def test_get_available_components(self):
# Target type
for target_type, num_values in [('classification', 15),
('regression', 14)]:
data_properties = {'target_type': target_type}
available_components = fp.FeaturePreprocessorChoice(data_properties)\
.get_available_components(data_properties)
self.assertEqual(len(available_components), num_values)
# Multiclass
data_properties = {'target_type': 'classification',
'multiclass': True}
available_components = fp.FeaturePreprocessorChoice(data_properties) \
.get_available_components(data_properties)
self.assertEqual(len(available_components), 15)
# Multilabel
data_properties = {'target_type': 'classification',
'multilabel': True}
available_components = fp.FeaturePreprocessorChoice(data_properties) \
.get_available_components(data_properties)
self.assertEqual(len(available_components), 12)
def _get_pipeline(self, init_params=None):
steps = []
default_dataset_properties = {'target_type': 'regression'}
# Add the always active preprocessing components
if init_params is not None and 'one_hot_encoding' in init_params:
ohe_init_params = init_params['one_hot_encoding']
if 'categorical_features' in ohe_init_params:
categorical_features = ohe_init_params['categorical_features']
else:
categorical_features = None
steps.extend(
[["categorical_encoding", OHEChoice(default_dataset_properties)],
["imputation", Imputation()],
["variance_threshold", VarianceThreshold()],
["rescaling", rescaling_components.RescalingChoice(
default_dataset_properties)]])
# Add the preprocessing component
steps.append(['preprocessor',
feature_preprocessing_components.FeaturePreprocessorChoice(
default_dataset_properties)])
# Add the classification component
steps.append(['regressor',
regression_components.RegressorChoice(
default_dataset_properties)])
return steps
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 _get_pipeline_steps(self, dataset_properties, init_params=None):
steps = []
default_dataset_properties = {'target_type': 'regression'}
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)
],
[
'feature_preprocessor',
feature_preprocessing_components.FeaturePreprocessorChoice(
default_dataset_properties)
],
[
'regressor',
regression_components.RegressorChoice(
default_dataset_properties)
]])
return steps
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
