60430579921746
Auto Loan | 1
Credit-Builder Loan | 0
Debt Consolidation Loan | 0
Home Equity Loan | 0
Mortgage Loan | 1
Payday Loan | 0
Personal Loan | 0
Student Loan | 0
Credit_History_Age_in_Months | 99.0
Spending Frequency_indexed | 0.0
Spending Frequency_encoded | (1,[0],[1.0])
Average Size of Payment_indexed | 0.0
Average Size of Payment_encoded | (2,[0],[1.0])
Occupation_indexed | 1.0
Occupation_encoded | (15,[1],[1.0])
Credit_Score_indexed | 1.0
Credit_Score_encoded | (2,[1],[1.0])
normalized Age | 0.21428571428571427
normalized Annual_Income | 7.632059689443358E-4
normalized Num_Bank_Accounts | 0.9
normalized Num_Credit_Card | 0.9
normalized Interest_Rate | 0.42424242424242425
normalized Num_of_Loan | 0.0048543689320388345
normalized Delay_from_due_date | 0.8709677419354839
normalized Num_of_Delayed_Payment | 0.7142857142857143
normalized Changed_Credit_Limit | 0.03333333333333333
normalized Num_Credit_Inquiries | 0.4117647058823529
normalized Outstanding_Debt | 0.5111699924152519
normalized Credit_Utilization_Ratio | 0.29959704373974994
normalized Payment_of_Min_Amount | 1.0
normalized Total_EMI_per_month | 5.739245160709586E-4
normalized Amount_invested_monthly | 0.004933189198577
normalized Monthly_Balance | 0.2163084171626397
normalized Auto Loan | 1.0
normalized Credit-Builder Loan | 0.0
normalized Debt Consolidation Loan | 0.0
normalized Home Equity Loan | 0.0
normalized Mortgage Loan | 1.0
normalized Payday Loan | 0.0
normalized Personal Loan | 0.0
normalized Student Loan | 0.0
normalized Credit_History_Age_in_Months | 0.2474747474747475
normalized Spending Frequency_indexed | 0.0
normalized Average Size of Payment_indexed | 0.0
normalized Occupation_indexed | 0.06666666666666667
-RECORD 1-----------------------------------------------------------
max Occupation_indexed | 15.0
min Occupation_indexed | 0.0
max Average Size of Payment_indexed | 2.0
min Average Size of Payment_indexed | 0.0
max Spending Frequency_indexed | 1.0
min Spending Frequency_indexed | 0.0
max Credit_History_Age_in_Months | 397.0
min Credit_History_Age_in_Months | 1.0
max Student Loan | 1
min Student Loan | 0
max Personal Loan | 1
min Personal Loan | 0
max Payday Loan | 1
min Payday Loan | 0
max Mortgage Loan | 1
min Mortgage Loan | 0
max Home Equity Loan | 1
min Home Equity Loan | 0
max Debt Consolidation Loan | 1
min Debt Consolidation Loan | 0
max Credit-Builder Loan | 1
min Credit-Builder Loan | 0
max Auto Loan | 1
min Auto Loan | 0
max Monthly_Balance | 1602.0405189622518
min Monthly_Balance | 0.08862786534905354
max Amount_invested_monthly | 10000.0
min Amount_invested_monthly | 0.0
max Total_EMI_per_month | 82178.0
min Total_EMI_per_month | 0.0
max Payment_of_Min_Amount | 1
min Payment_of_Min_Amount | 0
max Credit_Utilization_Ratio | 49.56451934738699
min Credit_Utilization_Ratio | 21.02766450595043
max Outstanding_Debt | 4997.1
min Outstanding_Debt | 0.23
max Num_Credit_Inquiries | 17.0
min Num_Credit_Inquiries | 0.0
max Changed_Credit_Limit | 30
min Changed_Credit_Limit | 0
max Num_of_Delayed_Payment | 28
min Num_of_Delayed_Payment | 0
max Delay_from_due_date | 62
min Delay_from_due_date | 0
max Num_of_Loan | 1030
min Num_of_Loan | 0
max Interest_Rate | 34
min Interest_Rate | 1
max Num_Credit_Card | 11
min Num_Credit_Card | 1
max Num_Bank_Accounts | 10
min Num_Bank_Accounts | 0
max Annual_Income | 18265510
min Annual_Income | 7005
max Age | 56
min Age | 14
Age | 18
Annual_Income | 17896
Num_Bank_Accounts | 4
Num_Credit_Card | 5
Interest_Rate | 16
Num_of_Loan | 1
Delay_from_due_date | 11
Num_of_Delayed_Payment | 15
Changed_Credit_Limit | 8
Num_Credit_Inquiries | 1.0
Outstanding_Debt | 1263.91
Credit_Utilization_Ratio | 29.087227801805557
Payment_of_Min_Amount | 1
Total_EMI_per_month | 10.578359076265064
Amount_invested_monthly | 200.46553640648318
Monthly_Balance | 238.69110451725174
Auto Loan | 0
Credit-Builder Loan | 0
Debt Consolidation Loan | 0
Home Equity Loan | 0
Mortgage Loan | 1
Payday Loan | 0
Personal Loan | 0
Student Loan | 0
Credit_History_Age_in_Months | 220.0
Spending Frequency_indexed | 0.0
Spending Frequency_encoded | (1,[0],[1.0])
Average Size of Payment_indexed | 0.0
Average Size of Payment_encoded | (2,[0],[1.0])
Occupation_indexed | 12.0
Occupation_encoded | (15,[12],[1.0])
Credit_Score_indexed | 2.0
Credit_Score_encoded | (2,[],[])
normalized Age | 0.09523809523809523
normalized Annual_Income | 5.964891430048627E-4
normalized Num_Bank_Accounts | 0.4
normalized Num_Credit_Card | 0.4
normalized Interest_Rate | 0.45454545454545453
normalized Num_of_Loan | 9.70873786407767E-4
normalized Delay_from_due_date | 0.1774193548387097
normalized Num_of_Delayed_Payment | 0.5357142857142857
normalized Changed_Credit_Limit | 0.26666666666666666
normalized Num_Credit_Inquiries | 0.058823529411764705
normalized Outstanding_Debt | 0.2528943118392113
normalized Credit_Utilization_Ratio | 0.28242647413801
normalized Payment_of_Min_Amount | 1.0
normalized Total_EMI_per_month | 1.2872495164478406E-4
normalized Amount_invested_monthly | 0.020046553640648317
normalized Monthly_Balance | 0.1489448453339786
normalized Auto Loan | 0.0
normalized Credit-Builder Loan | 0.0
normalized Debt Consolidation Loan | 0.0
normalized Home Equity Loan | 0.0
normalized Mortgage Loan | 1.0
normalized Payday Loan | 0.0
normalized Personal Loan | 0.0
normalized Student Loan | 0.0
normalized Credit_History_Age_in_Months | 0.553030303030303
normalized Spending Frequency_indexed | 0.0
normalized Average Size of Payment_indexed | 0.0
normalized Occupation_indexed | 0.8
-RECORD 2-----------------------------------------------------------
max Occupation_indexed | 15.0
min Occupation_indexed | 0.0
max Average Size of Payment_indexed | 2.0
min Average Size of Payment_indexed | 0.0
