def test_validate_inputs(sample_input_data):
# When
validated_inputs, errors = validate_inputs(input_data=sample_input_data)
# Then
# we expect that 2 rows are removed due to missing vars
# 1459 is the total number of rows in the test data set (test.csv)
# and 1457 number returned after 2 rows are filtered out.
assert len(sample_input_data) == 1459
assert len(validated_inputs) == 1457
def test_validate_inputs_identifies_errors(sample_input_data):
# Given
test_inputs = sample_input_data.copy()
# introduce errors
test_inputs.at[1, "BldgType"] = 50 # we expect a string
# When
validated_inputs, errors = validate_inputs(input_data=test_inputs)
# Then
assert errors
assert errors[1] == {"BldgType": ["Not a valid string."]}
def test_validate_inputs(sample_input_data):
"""These are static hardcodes; what's going on there. """
# When
validated_inputs, errors = validate_inputs(input_data=sample_input_data)
# Then
assert not errors
# we expect that 2 rows are removed due to missing vars
# 1459 is the total number of rows in the test data set (test.csv)
# and 1457 number returned after 2 rows are filtered out.
assert len(sample_input_data) == 1459
assert len(validated_inputs) == 1457
def test_pipeline_predict_takes_validated_input(pipeline_inputs,
sample_input_data):
# Given
X_train, X_test, y_train, y_test = pipeline_inputs
pipeline.price_pipe.fit(X_train, y_train)
# When
validated_inputs, errors = validate_inputs(input_data=sample_input_data)
predictions = pipeline.price_pipe.predict(
validated_inputs[config.model_config.features])
# Then
assert predictions is not None
assert errors is None
def make_prediction(
*,
input_data: t.Union[pd.DataFrame, dict],
) -> dict:
"""Make a prediction using a saved model pipeline."""
data = pd.DataFrame(input_data)
validated_data, errors = validate_inputs(input_data=data)
results = {"predictions": None, "version": _version, "errors": errors}
if not errors:
predictions = _price_pipe.predict(
X=validated_data[config.model_config.features])
_logger.info(f"Making predictions with model version: {_version} "
f"Predictions: {predictions}")
results = {
"predictions": predictions,
"version": _version,
"errors": errors
}
return results
