def test_pipeline_methods_preprocessing_svm():
# Test the various methods of the pipeline (preprocessing + svm).
iris = load_iris()
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_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
iris = load_iris()
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_pipeline_wrong_memory():
# Test that an error is raised when memory is not a string or a Memory
# instance
iris = load_iris()
X = iris.data
y = iris.target
# Define memory as an integer
memory = 1
cached_pipe = Pipeline([('transf', DummyTransf()), ('svc', SVC())],
memory=memory)
error_regex = ("'memory' should either be a string or a joblib.Memory"
" instance, got 'memory=1' instead.")
with raises(ValueError, match=error_regex):
cached_pipe.fit(X, y)
def _validate_estimator(self, default=DecisionTreeClassifier()):
"""
Check the estimator and the n_estimator attribute, set the
'base_estimator_' attribute.
:param default: classifier object used if base_estimator=None
:return:
"""
""""""
if not isinstance(self.n_estimators, (numbers.Integral, np.integer)):
raise ValueError("n_estimators must be an integer, "
"got {0}.".format(type(self.n_estimators)))
if self.n_estimators <= 0:
raise ValueError("n_estimators must be greater than zero, "
"got {0}.".format(self.n_estimators))
if self.base_estimator is not None:
base_estimator = clone(self.base_estimator)
else:
base_estimator = clone(default)
if isinstance(self.ratio, dict) and self.ratio != {}:
raise ValueError(
"'dict' type cannot be accepted for ratio in this class; "
"use alternative options")
self.base_estimator_ = Pipeline([
('sampler',
SMOTE(ratio=self.ratio,
k_neighbors=self.k_neighbors,
random_state=self.random_state)),
('classifier', base_estimator)
])
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_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
with raises(TypeError, match="unexpected keyword argument"):
pipe.score(X, sample_weight=np.array([2, 3]))
def test_pipeline_transform():
# Test whether pipeline works with a transformer at the end.
# Also test pipeline.transform and pipeline.inverse_transform
iris = load_iris()
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)])
error_regex = "'PCA' object has no attribute 'fit_predict'"
with raises(AttributeError, match=error_regex):
getattr(pipe, 'fit_predict')
def test_pipeline_with_step_that_it_is_pipeline():
# Test the various methods of the pipeline (anova).
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)
# Test with RandomUnderSampling + Anova + LogisticRegression
clf = LogisticRegression()
rus = RandomUnderSampler(random_state=0)
filter1 = SelectKBest(f_classif, k=2)
pipe1 = Pipeline([('rus', rus), ('anova', filter1)])
with raises(TypeError):
Pipeline([('pipe1', pipe1), ('logistic', clf)])
def test_pipeline_sample_transform():
# Test whether pipeline works with a sampler at the end.
# Also test pipeline.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)
pca = PCA()
pca2 = PCA()
pipeline = Pipeline([('pca', pca), ('rus', rus), ('pca2', pca2)])
pipeline.fit(X, y).transform(X)
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
with raises(TypeError, match="unexpected keyword argument"):
pipe.fit(None, None, clf__bad=True)
def test_pipeline_raise_set_params_error():
# Test pipeline raises set params error message for nested models.
pipe = Pipeline([('cls', LinearRegression())])
with raises(ValueError, match="Invalid parameter"):
pipe.set_params(fake='nope')
# nested model check
with raises(ValueError, match="Invalid parameter"):
pipe.set_params(fake__estimator='nope')
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
iris = load_iris()
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_with_step_that_implements_both_sample_and_transform():
# Test the various methods of the pipeline (anova).
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()
with raises(TypeError):
Pipeline([('step', FitTransformSample()), ('logistic', clf)])
def test_pipeline_sample():
