rxn.metrics.classification_translation.classification_translation

rxn.metrics.classification_translation.classification_translation(src_file, tgt_file, pred_file, model, n_best, beam_size, batch_size, gpu, max_length=3, as_external_command=False)

Do a classification translation.

This function takes care of tokenizing/detokenizing the input.

Note: no check is made that the source is canonical.

Parameters

• src_file (Union[str, Path]) – source file (tokenized or detokenized).

• tgt_file (Union[str, Path, None]) – ground truth class file (tokenized), not mandatory.

• pred_file (Union[str, Path]) – file where to save the predictions.

• model (Union[str, Path]) – model to do the translation

• n_best (int) – number of predictions to make for each input.

• beam_size (int) – beam size.

• batch_size (int) – batch size.

• gpu (bool) – whether to use the GPU.

• max_length (int, default: 3) – maximum sequence length.

• as_external_command (bool, default: False) –

Return type

None