sklearn.metrics.auc

AUC(area under the curve)ROC曲线下方的面积

auc(x, y, reorder=False)

    Compute Area Under the Curve (AUC) using the trapezoidal rule

    

    This is a general function, given points on a curve.  For computing the

    area under the ROC-curve, see :func:`roc_auc_score`.  For an alternative

    way to summarize a precision-recall curve, see

    :func:`average_precision_score`.

    

    Parameters

    ----------

    x : array, shape = [n]

        x coordinates.

    y : array, shape = [n]

        y coordinates.

    reorder : boolean, optional (default=False)

        If True, assume that the curve is ascending in the case of ties, as for

        an ROC curve. If the curve is non-ascending, the result will be wrong.

    

    Returns

    -------

    auc : float

    

    Examples

    --------

    >>> import numpy as np

    >>> from sklearn import metrics

    >>> y = np.array([1, 1, 2, 2])

    >>> pred = np.array([0.1, 0.4, 0.35, 0.8])

    >>> fpr, tpr, thresholds = metrics.roc_curve(y, pred, pos_label=2)

    >>> metrics.auc(fpr, tpr)

    0.75

    

    See also

    --------

    roc_auc_score : Compute the area under the ROC curve

    average_precision_score : Compute average precision from prediction scores

    precision_recall_curve :

        Compute precision-recall pairs for different probability thresholds