Created
June 11, 2021 05:46
-
-
Save tommydangerous/96aa83c3bdea3cfa42ceb42223501ef8 to your computer and use it in GitHub Desktop.
prepare_test_data.py
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
X_test = X_test_raw.copy() | |
# Add columns | |
X_test['can_vote'] = X_test['Age'].apply(lambda age: 1 if age >= 18 else 0) | |
X_test.loc[:, 'cabin_letter'] = X_test['Cabin'].apply( | |
lambda cabin: cabin[0] if cabin and type(cabin) is str else None, | |
) | |
# Remove columns | |
X_test = X_test.drop(columns=['Name', 'PassengerId']) | |
# Impute values | |
X_test.loc[X_test['Cabin'].isna(), 'Cabin'] = 'somewhere out of sight' | |
X_test.loc[X_test['cabin_letter'].isna(), 'cabin_letter'] = 'ZZZ' | |
X_test.loc[:, ['Age']] = age_imputer.transform(X_test[['Age']]) | |
X_test.loc[X_test['Embarked'].isna(), 'Embarked'] = 'no idea' | |
# Scale columns | |
X_test.loc[:, ['Age']] = scaler.transform(X_test[['Age']]) | |
# Encode values | |
X_test.loc[:, new_column_names] = categorical_encoder.transform( | |
X_test[categorical_columns], | |
).toarray() | |
# Select features | |
X_test = X_test[features_to_use].copy() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment