label.py 文件源码

def transform(self, y, replace_unique=False):
        """Transform labels to normalized encoding.

        Parameters
        ----------
        y : array-like of shape [n_samples]
            Target values.

        Returns
        -------
        y : array-like of shape [n_samples]
        """
        self._check_fitted()

        classes = np.unique(y)
        _check_numpy_unicode_bug(classes)
        if len(np.intersect1d(classes, self.classes_)) < len(classes):
            diff = np.setdiff1d(classes, self.classes_)
            if replace_unique:
                mode = stats.mode(y)[0][0] 
                for i in xrange(0,len(y)):
                    if y[i] in diff:
                        y[i]=mode
            else:
                raise ValueError("y contains new labels: %s" % str(diff))
        return np.searchsorted(self.classes_, y)