# Test whether pipeline works with a sampler at the end.
# Also test pipeline.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)
pipeline = Pipeline([('rus', rus)])
# test transform and fit_transform:
X_trans, y_trans = pipeline.fit(X, y).sample(X, y)
X_trans2, y_trans2 = pipeline.fit_sample(X, y)
X_trans3, y_trans3 = rus.fit_sample(X, y)
assert_allclose(X_trans, X_trans2, rtol=R_TOL)
assert_allclose(X_trans, X_trans3, rtol=R_TOL)
assert_allclose(y_trans, y_trans2, rtol=R_TOL)
assert_allclose(y_trans, y_trans3, rtol=R_TOL)
pca = PCA()
pipeline = Pipeline([('pca', PCA()),
('rus', rus)])
X_trans, y_trans = pipeline.fit(X, y).sample(X, y)
X_pca = pca.fit_transform(X)
X_trans2, y_trans2 = rus.fit_sample(X_pca, y)
# We round the value near to zero. It seems that PCA has some issue
# with that
X_trans[np.bitwise_and(X_trans < R_TOL, X_trans > -R_TOL)] = 0
X_trans2[np.bitwise_and(X_trans2 < R_TOL, X_trans2 > -R_TOL)] = 0
assert_allclose(X_trans, X_trans2, rtol=R_TOL)
assert_allclose(y_trans, y_trans2, rtol=R_TOL)
def test_set_pipeline_step_none():
# Test setting Pipeline steps to None
X = np.array([[1]])
y = np.array([1])
mult2 = Mult(mult=2)
mult3 = Mult(mult=3)
mult5 = Mult(mult=5)
def make():
return Pipeline([('m2', mult2), ('m3', mult3), ('last', mult5)])
pipeline = make()
exp = 2 * 3 * 5
assert_array_equal([[exp]], pipeline.fit_transform(X, y))
assert_array_equal([exp], pipeline.fit(X).predict(X))
assert_array_equal(X, pipeline.inverse_transform([[exp]]))
pipeline.set_params(m3=None)
exp = 2 * 5
assert_array_equal([[exp]], pipeline.fit_transform(X, y))
assert_array_equal([exp], pipeline.fit(X).predict(X))
assert_array_equal(X, pipeline.inverse_transform([[exp]]))
expected_params = {'steps': pipeline.steps,
'm2': mult2,
'm3': None,
'last': mult5,
'memory': None,
'm2__mult': 2,
'last__mult': 5}
assert pipeline.get_params(deep=True) == expected_params
pipeline.set_params(m2=None)
exp = 5
assert_array_equal([[exp]], pipeline.fit_transform(X, y))
assert_array_equal([exp], pipeline.fit(X).predict(X))
assert_array_equal(X, pipeline.inverse_transform([[exp]]))
# for other methods, ensure no AttributeErrors on None:
other_methods = ['predict_proba', 'predict_log_proba',
'decision_function', 'transform', 'score']
for method in other_methods:
getattr(pipeline, method)(X)
pipeline.set_params(m2=mult2)
exp = 2 * 5
assert_array_equal([[exp]], pipeline.fit_transform(X, y))
assert_array_equal([exp], pipeline.fit(X).predict(X))
assert_array_equal(X, pipeline.inverse_transform([[exp]]))
pipeline = make()
pipeline.set_params(last=None)
# mult2 and mult3 are active
exp = 6
pipeline.fit(X, y)
pipeline.transform(X)
assert_array_equal([[exp]], pipeline.fit(X, y).transform(X))
assert_array_equal([[exp]], pipeline.fit_transform(X, y))
assert_array_equal(X, pipeline.inverse_transform([[exp]]))
with raises(AttributeError, match="has no attribute 'predict'"):
getattr(pipeline, 'predict')
# Check None step at construction time
exp = 2 * 5
pipeline = Pipeline([('m2', mult2), ('m3', None), ('last', mult5)])
assert_array_equal([[exp]], pipeline.fit_transform(X, y))
assert_array_equal([exp], pipeline.fit(X).predict(X))
assert_array_equal(X, pipeline.inverse_transform([[exp]]))
def test_pipeline_methods_anova_rus():
# Test the various methods of the pipeline (anova).
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)
# Test with RandomUnderSampling + Anova + LogisticRegression
clf = LogisticRegression()
rus = RandomUnderSampler(random_state=0)
filter1 = SelectKBest(f_classif, k=2)
pipe = Pipeline([('rus', rus), ('anova', filter1), ('logistic', clf)])
pipe.fit(X, y)
pipe.predict(X)
pipe.predict_proba(X)
pipe.predict_log_proba(X)
pipe.score(X, y)
def test_pipeline_methods_rus_pca_svm():
# Test the various methods of the pipeline (pca + svm).
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)
# Test with PCA + SVC
clf = SVC(probability=True, random_state=0)
pca = PCA()
rus = RandomUnderSampler(random_state=0)
pipe = Pipeline([('rus', rus), ('pca', pca), ('svc', clf)])
pipe.fit(X, y)
pipe.predict(X)
pipe.predict_proba(X)
pipe.predict_log_proba(X)
pipe.score(X, y)
def test_pipeline_memory_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)
cachedir = mkdtemp()
try:
memory = Memory(cachedir=cachedir, verbose=10)
# Test with Transformer + SVC
clf = SVC(probability=True, random_state=0)
transf = DummySampler()
pipe = Pipeline([('transf', clone(transf)), ('svc', clf)])
cached_pipe = Pipeline([('transf', transf), ('svc', clf)],
memory=memory)
# Memoize the transformer at the first fit
cached_pipe.fit(X, y)
pipe.fit(X, y)
# Get the time stamp of the tranformer in the cached pipeline
expected_ts = cached_pipe.named_steps['transf'].timestamp_
# Check that cached_pipe and pipe yield identical results
assert_array_equal(pipe.predict(X), cached_pipe.predict(X))
assert_array_equal(pipe.predict_proba(X), cached_pipe.predict_proba(X))
assert_array_equal(pipe.predict_log_proba(X),
cached_pipe.predict_log_proba(X))
assert_array_equal(pipe.score(X, y), cached_pipe.score(X, y))
assert_array_equal(pipe.named_steps['transf'].means_,
cached_pipe.named_steps['transf'].means_)
assert not hasattr(transf, 'means_')
# Check that we are reading the cache while fitting
# a second time
cached_pipe.fit(X, y)
# Check that cached_pipe and pipe yield identical results
assert_array_equal(pipe.predict(X), cached_pipe.predict(X))
assert_array_equal(pipe.predict_proba(X), cached_pipe.predict_proba(X))
assert_array_equal(pipe.predict_log_proba(X),
cached_pipe.predict_log_proba(X))
assert_array_equal(pipe.score(X, y), cached_pipe.score(X, y))
assert_array_equal(pipe.named_steps['transf'].means_,
cached_pipe.named_steps['transf'].means_)
assert cached_pipe.named_steps['transf'].timestamp_ == expected_ts
# Create a new pipeline with cloned estimators
# Check that even changing the name step does not affect the cache hit
clf_2 = SVC(probability=True, random_state=0)
transf_2 = DummySampler()
cached_pipe_2 = Pipeline([('transf_2', transf_2), ('svc', clf_2)],
memory=memory)
cached_pipe_2.fit(X, y)
# Check that cached_pipe and pipe yield identical results
assert_array_equal(pipe.predict(X), cached_pipe_2.predict(X))
assert_array_equal(pipe.predict_proba(X),
cached_pipe_2.predict_proba(X))
assert_array_equal(pipe.predict_log_proba(X),
cached_pipe_2.predict_log_proba(X))
assert_array_equal(pipe.score(X, y), cached_pipe_2.score(X, y))
assert_array_equal(pipe.named_steps['transf'].means_,
cached_pipe_2.named_steps['transf_2'].means_)
assert cached_pipe_2.named_steps['transf_2'].timestamp_ == expected_ts
finally:
shutil.rmtree(cachedir)
def test_pipeline_memory_transformer():
iris = load_iris()
X = iris.data
y = iris.target
cachedir = mkdtemp()
try:
memory = Memory(cachedir=cachedir, verbose=10)
# Test with Transformer + SVC
clf = SVC(probability=True, random_state=0)
transf = DummyTransf()
pipe = Pipeline([('transf', clone(transf)), ('svc', clf)])
cached_pipe = Pipeline([('transf', transf), ('svc', clf)],
memory=memory)
# Memoize the transformer at the first fit
cached_pipe.fit(X, y)
pipe.fit(X, y)
# Get the time stamp of the tranformer in the cached pipeline
expected_ts = cached_pipe.named_steps['transf'].timestamp_
# Check that cached_pipe and pipe yield identical results
assert_array_equal(pipe.predict(X), cached_pipe.predict(X))
assert_array_equal(pipe.predict_proba(X), cached_pipe.predict_proba(X))
assert_array_equal(pipe.predict_log_proba(X),
cached_pipe.predict_log_proba(X))
assert_array_equal(pipe.score(X, y), cached_pipe.score(X, y))
assert_array_equal(pipe.named_steps['transf'].means_,
cached_pipe.named_steps['transf'].means_)
assert not hasattr(transf, 'means_')
# Check that we are reading the cache while fitting
# a second time
cached_pipe.fit(X, y)
# Check that cached_pipe and pipe yield identical results
assert_array_equal(pipe.predict(X), cached_pipe.predict(X))
assert_array_equal(pipe.predict_proba(X), cached_pipe.predict_proba(X))
assert_array_equal(pipe.predict_log_proba(X),
cached_pipe.predict_log_proba(X))
assert_array_equal(pipe.score(X, y), cached_pipe.score(X, y))
assert_array_equal(pipe.named_steps['transf'].means_,
cached_pipe.named_steps['transf'].means_)
assert cached_pipe.named_steps['transf'].timestamp_ == expected_ts
# Create a new pipeline with cloned estimators
# Check that even changing the name step does not affect the cache hit
clf_2 = SVC(probability=True, random_state=0)
transf_2 = DummyTransf()
cached_pipe_2 = Pipeline([('transf_2', transf_2), ('svc', clf_2)],
memory=memory)
cached_pipe_2.fit(X, y)
# Check that cached_pipe and pipe yield identical results
assert_array_equal(pipe.predict(X), cached_pipe_2.predict(X))
assert_array_equal(pipe.predict_proba(X),
cached_pipe_2.predict_proba(X))
assert_array_equal(pipe.predict_log_proba(X),
cached_pipe_2.predict_log_proba(X))
assert_array_equal(pipe.score(X, y), cached_pipe_2.score(X, y))
assert_array_equal(pipe.named_steps['transf'].means_,
cached_pipe_2.named_steps['transf_2'].means_)
assert cached_pipe_2.named_steps['transf_2'].timestamp_ == expected_ts
finally:
shutil.rmtree(cachedir)
def test_pipeline_methods_anova():
