def test_all_estimators_check_fit(X_y_binary, ts_data, test_estimator_needs_fitting_false, helper_functions):
estimators_to_check = [estimator for estimator in _all_estimators() if estimator not in [StackedEnsembleClassifier, StackedEnsembleRegressor, TimeSeriesBaselineEstimator]] + [test_estimator_needs_fitting_false]
for component_class in estimators_to_check:
if not component_class.needs_fitting:
continue
if ProblemTypes.TIME_SERIES_REGRESSION in component_class.supported_problem_types:
X, y = ts_data
else:
X, y = X_y_binary
component = helper_functions.safe_init_component_with_njobs_1(component_class)
with pytest.raises(ComponentNotYetFittedError, match=f'You must fit {component_class.__name__}'):
component.predict(X)
if ProblemTypes.BINARY in component.supported_problem_types or ProblemTypes.MULTICLASS in component.supported_problem_types:
with pytest.raises(ComponentNotYetFittedError, match=f'You must fit {component_class.__name__}'):
component.predict_proba(X)
with pytest.raises(ComponentNotYetFittedError, match=f'You must fit {component_class.__name__}'):
component.feature_importance
component.fit(X, y)
if ProblemTypes.BINARY in component.supported_problem_types or ProblemTypes.MULTICLASS in component.supported_problem_types:
component.predict_proba(X)
component.predict(X)
component.feature_importance
def test_scikit_learn_wrapper(X_y_binary, X_y_multi, X_y_regression, ts_data):
for estimator in [estimator for estimator in _all_estimators() if estimator.model_family != ModelFamily.ENSEMBLE]:
for problem_type in estimator.supported_problem_types:
if problem_type == ProblemTypes.BINARY:
X, y = X_y_binary
num_classes = 2
pipeline_class = BinaryClassificationPipeline
elif problem_type == ProblemTypes.MULTICLASS:
X, y = X_y_multi
num_classes = 3
pipeline_class = MulticlassClassificationPipeline
elif problem_type == ProblemTypes.REGRESSION:
X, y = X_y_regression
pipeline_class = RegressionPipeline
elif problem_type in [ProblemTypes.TIME_SERIES_REGRESSION, ProblemTypes.TIME_SERIES_MULTICLASS, ProblemTypes.TIME_SERIES_BINARY]:
continue
evalml_pipeline = pipeline_class([estimator])
scikit_estimator = scikit_learn_wrapped_estimator(evalml_pipeline)
scikit_estimator.fit(X, y)
y_pred = scikit_estimator.predict(X)
assert len(y_pred) == len(y)
assert not np.isnan(y_pred).all()
if problem_type in [ProblemTypes.BINARY, ProblemTypes.MULTICLASS]:
y_pred_proba = scikit_estimator.predict_proba(X)
assert y_pred_proba.shape == (len(y), num_classes)
assert not np.isnan(y_pred_proba).all().all()
def test_scikit_learn_wrapper(X_y_binary, X_y_multi, X_y_regression):
for estimator in [
estimator for estimator in _all_estimators()
if estimator.model_family != ModelFamily.ENSEMBLE
]:
for problem_type in estimator.supported_problem_types:
if problem_type == ProblemTypes.BINARY:
X, y = X_y_binary
num_classes = 2
elif problem_type == ProblemTypes.MULTICLASS:
X, y = X_y_multi
num_classes = 3
elif problem_type == ProblemTypes.REGRESSION:
X, y = X_y_regression
elif problem_type in [
ProblemTypes.TIME_SERIES_REGRESSION,
ProblemTypes.TIME_SERIES_MULTICLASS,
ProblemTypes.TIME_SERIES_BINARY
]:
# Skipping because make_pipeline_from_components does not yet work for time series.
continue
evalml_pipeline = make_pipeline_from_components([estimator()],
problem_type)
scikit_estimator = scikit_learn_wrapped_estimator(evalml_pipeline)
scikit_estimator.fit(X, y)
y_pred = scikit_estimator.predict(X)
assert len(y_pred) == len(y)
assert not np.isnan(y_pred).all()
if problem_type in [ProblemTypes.BINARY, ProblemTypes.MULTICLASS]:
y_pred_proba = scikit_estimator.predict_proba(X)
assert y_pred_proba.shape == (len(y), num_classes)
assert not np.isnan(y_pred_proba).all().all()
def test_all_transformers_needs_fitting():
for component_class in _all_transformers() + _all_estimators():
if component_class.__name__ in [
'DropColumns', 'SelectColumns', 'DelayedFeatureTransformer'
]:
assert not component_class.needs_fitting
else:
assert component_class.needs_fitting
def stackable_regressors(helper_functions):
stackable_regressors = []
for estimator_class in _all_estimators():
supported_problem_types = [handle_problem_types(pt) for pt in estimator_class.supported_problem_types]
if (set(supported_problem_types) == {ProblemTypes.REGRESSION, ProblemTypes.TIME_SERIES_REGRESSION} and
estimator_class.model_family not in _nonstackable_model_families and
estimator_class.model_family != ModelFamily.ENSEMBLE):
stackable_regressors.append(helper_functions.safe_init_component_with_njobs_1(estimator_class))
return stackable_regressors
def stackable_classifiers(helper_functions):
stackable_classifiers = []
for estimator_class in _all_estimators():
supported_problem_types = [handle_problem_types(pt) for pt in estimator_class.supported_problem_types]
if (set(supported_problem_types) == {ProblemTypes.BINARY, ProblemTypes.MULTICLASS,
ProblemTypes.TIME_SERIES_BINARY, ProblemTypes.TIME_SERIES_MULTICLASS} and
estimator_class.model_family not in _nonstackable_model_families and
estimator_class.model_family != ModelFamily.ENSEMBLE):
stackable_classifiers.append(estimator_class)
return stackable_classifiers
def all_pipeline_classes():
all_possible_pipeline_classes = []
for estimator in [
estimator for estimator in _all_estimators()
if estimator != StackedEnsembleClassifier
and estimator != StackedEnsembleRegressor
]:
for problem_type in estimator.supported_problem_types:
all_possible_pipeline_classes.append(
create_mock_pipeline(estimator, problem_type))
return all_possible_pipeline_classes
def test_serialization_protocol(mock_cloudpickle_dump, tmpdir):
path = os.path.join(str(tmpdir), 'pipe.pkl')
component = LogisticRegressionClassifier()
component.save(path)
assert len(mock_cloudpickle_dump.call_args_list) == 1
assert mock_cloudpickle_dump.call_args_list[0][1]['protocol'] == cloudpickle.DEFAULT_PROTOCOL
mock_cloudpickle_dump.reset_mock()
component.save(path, pickle_protocol=42)
assert len(mock_cloudpickle_dump.call_args_list) == 1
assert mock_cloudpickle_dump.call_args_list[0][1]['protocol'] == 42
@pytest.mark.parametrize("estimator_class", _all_estimators())
def test_estimators_accept_all_kwargs(estimator_class,
logistic_regression_binary_pipeline_class,
linear_regression_pipeline_class):
try:
estimator = estimator_class()
except EnsembleMissingPipelinesError:
if estimator_class == StackedEnsembleClassifier:
estimator = estimator_class(input_pipelines=[logistic_regression_binary_pipeline_class(parameters={})])
elif estimator_class == StackedEnsembleRegressor:
estimator = estimator_class(input_pipelines=[linear_regression_pipeline_class(parameters={})])
if estimator._component_obj is None:
pytest.skip(f"Skipping {estimator_class} because does not have component object.")
if estimator_class.model_family == ModelFamily.ENSEMBLE:
params = estimator.parameters
else:
