-
-
Save isauravmanitripathi/1a1acf9064cb1ad54c365ce6c0c44318 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#preprocessing | |
#remove missing values | |
loans = loans.dropna() | |
#remove outliers | |
q_low = loans["annual_inc"].quantile(0.08) | |
q_hi = loans["annual_inc"].quantile(0.92) loans = loans[(loans["annual_inc"] < q_hi) & (loans["annual_inc"] > q_low)] | |
loans = loans[(loans['dti'] <=45)] | |
q_hi = loans['bc_open_to_buy'].quantile(0.95) | |
loans = loans[(loans['bc_open_to_buy'] < q_hi)] | |
loans = loans[(loans['bc_util'] <=160)] | |
loans = loans[(loans['revol_util'] <=150)] | |
loans = loans[(loans['num_op_rev_tl'] <=35)] | |
#categorical features processing | |
cleaner_app_type = {"term": {" 36 months": 1.0, " 60 months": 2.0}, | |
"sub_grade": {"A1": 1.0, "A2": 2.0, "A3": 3.0, "A4": 4.0, | |
"A5": 5.0, "B1": 11.0, "B2": 12.0, "B3": 13.0, "B4": 14.0, | |
"B5": 15.0, "C1": 21.0, "C2": 22.0, "C3": 23.0, "C4": | |
24.0, "C5": 25.0, "D1": 31.0, "D2": 32.0, "D3": 33.0, | |
"D4": 34.0, "D5": 35.0, "E1": 41.0, "E2": 42.0, "E3": | |
43.0, "E4": 44.0, "E5": 45.0, "F1": 51.0, "F2": 52.0, | |
"F3": 53.0, "F4": 54.0, "F5": 55.0, "G1": 61.0, "G2": | |
62.0, "G3": 63.0, "G4": 64.0, "G5": 65.0, }, | |
"emp_length": {"< 1 year": 0.0, '1 year': 1.0, '2 years': 2.0, | |
'3 years': 3.0, '4 years': 4.0, '5 years': 5.0, '6 years': | |
6.0, '7 years': 7.0, '8 years': 8.0, '9 years': 9.0, '10+ | |
years': 10.0 } | |
} | |
loans = loans.replace(cleaner_app_type) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment