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_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