## Loan_ID Gender Married Dependents ## Length:381 Length:381 Length:381 Length:381 ## Class :character Class :character Class :character Class :character ## Mode :character Mode :character Mode :character Mode :character ## ## ## ## ## Education Self_Employed ApplicantIncome CoapplicantIncome ## Length:381 Length:381 Min. : 150 Min. : 0 ## Class :character Class :character 1st Qu.:2600 1st Qu.: 0 ## Mode :character Mode :character Median :3333 Median : 983 ## Mean :3580 Mean : 1277 ## 3rd Qu.:4288 3rd Qu.: 2016 ## Max. :9703 Max. :33837 ## ## LoanAmount Loan_Amount_Term Credit_History Property_Area ## Min. : 9 Min. : 12.0 Min. :0.0000 Length:381 ## 1st Qu.: 90 1st Qu.:360.0 1st Qu.:1.0000 Class :character ## Median :110 Median :360.0 Median :1.0000 Mode :character ## Mean :105 Mean :340.9 Mean :0.8376 ## 3rd Qu.:127 3rd Qu.:360.0 3rd Qu.:1.0000 ## Max. :150 Max. :480.0 Max. :1.0000 ## NA's :11 NA's :30 ## Loan_Status ## Length:381 ## Class :character ## Mode :character ## ## ## ##
Loading and Summarizing the Data
Data Cleaning
## [1] "Missing Values"
## Loan_ID Gender Married Dependents ## 0 0 0 0 ## Education Self_Employed ApplicantIncome CoapplicantIncome ## 0 0 0 0 ## LoanAmount Loan_Amount_Term Credit_History Property_Area ## 0 11 30 0 ## Loan_Status ## 0
## [1] "Data Types"
## Loan_ID Gender Married Dependents ## "character" "character" "character" "character" ## Education Self_Employed ApplicantIncome CoapplicantIncome ## "character" "character" "integer" "numeric" ## LoanAmount Loan_Amount_Term Credit_History Property_Area ## "numeric" "numeric" "numeric" "character" ## Loan_Status ## "character"
## [1] "Check for missing values: "
## [1] 0
Distribution of Applicant Income
Distribution of Self Employed Individuals (Pie Chart)
Loan Approval Based on Self Employed Individuals
Correlation of Applicant Income and Self Employment
Loan Amount vs. Applicant Income (Scatter Plot Code)
p <- ggplot(loan_data, aes(x = ApplicantIncome, y = LoanAmount)) +
geom_point(aes(color = Loan_Status), alpha = 0.5) +
geom_smooth(method = "lm", color = "blue", se = FALSE) +
labs(title = "Loan Amount vs. Applicant Income",
x = "Applicant Income",
y = "Loan Amount") +
scale_color_manual(values = c("Y" = "#76CD26",
"N" = "#CD2626")) +
theme_minimal()
# Converted ggplot to a plotly object to make the plot interactive
ggplotly(p)
Loan Amount vs. Applicant Income (Scatter Plot)
Credit History vs. Loan Status (Bar Plot)
Property Area Impact on Loan Status (Bar Plot)
Coapplicant Income Effect (Density Plot)
Loan Status vs. Number of Dependents (Bar Plot)
Loan Status by Gender vs. Marital Status (Bar Plot)
Interactive Scatter Plot Code
loan_data$Status_Education <- with(loan_data, paste(Loan_Status, Education))
plot_ly(loan_data, x = ~ApplicantIncome, y = ~LoanAmount,
type = 'scatter',
mode = 'markers',
color = ~Status_Education, colors = c('Y Graduate' = '#3498db',
'N Graduate' = '#2ecc71',
'Y Not Graduate' = '#f0948d',
'N Not Graduate' = '#7b59b6'),
marker = list(size = 10, opacity = 0.5)) %>%
layout(
title = 'Applicant Income vs. Loan Amount by Education and Loan Status',
xaxis = list(title = 'Applicant Income'),
yaxis = list(title = 'Loan Amount'),
legend = list(title = list(text = 'Combined Status')))