def test_pipeline_methods_preprocessing_svm():
# Test the various methods of the pipeline (preprocessing + svm).
X = iris.data
y = iris.target
n_samples = X.shape[0]
n_classes = len(np.unique(y))
scaler = StandardScaler()
pca = PCA(n_components=2, svd_solver='randomized', whiten=True)
clf = SVC(probability=True, random_state=0, decision_function_shape='ovr')
for preprocessing in [scaler, pca]:
pipe = Pipeline([('preprocess', preprocessing), ('svc', clf)])
pipe.fit(X, y)
# check shapes of various prediction functions
predict = pipe.predict(X)
assert predict.shape == (n_samples, )
proba = pipe.predict_proba(X)
assert proba.shape == (n_samples, n_classes)
log_proba = pipe.predict_log_proba(X)
assert log_proba.shape == (n_samples, n_classes)
decision_function = pipe.decision_function(X)
assert decision_function.shape == (n_samples, n_classes)
pipe.score(X, y)
def test_is_classifier():
svc = SVC()
assert is_classifier(svc)
assert is_classifier(GridSearchCV(svc, {'C': [0.1, 1]}))
assert is_classifier(Pipeline([('svc', svc)]))
assert is_classifier(
Pipeline([('svc_cv', GridSearchCV(svc, {'C': [0.1, 1]}))]))
def test_countvectorizer_custom_vocabulary_pipeline():
what_we_like = ["pizza", "beer"]
pipe = Pipeline([
('count', CountVectorizer(vocabulary=what_we_like)),
('tfidf', TfidfTransformer())])
X = pipe.fit_transform(ALL_FOOD_DOCS)
assert (set(pipe.named_steps['count'].vocabulary_) ==
set(what_we_like))
assert X.shape[1] == len(what_we_like)
def test_fit_predict_with_intermediate_fit_params():
# tests that Pipeline passes fit_params to intermediate steps
# when fit_predict is invoked
pipe = Pipeline([('transf', TransfFitParams()), ('clf', FitParamT())])
pipe.fit_predict(X=None,
y=None,
transf__should_get_this=True,
clf__should_succeed=True)
assert pipe.named_steps['transf'].fit_params['should_get_this']
assert pipe.named_steps['clf'].successful
assert 'should_succeed' not in pipe.named_steps['transf'].fit_params
def test_pipeline_fit_transform():
# Test whether pipeline works with a transformer missing fit_transform
X = iris.data
y = iris.target
transf = Transf()
pipeline = Pipeline([('mock', transf)])
# test fit_transform:
X_trans = pipeline.fit_transform(X, y)
X_trans2 = transf.fit(X, y).transform(X)
assert_array_almost_equal(X_trans, X_trans2)
def test_transform_target_regressor_route_pipeline():
X, y = friedman
regr = TransformedTargetRegressor(
regressor=DummyRegressorWithExtraFitParams(),
transformer=DummyTransformer())
estimators = [('normalize', StandardScaler()), ('est', regr)]
pip = Pipeline(estimators)
pip.fit(X, y, **{'est__check_input': False})
assert regr.transformer_.fit_counter == 1
def test_pipeline_correctly_adjusts_steps(passthrough):
X = np.array([[1]])
y = np.array([1])
mult2 = Mult(mult=2)
mult3 = Mult(mult=3)
mult5 = Mult(mult=5)
pipeline = Pipeline([('m2', mult2), ('bad', passthrough), ('m3', mult3),
('m5', mult5)])
pipeline.fit(X, y)
expected_names = ['m2', 'bad', 'm3', 'm5']
actual_names = [name for name, _ in pipeline.steps]
assert expected_names == actual_names
def test_pipeline_named_steps():
transf = Transf()
mult2 = Mult(mult=2)
pipeline = Pipeline([('mock', transf), ("mult", mult2)])
# Test access via named_steps bunch object
assert 'mock' in pipeline.named_steps
assert 'mock2' not in pipeline.named_steps
assert pipeline.named_steps.mock is transf
assert pipeline.named_steps.mult is mult2
# Test bunch with conflict attribute of dict
pipeline = Pipeline([('values', transf), ("mult", mult2)])
assert pipeline.named_steps.values is not transf
assert pipeline.named_steps.mult is mult2
def test_set_params():
# test nested estimator parameter setting
clf = Pipeline([("svc", SVC())])
