yikit.metrics package

yikit.metrics package#

Evaluation metrics for machine learning models.

This module provides various metrics for evaluating regression models, including root mean squared error and log-likelihood for NGBoost.

yikit.metrics.log_likelihood(estimator, X, y)#

Compute the negative log-likelihood for an NGBoost estimator.

Parameters:

  • estimator (NGBRegressor or NGBClassifier) – A fitted NGBoost regressor or classifier.

  • X (array-like of shape (n_samples, n_features)) – Input samples for which to compute the log-likelihood.

  • y (array-like of shape (n_samples,)) – True target values or class labels.

Returns:

The negative log-likelihood computed by the estimator. Returns -estimator.score(X, y).

Return type:

float

Raises:

TypeError – If the estimator is not an instance of NGBRegressor or NGBClassifier.

Notes

This function is only supported for NGBoost estimators.

yikit.metrics.root_mean_squared_error(y_true, y_pred, **kwargs)#

Compute the root mean squared error for a set of predictions.

Parameters:

  • y_true (array-like of shape (n_samples,)) – True target values.

  • y_pred (array-like of shape (n_samples,)) – Predicted target values.

  • **kwargs – Additional keyword arguments to pass to the root mean squared error function.

Returns:

The root mean squared error computed by the estimator.

Return type:

float

Notes

This function is a wrapper around the root mean squared error function from the scikit-learn library. If the root mean squared error function is not available, the mean squared error function is used instead.

Contents