sklearn.utils.class_weight
.compute_class_weight¶

sklearn.utils.class_weight.
compute_class_weight
(class_weight, *, classes, y)[source]¶ Estimate class weights for unbalanced datasets.
 Parameters
 class_weightdict, ‘balanced’ or None
If ‘balanced’, class weights will be given by
n_samples / (n_classes * np.bincount(y))
. If a dictionary is given, keys are classes and values are corresponding class weights. If None is given, the class weights will be uniform. classesndarray
Array of the classes occurring in the data, as given by
np.unique(y_org)
withy_org
the original class labels. yarraylike of shape (n_samples,)
Array of original class labels per sample.
 Returns
 class_weight_vectndarray of shape (n_classes,)
Array with class_weight_vect[i] the weight for ith class.
References
The “balanced” heuristic is inspired by Logistic Regression in Rare Events Data, King, Zen, 2001.