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_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
