Method __init__

pythia/utils/vocab.py:250–313

Use this vocab class when you have a custom vocabulary class but you want to use pretrained embedding vectos for it. This will only load the vectors which intersect with your vocabulary. Use the embedding_name specified in torchtext's pretrained aliases: ['charngram.1

(self, vocab_file, embedding_name, *args, **kwargs)

class IntersectedVocab(BaseVocab):
    def __init__(self, vocab_file, embedding_name, *args, **kwargs):
        """Use this vocab class when you have a custom vocabulary class but you
        want to use pretrained embedding vectos for it. This will only load
        the vectors which intersect with your vocabulary. Use the
        embedding_name specified in torchtext's pretrained aliases:
        ['charngram.100d', 'fasttext.en.300d', 'fasttext.simple.300d',
         'glove.42B.300d', 'glove.840B.300d', 'glove.twitter.27B.25d',
         'glove.twitter.27B.50d', 'glove.twitter.27B.100d',
         'glove.twitter.27B.200d', 'glove.6B.50d', 'glove.6B.100d',
         'glove.6B.200d', 'glove.6B.300d']

        Parameters
        ----------
        vocab_file : str
            Vocabulary file containing list of words with one word per line
            which will be used to collect vectors
        embedding_name : str
            Embedding name picked up from the list of the pretrained aliases
            mentioned above
        """
        super(IntersectedVocab, self).__init__(vocab_file, *args, **kwargs)

        self.type = "intersected"

        name = embedding_name.split(".")[0]
        dim = embedding_name.split(".")[2][:-1]
        middle = embedding_name.split(".")[1]

        class_name = EMBEDDING_NAME_CLASS_MAPPING[name]

        if not hasattr(vocab, class_name):
            from pythia.common.registry import registry

            writer = registry.get("writer")
            error = "Unknown embedding type: %s" % name, "error"
            if writer is not None:
                writer.write(error, "error")
            raise RuntimeError(error)

        params = [middle]

        if name == "glove":
            params.append(int(dim))

        vector_cache = os.path.join(get_pythia_root(), ".vector_cache")
        embedding = getattr(vocab, class_name)(*params, cache=vector_cache)

        self.vectors = torch.empty(
            (self.get_size(), len(embedding.vectors[0])), dtype=torch.float
        )

        self.embedding_dim = len(embedding.vectors[0])

        for i in range(0, 4):
            self.vectors[i] = torch.ones_like(self.vectors[i]) * 0.1 * i

        for i in range(4, self.get_size()):
            word = self.itos[i]