def test_balancing_get_weights_treed_single_label(self):
Y = np.array([0] * 80 + [1] * 20)
balancing = Balancing(strategy='weighting')
init_params, fit_params = balancing.get_weights(
Y, 'adaboost', None, None, None)
self.assertTrue(np.allclose(fit_params['classifier:sample_weight'],
np.array([0.4] * 80 + [1.6] * 20)))
def test_balancing_get_weights_treed_single_label(self):
Y = np.array([0] * 80 + [1] * 20)
balancing = Balancing(strategy='weighting')
init_params, fit_params = balancing.get_weights(
Y, 'adaboost', None, None, None)
self.assertTrue(np.allclose(fit_params['classifier:sample_weight'],
np.array([0.4] * 80 + [1.6] * 20)))
def test_balancing_get_weights_treed_multilabel(self):
Y = np.array([[0, 0, 0]] * 100 + [[1, 0, 0]] * 100 + [[0, 1, 0]] * 100 +
[[1, 1, 0]] * 100 + [[0, 0, 1]] * 100 + [[1, 0, 1]] * 10)
balancing = Balancing(strategy='weighting')
init_params, fit_params = balancing.get_weights(
Y, 'adaboost', None, None, None)
self.assertTrue(np.allclose(fit_params['classifier:sample_weight'],
np.array([0.4] * 500 + [4.0] * 10)))
def test_balancing_get_weights_treed_multilabel(self):
Y = np.array([[0, 0, 0]] * 100 + [[1, 0, 0]] * 100 + [[0, 1, 0]] * 100 +
[[1, 1, 0]] * 100 + [[0, 0, 1]] * 100 + [[1, 0, 1]] * 10)
balancing = Balancing(strategy='weighting')
init_params, fit_params = balancing.get_weights(
Y, 'adaboost', None, None, None)
self.assertTrue(np.allclose(fit_params['classifier:sample_weight'],
np.array([0.4] * 500 + [4.0] * 10)))
def test_balancing_get_weights_svm_sgd(self):
Y = np.array([0] * 80 + [1] * 20)
balancing = Balancing(strategy='weighting')
init_params, fit_params = balancing.get_weights(
Y, 'libsvm_svc', None, None, None)
self.assertEqual(("classifier:class_weight", "balanced"),
list(init_params.items())[0])
init_params, fit_params = balancing.get_weights(
Y, None, 'liblinear_svc_preprocessor', None, None)
self.assertEqual(("preprocessor:class_weight", "balanced"),
list(init_params.items())[0])
def test_balancing_get_weights_svm_sgd(self):
Y = np.array([0] * 80 + [1] * 20)
balancing = Balancing(strategy='weighting')
init_params, fit_params = balancing.get_weights(
Y, 'libsvm_svc', None, None, None)
self.assertEqual(("classifier:class_weight", "balanced"),
list(init_params.items())[0])
init_params, fit_params = balancing.get_weights(
Y, None, 'liblinear_svc_preprocessor', None, None)
self.assertEqual(("preprocessor:class_weight", "balanced"),
list(init_params.items())[0])
def test_balancing_get_weights_treed_single_label(self):
Y = np.array([0] * 80 + [1] * 20)
balancing = Balancing(strategy='weighting')
init_params, fit_params = balancing.get_weights(
Y, 'adaboost', None, None, None)
self.assertAlmostEqual(
np.mean(fit_params['classifier:sample_weight']), 1,
)
np.testing.assert_allclose(
fit_params['classifier:sample_weight'],
np.array([0.625] * 80 + [2.5] * 20),
)
def test_balancing_get_weights_treed_multilabel(self):
Y = np.array([[0, 0, 0]] * 100 + [[1, 0, 0]] * 100 + [[0, 1, 0]] * 100 +
[[1, 1, 0]] * 100 + [[0, 0, 1]] * 100 + [[1, 0, 1]] * 10)
balancing = Balancing(strategy='weighting')
init_params, fit_params = balancing.get_weights(
Y, 'adaboost', None, None, None)
print(fit_params['classifier:sample_weight'])
self.assertAlmostEqual(
np.mean(fit_params['classifier:sample_weight']), 1,
)
np.testing.assert_allclose(
fit_params['classifier:sample_weight'],
np.array([0.85] * 500 + [8.5] * 10),
)
def _get_pipeline(self):
steps = []
default_dataset_properties = {'target_type': 'classification'}
# Add the always active preprocessing components
steps.extend([["one_hot_encoding", OneHotEncoder()],
["imputation", Imputation()],
[
"rescaling",
rescaling_components.RescalingChoice(
default_dataset_properties)
], ["balancing", Balancing()]])
# Add the preprocessing component
steps.append([
'preprocessor',
feature_preprocessing_components.FeaturePreprocessorChoice(
default_dataset_properties)
])
# Add the classification component
steps.append([
'classifier',
classification_components.ClassifierChoice(
default_dataset_properties)
])
return steps
def _get_pipeline_steps(self, dataset_properties):
steps = []
default_dataset_properties = {'target_type': 'classification'}
if dataset_properties is not None and isinstance(
dataset_properties, dict):
default_dataset_properties.update(dataset_properties)
steps.extend(
[[
"data_preprocessing",
DataPreprocessor(dataset_properties=default_dataset_properties)
], ["balancing", Balancing()],
[
"feature_preprocessor",
feature_preprocessing_components.FeaturePreprocessorChoice(
default_dataset_properties)
],
[
'classifier',
classification_components.ClassifierChoice(
default_dataset_properties)
]])
return steps
def fit_transformer(self, X, y, fit_params=None):
if fit_params is None:
fit_params = {}
if self.configuration['balancing:strategy'] == 'weighting':
balancing = Balancing(strategy='weighting')
_init_params, _fit_params = balancing.get_weights(
y, self.configuration['classifier:__choice__'],
self.configuration['preprocessor:__choice__'], {}, {})
_init_params.update(self._init_params)
self.set_hyperparameters(configuration=self.configuration,
init_params=_init_params)
if _fit_params is not None:
fit_params.update(_fit_params)
X, fit_params = super().fit_transformer(X, y, fit_params=fit_params)
return X, fit_params
def pre_transform(self, X, y, fit_params=None):
self.num_targets = 1 if len(y.shape) == 1 else y.shape[1]
if fit_params is None:
fit_params = {}
if self.configuration['balancing:strategy'] == 'weighting':
balancing = Balancing(strategy='weighting')
_init_params, _fit_params = balancing.get_weights(
y, self.configuration['classifier:__choice__'],
self.configuration['preprocessor:__choice__'], {}, {})
self.set_hyperparameters(configuration=self.configuration,
init_params=_init_params)
if _fit_params is not None:
fit_params.update(_fit_params)
X, fit_params = super(SimpleClassificationPipeline,
self).pre_transform(X, y, fit_params=fit_params)
return X, fit_params
def _get_pipeline_steps(self):
steps = []
print(" going execute pipeline autosklearn")
default_dataset_properties = {'target_type': 'classification'}
steps.extend([
["feature_preprocessor",
feature_preprocessing_components.FeaturePreprocessorChoice(
default_dataset_properties)],
["data_preprocessing",
DataPreprocessor(dataset_properties=default_dataset_properties)],
["balancing",
Balancing()],
['classifier',
classification_components.ClassifierChoice(
default_dataset_properties)]
])
return steps