vwoptimize.py 文件源码

def classification_report(y_true, y_pred, labels=None, sample_weight=None, digits=4, threshold=None):
    # this function is copied from https://github.com/scikit-learn/scikit-learn/blob/412996f/sklearn/metrics/classification.py#L1341 (c) respective authors
    # I pulled it here to fix formatting bug.
    from sklearn.metrics import precision_recall_fscore_support, accuracy_score

    y_true = np.array(y_true)
    y_pred = np.array(y_pred)

    if labels is None:
        from sklearn.utils.multiclass import unique_labels

        if threshold is not None:
            y_true = y_true > threshold
            y_pred = y_pred > threshold

        labels = unique_labels(y_true, y_pred)
    else:
        labels = np.asarray(labels)

    last_line_heading = 'avg / total'
    target_names = ['%s' % l for l in labels]

    results = [["", "precision", "recall", "f1-score", "support", "accuracy"]]

    p, r, f1, s = precision_recall_fscore_support(y_true, y_pred,
                                                  labels=labels,
                                                  average=None,
                                                  sample_weight=sample_weight)

    for i, label in enumerate(labels):
        values = [target_names[i]]
        for v in (p[i], r[i], f1[i]):
            values += ["{0:0.{1}f}".format(v, digits)]
        values += ["{0}".format(s[i])]
        accuracy = accuracy_score(y_true == label, y_pred == label, sample_weight=sample_weight)
        values += ["{0:0.{1}f}".format(accuracy, digits)]
        results.append(values)

    values = [last_line_heading]
    for v in (np.average(p, weights=s),
              np.average(r, weights=s),
              np.average(f1, weights=s)):
        values += ["{0:0.{1}f}".format(v, digits)]
    values += ['{0}'.format(np.sum(s))]
    accuracy = accuracy_score(y_true, y_pred, sample_weight=sample_weight)
    values += ["{0:0.{1}f}".format(accuracy, digits)]
    results.append(values)

    return results