• Part 2. Clean the data.
  • Change the loan amount into whole numbers. Make sure you pay attention to the units.
  • Change interest rate into %.
  • Change the term into a whole number in the term of month.
  • Take emp_lenth into year, if its below 1 year, the number is 0, if its more than 10 years, the number is 10.
  • You are going to load grade into numbers:
    • For example, Grade A will be assigned a number of 1, B to a number of 2, etc.
  • You are going to recalculate the DTI number.
    • If the DTI number is missing, use the ratio of annual payment and annual income instead. Hint the coalesce operator is??

Part 3. A brief idea of the data

1. What's the percentage of loan that is fully funded?
2. What"s the percentage of loan that has a DTI less than 1 ?
3. Which month has the highest number of applications?
4. The highest amount of funded amount?
5. The highest interest rate?
6. What's the average/ max//min// number of observations with regarding to interest rate of different Grades?
7. What's the average/max/min/number of observations with regarding to interest rate of different employment lengths?
8. What's the average/ max//min// number of observations with regarding to interest rate of different Grades and employment lengths?