def _make_transformer(self, random_state=None):
"""Make and configure a copy of the `base_transformer` attribute.
Warning: This method should be used to properly instantiate new
sub-estimators.
"""
transformer = clone(self.base_transformer_)
if random_state is not None:
_set_random_states(transformer, random_state)
return transformer
def _make_sampler_estimator(self, random_state=None):
"""Make and configure a copy of the `base_estimator_` attribute.
Warning: This method should be used to properly instantiate new
sub-estimators.
"""
estimator = clone(self.base_estimator_)
estimator.set_params(**dict(
(p, getattr(self, p)) for p in self.estimator_params))
sampler = clone(self.base_sampler_)
if random_state is not None:
_set_random_states(estimator, random_state)
_set_random_states(sampler, random_state)
return estimator, sampler
def _make_sampler_estimator(self, random_state=None):
"""Make and configure a copy of the `base_estimator_` attribute.
Warning: This method should be used to properly instantiate new
sub-estimators.
"""
estimator = clone(self.base_estimator_)
estimator.set_params(**dict((p, getattr(self, p))
for p in self.estimator_params))
sampler = clone(self.base_sampler_)
if random_state is not None:
_set_random_states(estimator, random_state)
_set_random_states(sampler, random_state)
return estimator, sampler
def _make_sampler_estimator(self, append=True, random_state=None):
"""Make and configure a copy of the `base_estimator_` attribute.
Warning: This method should be used to properly instantiate new
sub-estimators.
"""
estimator = clone(self.base_estimator_)
estimator.set_params(
**{p: getattr(self, p)
for p in self.estimator_params})
sampler = clone(self.base_sampler_)
if random_state is not None:
_set_random_states(estimator, random_state)
_set_random_states(sampler, random_state)
if append:
self.estimators_.append(estimator)
self.samplers_.append(sampler)
self.pipelines_.append(
make_pipeline(deepcopy(sampler), deepcopy(estimator)))
return estimator, sampler
def _make_sampler_estimator(self, append=True, random_state=None):
"""Make and configure a copy of the `base_estimator_` attribute.
Warning: This method should be used to properly instantiate new
sub-estimators.
"""
estimator = clone(self.base_estimator_)
estimator.set_params(**dict(
(p, getattr(self, p)) for p in self.estimator_params))
sampler = clone(self.base_sampler_)
if random_state is not None:
_set_random_states(estimator, random_state)
_set_random_states(sampler, random_state)
if append:
self.estimators_.append(estimator)
self.samplers_.append(sampler)
self.pipelines_.append(
make_pipeline(deepcopy(sampler), deepcopy(estimator)))
# do not return the indices within a pipeline
self.pipelines_[-1].named_steps['randomundersampler'].set_params(
return_indices=False)
return estimator, sampler
def test_set_random_states():
# Linear Discriminant Analysis doesn't have random state: smoke test
_set_random_states(LinearDiscriminantAnalysis(), random_state=17)
clf1 = Perceptron(tol=1e-3, random_state=None)
assert_equal(clf1.random_state, None)
# check random_state is None still sets
_set_random_states(clf1, None)
assert_true(isinstance(clf1.random_state, int))
# check random_state fixes results in consistent initialisation
_set_random_states(clf1, 3)
assert_true(isinstance(clf1.random_state, int))
clf2 = Perceptron(tol=1e-3, random_state=None)
_set_random_states(clf2, 3)
assert_equal(clf1.random_state, clf2.random_state)
# nested random_state
def make_steps():
return [('sel', SelectFromModel(Perceptron(tol=1e-3,
random_state=None))),
('clf', Perceptron(tol=1e-3, random_state=None))]
est1 = Pipeline(make_steps())
_set_random_states(est1, 3)
assert_true(isinstance(est1.steps[0][1].estimator.random_state, int))
assert_true(isinstance(est1.steps[1][1].random_state, int))
assert_not_equal(est1.get_params()['sel__estimator__random_state'],
est1.get_params()['clf__random_state'])
# ensure multiple random_state paramaters 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_equal(est1.get_params()['sel__estimator__random_state'],
est2.get_params()['sel__estimator__random_state'])
assert_equal(est1.get_params()['clf__random_state'],
est2.get_params()['clf__random_state'])