# non-existing parameter in svc
assert_raises(ValueError, clf.set_params, svc__stupid_param=True)
# non-existing parameter of pipeline
assert_raises(ValueError, clf.set_params, svm__stupid_param=True)
def test_count_vectorizer_pipeline_grid_selection():
# raw documents
data = JUNK_FOOD_DOCS + NOTJUNK_FOOD_DOCS
# label junk food as -1, the others as +1
target = [-1] * len(JUNK_FOOD_DOCS) + [1] * len(NOTJUNK_FOOD_DOCS)
# split the dataset for model development and final evaluation
train_data, test_data, target_train, target_test = train_test_split(
data, target, test_size=.2, random_state=0)
pipeline = Pipeline([('vect', CountVectorizer()),
('svc', LinearSVC())])
parameters = {
'vect__ngram_range': [(1, 1), (1, 2)],
'svc__loss': ('hinge', 'squared_hinge')
}
# find the best parameters for both the feature extraction and the
# classifier
grid_search = GridSearchCV(pipeline, parameters, n_jobs=1, cv=3)
# Check that the best model found by grid search is 100% correct on the
# held out evaluation set.
pred = grid_search.fit(train_data, target_train).predict(test_data)
assert_array_equal(pred, target_test)
# on this toy dataset bigram representation which is used in the last of
# the grid_search is considered the best estimator since they all converge
# to 100% accuracy models
assert grid_search.best_score_ == 1.0
best_vectorizer = grid_search.best_estimator_.named_steps['vect']
assert best_vectorizer.ngram_range == (1, 1)
def test_pipeline_fit_params():
# Test that the pipeline can take fit parameters
pipe = Pipeline([('transf', Transf()), ('clf', FitParamT())])
pipe.fit(X=None, y=None, clf__should_succeed=True)
# classifier should return True
assert pipe.predict(None)
# and transformer params should not be changed
assert pipe.named_steps['transf'].a is None
assert pipe.named_steps['transf'].b is None
# invalid parameters should raise an error message
assert_raise_message(TypeError,
"fit() got an unexpected keyword argument 'bad'",
pipe.fit,
None,
None,
clf__bad=True)
def test_pipeline_sample_weight_supported():
# Pipeline should pass sample_weight
X = np.array([[1, 2]])
pipe = Pipeline([('transf', Transf()), ('clf', FitParamT())])
pipe.fit(X, y=None)
assert pipe.score(X) == 3
assert pipe.score(X, y=None) == 3
assert pipe.score(X, y=None, sample_weight=None) == 3
assert pipe.score(X, sample_weight=np.array([2, 3])) == 8
def test_pipeline_slice():
pipe = Pipeline([('transf1', Transf()), ('transf2', Transf()),
('clf', FitParamT())])
pipe2 = pipe[:-1]
assert isinstance(pipe2, Pipeline)
assert pipe2.steps == pipe.steps[:-1]
assert 2 == len(pipe2.named_steps)
assert_raises(ValueError, lambda: pipe[::-1])
def test_pipeline_transform():
# Test whether pipeline works with a transformer at the end.
# Also test pipeline.transform and pipeline.inverse_transform
X = iris.data
pca = PCA(n_components=2, svd_solver='full')
pipeline = Pipeline([('pca', pca)])
# test transform and fit_transform:
X_trans = pipeline.fit(X).transform(X)
X_trans2 = pipeline.fit_transform(X)
X_trans3 = pca.fit_transform(X)
assert_array_almost_equal(X_trans, X_trans2)
assert_array_almost_equal(X_trans, X_trans3)
X_back = pipeline.inverse_transform(X_trans)
X_back2 = pca.inverse_transform(X_trans)
assert_array_almost_equal(X_back, X_back2)
def test_fit_predict_on_pipeline_without_fit_predict():
# tests that a pipeline does not have fit_predict method when final
# step of pipeline does not have fit_predict defined
scaler = StandardScaler()
pca = PCA(svd_solver='full')
pipe = Pipeline([('scaler', scaler), ('pca', pca)])
assert_raises_regex(AttributeError,
"'PCA' object has no attribute 'fit_predict'", getattr,
pipe, 'fit_predict')
def test_ovr_pipeline():
