def main(input_data, output_model):
""" Runs modeling scripts using processed data (../raw) to
create model. Model is saved as pickle (saved in ../models).
"""
logger = logging.getLogger(__name__)
logger.info('training model')
data = DataSet(train_dir=input_data)
train = data.get_train_set()
X_train = data.get_features(train)
y = data.get_label(train)
clf = models[4]
param_grid = params[4]
model = Model.tune(clf, X_train, y, param_grid)
model.save(output_model + model.name)
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)