precision_recall_gain.prg.precision_recall_gain_curve()

Complexity

Conditions

3

Size

Total Lines	115
Code Lines	24

Duplication

Lines	0
Ratio	0 %

Importance

Changes

0

from functools import partial
def precision_recall_gain_curve(y_true, probas_pred, pos_label=1, sample_weight=None):
    """Compute precision-recall pairs for different probability thresholds.

    Note: this implementation is restricted to the binary classification task.

    The precision is the ratio ``tp / (tp + fp)`` where ``tp`` is the number of
    true positives and ``fp`` the number of false positives. The precision is
    intuitively the ability of the classifier not to label as positive a sample
    that is negative.

    The recall is the ratio ``tp / (tp + fn)`` where ``tp`` is the number of
    true positives and ``fn`` the number of false negatives. The recall is
    intuitively the ability of the classifier to find all the positive samples.

    The last precision and recall values are 1. and 0. respectively and do not
    have a corresponding threshold. This ensures that the graph starts on the
    y axis.

    Read more in the :ref:`User Guide <precision_recall_f_measure_metrics>`.

    Parameters
    ----------
    y_true : ndarray of shape (n_samples,)
        True binary labels. If labels are not either {-1, 1} or {0, 1}, then
        pos_label should be explicitly given.

    probas_pred : ndarray of shape (n_samples,)
        Estimated probabilities or output of a decision function.

    pos_label : int or str, default=None
        The label of the positive class.
        When ``pos_label=None``, if y_true is in {-1, 1} or {0, 1},
        ``pos_label`` is set to 1, otherwise an error will be raised.

    sample_weight : array-like of shape (n_samples,), default=None
        Sample weights.

    Returns
    -------
    precision : ndarray of shape (n_thresholds + 1,)
        Precision values such that element i is the precision of
        predictions with score >= thresholds[i] and the last element is 1.

    recall : ndarray of shape (n_thresholds + 1,)
        Decreasing recall values such that element i is the recall of
        predictions with score >= thresholds[i] and the last element is 0.

    thresholds : ndarray of shape (n_thresholds,)
        Increasing thresholds on the decision function used to compute
        precision and recall. n_thresholds <= len(np.unique(probas_pred)).

    See Also
    --------
    plot_precision_recall_curve : Plot Precision Recall Curve for binary
        classifiers.
    PrecisionRecallDisplay : Precision Recall visualization.
    average_precision_score : Compute average precision from prediction scores.
    det_curve: Compute error rates for different probability thresholds.
    roc_curve : Compute Receiver operating characteristic (ROC) curve.

    Examples
    --------
    >>> import numpy as np
    >>> from sklearn.metrics import precision_recall_curve
    >>> y_true = np.array([0, 0, 1, 1])
    >>> y_scores = np.array([0.1, 0.4, 0.35, 0.8])
    >>> precision, recall, thresholds = precision_recall_curve(
    ...     y_true, y_scores)
    >>> precision
    array([0.66666667, 0.5       , 1.        , 1.        ])
    >>> recall
    array([1. , 0.5, 0.5, 0. ])
    >>> thresholds
    array([0.35, 0.4 , 0.8 ])

    """
    if pos_label != 1:
        raise NotImplementedError("Have not implemented non-binary targets")
    if sample_weight is not None:
        raise NotImplementedError

    # calc true and false poitives per binary classification thresh
    fps, tps, thresholds = _binary_clf_curve(
        y_true, probas_pred, pos_label=pos_label, sample_weight=sample_weight
    )

    precision = tps / (tps + fps)
    precision[np.isnan(precision)] = 0
    recall = tps / tps[-1]

    # stop when full recall attained
    # and reverse the outputs so recall is decreasing
    last_ind = tps.searchsorted(tps[-1])
    sl = slice(last_ind, None, -1)  # equivalent to slice [last_ind:None:-1]
    precision, recall, thresholds = (
        np.r_[precision[sl], 1],
        np.r_[recall[sl], 0],
        thresholds[sl],
    )

    # everything above is taken from sklearn.metrics._ranking.precision_recall_curve

    # logic taken from sklearn.metrics._ranking.det_curve
    # fns = tps[-1] - tps
    p_count = tps[-1]
    n_count = fps[-1]
    proportion_of_positives = p_count / n_count

    precision_gains, recall_gains = precision_recall_gain(
        precisions=precision,
        recalls=recall,
        proportion_of_positives=proportion_of_positives,
    )

    return precision_gains, recall_gains