def run_training() -> None:
"""Train the model."""
# read training data
data = load_dataset(file_name=config.TRAINING_DATA_FILE)
# Feature engineering
r2 = setup(data,
target='charges',
session_id=123,
normalize=True,
polynomial_features=True,
trigonometry_features=True,
feature_interaction=True,
bin_numeric_features=['age', 'bmi'],
silent=True)
# Model Training and Validation
lr = create_model('lr', verbose=False)
# Prepare versioned save file name
save_file_name = f"{config.PIPELINE_SAVE_FILE}{_version}"
save_path = config.TRAINED_MODEL_DIR / save_file_name
# Remove old pipelines
keep_file_name = f"{config.PIPELINE_SAVE_FILE}{_version}.pkl"
remove_old_pipelines(files_to_keep=keep_file_name)
# save transformation pipeline and model
save_model(lr, model_name=str(save_path))
def test_make_single_prediction():
# Given
test_data = load_dataset(file_name='inscharges-test.csv')
single_test_json = test_data[0:1].to_json(orient='records')
# When
subject = make_prediction(input_data=single_test_json)
predicted_value = (subject.get('predictions')['Label']).values[0]
# Then
assert subject is not None
assert isinstance(predicted_value, float)
def test_make_multiple_predictions():
# Given
test_data = load_dataset(file_name='inscharges-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 len(subject.get('predictions')) == 20
# We expect no rows to be filtered out
assert len(subject.get('predictions')) == original_data_length
def test_prediction_endpoint_validation_200(flask_test_client):
# Given
# Load the test data from the regression_model package.
# This is important as it makes it harder for the test
# data versions to get confused by not spreading it
# across packages.
test_data = load_dataset(file_name=config.TESTING_DATA_FILE)
post_json = test_data[0:2].to_json(orient='records')
# When
response = flask_test_client.post('/v1/predict/inscharge', json=post_json)
# Then
assert response.status_code == 200
response_json = json.loads(response.data)
_logger.info(f'Response Json: {response_json}')
def test_prediction_endpoint_returns_prediction(flask_test_client):
# Given
# Load the test data from the regression_model package
# This is important as it makes it harder for the test
# data versions to get confused by not spreading it
# across packages.
test_data = load_dataset(file_name=model_config.TESTING_DATA_FILE)
post_json = test_data[0:5].to_json(orient='records')
# When
response = flask_test_client.post('/v1/predict/inscharge', json=post_json)
# Then
assert response.status_code == 200
response_json = json.loads(response.data)
prediction = response_json['predictions']
response_version = response_json['version']
#assert len(prediction) == 5
assert response_version == _version