dataset_tools.py 文件源码

def dataset_to_file(dataset, ngrams, filename='dataset'):
    """Save a dataset to a file.

    Args:
        dataset (:class:`np.ndarray`): the dataset to save (built with :func:`dataset_tools.build_dataset`)
        ngrams (list of strings): the ngrams used to compute the features
        filename (string): the filename without extension (will be .npz)
    """
    num_samples, num_entries, num_features = dataset.shape
    # We rehaspe the ndarray from 3D to 2D in order to write it into a text file
    # Each line of the file will correspond to one cited paper
    # Therefore, on each there will be the `num_entries` sets of features
    dataset_sp = sparse.csr_matrix(dataset.reshape(num_samples*num_entries, num_features))
    np.savez(filename, num_entries=np.array([num_entries]), data=dataset_sp.data, indices=dataset_sp.indices,
             indptr=dataset_sp.indptr, shape=dataset_sp.shape, ngrams=ngrams)