def run_training() -> None:
"""Train the model."""
_logger.info(f"training the pipeline with version: {_version}")
# read training data
data = load_dataset(file_name=config.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=0.1, random_state=0
) # we are setting the seed here
pipeline.marathon_pipeline.fit(X_train[config.FEATURES], y_train)
_logger.info(f"saving model version: {_version}")
save_pipeline(pipeline_to_persist=pipeline.marathon_pipeline)
print("########################################")
print("Test prediction: ")
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)
print(subject)
def test_prediction_endpoint_returns_prediction(flask_test_client):
# 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.DATASET_FILE)
X_train, X_test, y_train, y_test = train_test_split(
test_data.drop(model_config.TARGET, axis=1),
test_data[model_config.TARGET],
test_size=0.2,
random_state=0) # we are setting the seed here
post_json = X_test.to_json(orient='records')
response = flask_test_client.post('/v1/predict/regression',
json=json.loads(post_json))
# Check status code is OK
assert response.status_code == 200
# Check performance, accuracy.
response_json = json.loads(response.data)
prediction = response_json['predictions']
assert prediction is not None
assert accuracy_score(y_test, prediction) < 1
# Check versions match
response_version = response_json['version']
assert response_version == _version
# Check correct number of errors removed
assert len(prediction) + len(response_json.get('errors')) == len(X_test)
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[0:1].to_json(orient="records")
#when
response = flask_test_client.post("/v1/predict/regression", 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 math.ceil(prediction[0]) == 12
assert response_version == _version
# The response_version looks like {"predictions": 11.84092..., "version": None}
# So indeed the version is none, due to some null objects created while changing from
# one data type to another. Solve this problem in later versions.
# Problem has been solved in the later versions.
def make_prediction():
"""Make a prediction using a saved model pipeline.
Args:
input_data: Array of model prediction inputs.
Returns:
Predictions for each input row, as well as the model version.
"""
test_data = load_dataset(file_name='test.csv')
data = pd.DataFrame(test_data)
validated_data = validate_inputs(input_data=data)
prediction = _price_pipe.predict(validated_data[config.FEATURES])
output = np.exp(prediction)
results = {'predictions': output, 'version': _version}
_logger.info(
f'Making predictions with model version: {_version} '
f'Inputs: {validated_data} '
f'Predictions: {results}')
return results
def test_model_prediction_differential(
*, save_file: str = 'test_data_predictions.csv'):
"""
This test compares the prediction result similarity of
the current model with the previous model's results.
"""
# Given
# Load the saved previous model predictions
previous_model_df = pd.read_csv(f'{config.PACKAGE_ROOT}/{save_file}')
previous_model_predictions = previous_model_df.predictions.values
test_data = load_dataset(file_name=model_config.TESTING_DATA_FILE)
multiple_test_input = test_data[99:600]
# When
current_result = make_prediction(input_data=multiple_test_input)
current_model_predictions = current_result.get('predictions')
# Then
# diff the current model vs. the old model
#assert len(previous_model_predictions) == len(current_model_predictions)
# Perform the differential test
for previous_value, current_value in zip(previous_model_predictions,
current_model_predictions):
# convert numpy float64 to Python float.
previous_value = previous_value.item()
current_value = current_value.item()
def run_training() -> None:
"""Train the model."""
# read training data
data = load_dataset(file_name=config.TRAINING_DATA_FILE)
# print(data.head())
# divide train and test
X_train, X_test, y_train, y_test = train_test_split(
data[config.FEATURES],
data[config.TARGET],
test_size=0.1,
random_state=0) # we are setting the seed here
pipeline.end_to_end_pipeline.fit(X_train[config.FEATURES], y_train)
pred = pipeline.end_to_end_pipeline.predict(X_test)
# determine mse and rmse
print("test mse: {}".format(int(mean_squared_error(y_test, (pred)))))
print("test rmse: {}".format(
int(np.sqrt(mean_squared_error(y_test, (pred))))))
print("test r2: {}".format(r2_score(y_test, (pred))))
print(pipeline.end_to_end_pipeline.named_steps["Linear_model"].coef_)
_version = "0.0.1"
_logger.info(f"saving model version: {_version}")
save_pipeline(pipeline_to_persist=pipeline.end_to_end_pipeline)
def test_model_prediction_differential(*, save_file="test_data_predictions.csv"):
