autointent.metrics.DecisionMetricFn#

class autointent.metrics.DecisionMetricFn#

Bases: Protocol

Protocol for decision metrics.

__call__(y_true, y_pred)#

Calculate decision metric.

Parameters:

  • y_true (autointent.metrics.custom_types.LABELS_VALUE_TYPE) – True values of labels - multiclass case: list representing an array shape (n_samples,) of integer class labels - multilabel case: list representing a matrix of shape (n_samples, n_classes) with binary values

  • y_pred (autointent.metrics.custom_types.LABELS_VALUE_TYPE) – Predicted values of labels. Same shape as y_true

Returns:

Score of the decision metric

Return type:

float