# Test with pipeline of length one
# This test is needed because the multiclass estimators may fail to detect
# the presence of predict_proba or decision_function.
clf = Pipeline([("tree", DecisionTreeClassifier())])
ovr_pipe = OneVsRestClassifier(clf)
ovr_pipe.fit(iris.data, iris.target)
ovr = OneVsRestClassifier(DecisionTreeClassifier())
ovr.fit(iris.data, iris.target)
assert_array_equal(ovr.predict(iris.data), ovr_pipe.predict(iris.data))
def test_pipeline_index():
transf = Transf()
clf = FitParamT()
pipe = Pipeline([('transf', transf), ('clf', clf)])
assert pipe[0] == transf
assert pipe['transf'] == transf
assert pipe[-1] == clf
assert pipe['clf'] == clf
assert_raises(IndexError, lambda: pipe[3])
assert_raises(KeyError, lambda: pipe['foobar'])
def test_gridsearch_pipeline():
# Test if we can do a grid-search to find parameters to separate
# circles with a perceptron model.
X, y = make_circles(n_samples=400, factor=.3, noise=.05, random_state=0)
kpca = KernelPCA(kernel="rbf", n_components=2)
pipeline = Pipeline([("kernel_pca", kpca),
("Perceptron", Perceptron(max_iter=5))])
param_grid = dict(kernel_pca__gamma=2.**np.arange(-2, 2))
grid_search = GridSearchCV(pipeline, cv=3, param_grid=param_grid)
grid_search.fit(X, y)
assert grid_search.best_score_ == 1
def test_calibration_nan_imputer():
"""Test that calibration can accept nan"""
X, y = make_classification(n_samples=10, n_features=2,
n_informative=2, n_redundant=0,
random_state=42)
X[0, 0] = np.nan
clf = Pipeline(
[('imputer', SimpleImputer()),
('rf', RandomForestClassifier(n_estimators=1))])
clf_c = CalibratedClassifierCV(clf, cv=2, method='isotonic')
clf_c.fit(X, y)
clf_c.predict(X)
def test_vectorizer_pipeline_cross_validation():
# raw documents
data = JUNK_FOOD_DOCS + NOTJUNK_FOOD_DOCS
# label junk food as -1, the others as +1
target = [-1] * len(JUNK_FOOD_DOCS) + [1] * len(NOTJUNK_FOOD_DOCS)
pipeline = Pipeline([('vect', TfidfVectorizer()),
('svc', LinearSVC())])
cv_scores = cross_val_score(pipeline, data, target, cv=3)
assert_array_equal(cv_scores, [1., 1., 1.])
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_pipeline_wrong_memory():
# Test that an error is raised when memory is not a string or a Memory
# instance
X = iris.data
y = iris.target
# Define memory as an integer
memory = 1
cached_pipe = Pipeline([('transf', DummyTransf()), ('svc', SVC())],
memory=memory)
assert_raises_regex(
ValueError, "'memory' should be None, a string or"
" have the same interface as joblib.Memory."
" Got memory='1' instead.", cached_pipe.fit, X, y)
def test_predict_with_predict_params():
# tests that Pipeline passes predict_params to the final estimator
# when predict is invoked
pipe = Pipeline([('transf', Transf()), ('clf', DummyEstimatorParams())])
pipe.fit(None, None)
pipe.predict(X=None, got_attribute=True)
assert pipe.named_steps['clf'].got_attribute
def test_pipeline_with_cache_attribute():
X = np.array([[1, 2]])
pipe = Pipeline([('transf', Transf()), ('clf', Mult())],
memory=DummyMemory())
pipe.fit(X, y=None)
dummy = WrongDummyMemory()
pipe = Pipeline([('transf', Transf()), ('clf', Mult())], memory=dummy)
assert_raises_regex(
ValueError, "'memory' should be None, a string or"
" have the same interface as joblib.Memory."
