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('passthrough')
assert pipeline.steps[0] == ('passthrough', 'passthrough')
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_classes_property():
X = iris.data
y = iris.target
reg = make_pipeline(SelectKBest(k=1), LinearRegression())
reg.fit(X, y)
assert_raises(AttributeError, getattr, reg, "classes_")
clf = make_pipeline(SelectKBest(k=1), LogisticRegression(random_state=0))
assert_raises(AttributeError, getattr, clf, "classes_")
clf.fit(X, y)
assert_array_equal(clf.classes_, np.unique(y))
def test_make_pipeline_memory():
cachedir = mkdtemp()
if LooseVersion(joblib.__version__) < LooseVersion('0.12'):
# Deal with change of API in joblib
memory = joblib.Memory(cachedir=cachedir, verbose=10)
else:
memory = joblib.Memory(location=cachedir, verbose=10)
pipeline = make_pipeline(DummyTransf(), SVC(), memory=memory)
assert pipeline.memory is memory
pipeline = make_pipeline(DummyTransf(), SVC())
assert pipeline.memory is None
assert len(pipeline) == 2
shutil.rmtree(cachedir)
def test_noise_sim(sim):
p = Pipeline([('s', sim), ('c', DecisionTreeClassifier())])
p.fit(X, y)
p.predict(X)
p = make_pipeline(sim, DecisionTreeClassifier())
p.fit(X, y)
p.predict(X)
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"
assert_raise_message(TypeError,
'Unknown keyword arguments: "random_parameter"',
make_pipeline,
t1,
t2,
random_parameter='rnd')
def test_score_samples_on_pipeline_without_score_samples():
X = np.array([[1], [2]])
y = np.array([1, 2])
# Test that a pipeline does not have score_samples method when the final
# step of the pipeline does not have score_samples defined.
pipe = make_pipeline(LogisticRegression())
pipe.fit(X, y)
with pytest.raises(AttributeError,
match="'LogisticRegression' object has no attribute "
"'score_samples'"):
pipe.score_samples(X)
def test_n_features_in_pipeline():
# make sure pipelines delegate n_features_in to the first step
X = [[1, 2], [3, 4], [5, 6]]
y = [0, 1, 2]
ss = StandardScaler()
gbdt = HistGradientBoostingClassifier()
pipe = make_pipeline(ss, gbdt)
assert not hasattr(pipe, 'n_features_in_')
pipe.fit(X, y)
assert pipe.n_features_in_ == ss.n_features_in_ == 2
# if the first step has the n_features_in attribute then the pipeline also
# has it, even though it isn't fitted.
ss = StandardScaler()
gbdt = HistGradientBoostingClassifier()
pipe = make_pipeline(ss, gbdt)
ss.fit(X, y)
assert pipe.n_features_in_ == ss.n_features_in_ == 2
assert not hasattr(gbdt, 'n_features_in_')
def test_example_two():
from skclean.simulate_noise import UniformNoise
from skclean.detectors import KDN
from skclean.handlers import Filter
from skclean.pipeline import Pipeline, make_pipeline # Importing from skclean, not sklearn
from skclean.utils import load_data
X, y = load_data('breast_cancer')
clf = Pipeline([
('scale', StandardScaler()), # Scale features
('feat_sel', VarianceThreshold(.2)), # Feature selection
('detector', KDN()), # Detect mislabeled samples
('handler', Filter(SVC())
), # Filter out likely mislabeled samples and then train a SVM
])
clf_g = GridSearchCV(clf, {'detector__n_neighbors': [2, 5, 10]})
n_clf_g = make_pipeline(UniformNoise(.3),
clf_g) # Create label noise at the very first step
print(cross_val_score(n_clf_g, X, y,
cv=5).mean()) # 5-fold cross validation
def test_pipeline_param_error():
clf = make_pipeline(LogisticRegression())
with pytest.raises(ValueError,
match="Pipeline.fit does not accept "
"the sample_weight parameter"):
clf.fit([[0], [0]], [0, 1], sample_weight=[1, 1])
('d', KDN()),
('e', skclean.handlers.SampleWeight(dummy))
])
# Inside Pipeline
tmp_Handlers = []
for h in NOISE_HANDLERS:
if h.iterative: # Exclude iterative handlers
continue
ch = clone(h)
ch.detector = None
tmp_Handlers.append(ch)
preli_steps = [UniformNoise(.2, random_state=SEED), StandardScaler()]
all_comb = product(NOISE_DETECTORS, tmp_Handlers)
INSIDE_PIPE = [make_pipeline(*preli_steps + list(comb)) for comb in all_comb]
# Outside Pipe
OUTSIDE_PIPE = []
for h in NOISE_HANDLERS:
for d in NOISE_DETECTORS:
ch, d = clone(h), clone(d)
ch.detector = d
if 'random_state' in ch.get_params(): # trying to avoid flaky tests
ch.set_params(random_state=42)
OUTSIDE_PIPE.append(ch)
ALL_COMBS = INSIDE_PIPE + OUTSIDE_PIPE
ALL_ESTIMATORS = NOISE_SIMULATORS + NOISE_DETECTORS + ALL_COMBS + [PIPELINE]