def test_Pipeline_random_state():
steps = [('transform', RandomIntervalFeatureExtractor(features=[np.mean])),
('clf', DecisionTreeClassifier())]
pipe = Pipeline(steps)
# Check that pipe is initiated without random_state
assert pipe.random_state is None
assert pipe.get_params()['random_state'] is None
# Check that all components are initiated without random_state
for step in pipe.steps:
assert step[1].random_state is None
assert step[1].get_params()['random_state'] is None
# Check that if random state is set, it's set to itself and all its random components
rs = 1234
pipe.set_params(**{'random_state': rs})
assert pipe.random_state == rs
assert pipe.get_params()['random_state'] == rs
for step in pipe.steps:
assert step[1].random_state == rs
assert step[1].get_params()['random_state'] == rs
# Check specific results
X_train, y_train = load_gunpoint(return_X_y=True)
X_test, y_test = load_gunpoint("TEST", return_X_y=True)
steps = [
('segment', RandomIntervalSegmenter(n_intervals=3)),
('extract',
RowwiseTransformer(FunctionTransformer(func=np.mean,
validate=False))),
('clf', DecisionTreeClassifier())
]
pipe = Pipeline(steps, random_state=rs)
pipe.fit(X_train, y_train)
y_pred_first = pipe.predict(X_test)
N_ITER = 10
for _ in range(N_ITER):
pipe = Pipeline(steps, random_state=rs)
pipe.fit(X_train, y_train)
y_pred = pipe.predict(X_test)
np.testing.assert_array_equal(y_pred_first, y_pred)
def test_Pipeline_check_input():
steps = [('transform', RandomIntervalFeatureExtractor(features=[np.mean]))]
pipe = Pipeline(steps)
# Check that pipe is initiated without check_input set to True
assert pipe.check_input is True
assert pipe.get_params()['check_input'] is True
# Check that all components are initiated with check_input set to True
for step in pipe.steps:
assert step[1].check_input is True
assert step[1].get_params()['check_input'] is True
# Check that if random state is set, it's set to itself and all its random components
ci = False
pipe.set_params(**{'check_input': ci})
assert pipe.check_input == ci
assert pipe.get_params()['check_input'] == ci
for step in pipe.steps:
assert step[1].check_input == ci
assert step[1].get_params()['check_input'] == ci
def __init__(self,
base_estimator=None,
n_estimators=500,
criterion='mse',
max_depth=None,
min_samples_split=2,
min_samples_leaf=1,
min_weight_fraction_leaf=0.,
max_features=None,
max_leaf_nodes=None,
min_impurity_decrease=0.,
min_impurity_split=None,
bootstrap=False,
oob_score=False,
n_jobs=None,
random_state=None,
verbose=0,
warm_start=False,
check_input=True):
if base_estimator is None:
features = [np.mean, np.std, time_series_slope]
steps = [('transform',
RandomIntervalFeatureExtractor(n_intervals='sqrt',
features=features)),
('clf', DecisionTreeRegressor())]
base_estimator = Pipeline(steps)
elif not isinstance(base_estimator, Pipeline):
raise ValueError(
'Base estimator must be pipeline with transforms.')
elif not isinstance(base_estimator.steps[-1][1],
DecisionTreeRegressor):
raise ValueError(
'Last step in base estimator pipeline must be DecisionTreeRegressor.'
)
# Assign values, even though passed on to base estimator below, necessary here for cloning
self.criterion = criterion
self.max_depth = max_depth
self.min_samples_split = min_samples_split
self.min_samples_leaf = min_samples_leaf
self.min_weight_fraction_leaf = min_weight_fraction_leaf
self.max_features = max_features
self.max_leaf_nodes = max_leaf_nodes
self.min_impurity_decrease = min_impurity_decrease
self.min_impurity_split = min_impurity_split
# Rename estimator params according to name in pipeline.
estimator = base_estimator.steps[-1][0]
estimator_params = {
"criterion": criterion,
"max_depth": max_depth,
"min_samples_split": min_samples_split,
"min_samples_leaf": min_samples_leaf,
"min_weight_fraction_leaf": min_weight_fraction_leaf,
"max_features": max_features,
"max_leaf_nodes": max_leaf_nodes,
"min_impurity_decrease": min_impurity_decrease,
"min_impurity_split": min_impurity_split,
}
estimator_params = {
f'{estimator}__{pname}': pval
for pname, pval in estimator_params.items()
}
# Pass on params.
super(TimeSeriesForestRegressor, self).__init__(
base_estimator=base_estimator,
n_estimators=n_estimators,
estimator_params=tuple(estimator_params.keys()),
bootstrap=bootstrap,
oob_score=oob_score,
n_jobs=n_jobs,
random_state=random_state,
verbose=verbose,
warm_start=warm_start,
)
# Assign random state to pipeline.
base_estimator.set_params(**{
'random_state': random_state,
'check_input': False
})
# Store renamed estimator params.
for pname, pval in estimator_params.items():
self.__setattr__(pname, pval)
self.check_input = check_input