mojolearn.f_classif

mojolearn.f_classif(X, y)

Compute the ANOVA F-value of each feature against the class labels.

Follows scikit-learn’s f_classif. As in scikit-learn, a constant feature (or a single class) scores NaN with p-value NaN, and a feature that is constant within every class but not across them scores +inf with p-value 0. Computation is float32.

Parameters:

• X (array-like of shape (n_samples, n_features)) – Feature matrix.

• y (array-like of shape (n_samples,)) – Class labels.

Returns:

• f_statistic (array of shape (n_features,)) – F-value of each feature.

• p_values (array of shape (n_features,)) – p-value of each F-value.

Examples

>>> import numpy as np, mojolearn
>>> rng = np.random.default_rng(0)
>>> X = rng.random((1000, 8), dtype=np.float32)
>>> y = rng.integers(0, 3, 1000)
>>> F, p = mojolearn.f_classif(X, y)