tagger.py 文件源码

def annotate(self, tokens):
        X_focus = self.preprocessor.transform(tokens=tokens)['X_focus']
        X_context = self.pretrainer.transform(tokens=tokens)

        # get predictions:
        new_in = {}
        if self.include_token:
            new_in['focus_in'] = X_focus
        if self.include_context:
            new_in['context_in'] = X_context
        preds = self.model.predict(new_in)

        if isinstance(preds, np.ndarray):
            preds = [preds]

        annotation_dict = {'tokens': tokens}
        if self.include_lemma:
            pred_lemmas = self.preprocessor.inverse_transform_lemmas(predictions=preds[self.lemma_out_idx])
            annotation_dict['lemmas'] = pred_lemmas
            if self.postcorrect:
                for i in range(len(pred_lemmas)):
                    if pred_lemmas[i] not in self.known_lemmas:
                        pred_lemmas[i] = min(self.known_lemmas,
                                            key=lambda x: editdistance.eval(x, pred_lemmas[i]))
                annotation_dict['postcorrect_lemmas'] = pred_lemmas

        if self.include_pos:
            pred_pos = self.preprocessor.inverse_transform_pos(predictions=preds[self.pos_out_idx])
            annotation_dict['pos'] = pred_pos

        if self.include_morph:
            pred_morph = self.preprocessor.inverse_transform_morph(predictions=preds[self.morph_out_idx])
            annotation_dict['morph'] = pred_morph

        return annotation_dict