def test_stacked_fit_predict_classification(X_y_binary, X_y_multi, stackable_classifiers, problem_type):
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
input_pipelines = [make_pipeline_from_components([classifier], problem_type)
for classifier in stackable_classifiers]
clf = StackedEnsembleClassifier(input_pipelines=input_pipelines, n_jobs=1)
clf.fit(X, y)
y_pred = clf.predict(X)
assert len(y_pred) == len(y)
assert isinstance(y_pred, ww.DataColumn)
assert not np.isnan(y_pred.to_series()).all()
y_pred_proba = clf.predict_proba(X)
assert isinstance(y_pred_proba, ww.DataTable)
assert y_pred_proba.shape == (len(y), num_classes)
assert not np.isnan(y_pred_proba.to_dataframe()).all().all()
clf = StackedEnsembleClassifier(input_pipelines=input_pipelines, final_estimator=RandomForestClassifier(), n_jobs=1)
clf.fit(X, y)
y_pred = clf.predict(X)
assert len(y_pred) == len(y)
assert isinstance(y_pred, ww.DataColumn)
assert not np.isnan(y_pred.to_series()).all()
y_pred_proba = clf.predict_proba(X)
assert y_pred_proba.shape == (len(y), num_classes)
assert isinstance(y_pred_proba, ww.DataTable)
assert not np.isnan(y_pred_proba.to_dataframe()).all().all()
def test_stacked_ensemble_multilevel(logistic_regression_binary_pipeline_class):
# checks passing a stacked ensemble classifier as a final estimator
X = pd.DataFrame(np.random.rand(50, 5))
y = pd.Series([1, 0] * 25)
base = StackedEnsembleClassifier(input_pipelines=[logistic_regression_binary_pipeline_class(parameters={})], n_jobs=1)
clf = StackedEnsembleClassifier(input_pipelines=[logistic_regression_binary_pipeline_class(parameters={})],
final_estimator=base,
n_jobs=1)
clf.fit(X, y)
y_pred = clf.predict(X)
assert len(y_pred) == len(y)
assert not np.isnan(y_pred.to_series()).all()
def test_stacked_ensemble_n_jobs_negative_one(X_y_binary, logistic_regression_binary_pipeline_class):
X, y = X_y_binary
input_pipelines = [logistic_regression_binary_pipeline_class(parameters={})]
clf = StackedEnsembleClassifier(input_pipelines=input_pipelines, n_jobs=-1)
expected_parameters = {
"input_pipelines": input_pipelines,
"final_estimator": None,
'cv': None,
'n_jobs': -1
}
assert clf.parameters == expected_parameters
clf.fit(X, y)
y_pred = clf.predict(X)
assert len(y_pred) == len(y)
assert not np.isnan(y_pred.to_series()).all()
def test_stacked_ensemble_init_with_multiple_same_estimators(X_y_binary, logistic_regression_binary_pipeline_class):
# Checks that it is okay to pass multiple of the same type of estimator
X, y = X_y_binary
input_pipelines = [logistic_regression_binary_pipeline_class(parameters={}),
logistic_regression_binary_pipeline_class(parameters={})]
clf = StackedEnsembleClassifier(input_pipelines=input_pipelines, n_jobs=1)
expected_parameters = {
"input_pipelines": input_pipelines,
"final_estimator": None,
'cv': None,
'n_jobs': 1
}
assert clf.parameters == expected_parameters
fitted = clf.fit(X, y)
assert isinstance(fitted, StackedEnsembleClassifier)
y_pred = clf.predict(X)
assert len(y_pred) == len(y)
assert not np.isnan(y_pred.to_series()).all()
