Created
May 16, 2022 11:53
-
-
Save audhiaprilliant/6c7f0367957224c03416b94a7effdb82 to your computer and use it in GitHub Desktop.
End to end machine learning model deployment using flask
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
| # -------------------- TESTING SET -------------------- | |
| # Data frame metadata | |
| df_test.info() | |
| # Change column types | |
| df_test = df_test.astype({'Credit_History': object}) | |
| df_test.select_dtypes(include = ['object']).dtypes | |
| # Summary statistics of categorical columns | |
| for i in df_test.select_dtypes('object').columns: | |
| print(df_test[i].value_counts(),'\n') | |
| # Check missing values | |
| df_test.isna().sum() | |
| # Handle missing values | |
| # 1 Dependents | |
| print('Number of missing values in Dependents is about {} rows'.format(df_test['Dependents'].isna().sum())) | |
| # Replace missing values with "0" | |
| df_test['Dependents'].fillna(value = '0', inplace = True) | |
| # 2 Self_Employed | |
| print('Number of missing values in Self_Employed is about {} rows'.format(df_test['Self_Employed'].isna().sum())) | |
| # Replace missing values with "No" | |
| df_test['Self_Employed'].fillna(value = 'No', inplace = True) | |
| # 3 Loan_Amount_Term | |
| # Replace missing values with "360" | |
| df_test['Loan_Amount_Term'].fillna(value = 360, inplace = True) | |
| # 4 Gender, Married, LoanAmount and Credit_History | |
| # Drop missing values | |
| df_test.dropna(axis = 0, how = 'any', inplace = True) | |
| # Check missing values | |
| df_test.isna().sum() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment