def test_set_random_states():
# Linear Discriminant Analysis doesn't have random state: smoke test
_set_random_states(LinearDiscriminantAnalysis(), random_state=17)
clf1 = Perceptron(random_state=None)
assert clf1.random_state is None
# check random_state is None still sets
_set_random_states(clf1, None)
assert isinstance(clf1.random_state, int)
# check random_state fixes results in consistent initialisation
_set_random_states(clf1, 3)
assert isinstance(clf1.random_state, int)
clf2 = Perceptron(random_state=None)
_set_random_states(clf2, 3)
assert clf1.random_state == clf2.random_state
# nested random_state
def make_steps():
return [('sel', SelectFromModel(Perceptron(random_state=None))),
('clf', Perceptron(random_state=None))]
est1 = Pipeline(make_steps())
_set_random_states(est1, 3)
assert isinstance(est1.steps[0][1].estimator.random_state, int)
assert isinstance(est1.steps[1][1].random_state, int)
assert (est1.get_params()['sel__estimator__random_state'] !=
est1.get_params()['clf__random_state'])
# ensure multiple random_state parameters are invariant to get_params()
# iteration order
class AlphaParamPipeline(Pipeline):
def get_params(self, *args, **kwargs):
params = Pipeline.get_params(self, *args, **kwargs).items()
return OrderedDict(sorted(params))
class RevParamPipeline(Pipeline):
def get_params(self, *args, **kwargs):
params = Pipeline.get_params(self, *args, **kwargs).items()
return OrderedDict(sorted(params, reverse=True))
for cls in [AlphaParamPipeline, RevParamPipeline]:
est2 = cls(make_steps())
_set_random_states(est2, 3)
assert (est1.get_params()['sel__estimator__random_state'] ==
est2.get_params()['sel__estimator__random_state'])
assert (est1.get_params()['clf__random_state'] == est2.get_params()
['clf__random_state'])
def test_pipeline_init():
# Test the various init parameters of the pipeline.
assert_raises(TypeError, Pipeline)
# Check that we can't instantiate pipelines with objects without fit
# method
assert_raises_regex(TypeError,
'Last step of Pipeline should implement fit '
'or be the string \'passthrough\''
'.*NoFit.*',
Pipeline, [('clf', NoFit())])
# Smoke test with only an estimator
clf = NoTrans()
pipe = Pipeline([('svc', clf)])
assert (pipe.get_params(deep=True) ==
dict(svc__a=None, svc__b=None, svc=clf,
**pipe.get_params(deep=False)))
# 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 estimators are not cloned on pipeline construction
assert pipe.named_steps['anova'] is filter1
assert pipe.named_steps['svc'] is clf
# Check that we can't instantiate with non-transformers on the way
# Note that NoTrans implements fit, but not transform
assert_raises_regex(TypeError,
'All intermediate steps should be transformers'
'.*\\bNoTrans\\b.*',
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
assert_raises(ValueError, pipe.set_params, anova__C=0.1)
# Test clone
pipe2 = assert_no_warnings(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 get_params(self, *args, **kwargs):
params = Pipeline.get_params(self, *args, **kwargs).items()
return OrderedDict(sorted(params, reverse=True))