def numericalize()

in pytext/legacy/data/field.py [0:0]

• 40 lines of code
• 19 McCabe index (conditional complexity)

    def numericalize(self, arr, device=None):
        """Turn a batch of examples that use this field into a Variable.

        If the field has include_lengths=True, a tensor of lengths will be
        included in the return value.

        Arguments:
            arr (List[List[str]], or tuple of (List[List[str]], List[int])): List of tokenized
                and padded examples, or tuple of List of
                tokenized and padded examples and List of lengths of each
                example if self.include_lengths is True.
            device (str or torch.device): A string or instance of `torch.device`
                specifying which device the Variables are going to be created on.
                If left as default, the tensors will be created on cpu. Default: None.
        """
        if self.include_lengths and not isinstance(arr, tuple):
            raise ValueError(
                "Field has include_lengths set to True, but "
                "input data is not a tuple of "
                "(data batch, batch lengths)."
            )
        if isinstance(arr, tuple):
            arr, lengths = arr
            lengths = torch.tensor(lengths, dtype=self.dtype, device=device)

        if self.use_vocab:
            if self.sequential:
                arr = [[self.vocab.stoi[x] for x in ex] for ex in arr]
            else:
                arr = [self.vocab.stoi[x] for x in arr]

            if self.postprocessing is not None:
                arr = self.postprocessing(arr, self.vocab)
        else:
            if self.dtype not in self.dtypes:
                raise ValueError(
                    "Specified Field dtype {} can not be used with "
                    "use_vocab=False because we do not know how to numericalize it. "
                    "Please raise an issue at "
                    "https://github.com/pytorch/text/issues".format(self.dtype)
                )
            numericalization_func = self.dtypes[self.dtype]
            # It doesn't make sense to explicitly coerce to a numeric type if
            # the data is sequential, since it's unclear how to coerce padding tokens
            # to a numeric type.
            if not self.sequential:
                arr = [
                    numericalization_func(x) if isinstance(x, str) else x for x in arr
                ]
            if self.postprocessing is not None:
                arr = self.postprocessing(arr, None)

        var = torch.tensor(arr, dtype=self.dtype, device=device)

        if self.sequential and not self.batch_first:
            var.t_()
        if self.sequential:
            var = var.contiguous()

        if self.include_lengths:
            return var, lengths
        return var