def main(input_train, input_test, output_train, output_test):
""" Runs data processing scripts to turn raw data from (../raw) into
cleaned data ready to be analyzed (saved in ../processed).
"""
logger = logging.getLogger(__name__)
logger.info('making final data set from raw data')
raw_data = DataSet(input_train, input_test)
df_train = raw_data.get_train_set()
df_test = raw_data.get_test_set()
TitanicPreProcessing(df_train, output_train)
TitanicPreProcessing(df_test, output_test)
def main(input_filepath, output_filepath):
""" Runs data processing scripts to turn raw data from (../raw) into
cleaned data ready to be analyzed (saved in ../processed).
"""
logger = logging.getLogger(__name__)
logger.info('making final data set from raw data')
raw_data = DataSet(train_dir=input_filepath + '/train.csv',
test_dir=input_filepath + '/test.csv')
cleaning = DataWrangling(train_dir=output_filepath + '/train_clean.csv',
test_dir=output_filepath + '/test_clean.csv')
df_train = raw_data.get_train_set()
df_test = raw_data.get_test_set()
df_train_clean = cleaning.apply_preprocessing(df_train, target='Survived')
df_test_clean = cleaning.apply_preprocessing(df_test, target='Survived')
cleaning.processed_train_data(df_train_clean)
cleaning.processed_test_data(df_test_clean)
def main(input_train, input_test, input_model, output_prediction):
""" Runs modeling scripts using model pickle (../models) to predict
outcomes. Outcomes file is saved as .csv (saved in ../models).
"""
logger = logging.getLogger(__name__)
logger.info('predicting outcomes')
data = DataSet(train_dir=input_train, test_dir=input_test)
test = data.get_test_set()
X_test = data.get_features(test)
model = Model.load(input_model + 'XGBClassifier')
y_pred = model.predict(X_test)
output = pd.DataFrame({
'PassengerId': test['PassengerId'],
'Survived': y_pred
})
output.to_csv(output_prediction + 'submission_{}.csv'.format(model.name),
index=False)