max Spending Frequency_indexed | 1.0
min Spending Frequency_indexed | 0.0
max Credit_History_Age_in_Months | 397.0
min Credit_History_Age_in_Months | 1.0
max Student Loan | 1
min Student Loan | 0
max Personal Loan | 1
min Personal Loan | 0
max Payday Loan | 1
min Payday Loan | 0
max Mortgage Loan | 1
min Mortgage Loan | 0
max Home Equity Loan | 1
min Home Equity Loan | 0
max Debt Consolidation Loan | 1
min Debt Consolidation Loan | 0
max Credit-Builder Loan | 1
min Credit-Builder Loan | 0
max Auto Loan | 1
min Auto Loan | 0
max Monthly_Balance | 1602.0405189622518
min Monthly_Balance | 0.08862786534905354
max Amount_invested_monthly | 10000.0
min Amount_invested_monthly | 0.0
max Total_EMI_per_month | 82178.0
min Total_EMI_per_month | 0.0
max Payment_of_Min_Amount | 1
min Payment_of_Min_Amount | 0
max Credit_Utilization_Ratio | 49.56451934738699
min Credit_Utilization_Ratio | 21.02766450595043
max Outstanding_Debt | 4997.1
min Outstanding_Debt | 0.23
max Num_Credit_Inquiries | 17.0
min Num_Credit_Inquiries | 0.0
max Changed_Credit_Limit | 30
min Changed_Credit_Limit | 0
max Num_of_Delayed_Payment | 28
min Num_of_Delayed_Payment | 0
max Delay_from_due_date | 62
min Delay_from_due_date | 0
max Num_of_Loan | 1030
min Num_of_Loan | 0
max Interest_Rate | 34
min Interest_Rate | 1
max Num_Credit_Card | 11
min Num_Credit_Card | 1
max Num_Bank_Accounts | 10
min Num_Bank_Accounts | 0
max Annual_Income | 18265510
min Annual_Income | 7005
max Age | 56
min Age | 14
Age | 25
Annual_Income | 68267
Num_Bank_Accounts | 7
Num_Credit_Card | 7
Interest_Rate | 32
Num_of_Loan | 2
Delay_from_due_date | 17
Num_of_Delayed_Payment | 15
Changed_Credit_Limit | 16
Num_Credit_Inquiries | 7.0
Outstanding_Debt | 2357.03
Credit_Utilization_Ratio | 39.879088332887136
Payment_of_Min_Amount | 1
Total_EMI_per_month | 316.7432761786178
Amount_invested_monthly | 243.8134660545594
Monthly_Balance | 504.1605423847503
Auto Loan | 1
Credit-Builder Loan | 0
Debt Consolidation Loan | 0
Home Equity Loan | 0
Mortgage Loan | 0
Payday Loan | 0
Personal Loan | 0
Student Loan | 0
Credit_History_Age_in_Months | 128.0
Spending Frequency_indexed | 1.0
Spending Frequency_encoded | (1,[],[])
Average Size of Payment_indexed | 0.0
Average Size of Payment_encoded | (2,[0],[1.0])
Occupation_indexed | 4.0
Occupation_encoded | (15,[4],[1.0])
Credit_Score_indexed | 0.0
Credit_Score_encoded | (2,[0],[1.0])
normalized Age | 0.2619047619047619
normalized Annual_Income | 0.0033552582755269392
normalized Num_Bank_Accounts | 0.7
normalized Num_Credit_Card | 0.6
normalized Interest_Rate | 0.9393939393939394
normalized Num_of_Loan | 0.001941747572815534
normalized Delay_from_due_date | 0.27419354838709675
normalized Num_of_Delayed_Payment | 0.5357142857142857
normalized Changed_Credit_Limit | 0.5333333333333333
normalized Num_Credit_Inquiries | 0.4117647058823529
normalized Outstanding_Debt | 0.4716552561903751
normalized Credit_Utilization_Ratio | 0.6605992122006293
normalized Payment_of_Min_Amount | 1.0
normalized Total_EMI_per_month | 0.003854356107213826
normalized Amount_invested_monthly | 0.02438134660545594
normalized Monthly_Balance | 0.31466108147245836
normalized Auto Loan | 1.0
normalized Credit-Builder Loan | 0.0
normalized Debt Consolidation Loan | 0.0
normalized Home Equity Loan | 0.0
normalized Mortgage Loan | 0.0
normalized Payday Loan | 0.0
normalized Personal Loan | 0.0
normalized Student Loan | 0.0
normalized Credit_History_Age_in_Months | 0.3207070707070707
normalized Spending Frequency_indexed | 1.0
normalized Average Size of Payment_indexed | 0.0
normalized Occupation_indexed | 0.26666666666666666
-RECORD 3-----------------------------------------------------------
max Occupation_indexed | 15.0
min Occupation_indexed | 0.0
max Average Size of Payment_indexed | 2.0
min Average Size of Payment_indexed | 0.0
max Spending Frequency_indexed | 1.0
min Spending Frequency_indexed | 0.0
max Credit_History_Age_in_Months | 397.0
min Credit_History_Age_in_Months | 1.0
max Student Loan | 1
min Student Loan | 0
max Personal Loan | 1
min Personal Loan | 0
max Payday Loan | 1
min Payday Loan | 0
max Mortgage Loan | 1
min Mortgage Loan | 0
max Home Equity Loan | 1
min Home Equity Loan | 0
max Debt Consolidation Loan | 1
min Debt Consolidation Loan | 0
max Credit-Builder Loan | 1
min Credit-Builder Loan | 0
max Auto Loan | 1
min Auto Loan | 0
max Monthly_Balance | 1602.0405189622518
min Monthly_Balance | 0.08862786534905354
max Amount_invested_monthly | 10000.0
min Amount_invested_monthly | 0.0
max Total_EMI_per_month | 82178.0
min Total_EMI_per_month | 0.0
max Payment_of_Min_Amount | 1
min Payment_of_Min_Amount | 0
max Credit_Utilization_Ratio | 49.56451934738699
min Credit_Utilization_Ratio | 21.02766450595043
max Outstanding_Debt | 4997.1
min Outstanding_Debt | 0.23
max Num_Credit_Inquiries | 17.0
min Num_Credit_Inquiries | 0.0
max Changed_Credit_Limit | 30
min Changed_Credit_Limit | 0
max Num_of_Delayed_Payment | 28
min Num_of_Delayed_Payment | 0
max Delay_from_due_date | 62
min Delay_from_due_date | 0
max Num_of_Loan | 1030
min Num_of_Loan | 0
max Interest_Rate | 34
min Interest_Rate | 1
max Num_Credit_Card | 11
min Num_Credit_Card | 1
max Num_Bank_Accounts | 10
min Num_Bank_Accounts | 0
max Annual_Income | 18265510
min Annual_Income | 7005
max Age | 56
min Age | 14
Age | 31
Annual_Income | 17680
Num_Bank_Accounts | 6
Num_Credit_Card | 6
Interest_Rate | 9
Num_of_Loan | 4
Delay_from_due_date | 9
Num_of_Delayed_Payment | 12
Changed_Credit_Limit | 11
Num_Credit_Inquiries | 12.0
Outstanding_Debt | 887.98
Credit_Utilization_Ratio | 37.56029322078355
Payment_of_Min_Amount | 1
Total_EMI_per_month | 31.68734043318193
Amount_invested_monthly | 90.88441778412479
Monthly_Balance | 292.36732511602656
Auto Loan | 1
Credit-Builder Loan | 0
Debt Consolidation Loan | 0
Home Equity Loan | 1
Mortgage Loan | 1
Payday Loan | 0
Personal Loan | 1
Student Loan | 0
Credit_History_Age_in_Months | 309.0
Spending Frequency_indexed | 0.0
Spending Frequency_encoded | (1,[0],[1.0])
Average Size of Payment_indexed | 0.0
Average Size of Payment_encoded | (2,[0],[1.0])
Occupation_indexed | 2.0
Occupation_encoded | (15,[2],[1.0])
Credit_Score_indexed | 0.0
Credit_Score_encoded | (2,[0],[1.0])
normalized Age | 0.40476190476190477
normalized Annual_Income | 5.846590397187503E-4
normalized Num_Bank_Accounts | 0.6
normalized Num_Credit_Card | 0.5
normalized Interest_Rate | 0.24242424242424243
normalized Num_of_Loan | 0.003883495145631068
normalized Delay_from_due_date | 0.14516129032258066
normalized Num_of_Delayed_Payment | 0.42857142857142855
normalized Changed_Credit_Limit | 0.36666666666666664
normalized Num_Credit_Inquiries | 0.7058823529411765
normalized Outstanding_Debt | 0.17766121592116663
normalized Credit_Utilization_Ratio | 0.5793430567837888
normalized Payment_of_Min_Amount | 1.0
normalized Total_EMI_per_month | 3.8559395985764963E-4
normalized Amount_invested_monthly | 0.00908844177841248
normalized Monthly_Balance | 0.1824516072393072
normalized Auto Loan | 1.0
normalized Credit-Builder Loan | 0.0
normalized Debt Consolidation Loan | 0.0
normalized Home Equity Loan | 1.0
normalized Mortgage Loan | 1.0
normalized Payday Loan | 0.0
normalized Personal Loan | 1.0
normalized Student Loan | 0.0
normalized Credit_History_Age_in_Months | 0.7777777777777778
normalized Spending Frequency_indexed | 0.0
normalized Average Size of Payment_indexed | 0.0
normalized Occupation_indexed | 0.13333333333333333
only showing top 4 rows
column_max = credit_score.agg(F.max(output_columns[0]))
column_min = credit_score.agg(F.min(output_columns[0]))
max_column = ('max ' + output_columns[0])
min_column = ('min ' + output_columns[0])
normalized_column = ('normalized ' + output_columns[0])
normalized_credit_score = normalized_credit_score.select(
F.max(output_columns[0]).alias(max_column),
F.min(output_columns[0]).alias(min_column))\
.crossJoin(normalized_credit_score)\
.withColumn(normalized_column,
(col(output_columns[0]) - col(min_column))/(col(max_column) - col(min_column))
)
normalized_credit_score = normalized_credit_score.checkpoint()
normalized_credit_score.show(4,truncate=False,vertical=True)-RECORD 0-----------------------------------------------------------
max Credit_Score_indexed | 2.0
min Credit_Score_indexed | 0.0
max Occupation_indexed | 15.0
min Occupation_indexed | 0.0
max Average Size of Payment_indexed | 2.0
min Average Size of Payment_indexed | 0.0
max Spending Frequency_indexed | 1.0
min Spending Frequency_indexed | 0.0
max Credit_History_Age_in_Months | 397.0
min Credit_History_Age_in_Months | 1.0
max Student Loan | 1
min Student Loan | 0
max Personal Loan | 1
min Personal Loan | 0
max Payday Loan | 1
min Payday Loan | 0
max Mortgage Loan | 1
min Mortgage Loan | 0
max Home Equity Loan | 1
min Home Equity Loan | 0
max Debt Consolidation Loan | 1
min Debt Consolidation Loan | 0
max Credit-Builder Loan | 1
min Credit-Builder Loan | 0
max Auto Loan | 1
min Auto Loan | 0
max Monthly_Balance | 1602.0405189622518
min Monthly_Balance | 0.08862786534905354
max Amount_invested_monthly | 10000.0
min Amount_invested_monthly | 0.0
max Total_EMI_per_month | 82178.0
min Total_EMI_per_month | 0.0
max Payment_of_Min_Amount | 1
min Payment_of_Min_Amount | 0
max Credit_Utilization_Ratio | 49.56451934738699
min Credit_Utilization_Ratio | 21.02766450595043
max Outstanding_Debt | 4997.1
min Outstanding_Debt | 0.23
max Num_Credit_Inquiries | 17.0
min Num_Credit_Inquiries | 0.0
max Changed_Credit_Limit | 30
min Changed_Credit_Limit | 0
max Num_of_Delayed_Payment | 28
min Num_of_Delayed_Payment | 0
max Delay_from_due_date | 62
min Delay_from_due_date | 0
max Num_of_Loan | 1030
min Num_of_Loan | 0
max Interest_Rate | 34
min Interest_Rate | 1
max Num_Credit_Card | 11
min Num_Credit_Card | 1
max Num_Bank_Accounts | 10
min Num_Bank_Accounts | 0
max Annual_Income | 18265510
min Annual_Income | 7005
max Age | 56
min Age | 14
Age | 23
Annual_Income | 20940
Num_Bank_Accounts | 9
Num_Credit_Card | 10
Interest_Rate | 15
Num_of_Loan | 5
Delay_from_due_date | 54
Num_of_Delayed_Payment | 20
Changed_Credit_Limit | 1
Num_Credit_Inquiries | 7.0
Outstanding_Debt | 2554.48
Credit_Utilization_Ratio | 29.577221854075194
Payment_of_Min_Amount | 1
Total_EMI_per_month | 47.16396888167924
Amount_invested_monthly | 49.33189198577
Monthly_Balance | 346.60430579921746
Auto Loan | 1
Credit-Builder Loan | 0
Debt Consolidation Loan | 0
Home Equity Loan | 0
Mortgage Loan | 1
Payday Loan | 0
Personal Loan | 0
Student Loan | 0
Credit_History_Age_in_Months | 99.0
Spending Frequency_indexed | 0.0
Spending Frequency_encoded | (1,[0],[1.0])
Average Size of Payment_indexed | 0.0
Average Size of Payment_encoded | (2,[0],[1.0])
Occupation_indexed | 1.0
Occupation_encoded | (15,[1],[1.0])
Credit_Score_indexed | 1.0
Credit_Score_encoded | (2,[1],[1.0])
normalized Age | 0.21428571428571427
normalized Annual_Income | 7.632059689443358E-4
normalized Num_Bank_Accounts | 0.9
normalized Num_Credit_Card | 0.9
normalized Interest_Rate | 0.42424242424242425
normalized Num_of_Loan | 0.0048543689320388345
normalized Delay_from_due_date | 0.8709677419354839
normalized Num_of_Delayed_Payment | 0.7142857142857143
normalized Changed_Credit_Limit | 0.03333333333333333
normalized Num_Credit_Inquiries | 0.4117647058823529
normalized Outstanding_Debt | 0.5111699924152519
normalized Credit_Utilization_Ratio | 0.29959704373974994
normalized Payment_of_Min_Amount | 1.0
normalized Total_EMI_per_month | 5.739245160709586E-4
normalized Amount_invested_monthly | 0.004933189198577
normalized Monthly_Balance | 0.2163084171626397
normalized Auto Loan | 1.0
normalized Credit-Builder Loan | 0.0
normalized Debt Consolidation Loan | 0.0
normalized Home Equity Loan | 0.0
normalized Mortgage Loan | 1.0
normalized Payday Loan | 0.0
normalized Personal Loan | 0.0
normalized Student Loan | 0.0
normalized Credit_History_Age_in_Months | 0.2474747474747475
normalized Spending Frequency_indexed | 0.0
normalized Average Size of Payment_indexed | 0.0
normalized Occupation_indexed | 0.06666666666666667
normalized Credit_Score_indexed | 0.5
-RECORD 1-----------------------------------------------------------
max Credit_Score_indexed | 2.0
min Credit_Score_indexed | 0.0
max Occupation_indexed | 15.0
min Occupation_indexed | 0.0
max Average Size of Payment_indexed | 2.0
min Average Size of Payment_indexed | 0.0
max Spending Frequency_indexed | 1.0
min Spending Frequency_indexed | 0.0
max Credit_History_Age_in_Months | 397.0
min Credit_History_Age_in_Months | 1.0
max Student Loan | 1
min Student Loan | 0
max Personal Loan | 1
min Personal Loan | 0
max Payday Loan | 1
min Payday Loan | 0
max Mortgage Loan | 1
min Mortgage Loan | 0
max Home Equity Loan | 1
min Home Equity Loan | 0
max Debt Consolidation Loan | 1
min Debt Consolidation Loan | 0
max Credit-Builder Loan | 1
min Credit-Builder Loan | 0
max Auto Loan | 1
min Auto Loan | 0
max Monthly_Balance | 1602.0405189622518
min Monthly_Balance | 0.08862786534905354
max Amount_invested_monthly | 10000.0
min Amount_invested_monthly | 0.0
max Total_EMI_per_month | 82178.0
min Total_EMI_per_month | 0.0
max Payment_of_Min_Amount | 1
min Payment_of_Min_Amount | 0
max Credit_Utilization_Ratio | 49.56451934738699
min Credit_Utilization_Ratio | 21.02766450595043
max Outstanding_Debt | 4997.1
min Outstanding_Debt | 0.23
max Num_Credit_Inquiries | 17.0
min Num_Credit_Inquiries | 0.0
max Changed_Credit_Limit | 30
min Changed_Credit_Limit | 0
max Num_of_Delayed_Payment | 28
min Num_of_Delayed_Payment | 0
max Delay_from_due_date | 62
min Delay_from_due_date | 0
max Num_of_Loan | 1030
min Num_of_Loan | 0
max Interest_Rate | 34
min Interest_Rate | 1
max Num_Credit_Card | 11
min Num_Credit_Card | 1
max Num_Bank_Accounts | 10
min Num_Bank_Accounts | 0
max Annual_Income | 18265510
min Annual_Income | 7005
max Age | 56
min Age | 14
Age | 18
Annual_Income | 17896
Num_Bank_Accounts | 4
Num_Credit_Card | 5
Interest_Rate | 16
Num_of_Loan | 1
Delay_from_due_date | 11
Num_of_Delayed_Payment | 15
Changed_Credit_Limit | 8
Num_Credit_Inquiries | 1.0
Outstanding_Debt | 1263.91
Credit_Utilization_Ratio | 29.087227801805557
Payment_of_Min_Amount | 1
Total_EMI_per_month | 10.578359076265064
Amount_invested_monthly | 200.46553640648318
Monthly_Balance | 238.69110451725174
Auto Loan | 0
Credit-Builder Loan | 0
Debt Consolidation Loan | 0
Home Equity Loan | 0
Mortgage Loan | 1
Payday Loan | 0
Personal Loan | 0
Student Loan | 0
Credit_History_Age_in_Months | 220.0
Spending Frequency_indexed | 0.0
Spending Frequency_encoded | (1,[0],[1.0])
Average Size of Payment_indexed | 0.0
Average Size of Payment_encoded | (2,[0],[1.0])
Occupation_indexed | 12.0
Occupation_encoded | (15,[12],[1.0])
Credit_Score_indexed | 2.0
Credit_Score_encoded | (2,[],[])
normalized Age | 0.09523809523809523
normalized Annual_Income | 5.964891430048627E-4
normalized Num_Bank_Accounts | 0.4
normalized Num_Credit_Card | 0.4
normalized Interest_Rate | 0.45454545454545453
normalized Num_of_Loan | 9.70873786407767E-4
normalized Delay_from_due_date | 0.1774193548387097
normalized Num_of_Delayed_Payment | 0.5357142857142857
normalized Changed_Credit_Limit | 0.26666666666666666
normalized Num_Credit_Inquiries | 0.058823529411764705
normalized Outstanding_Debt | 0.2528943118392113
normalized Credit_Utilization_Ratio | 0.28242647413801
normalized Payment_of_Min_Amount | 1.0
normalized Total_EMI_per_month | 1.2872495164478406E-4
normalized Amount_invested_monthly | 0.020046553640648317
normalized Monthly_Balance | 0.1489448453339786
normalized Auto Loan | 0.0
normalized Credit-Builder Loan | 0.0
normalized Debt Consolidation Loan | 0.0
normalized Home Equity Loan | 0.0
normalized Mortgage Loan | 1.0
normalized Payday Loan | 0.0
normalized Personal Loan | 0.0
normalized Student Loan | 0.0
normalized Credit_History_Age_in_Months | 0.553030303030303
normalized Spending Frequency_indexed | 0.0
normalized Average Size of Payment_indexed | 0.0
normalized Occupation_indexed | 0.8
normalized Credit_Score_indexed | 1.0
-RECORD 2-----------------------------------------------------------
max Credit_Score_indexed | 2.0
min Credit_Score_indexed | 0.0
max Occupation_indexed | 15.0
min Occupation_indexed | 0.0
max Average Size of Payment_indexed | 2.0
min Average Size of Payment_indexed | 0.0
max Spending Frequency_indexed | 1.0
min Spending Frequency_indexed | 0.0
max Credit_History_Age_in_Months | 397.0
min Credit_History_Age_in_Months | 1.0
max Student Loan | 1
min Student Loan | 0
max Personal Loan | 1
min Personal Loan | 0
max Payday Loan | 1
min Payday Loan | 0
max Mortgage Loan | 1
min Mortgage Loan | 0
max Home Equity Loan | 1
min Home Equity Loan | 0
max Debt Consolidation Loan | 1
min Debt Consolidation Loan | 0
max Credit-Builder Loan | 1
min Credit-Builder Loan | 0
max Auto Loan | 1
min Auto Loan | 0
max Monthly_Balance | 1602.0405189622518
min Monthly_Balance | 0.08862786534905354
max Amount_invested_monthly | 10000.0
min Amount_invested_monthly | 0.0
max Total_EMI_per_month | 82178.0
min Total_EMI_per_month | 0.0
max Payment_of_Min_Amount | 1
min Payment_of_Min_Amount | 0
max Credit_Utilization_Ratio | 49.56451934738699
min Credit_Utilization_Ratio | 21.02766450595043
max Outstanding_Debt | 4997.1
min Outstanding_Debt | 0.23
max Num_Credit_Inquiries | 17.0
min Num_Credit_Inquiries | 0.0
max Changed_Credit_Limit | 30
min Changed_Credit_Limit | 0
max Num_of_Delayed_Payment | 28
min Num_of_Delayed_Payment | 0
max Delay_from_due_date | 62
min Delay_from_due_date | 0
max Num_of_Loan | 1030
min Num_of_Loan | 0
max Interest_Rate | 34
min Interest_Rate | 1
max Num_Credit_Card | 11
min Num_Credit_Card | 1
max Num_Bank_Accounts | 10
min Num_Bank_Accounts | 0
max Annual_Income | 18265510
min Annual_Income | 7005
max Age | 56
min Age | 14
Age | 25
Annual_Income | 68267
Num_Bank_Accounts | 7
Num_Credit_Card | 7
Interest_Rate | 32
Num_of_Loan | 2
Delay_from_due_date | 17
Num_of_Delayed_Payment | 15
Changed_Credit_Limit | 16
Num_Credit_Inquiries | 7.0
Outstanding_Debt | 2357.03
Credit_Utilization_Ratio | 39.879088332887136
Payment_of_Min_Amount | 1
Total_EMI_per_month | 316.7432761786178
Amount_invested_monthly | 243.8134660545594
Monthly_Balance | 504.1605423847503
Auto Loan | 1
Credit-Builder Loan | 0
Debt Consolidation Loan | 0
Home Equity Loan | 0
Mortgage Loan | 0
Payday Loan | 0
Personal Loan | 0
Student Loan | 0
Credit_History_Age_in_Months | 128.0
Spending Frequency_indexed | 1.0
Spending Frequency_encoded | (1,[],[])
Average Size of Payment_indexed | 0.0
Average Size of Payment_encoded | (2,[0],[1.0])
Occupation_indexed | 4.0
Occupation_encoded | (15,[4],[1.0])
Credit_Score_indexed | 0.0
Credit_Score_encoded | (2,[0],[1.0])
normalized Age | 0.2619047619047619
normalized Annual_Income | 0.0033552582755269392
normalized Num_Bank_Accounts | 0.7
normalized Num_Credit_Card | 0.6
normalized Interest_Rate | 0.9393939393939394
normalized Num_of_Loan | 0.001941747572815534
normalized Delay_from_due_date | 0.27419354838709675
normalized Num_of_Delayed_Payment | 0.5357142857142857
normalized Changed_Credit_Limit | 0.5333333333333333
normalized Num_Credit_Inquiries | 0.4117647058823529
normalized Outstanding_Debt | 0.4716552561903751
normalized Credit_Utilization_Ratio | 0.6605992122006293
normalized Payment_of_Min_Amount | 1.0
normalized Total_EMI_per_month | 0.003854356107213826
normalized Amount_invested_monthly | 0.02438134660545594
normalized Monthly_Balance | 0.31466108147245836
normalized Auto Loan | 1.0
normalized Credit-Builder Loan | 0.0
normalized Debt Consolidation Loan | 0.0
normalized Home Equity Loan | 0.0
normalized Mortgage Loan | 0.0
normalized Payday Loan | 0.0
normalized Personal Loan | 0.0
normalized Student Loan | 0.0
normalized Credit_History_Age_in_Months | 0.3207070707070707
normalized Spending Frequency_indexed | 1.0
normalized Average Size of Payment_indexed | 0.0
normalized Occupation_indexed | 0.26666666666666666
normalized Credit_Score_indexed | 0.0
-RECORD 3-----------------------------------------------------------
max Credit_Score_indexed | 2.0
min Credit_Score_indexed | 0.0
max Occupation_indexed | 15.0
min Occupation_indexed | 0.0
max Average Size of Payment_indexed | 2.0
min Average Size of Payment_indexed | 0.0
max Spending Frequency_indexed | 1.0
min Spending Frequency_indexed | 0.0
max Credit_History_Age_in_Months | 397.0
min Credit_History_Age_in_Months | 1.0
max Student Loan | 1
min Student Loan | 0
max Personal Loan | 1
min Personal Loan | 0
max Payday Loan | 1
min Payday Loan | 0
max Mortgage Loan | 1
min Mortgage Loan | 0
max Home Equity Loan | 1
min Home Equity Loan | 0
max Debt Consolidation Loan | 1
min Debt Consolidation Loan | 0
max Credit-Builder Loan | 1
min Credit-Builder Loan | 0
max Auto Loan | 1
min Auto Loan | 0
max Monthly_Balance | 1602.0405189622518
min Monthly_Balance | 0.08862786534905354
max Amount_invested_monthly | 10000.0
min Amount_invested_monthly | 0.0
max Total_EMI_per_month | 82178.0
min Total_EMI_per_month | 0.0
max Payment_of_Min_Amount | 1
min Payment_of_Min_Amount | 0
max Credit_Utilization_Ratio | 49.56451934738699
min Credit_Utilization_Ratio | 21.02766450595043
max Outstanding_Debt | 4997.1
min Outstanding_Debt | 0.23
max Num_Credit_Inquiries | 17.0
min Num_Credit_Inquiries | 0.0
max Changed_Credit_Limit | 30
min Changed_Credit_Limit | 0
max Num_of_Delayed_Payment | 28
min Num_of_Delayed_Payment | 0
max Delay_from_due_date | 62
min Delay_from_due_date | 0
max Num_of_Loan | 1030
min Num_of_Loan | 0
max Interest_Rate | 34
min Interest_Rate | 1
max Num_Credit_Card | 11
min Num_Credit_Card | 1
max Num_Bank_Accounts | 10
min Num_Bank_Accounts | 0
max Annual_Income | 18265510
min Annual_Income | 7005
max Age | 56
min Age | 14
Age | 31
Annual_Income | 17680
Num_Bank_Accounts | 6
Num_Credit_Card | 6
Interest_Rate | 9
Num_of_Loan | 4
Delay_from_due_date | 9
Num_of_Delayed_Payment | 12
Changed_Credit_Limit | 11
Num_Credit_Inquiries | 12.0
Outstanding_Debt | 887.98
Credit_Utilization_Ratio | 37.56029322078355
Payment_of_Min_Amount | 1
Total_EMI_per_month | 31.68734043318193
Amount_invested_monthly | 90.88441778412479
Monthly_Balance | 292.36732511602656
Auto Loan | 1
Credit-Builder Loan | 0
Debt Consolidation Loan | 0
Home Equity Loan | 1
Mortgage Loan | 1
Payday Loan | 0
Personal Loan | 1
Student Loan | 0
Credit_History_Age_in_Months | 309.0
Spending Frequency_indexed | 0.0
Spending Frequency_encoded | (1,[0],[1.0])
Average Size of Payment_indexed | 0.0
Average Size of Payment_encoded | (2,[0],[1.0])
Occupation_indexed | 2.0
Occupation_encoded | (15,[2],[1.0])
Credit_Score_indexed | 0.0
Credit_Score_encoded | (2,[0],[1.0])
normalized Age | 0.40476190476190477
normalized Annual_Income | 5.846590397187503E-4
normalized Num_Bank_Accounts | 0.6
normalized Num_Credit_Card | 0.5
normalized Interest_Rate | 0.24242424242424243
normalized Num_of_Loan | 0.003883495145631068
normalized Delay_from_due_date | 0.14516129032258066
normalized Num_of_Delayed_Payment | 0.42857142857142855
normalized Changed_Credit_Limit | 0.36666666666666664
normalized Num_Credit_Inquiries | 0.7058823529411765
normalized Outstanding_Debt | 0.17766121592116663
normalized Credit_Utilization_Ratio | 0.5793430567837888
normalized Payment_of_Min_Amount | 1.0
normalized Total_EMI_per_month | 3.8559395985764963E-4
normalized Amount_invested_monthly | 0.00908844177841248
normalized Monthly_Balance | 0.1824516072393072
normalized Auto Loan | 1.0
normalized Credit-Builder Loan | 0.0
normalized Debt Consolidation Loan | 0.0
normalized Home Equity Loan | 1.0
normalized Mortgage Loan | 1.0
normalized Payday Loan | 0.0
normalized Personal Loan | 1.0
normalized Student Loan | 0.0
normalized Credit_History_Age_in_Months | 0.7777777777777778
normalized Spending Frequency_indexed | 0.0
normalized Average Size of Payment_indexed | 0.0
normalized Occupation_indexed | 0.13333333333333333
normalized Credit_Score_indexed | 0.0
only showing top 4 rows
Multilayer Perceptron Classifier
Implementing a multilayer perceptron classifier.
from pyspark.ml.classification import MultilayerPerceptronClassifier
from pyspark.ml.evaluation import MulticlassClassificationEvaluator
from pyspark.ml.tuning import CrossValidator, ParamGridBuilder
# Vector Assemble another set of input but with similar features
input_columns = credit_score_columns + credit_score_columns_indexed
normalized_input_columns = []
for column in input_columns:
normalized_input_columns.append('normalized ' + column)
print(input_columns)
print('Number of Features: ', len(input_columns))
vector_assembler = VectorAssembler(
inputCols = normalized_input_columns,
outputCol = 'features'
)
# Checking the output column
print('The ', output_columns[0])
dataset = vector_assembler.transform(normalized_credit_score)
dataset = dataset.checkpoint()
dataset_train, dataset_test = dataset.randomSplit([0.7,0.3], seed = 100)
dataset_train = dataset_train.checkpoint()
dataset_test = dataset_test.checkpoint()
dataset_train.show(1, vertical = True, truncate = False)
mlp = MultilayerPerceptronClassifier(
seed = 100,
featuresCol = 'features',
labelCol = output_columns[0],
predictionCol = 'prediction_column')
mlp_params = ParamGridBuilder()\
.addGrid(mlp.maxIter, [100])\
.addGrid(mlp.layers,[
[28,3],
[28,14,3],
[28,14,7,3],
[28,28,14,3 ]
])\
.addGrid(mlp.stepSize, [0.03, 0.07, 0.3])\
.build()
mlp_evaluator = MulticlassClassificationEvaluator(
labelCol = output_columns[0],
predictionCol = 'prediction_column'
)
mlp_cv = CrossValidator(
estimator = mlp,
estimatorParamMaps = mlp_params,
evaluator = mlp_evaluator,
numFolds = 10,
seed = 100
)
mlp_cv = mlp_cv.fit(dataset_train)
mlp_evaluator.evaluate(mlp_cv.transform(dataset_test))
mlp_best_model = mlp_cv.bestModel
print('Best model:', mlp_best_model)
mlp_predictions = mlp_best_model.transform(dataset_test)
mlp_accuracy = mlp_evaluator.evaluate(mlp_predictions, {mlp_evaluator.metricName:'accuracy'})
mlp_f1 = mlp_evaluator.evaluate(mlp_predictions, {mlp_evaluator.metricName:'f1'})
mlp_fmeasure_label = mlp_evaluator.evaluate(
mlp_predictions, {mlp_evaluator.metricName:'fMeasureByLabel'})
print(f'Acc: {mlp_accuracy} \nF1: {mlp_f1}\nfmeasure by label: {mlp_fmeasure_label}' )
mlp_predictions.select['Age', 'Annual_Income', 'Num_Bank_Accounts', 'Num_Credit_Card', 'Interest_Rate', 'Num_of_Loan', 'Delay_from_due_date', 'Num_of_Delayed_Payment', 'Changed_Credit_Limit', 'Num_Credit_Inquiries', 'Outstanding_Debt', 'Credit_Utilization_Ratio', 'Payment_of_Min_Amount', 'Total_EMI_per_month', 'Amount_invested_monthly', 'Monthly_Balance', 'Auto Loan', 'Credit-Builder Loan', 'Debt Consolidation Loan', 'Home Equity Loan', 'Mortgage Loan', 'Payday Loan', 'Personal Loan', 'Student Loan', 'Credit_History_Age_in_Months', 'Spending Frequency_indexed', 'Average Size of Payment_indexed', 'Occupation_indexed']
Number of Features: 28
The Credit_Score_indexed
-RECORD 0---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
max Credit_Score_indexed | 2.0
min Credit_Score_indexed | 0.0
max Occupation_indexed | 15.0
min Occupation_indexed | 0.0
max Average Size of Payment_indexed | 2.0
min Average Size of Payment_indexed | 0.0
max Spending Frequency_indexed | 1.0
min Spending Frequency_indexed | 0.0
max Credit_History_Age_in_Months | 397.0
min Credit_History_Age_in_Months | 1.0
max Student Loan | 1
min Student Loan | 0
max Personal Loan | 1
min Personal Loan | 0
max Payday Loan | 1
min Payday Loan | 0
max Mortgage Loan | 1
min Mortgage Loan | 0
max Home Equity Loan | 1
min Home Equity Loan | 0
max Debt Consolidation Loan | 1
min Debt Consolidation Loan | 0
max Credit-Builder Loan | 1
min Credit-Builder Loan | 0
max Auto Loan | 1
min Auto Loan | 0
max Monthly_Balance | 1602.0405189622518
min Monthly_Balance | 0.08862786534905354
max Amount_invested_monthly | 10000.0
min Amount_invested_monthly | 0.0
max Total_EMI_per_month | 82178.0
min Total_EMI_per_month | 0.0
max Payment_of_Min_Amount | 1
min Payment_of_Min_Amount | 0
max Credit_Utilization_Ratio | 49.56451934738699
min Credit_Utilization_Ratio | 21.02766450595043
max Outstanding_Debt | 4997.1
min Outstanding_Debt | 0.23
max Num_Credit_Inquiries | 17.0
min Num_Credit_Inquiries | 0.0
max Changed_Credit_Limit | 30
min Changed_Credit_Limit | 0
max Num_of_Delayed_Payment | 28
min Num_of_Delayed_Payment | 0
max Delay_from_due_date | 62
min Delay_from_due_date | 0
max Num_of_Loan | 1030
min Num_of_Loan | 0
max Interest_Rate | 34
min Interest_Rate | 1
max Num_Credit_Card | 11
min Num_Credit_Card | 1
max Num_Bank_Accounts | 10
min Num_Bank_Accounts | 0
max Annual_Income | 18265510
min Annual_Income | 7005
max Age | 56
min Age | 14
Age | 15
Annual_Income | 7871
Num_Bank_Accounts | 7
Num_Credit_Card | 10
Interest_Rate | 33
Num_of_Loan | 3
