Classes

class ResidualBoostingRegressor (estimator, n_estimators=10)

Base class for all estimators in scikit-learn.

Inheriting from this class provides default implementations of:

• setting and getting parameters used by GridSearchCV and friends;
• textual and HTML representation displayed in terminals and IDEs;
• estimator serialization;
• parameters validation;
• data validation;
• feature names validation.

Read more in the :ref:User Guide <rolling_your_own_estimator>.

Notes

All estimators should specify all the parameters that can be set at the class level in their __init__ as explicit keyword arguments (no *args or **kwargs).

Examples

>>> import numpy as np
>>> from sklearn.base import BaseEstimator
>>> class MyEstimator(BaseEstimator):
...     def __init__(self, *, param=1):
...         self.param = param
...     def fit(self, X, y=None):
...         self.is_fitted_ = True
...         return self
...     def predict(self, X):
...         return np.full(shape=X.shape[0], fill_value=self.param)
>>> estimator = MyEstimator(param=2)
>>> estimator.get_params()
{'param': 2}
>>> X = np.array([[1, 2], [2, 3], [3, 4]])
>>> y = np.array([1, 0, 1])
>>> estimator.fit(X, y).predict(X)
array([2, 2, 2])
>>> estimator.set_params(param=3).fit(X, y).predict(X)
array([3, 3, 3])

A meta-estimator that fits a base estimator to the residuals of the previous estimators.

Parameters

estimator : estimator

The estimator to fit on the residual of the previous step.

n_estimators : int, default=10

The number of estimators to fit.

Expand source code

class ResidualBoostingRegressor(BaseEstimator, RegressorMixin):
    def __init__(self, estimator, n_estimators=10):
        """
        A meta-estimator that fits a base estimator to the residuals of the
        previous estimators.

        Parameters
        ----------
        estimator : estimator
            The estimator to fit on the residual of the previous step.
        n_estimators : int, default=10
            The number of estimators to fit.
        """
        self.estimator = estimator
        self.n_estimators = n_estimators

    def fit(self, X, y):
        """
        Fit the ensemble of base estimators on the training data.

        Parameters
        ----------
        X : array-like of shape (n_samples, n_features)
            Training data.
        y : array-like of shape (n_samples,)
            Target values.

        Returns
        -------
        self : ResidualBoostingRegressor
            The fitted model.
        """
        # Check that X and y have correct shape
        X, y = check_X_y(X, y)

        self.estimators_ = []
        current_prediction = np.zeros(y.shape)

        for _ in range(self.n_estimators):
            residual = y - current_prediction
            estimator = clone(self.estimator)
            estimator.fit(X, residual)
            self.estimators_.append(estimator)
            current_prediction += estimator.predict(X)

        return self

    def predict(self, X):
        """
        Predict regression target for X.

        Parameters
        ----------
        X : array-like of shape (n_samples, n_features)
            The input samples.

        Returns
        -------
        y_pred : ndarray of shape (n_samples,)
            The predicted values.
        """
        # Check is fit had been called
        check_is_fitted(self)
        # Input validation
        X = check_array(X)

        predictions = sum(estimator.predict(X)
                          for estimator in self.estimators_)
        return predictions

Ancestors

• sklearn.base.BaseEstimator
• sklearn.utils._estimator_html_repr._HTMLDocumentationLinkMixin
• sklearn.utils._metadata_requests._MetadataRequester
• sklearn.base.RegressorMixin

Methods

def fit(self, X, y)

Fit the ensemble of base estimators on the training data.

Parameters

X : array-like of shape (n_samples, n_features)

Training data.

y : array-like of shape (n_samples,)

Target values.

Returns

self : ResidualBoostingRegressor

The fitted model.

Expand source code

def fit(self, X, y):
    """
    Fit the ensemble of base estimators on the training data.

    Parameters
    ----------
    X : array-like of shape (n_samples, n_features)
        Training data.
    y : array-like of shape (n_samples,)
        Target values.

    Returns
    -------
    self : ResidualBoostingRegressor
        The fitted model.
    """
    # Check that X and y have correct shape
    X, y = check_X_y(X, y)

    self.estimators_ = []
    current_prediction = np.zeros(y.shape)

    for _ in range(self.n_estimators):
        residual = y - current_prediction
        estimator = clone(self.estimator)
        estimator.fit(X, residual)
        self.estimators_.append(estimator)
        current_prediction += estimator.predict(X)

    return self

def predict(self, X)

Predict regression target for X.

Parameters

X : array-like of shape (n_samples, n_features)

The input samples.

Returns

y_pred : ndarray of shape (n_samples,)

The predicted values.

Expand source code

def predict(self, X):
    """
    Predict regression target for X.

    Parameters
    ----------
    X : array-like of shape (n_samples, n_features)
        The input samples.

    Returns
    -------
    y_pred : ndarray of shape (n_samples,)
        The predicted values.
    """
    # Check is fit had been called
    check_is_fitted(self)
    # Input validation
    X = check_array(X)

    predictions = sum(estimator.predict(X)
                      for estimator in self.estimators_)
    return predictions

class SimpleBaggingRegressor (estimator, n_estimators=10, random_state=None)

Expand source code

class SimpleBaggingRegressor:
    def __init__(self, estimator, n_estimators=10, random_state=None):
        self.estimator = estimator
        self.n_estimators = n_estimators
        self.random_state = random_state

    def fit(self, X, y):
        np.random.seed(self.random_state)
        self.estimators_ = []

        rng = np.random.default_rng(self.random_state)
        for _ in range(self.n_estimators):
            # Simple bootstrap sampling
            # sample_indices = np.random.choice(
            # range(X.shape[0]), size=X.shape[0], replace=True)
            sample_indices = rng.choice(
                range(X.shape[0]), size=X.shape[0], replace=True)
            X_sample = X[sample_indices]
            y_sample = y[sample_indices]

            # Fit a base estimator
            # estimator = DecisionTreeRegressor()
            estimator = clone(self.estimator)
            estimator.fit(X_sample, y_sample)
            self.estimators_.append(estimator)

    def predict(self, X):
        # Collect predictions from each base estimator
        predictions = np.array([estimator.predict(X)
                               for estimator in self.estimators_])

        # Aggregate predictions
        return np.mean(predictions, axis=0)

Methods

def fit(self, X, y)

Expand source code

def fit(self, X, y):
    np.random.seed(self.random_state)
    self.estimators_ = []

    rng = np.random.default_rng(self.random_state)
    for _ in range(self.n_estimators):
        # Simple bootstrap sampling
        # sample_indices = np.random.choice(
        # range(X.shape[0]), size=X.shape[0], replace=True)
        sample_indices = rng.choice(
            range(X.shape[0]), size=X.shape[0], replace=True)
        X_sample = X[sample_indices]
        y_sample = y[sample_indices]

        # Fit a base estimator
        # estimator = DecisionTreeRegressor()
        estimator = clone(self.estimator)
        estimator.fit(X_sample, y_sample)
        self.estimators_.append(estimator)

def predict(self, X)

Expand source code

def predict(self, X):
    # Collect predictions from each base estimator
    predictions = np.array([estimator.predict(X)
                           for estimator in self.estimators_])

    # Aggregate predictions
    return np.mean(predictions, axis=0)