clustering.py 文件源码

def get_cv(self, X, y):
        unique_event_ids = np.unique(y[:, 0])
        event_cv = ShuffleSplit(
            n_splits=self.n_cv, test_size=self.cv_test_size,
            random_state=self.random_state)
        for train_event_is, test_event_is in event_cv.split(unique_event_ids):
            train_is = np.where(
                np.in1d(y[:, 0], unique_event_ids[train_event_is]))[0]
            test_is = np.where(
                np.in1d(y[:, 0], unique_event_ids[test_event_is]))[0]
            yield train_is, test_is