# Test the various methods of the pipeline (anova).
iris = load_iris()
X = iris.data
y = iris.target
# Test with Anova + LogisticRegression
clf = LogisticRegression()
filter1 = SelectKBest(f_classif, k=2)
pipe = Pipeline([('anova', filter1), ('logistic', clf)])
pipe.fit(X, y)
pipe.predict(X)
pipe.predict_proba(X)
pipe.predict_log_proba(X)
pipe.score(X, y)
def make():
return Pipeline([('m2', mult2), ('m3', mult3), ('last', mult5)])
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', ())])
with raises(TypeError):
pipeline.fit([[1]], [1])
with raises(TypeError):
pipeline.fit_transform([[1]], [1])
def test_pipeline_init():
# Test the various init parameters of the pipeline.
with raises(TypeError):
Pipeline()
# Check that we can't instantiate pipelines with objects without fit
# method
error_regex = 'Last step of Pipeline should implement fit. .*NoFit.*'
with raises(TypeError, match=error_regex):
Pipeline([('clf', NoFit())])
# Smoke test with only an estimator
clf = NoTrans()
pipe = Pipeline([('svc', clf)])
expected = dict(svc__a=None, svc__b=None, svc=clf,
**pipe.get_params(deep=False))
assert pipe.get_params(deep=True) == expected
# Check that params are set
pipe.set_params(svc__a=0.1)
assert clf.a == 0.1
assert clf.b is None
# Smoke test the repr:
repr(pipe)
# Test with two objects
clf = SVC()
filter1 = SelectKBest(f_classif)
pipe = Pipeline([('anova', filter1), ('svc', clf)])
# Check that we can't instantiate with non-transformers on the way
# Note that NoTrans implements fit, but not transform
error_regex = 'implement fit and transform or sample'
with raises(TypeError, match=error_regex):
Pipeline([('t', NoTrans()), ('svc', clf)])
# Check that params are set
pipe.set_params(svc__C=0.1)
assert clf.C == 0.1
# Smoke test the repr:
repr(pipe)
# Check that params are not set when naming them wrong
with raises(ValueError):
pipe.set_params(anova__C=0.1)
# Test clone
pipe2 = clone(pipe)
assert not pipe.named_steps['svc'] is pipe2.named_steps['svc']
# Check that apart from estimators, the parameters are the same
params = pipe.get_params(deep=True)
params2 = pipe2.get_params(deep=True)
for x in pipe.get_params(deep=False):
params.pop(x)
for x in pipe2.get_params(deep=False):
params2.pop(x)
# Remove estimators that where copied
params.pop('svc')
params.pop('anova')
params2.pop('svc')
params2.pop('anova')
assert params == params2
def test_pipeline_methods_pca_svm():
# Test the various methods of the pipeline (pca + svm).
iris = load_iris()
X = iris.data
y = iris.target
# Test with PCA + SVC
clf = SVC(probability=True, random_state=0)
pca = PCA(svd_solver='full', n_components='mle', whiten=True)
pipe = Pipeline([('pca', pca), ('svc', clf)])
pipe.fit(X, y)
pipe.predict(X)
pipe.predict_proba(X)
pipe.predict_log_proba(X)
pipe.score(X, y)