Data Set Link : kaggle.com/datasets/uciml/default-of-credit..

Introduction to the data set

• Limit_Bal - Credit Balance Given
• Sex - categorical data 1 for Males, 2 for female
• Education - 1 for graduate, 2 universities, 3- high school, 4 - others, 6 & 5 - unknown
• Marriage - categorical data e 1- unmarried, 2 , married
• Payments made ------ 0 to 4
  • -1 indicates was paid on time
  • 1 indicates a delay of a month
  • 2 indicates a delay for two months
  • 3 indicates 3 months delay similar till 9

• Bill Amount April to September 2005

• Amount paid from April to September 2005

• Any default payment set up categorical 0 indicates no, 1 indicates yes

Univariate Analysis of Categorical Data

• SEX category

Conclusion number of females greater than males

• EDUCATION category

• Here there is no documentation of category number 0,6 & 5

• Marriage Category

Again Category number 0 is not documented

• We will have to fix these issues

• PAY_0 to PAY_6 ---- Categorical Columns

We have no idea about what is -2 as it is not documented

With this feature exploration is complete