# This test compares the prediction result similarity of the
# current model with the previous model's results.
save_file = "test_data_predictions.csv"
#Given
previous_model_df = pd.read_csv(f'{model_config.PACKAGE_ROOT}/{save_file}')
previous_model_predictions = previous_model_df.predictions.values
test_data = load_dataset(file_name=config.TESTING_DATA_FILE)
multiple_test_json = test_data[99:600]
# When
response = make_prediction(input_data=multiple_test_json)
current_model_predictions = response.get("predictions")
assert len(previous_model_predictions) == len(current_model_predictions)
# Perform the differential test
for previous_value, current_value in zip(previous_model_predictions,current_model_predictions):
# convert numpy float64 to python float
previous_value = previous_value.item()
current_value = current_value.item()
# rel_tol is the relative tolerance - it is the maximum allowed
assert math.isclose(previous_value, current_value, rel_tol=config.ACCEPTABLE_MODEL_DIFFERENCE)
def test_make_single_prediction():
test_data = load_dataset(file_name='test.csv')
single_test_input = test_data[0:1]
subject = make_prediction(input_data=single_test_input)
assert subject is not None
assert isinstance(subject.get('predictions')[0], float)
assert math.ceil(subject.get('predictions')[0]) == 112476
def test_make_single_prediction():
"""Test a prediction is correct"""
# load test file
test_data = load_dataset(file_name='test.csv')
# make a single predicition
single_test_input = test_data[0:1]
subject = make_prediction(input_data=single_test_input)
assert subject is not None
assert isinstance(subject.get('predictions')[0], float)
assert math.ceil(subject.get('predictions')[0]) == 112476
def test_prediction_endpoint_validation_200(flask_test_client):
test_data = load_dataset(file_name= config.TRAINING_DATA_FILE)
post_json = test_data.to_json(orient= 'records')
response = flask_test_client.post('/v1/predict/regression', json = post_json)
assert response.status_code == 200
response_json = json.loads(response.data)
#assert len(response_json.get('predictions')) + len(response_json.get('errors')) == len(test_data)
def test_make_single_prediction():
# Given
test_data = load_dataset(file_name='test.csv')
single_test_json = test_data[0:1]
# When
subject = make_prediction(input_data=single_test_json)
# Then
assert subject is not None
assert isinstance(subject.get('predictions')[0], float)
def run_training() :
data = load_dataset(file_name= TRAINING_DATA_FILE)
X_train, X_test , Y_train, Y_test = train_test_split(data[FEATURES],data[TARGET],
test_size = 0.2, random_state=0 )
Y_train = np.log(Y_train)
Y_test = np.log(Y_test)
price_pipe.fit(X_train[FEATURES], Y_train)
_logger.info(f"saving model version:{_version}")
save_pipeline(pipeline_to_save=price_pipe)
def test_make_multiple_predictions():
test_data = load_dataset(file_name='test.csv')
original_data_length = len(test_data)
multiple_test_input = test_data
subject = make_prediction(input_data=multiple_test_input)
assert subject is not None
assert len(subject.get('predictions')) == 1451
assert len(subject.get('predictions')) != original_data_length
def pipeline_inputs():
data = load_dataset(filename=config.TESTING_DATA_FILE)
#train test split
X_train, X_test, y_train, y_test = train_test_split(
data[config.FEATURES],
data[config.TARGET],
test_size=config.TEST_SIZE,
random_state=config.RANDOM_STATE,
)
return X_train, X_test, y_train, y_test
def test_make_single_prediction():
# Given
test_data = load_dataset(file_name="test.csv")
single_test_input = test_data[0:1]
# When
subject = make_prediction(input_data=single_test_input)
# Then
assert subject is not None
assert isinstance(subject.get("predictions")[0], float)
assert math.ceil(subject.get("predictions")[0]) == 112476
def test_make_multiple_predictions():
# Given
test_data = load_dataset(file_name='test.xlsx')
original_data_length = len(test_data)
multiple_test_input = test_data
# When
subject = make_prediction(input_data=multiple_test_input)
# Then
assert subject is not None
assert len(subject.get('predictions')) == original_data_length
def test_make_multiple_predictions():
"""Test a prediction is correct"""
# load test file
test_data = load_dataset(file_name='test.csv')
original_data_length = len(test_data)
# make a prediciton for all the testset
multiple_test_input = test_data
subject = make_prediction(input_data=multiple_test_input)
assert subject is not None
assert len(subject.get('predictions')) == 1451
