def run_training_swagger() -> None:
"""Train the model."""
# read training data
data = load_dataset(file_name=config.TRAINING_DATA_FILE)
pipeline.loan_status_pipe.fit(data[config.FEATURES], data[config.TARGET])
save_pipeline_swagger(pipeline_to_persist=pipeline.loan_status_pipe)
return
def test_make_single_prediction():
# Given
test_data = load_dataset(file_name='test.csv')
single_test_json = test_data[0:1].to_json(orient='records')
# When
subject = make_prediction(input_data=single_test_json)
# Then
assert subject is not None
assert isinstance(subject.get('predictions'), list)
assert (subject.get('predictions')[0]) == 0
def test_make_multiple_predictions():
# Given
test_data = load_dataset(file_name='test.csv')
#original_data_length = len(test_data)
multiple_test_json = test_data.to_json(orient='records')
# When
subject = make_prediction(input_data=multiple_test_json)
# Then
assert subject is not None
assert isinstance(subject.get('predictions'), list)
assert (subject.get('predictions')).count(1) == 45931
assert (subject.get('predictions')).count(0) == 34069
def run_training() -> None:
"""Train the model."""
# read training data
data = load_dataset(file_name=config.TRAINING_DATA_FILE)
# read training data
#data = pd.read_csv(TRAINING_DATA_FILE)
# divide train and test
# X_train, X_test, y_train, y_test = train_test_split(
# data[config.FEATURES],
# data[config.TARGET],
# test_size=0.33, random_state=42) # we are setting the seed here
pipeline.loan_status_pipe.fit(data[config.FEATURES], data[config.TARGET])
_logger.info(f'saving model version: {_version}')
save_pipeline(pipeline_to_persist=pipeline.loan_status_pipe)
return