Extending Auto-Sklearn with Data Preprocessor Component

The following example demonstrates how to turn off data preprocessing step in auto-skearn.

import autosklearn.classification
import autosklearn.pipeline.components.data_preprocessing
import sklearn.metrics
from ConfigSpace.configuration_space import ConfigurationSpace
from autosklearn.pipeline.components.base import AutoSklearnPreprocessingAlgorithm
from autosklearn.pipeline.constants import SPARSE, DENSE, UNSIGNED_DATA, INPUT
from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split

Create NoPreprocessing component for auto-sklearn

class NoPreprocessing(AutoSklearnPreprocessingAlgorithm):

    def __init__(self, **kwargs):
        """ This preprocessors does not change the data """
        # Some internal checks makes sure parameters are set
        for key, val in kwargs.items():
            setattr(self, key, val)

    def fit(self, X, Y=None):
        return self

    def transform(self, X):
        return X

    def get_properties(dataset_properties=None):
        return {
            'shortname': 'NoPreprocessing',
            'name': 'NoPreprocessing',
            'handles_regression': True,
            'handles_classification': True,
            'handles_multiclass': True,
            'handles_multilabel': True,
            'handles_multioutput': True,
            'is_deterministic': True,
            'input': (SPARSE, DENSE, UNSIGNED_DATA),
            'output': (INPUT,)

    def get_hyperparameter_search_space(dataset_properties=None):
        return ConfigurationSpace()  # Return an empty configuration as there is None

# Add NoPreprocessing component to auto-sklearn.

Create dataset

X, y = load_breast_cancer(return_X_y=True)
X_train, X_test, y_train, y_test = train_test_split(X, y)

Fit the model without performing data preprocessing

clf = autosklearn.classification.AutoSklearnClassifier(
        'data_preprocessor': ['NoPreprocessing']
    # Bellow two flags are provided to speed up calculations
    # Not recommended for a real implementation
    smac_scenario_args={'runcount_limit': 5},
clf.fit(X_train, y_train)

# To check that models were found without issue when running examples
assert len(clf.get_models_with_weights()) > 0


auto-sklearn results:
  Dataset name: 2613be54-419a-11ec-8a32-1b4c952643c3
  Metric: accuracy
  Best validation score: 0.936170
  Number of target algorithm runs: 5
  Number of successful target algorithm runs: 5
  Number of crashed target algorithm runs: 0
  Number of target algorithms that exceeded the time limit: 0
  Number of target algorithms that exceeded the memory limit: 0