Delay_from_due_date | 45
Num_of_Delayed_Payment | 18
Changed_Credit_Limit | 7
Num_Credit_Inquiries | 7.0
Outstanding_Debt | 1953.63
Credit_Utilization_Ratio | 26.845529088998127
Payment_of_Min_Amount | 1
Total_EMI_per_month | 10.13245254860697
Amount_invested_monthly | 99.9522324647817
Monthly_Balance | 256.313731653278
Auto Loan | 0
Credit-Builder Loan | 0
Debt Consolidation Loan | 0
Home Equity Loan | 0
Mortgage Loan | 0
Payday Loan | 0
Personal Loan | 0
Student Loan | 1
Credit_History_Age_in_Months | 235.0
Spending Frequency_indexed | 0.0
Spending Frequency_encoded | (1,[0],[1.0])
Average Size of Payment_indexed | 0.0
Average Size of Payment_encoded | (2,[0],[1.0])
Occupation_indexed | 11.0
Occupation_encoded | (15,[11],[1.0])
Credit_Score_indexed | 0.0
Credit_Score_encoded | (2,[0],[1.0])
normalized Age | 0.023809523809523808
normalized Annual_Income | 4.74299511378396E-5
normalized Num_Bank_Accounts | 0.7
normalized Num_Credit_Card | 0.9
normalized Interest_Rate | 0.9696969696969697
normalized Num_of_Loan | 0.002912621359223301
normalized Delay_from_due_date | 0.7258064516129032
normalized Num_of_Delayed_Payment | 0.6428571428571429
normalized Changed_Credit_Limit | 0.23333333333333334
normalized Num_Credit_Inquiries | 0.4117647058823529
normalized Outstanding_Debt | 0.3909247188740151
normalized Credit_Utilization_Ratio | 0.20387196190240084
normalized Payment_of_Min_Amount | 1.0
normalized Total_EMI_per_month | 1.2329884578119412E-4
normalized Amount_invested_monthly | 0.00999522324647817
normalized Monthly_Balance | 0.1599455671621226
normalized Auto Loan | 0.0
normalized Credit-Builder Loan | 0.0
normalized Debt Consolidation Loan | 0.0
normalized Home Equity Loan | 0.0
normalized Mortgage Loan | 0.0
normalized Payday Loan | 0.0
normalized Personal Loan | 0.0
normalized Student Loan | 1.0
normalized Credit_History_Age_in_Months | 0.5909090909090909
normalized Spending Frequency_indexed | 0.0
normalized Average Size of Payment_indexed | 0.0
normalized Occupation_indexed | 0.7333333333333333
normalized Credit_Score_indexed | 0.0
features | [0.023809523809523808,4.74299511378396E-5,0.7,0.9,0.9696969696969697,0.002912621359223301,0.7258064516129032,0.6428571428571429,0.23333333333333334,0.4117647058823529,0.3909247188740151,0.20387196190240084,1.0,1.2329884578119412E-4,0.00999522324647817,0.1599455671621226,0.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,0.5909090909090909,0.0,0.0,0.7333333333333333]
only showing top 1 row
Best model: MultilayerPerceptronClassificationModel: uid=MultilayerPerceptronClassifier_a495b8303817, numLayers=4, numClasses=3, numFeatures=28
Acc: 0.5884237016700984
F1: 0.5514117285546243
fmeasure by label: 0.6960067969413762Decision Tree Classifier
Now we will implement decisioin tree classifier, there is also a random tree classifier which will also be implemented later.
from pyspark.ml.classification import DecisionTreeClassifier
# Set up the features and label/target variable for the model
input_columns = credit_score_columns + credit_score_columns_indexed
vector_assembler = VectorAssembler(
inputCols = input_columns,
outputCol = 'features'
)
print('The target variable / label: ', output_columns[0])
dataset_2 = vector_assembler.transform(credit_score)
dataset_2 = dataset_2.checkpoint()
dataset_2_train, dataset_2_test = dataset_2\
.randomSplit([0.7,0.3], seed = 100)
dataset_2_train = dataset_2_train.select('features',output_columns[0])
dataset_2_test = dataset_2_test.select('features',output_columns[0])
dataset_2_train = dataset_2_train.checkpoint()
dataset_2_test = dataset_2_test.checkpoint()
# Initializing the Decision Tree Classifier model
dtc = DecisionTreeClassifier(
seed = 100,
featuresCol = 'features',
labelCol = output_columns[0],
predictionCol = 'prediction_column',
checkpointInterval = 2
)
# Set the sets of parameters to for the model to go through
dtc_params = ParamGridBuilder()\
.addGrid(dtc.maxDepth, [5, 10, 15])\
.addGrid(dtc.impurity, ['gini', 'entropy'])\
.addGrid(dtc.minInstancesPerNode, [1,5,10])\
.build()
dtc_evaluator = MulticlassClassificationEvaluator(
labelCol = output_columns[0],
predictionCol = 'prediction_column'
)
dtc_cv = CrossValidator(
estimator = dtc,
estimatorParamMaps = dtc_params,
evaluator = dtc_evaluator,
numFolds = 10,
seed = 100
)
dtc_cv = dtc_cv.fit(dataset_2_train)
print(dtc_cv.avgMetrics)
print(dtc_cv.subModels)
print(dtc_cv.estimatorParamMaps)
dtc_best_model = dtc_cv.bestModel
print('Best Model: ', dtc_best_model)
dtc_predictions = dtc_best_model.transform(dataset_2_test)
dtc_accuracy = dtc_evaluator.evaluate(dtc_predictions, {dtc_evaluator.metricName:'accuracy'})
dtc_f1 = dtc_evaluator.evaluate(dtc_predictions, {dtc_evaluator.metricName:'f1'})
dtc_fmeasure_label = dtc_evaluator.evaluate(
dtc_predictions, {dtc_evaluator.metricName:'fMeasureByLabel'})
print(f'Acc: {dtc_accuracy} \nF1: {dtc_f1}\nfmeasure by label: {dtc_fmeasure_label}' )The target variable / label: Credit_Score_indexed
[0.5349722002779791, 0.5352171928737592, 0.5343327133865025, 0.547534860623849, 0.5454961717111608, 0.5468401250463606, 0.4464503318893468, 0.44701427412598566, 0.4535384851316914, 0.46360948265964924, 0.4549858511500099, 0.46843323434150824, 0.35688652244012287, 0.3697530041680032, 0.405632220759721, 0.36657549058608685, 0.36777042977852775, 0.4150521576364654]
None
CrossValidatorModel_db4d44635c22__estimatorParamMaps
Best Model: DecisionTreeClassificationModel: uid=DecisionTreeClassifier_71a4c498d29f, depth=5, numNodes=43, numClasses=3, numFeatures=28
Acc: 0.5913978494623656
F1: 0.5572305250609302
fmeasure by label: 0.6871596697698928Random Forest Classifier
As mentioned, Random Forest Classifier will also be implemented, similar to the Decision Tree Classifier above.
