def test_fit_predict_on_pipeline():
# test that the fit_predict method is implemented on a pipeline
# test that the fit_predict on pipeline yields same results as applying
# transform and clustering steps separately
scaler = StandardScaler()
km = KMeans(random_state=0)
# As pipeline doesn't clone estimators on construction,
# it must have its own estimators
scaler_for_pipeline = StandardScaler()
km_for_pipeline = KMeans(random_state=0)
# first compute the transform and clustering step separately
scaled = scaler.fit_transform(iris.data)
separate_pred = km.fit_predict(scaled)
# use a pipeline to do the transform and clustering in one step
pipe = Pipeline([('scaler', scaler_for_pipeline),
('Kmeans', km_for_pipeline)])
pipeline_pred = pipe.fit_predict(iris.data)
assert_array_almost_equal(pipeline_pred, separate_pred)
def test_partial_dependence_pipeline():
# check that the partial dependence support pipeline
iris = load_iris()
scaler = StandardScaler()
clf = DummyClassifier(random_state=42)
pipe = make_pipeline(scaler, clf)
clf.fit(scaler.fit_transform(iris.data), iris.target)
pipe.fit(iris.data, iris.target)
features = 0
pdp_pipe, values_pipe = partial_dependence(pipe,
iris.data,
features=[features],
grid_resolution=10)
pdp_clf, values_clf = partial_dependence(clf,
scaler.transform(iris.data),
features=[features],
grid_resolution=10)
assert_allclose(pdp_pipe, pdp_clf)
assert_allclose(
values_pipe[0],
values_clf[0] * scaler.scale_[features] + scaler.mean_[features])