297e14732849f2b8025de6e2bf80ac05cab82b44,src/gluonnlp/data/corpora/google_billion_word.py,GBWStream,__init__,#GBWStream#Any#Any#Any#Any#Any#,133

Before Change

                                    "0a8e2b7496ba0b5c05158f282b9b351356875445")}
        self._vocab_file = ("gbw-ebb1a287.vocab",
                            "ebb1a287ca14d8fa6f167c3a779e5e7ed63ac69f")
        super(GBWStream, self).__init__("gbw", segment, bos, eos, skip_empty, root)

    @property
    def vocab(self):
        path = self._get_vocab()

After Change

    def __init__(self, segment="train", skip_empty=True, bos=None, eos=EOS_TOKEN,
                 root=os.path.join(get_home_dir(), "datasets", "gbw")):
        root = os.path.expanduser(root)
        if not os.path.isdir(root):
            os.makedirs(root)
        self._root = root
        self._dir = os.path.join(root, "1-billion-word-language-modeling-benchmark-r13output")
        self._namespace = "gluon/dataset/gbw"
        subdir_name, pattern, data_hash = self._data_file[segment]
        self._subdir = os.path.join(self._dir, subdir_name)
        self._file_pattern = os.path.join(self._subdir, pattern)
        self._data_hash = data_hash
        self._get_data()

Instances