" Got memory='{}' instead.".format(dummy), pipe.fit, X)
def test_set_params_passes_all_parameters():
# Make sure all parameters are passed together to set_params
# of nested estimator. Regression test for #9944
class TestDecisionTree(DecisionTreeClassifier):
def set_params(self, **kwargs):
super().set_params(**kwargs)
# expected_kwargs is in test scope
assert kwargs == expected_kwargs
return self
expected_kwargs = {'max_depth': 5, 'min_samples_leaf': 2}
for est in [
Pipeline([('estimator', TestDecisionTree())]),
GridSearchCV(TestDecisionTree(), {})
]:
est.set_params(estimator__max_depth=5, estimator__min_samples_leaf=2)
def test_imputation_pipeline_grid_search():
# Test imputation within a pipeline + gridsearch.
X = _sparse_random_matrix(100, 100, density=0.10)
missing_values = X.data[0]
pipeline = Pipeline([('imputer',
SimpleImputer(missing_values=missing_values)),
('tree',
tree.DecisionTreeRegressor(random_state=0))])
parameters = {
'imputer__strategy': ["mean", "median", "most_frequent"]
}
Y = _sparse_random_matrix(100, 1, density=0.10).toarray()
gs = GridSearchCV(pipeline, parameters)
gs.fit(X, Y)
def test_pipeline_sample_weight_unsupported():
# When sample_weight is None it shouldn't be passed
X = np.array([[1, 2]])
pipe = Pipeline([('transf', Transf()), ('clf', Mult())])
pipe.fit(X, y=None)
assert pipe.score(X) == 3
assert pipe.score(X, sample_weight=None) == 3
assert_raise_message(
TypeError,
"score() got an unexpected keyword argument 'sample_weight'",
pipe.score,
X,
sample_weight=np.array([2, 3]))
def test_set_pipeline_steps():
transf1 = Transf()
transf2 = Transf()
pipeline = Pipeline([('mock', transf1)])
assert pipeline.named_steps['mock'] is transf1
# Directly setting attr
pipeline.steps = [('mock2', transf2)]
assert 'mock' not in pipeline.named_steps
assert pipeline.named_steps['mock2'] is transf2
assert [('mock2', transf2)] == pipeline.steps
# Using set_params
pipeline.set_params(steps=[('mock', transf1)])
assert [('mock', transf1)] == pipeline.steps
# Using set_params to replace single step
pipeline.set_params(mock=transf2)
assert [('mock', transf2)] == pipeline.steps
# With invalid data
pipeline.set_params(steps=[('junk', ())])
assert_raises(TypeError, pipeline.fit, [[1]], [1])
assert_raises(TypeError, pipeline.fit_transform, [[1]], [1])
def test_pipeline_raise_set_params_error():
# Test pipeline raises set params error message for nested models.
pipe = Pipeline([('cls', LinearRegression())])
# expected error message
error_msg = ('Invalid parameter %s for estimator %s. '
'Check the list of available parameters '
'with `estimator.get_params().keys()`.')
assert_raise_message(ValueError,
error_msg % ('fake', pipe),
pipe.set_params,
fake='nope')
# nested model check
assert_raise_message(ValueError,
error_msg % ("fake", pipe),
pipe.set_params,
fake__estimator='nope')
def test_pipeline_score_samples_pca_lof():
X = iris.data
# Test that the score_samples method is implemented on a pipeline.
# Test that the score_samples method on pipeline yields same results as
# applying transform and score_samples steps separately.
pca = PCA(svd_solver='full', n_components='mle', whiten=True)
lof = LocalOutlierFactor(novelty=True)
pipe = Pipeline([('pca', pca), ('lof', lof)])
pipe.fit(X)
# Check the shapes
assert pipe.score_samples(X).shape == (X.shape[0], )
# Check the values
lof.fit(pca.fit_transform(X))
assert_allclose(pipe.score_samples(X), lof.score_samples(pca.transform(X)))