data.py 文件源码

def __init__(self, inputs, labels, test_indices=None, **kwargs):
        """Encapsulates all pieces of data to run an experiment. This is basically a bag of items that makes it
        easy to serialize and deserialize everything as a unit.

        Args:
            inputs: The raw model inputs. This can be set to None if you dont want
                to serialize this value when you save the dataset.
            labels: The raw output labels.
            test_indices: The optional test indices to use. Ideally, this should be generated one time and reused
                across experiments to make results comparable. `generate_test_indices` can be used generate first
                time indices.
            **kwargs: Additional key value items to store.
        """
        self.X = np.array(inputs)
        self.y = np.array(labels)
        for key, value in kwargs.items():
            setattr(self, key, value)

        self._test_indices = None
        self._train_indices = None
        self.test_indices = test_indices

        self.is_multi_label = isinstance(labels[0], (set, list, tuple))
        self.label_encoder = MultiLabelBinarizer() if self.is_multi_label else LabelBinarizer()
        self.y = self.label_encoder.fit_transform(self.y).flatten()