from pyspark.ml.classification import RandomForestClassifier
# Set up the features and label/target variable for the model
input_columns = credit_score_columns + credit_score_columns_indexed
vector_assembler = VectorAssembler(
inputCols = input_columns,
outputCol = 'features'
)
print('The target variable / label: ', output_columns[0])
dataset_3 = vector_assembler.transform(credit_score)
dataset_3 = dataset_3.checkpoint()
dataset_3_train, dataset_3_test = dataset_3\
.randomSplit([0.7,0.3], seed = 100)
dataset_3_train = dataset_3_train.select('features',output_columns[0])
dataset_3_test = dataset_3_test.select('features',output_columns[0])
dataset_3_train = dataset_3_train.checkpoint()
dataset_3_test = dataset_3_test.checkpoint()
# Initializing the Decision Tree Classifier model
rfc = RandomForestClassifier(
seed = 100,
featuresCol = 'features',
labelCol = output_columns[0],
predictionCol = 'prediction_column',
checkpointInterval = 2
)
# Set the sets of parameters to for the model to go through
rfc_params = ParamGridBuilder()\
.addGrid(rfc.maxDepth, [5, 10, 15])\
.addGrid(rfc.impurity, ['gini', 'entropy'])\
.addGrid(rfc.minInstancesPerNode, [1,5,10])\
.build()
rfc_evaluator = MulticlassClassificationEvaluator(
labelCol = output_columns[0],
predictionCol = 'prediction_column'
)
rfc_cv = CrossValidator(
estimator = rfc,
estimatorParamMaps = rfc_params,
evaluator = rfc_evaluator,
numFolds = 10,
seed = 100
)
rfc_cv = rfc_cv.fit(dataset_3_train)
print(rfc_cv.avgMetrics)
print(rfc_cv.subModels)
print(rfc_cv.estimatorParamMaps)
rfc_best_model = rfc_cv.bestModel
print('Best Model: ', rfc_best_model)
rfc_predictions = rfc_best_model.transform(dataset_3_test)
rfc_accuracy = rfc_evaluator.evaluate(rfc_predictions, {rfc_evaluator.metricName:'accuracy'})
rfc_f1 = dtc_evaluator.evaluate(rfc_predictions, {rfc_evaluator.metricName:'f1'})
rfc_fmeasure_label = rfc_evaluator.evaluate(
rfc_predictions, {rfc_evaluator.metricName:'fMeasureByLabel'})
print(f'Acc: {rfc_accuracy} \nF1: {rfc_f1}\nfmeasure by label: {rfc_fmeasure_label}')The target variable / label: Credit_Score_indexed
[0.48869379158901444, 0.4889470397089834, 0.4918453238300716, 0.4884958353422281, 0.4886775409282404, 0.5024005263949194, 0.44441389924284214, 0.46147205320030105, 0.4739855491815938, 0.4591718742515155, 0.4657209343927897, 0.47462976697956727, 0.3476489700563035, 0.3950336383541872, 0.42617124634719034, 0.35210840998360904, 0.3981631971771803, 0.4273711957131585]
None
CrossValidatorModel_2bb2577218d7__estimatorParamMaps
Best Model: RandomForestClassificationModel: uid=RandomForestClassifier_5e71782f1d3a, numTrees=20, numClasses=3, numFeatures=28
Acc: 0.5861358956760466
F1: 0.5298218104265964
fmeasure by label: 0.7059206245933637The results across all models are similar, and unfortunately, they fall short of ideal performance.
The subpar performance of these models is likely due to several factors. Data preprocessing could have been more robust, and the removal of the time-series component likely played a role. Additionally, the simple imputation of missing values using the mode probably reduced the models' ability to distinguish between samples. Applying normalization without sufficient context may have negatively impacted the dataset's quality. Finally, the inconsistency in categorical encoding likely hindered the models. For example, while Type_of_Loan was one-hot encoded, which is a method that could have been applied more broadly, Occupation was represented using indexed values. A machine learning model might misinterpret these indices as ordinal data, which suggested that a value of 4 is twice that of 2 when they are actually distinct categories.
As shown above, the results are as follows:
| Measure/Model | MLP | DTC | RFC |
|---|---|---|---|
| Accuracy | 0.588 | 0.591 | 0.586 |
| F1 | 0.551 | 0.557 | 0.530 |
| F-measure by label | 0.696 | 0.687 | 0.706 |
The accuracy of the best performing models show only marginal differences. The Decision Tree Classifier achieved the highest accuracy at 59.1%, while the Multilayer Perceptron (MLP) and Random Forest Classifier (RFC) followed closely at 58.8% and 58.6%, respectively. In terms of the F1 measure, which balances precision and recall, the Decision Tree Classifier remains the top performer at 55.7%. The MLP followed at 55.1% and the RFC at 53%. While the MLP and DTC results were comparable, the F-measure by label yielded different insights. Interestingly, the RFC scored highest here at 70.6%, with the MLP at 69.6% and the DTC at 68.7%. It remains unclear why this particular metric is higher for the RFC or why the Spark implementation returned a single value instead of per-label outputs as expected.
Conclusion
In this project, we did not succeed in developing an efficient model that maintains accuracy with a minimal feature set. With accuracy and F1 scores failing to exceed 60%, the models are currently insufficient for practical credit score prediction. Additionally, no single model demonstrated significant superiority over the others, as performance differences remained negligible.
Potential reasons for this limited performance include suboptimal data preprocessing and parameter tuning. While we implemented grid search, the chosen parameter ranges may not have been ideal. Due to the significant computation time required for training, we did not explore further individual parameter optimizations. Another critical factor was the removal of the time-series component, which not only reduced the volume of training data but also discarded vital temporal information that likely plays a key role in credit score determination.