embeddings_dict.py 文件源码

def __init__(self, opt, embedding_dim):
        """Initialize the class according to given parameters."""

        self.tok2emb = {}
        self.embedding_dim = embedding_dim
        self.opt = copy.deepcopy(opt)
        self.load_items()

        nltk.download('punkt')

        if not self.opt.get('fasttext_model'):
            raise RuntimeError('No pretrained fasttext model provided')
        self.fasttext_model_file = self.opt.get('fasttext_model')
        if not os.path.isfile(self.fasttext_model_file):
            emb_path = os.environ.get('EMBEDDINGS_URL')
            if not emb_path:
                raise RuntimeError('No pretrained fasttext model provided')
            fname = os.path.basename(self.fasttext_model_file)
            try:
                print('Trying to download a pretrained fasttext model from the repository')
                url = urllib.parse.urljoin(emb_path, fname)
                urllib.request.urlretrieve(url, self.fasttext_model_file)
                print('Downloaded a fasttext model')
            except Exception as e:
                raise RuntimeError('Looks like the `EMBEDDINGS_URL` variable is set incorrectly', e)

        self.fasttext_model = fasttext.load_model(self.fasttext_model_file)