# It is expected some rows to be filtered out
assert len(subject.get('predictions')) != original_data_length
def test_prediction_endpoint_returns_prediction(test_client):
test_data = load_dataset(file_name=model_config.TESTING_DATA_FILE)
post_json = test_data[0:1].to_json(orient="records")
response = test_client.post(f"/api/v1/score", json=post_json)
assert response.status_code == 200
response_json = json.loads(response.data)
prediction = response_json["predictions"]
response_version = response_json["version"]
assert math.ceil(prediction) == 112476
assert response_version == _version
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')[0], float)
assert math.ceil(subject.get('predictions')[0]) == 112476
def run_training() -> None:
"""Train the model"""
data = load_dataset(file_name=config.TRAINING_DATA_FILE)
# divide train and test
X, y = data[config.FEATURES], data[config.TARGET]
pipeline.fit(X, y)
_logger.info(f"saving model version: {_version}")
save_pipeline(pipeline_to_persist=pipeline)
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')
print("hola")
# When
subject = make_prediction(input_data=single_test_json)
# Then
assert subject is not None
assert isinstance(subject.get('predictions')[0], float)
assert subject.get('predictions')[0]>=3.6 and subject.get('predictions')[0]<=3.7
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[0:1].to_json(orient='records')
# When
response = flask_test_client.post('/v1/predict/regression',
<<<<<<< HEAD
json=json.loads(post_json))
def test_make_multiple_prediction():
#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 len(subject.get('predictions')) == 1451
assert len(subject.get('predictions')) != original_data_length
def test_make_single_prediction():
# Given
test_data = load_dataset(file_name='test.csv')
single_test_input = test_data[0:1]
print(single_test_input)
# When
subject = make_prediction(input_data=single_test_input)
# Then
assert subject is not None
assert isinstance(subject.get('predictions')[0], np.int64)
def test_health_prediction_endpoint_returns_200(flask_test_client):
test_data = load_dataset(filename=model_config.TEST_DATA_FILE)
post_json = test_data.to_json(orient='records')
#when
resonse = flask_test_client.get('/v1/predict/regression')
#then
assert resonse.status_code == 200
resonse_data = json.load(resonse.data)
prediction = resonse_data['predictions']
response_version = resonse_data['version']
assert math.ceil(prediction) == 9
assert response_version == _version
def test_prediction_endpoint_validation_200(flask_test_client):
data = load_dataset(TESTING_DATA_FILE)
data_json = data.to_json(orient='records')
response = flask_test_client('/v1/prediction/regression',
json=json.loads(data_json))
assert response.status_code == 200
response_json = json.loads(response.data)
assert len(response_json.get('predictions')) + len(
response_json.get('errors')) == len(data_json)
def make_single_prediction():
test_data_file = 'test_one.csv'
df = load_dataset(filename=test_data_file)
print('testdata')
print(len(df))
df = df[0:1]
print(df['booking_date'])
output = make_prediction(input_data=df)
print(output)
assert output is not None
# assert isinstance(output['predictions'][0],float)
print(math.ceil(output['predictions'][0]))
assert math.ceil(output['predictions'][0]) == 9
def test_make_multiple_predictions():
# Given
test_data = load_dataset(file_name='test.csv')
original_data_length = test_data.shape[0]
multiple_test_json = test_data
# When
subject = make_prediction(input_data=multiple_test_json)
# Then
assert subject is not None
assert len(subject.get('predictions')) == 1451
assert len(subject.get("predictions")) != original_data_length
def test_make_single_prediction():
# Given
test_data = load_dataset(file_name='test.csv')
single_test_input = test_data[0:1] #select single row from the csv
# When
subject = make_prediction(input_data=single_test_input)
# Then
assert subject is not None
assert isinstance(
subject.get('predictions')[0], float
) #prediction come as dictionary so we extract preditions and that should be float
assert math.ceil(subject.get('predictions')[0]) == 112476
def test_make_multiple_predictions():
# Given
test_data = load_dataset(file_name='test.csv')
original_data_length = len(test_data)
multiple_test_input = test_data
# When
subject = make_prediction(input_data=multiple_test_input)
# Then
assert subject is not None
assert len(subject.get('predictions')) == 1451
# We expect some rows to be filtered out
assert len(subject.get('predictions')) != original_data_length