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('prediction')[0], float)
assert math.ceil(subject.get('prediction')[0]) == 112476
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('prediction')) == 1451
assert len(subject.get('prediction')) != original_data_length
def test_make_single_prediction():
# given
test_data = load_dataset(file_name='xtest.csv')
single_test_json = test_data[0:1].to_json(orient='records')
# reads the 1st line of 'test.csv'
# when
subject = make_prediction(input_data=single_test_json)
# print(subject.get('predictions')[0])
# the above print statement was used to get the correct predicted value for
# line 22 ~ subject to change after editing
# then
assert subject is not None
assert isinstance(subject.get('predictions')[0],
float) # calling the 'predictions' keyword from the dict
assert math.ceil(subject.get('predictions')[0]) == 16 # see line 17
def test_make_multiple_predictions():
# given
test_data = load_dataset(file_name='xtest.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)
# print(original_data_length) # only work when tests fail
# print(subject.get('predictions')) --> verified the points for each individual player is outputted
# then
assert subject is not None
assert len(subject.get('predictions')) == 1034 # white box testing
# we dont expect any rows to be filtered out
assert len(subject.get('predictions')) == original_data_length
def predict():
if request.method == 'POST':
# Extract POST data from request body as JSON
json_data = request.get_json()
_logger.debug(f'Inputs: {json_data}')
# Validate the input using marshmallow schema
input_data, errors = validate_inputs(input_json=json_data)
# Model prediction
result = make_prediction(input_data=json_data)
_logger.debug(f'Outputs: {result}')
# Convert numpy ndarray to list
predictions = result.get('predictions').tolist()
version = result.get('version')
# return JSON response
return jsonify({
'predictions': predictions,
'version': version,
'errors': errors
})