Last active
June 4, 2019 17:09
-
-
Save edunuke/21811cb8a4a8db4d5fdd8dd96edd8b4a to your computer and use it in GitHub Desktop.
This file contains hidden or 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
| # load datasets | |
| users_df = pd.read_csv("dataset/users_data.csv", index_col=0) | |
| risk_df = pd.read_csv("dataset/risk_data.csv", index_col=0) | |
| products_df = pd.read_csv("dataset/products_data.csv", index_col=0) | |
| # Static Constants | |
| SEED = 123 | |
| TARGET_NAME = "product_code" | |
| RESAMPLED= False | |
| USER_COLS= ['client_id', 'age', 'salary', 'nationality', 'residence'] | |
| RISK_COLS = ['client_id', 'total_misspay_count', 'credit_score', 'total_debt_capacity'] | |
| PROD_COLS = ['client_id', 'product_code', 'prod_category', 'prod_subcategory','product_limit'] | |
| # Variables | |
| risk_shape = risk_df.shape | |
| products_shape = products_df.shape | |
| user_shape = users_df.shape | |
| n_users = len(set(users_df.client_id)) | |
| n_products= len(set(products_df[TARGET_NAME])) | |
| n_risk = len(set(risk_df.total_misspay_count)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment