dataset_tools.py 文件源码

def dataset_from_file(filename):
    """Load a dataset from file.

    Args:
        filename (string): the name of the file from which extract the dataset

    Returns:
        tuple: the dataset (np.ndarray) and the ngrams (list of strings)
    """
    loader = np.load(filename)
    num_entries = loader['num_entries'][0]
    sp_dataset = sparse.csr_matrix((loader['data'], loader['indices'], loader['indptr']),
                         shape = loader['shape'])
    dataset = sp_dataset.toarray()
    samp_entries, num_features = dataset.shape
    return dataset.reshape(int(samp_entries / num_entries), num_entries, num_features), loader['ngrams']