def test_pipeline_ducktyping():
pipeline = make_pipeline(Mult(5))
pipeline.predict
pipeline.transform
pipeline.inverse_transform
pipeline = make_pipeline(Transf())
assert not hasattr(pipeline, 'predict')
pipeline.transform
pipeline.inverse_transform
pipeline = make_pipeline(None)
assert not hasattr(pipeline, 'predict')
pipeline.transform
pipeline.inverse_transform
pipeline = make_pipeline(Transf(), NoInvTransf())
assert not hasattr(pipeline, 'predict')
pipeline.transform
assert not hasattr(pipeline, 'inverse_transform')
pipeline = make_pipeline(NoInvTransf(), Transf())
assert not hasattr(pipeline, 'predict')
pipeline.transform
assert not hasattr(pipeline, 'inverse_transform')
def test_make_pipeline():
t1 = Transf()
t2 = Transf()
pipe = make_pipeline(t1, t2)
assert isinstance(pipe, Pipeline)
assert pipe.steps[0][0] == "transf-1"
assert pipe.steps[1][0] == "transf-2"
pipe = make_pipeline(t1, t2, FitParamT())
assert isinstance(pipe, Pipeline)
assert pipe.steps[0][0] == "transf-1"
assert pipe.steps[1][0] == "transf-2"
assert pipe.steps[2][0] == "fitparamt"
def test_classes_property():
iris = load_iris()
X = iris.data
y = iris.target
reg = make_pipeline(SelectKBest(k=1), LinearRegression())
reg.fit(X, y)
with raises(AttributeError):
getattr(reg, "classes_")
clf = make_pipeline(SelectKBest(k=1), LogisticRegression(random_state=0))
with raises(AttributeError):
getattr(clf, "classes_")
clf.fit(X, y)
assert_array_equal(clf.classes_, np.unique(y))
def test_pipeline_fit_then_sample_3_samplers_with_sampler_last_estimator():
X, y = make_classification(
n_classes=2,
class_sep=2,
weights=[0.1, 0.9],
n_informative=3,
n_redundant=1,
flip_y=0,
n_features=20,
n_clusters_per_class=1,
n_samples=50000,
random_state=0)
rus = RandomUnderSampler(random_state=42)
enn = ENN()
pipeline = make_pipeline(rus, enn, rus)
X_fit_sample_resampled, y_fit_sample_resampled = pipeline.fit_sample(X, y)
pipeline = make_pipeline(rus, enn, rus)
pipeline.fit(X, y)
X_fit_then_sample_res, y_fit_then_sample_res = pipeline.sample(X, y)
assert_array_equal(X_fit_sample_resampled, X_fit_then_sample_res)
assert_array_equal(y_fit_sample_resampled, y_fit_then_sample_res)
def test_single_estimator():
# Check singleton ensembles.
X_train, X_test, y_train, y_test = train_test_split(imb_iris.data,
imb_iris.target,
random_state=0)
clf1 = SMOTEBagging(base_estimator=KNeighborsClassifier(),
n_estimators=1,
bootstrap=False,
bootstrap_features=False,
random_state=0).fit(X_train, y_train)
clf2 = make_pipeline(
SMOTE(random_state=clf1.estimators_[0].steps[0][1].random_state),
KNeighborsClassifier()).fit(X_train, y_train)
assert_array_equal(clf1.predict(X_test), clf2.predict(X_test))
def test_pipeline_none_sampler_sample():
# Test pipeline using None step and a sampler
X, y = make_classification(
n_classes=2,
class_sep=2,
weights=[0.1, 0.9],
n_informative=3,
n_redundant=1,
flip_y=0,
n_features=20,
n_clusters_per_class=1,
n_samples=5000,
random_state=0)
rus = RandomUnderSampler(random_state=0)
pipe = make_pipeline(None, rus)
pipe.fit(X, y)
pipe.sample(X, y)
def test_pipeline_none_classifier():
# Test pipeline using None as preprocessing step and a classifier
X, y = make_classification(
n_classes=2,
class_sep=2,
weights=[0.1, 0.9],
n_informative=3,
n_redundant=1,
flip_y=0,
n_features=20,
n_clusters_per_class=1,
n_samples=5000,
random_state=0)
clf = LogisticRegression(random_state=0)
pipe = make_pipeline(None, clf)
pipe.fit(X, y)
pipe.predict(X)
pipe.predict_proba(X)
pipe.decision_function(X)
pipe.score(X, y)
def test_pipeline_none_transformer():
# Test pipeline using None and a transformer that implements transform and
# inverse_transform
X, y = make_classification(
n_classes=2,
class_sep=2,
weights=[0.1, 0.9],
n_informative=3,
n_redundant=1,
flip_y=0,
n_features=20,
n_clusters_per_class=1,
n_samples=5000,
random_state=0)
pca = PCA(whiten=True)
pipe = make_pipeline(None, pca)
pipe.fit(X, y)
X_trans = pipe.transform(X)
X_inversed = pipe.inverse_transform(X_trans)
assert_array_almost_equal(X, X_inversed)
def test_bagging_with_pipeline():
estimator = SMOTEBagging(make_pipeline(SelectKBest(k=1),
DecisionTreeClassifier()),
max_features=2)
estimator.fit(imb_iris.data, imb_iris.target).predict(imb_iris.data)