def fpr_and_fdr_at_recall()

in ood/metrics.py [0:0]

• 26 lines of code
• 10 McCabe index (conditional complexity)

def fpr_and_fdr_at_recall(y_true, y_score, recall_level=0.95, pos_label=None):
    classes = np.unique(y_true)
    if (pos_label is None and
            not (np.array_equal(classes, [0, 1]) or
                     np.array_equal(classes, [-1, 1]) or
                     np.array_equal(classes, [0]) or
                     np.array_equal(classes, [-1]) or
                     np.array_equal(classes, [1]))):
        raise ValueError("Data is not binary and pos_label is not specified")
    elif pos_label is None:
        pos_label = 1.

    # make y_true a boolean vector
    y_true = (y_true == pos_label)

    # sort scores and corresponding truth values
    desc_score_indices = np.argsort(y_score, kind="mergesort")[::-1]
    y_score = y_score[desc_score_indices]
    y_true = y_true[desc_score_indices]

    # y_score typically has many tied values. Here we extract
    # the indices associated with the distinct values. We also
    # concatenate a value for the end of the curve.
    distinct_value_indices = np.where(np.diff(y_score))[0]
    threshold_idxs = np.r_[distinct_value_indices, y_true.size - 1]

    # accumulate the true positives with decreasing threshold
    tps = stable_cumsum(y_true)[threshold_idxs]
    fps = 1 + threshold_idxs - tps      # add one because of zero-based indexing

    thresholds = y_score[threshold_idxs]

    recall = tps / tps[-1]

    last_ind = tps.searchsorted(tps[-1])
    sl = slice(last_ind, None, -1)      # [last_ind::-1]
    recall, fps, tps, thresholds = np.r_[recall[sl], 1], np.r_[fps[sl], 0], np.r_[tps[sl], 0], thresholds[sl]

    cutoff = np.argmin(np.abs(recall - recall_level))

    return fps[cutoff] / (np.sum(np.logical_not(y_true))), thresholds[cutoff]   # , fps[cutoff]/(fps[cutoff] + tps[cutoff])