预测已切词的句子。 Args: x: list(list(str)), 已分词的句子，类型为list Returns: outputs: list, 依存分析结果 Example: >>> ddp = DDParser() >>> inputs = [['百度', '是', '一家', '高科技', '公司'], ['他', '送', '了', '一本', '书']] >>> ddp.parse_seg(inputs)
(self, inputs)
| 411 | return outputs |
| 412 | |
| 413 | def parse_seg(self, inputs): |
| 414 | """ |
| 415 | 预测已切词的句子。 |
| 416 | |
| 417 | Args: |
| 418 | x: list(list(str)), 已分词的句子，类型为list |
| 419 | |
| 420 | Returns: |
| 421 | outputs: list, 依存分析结果 |
| 422 | |
| 423 | Example: |
| 424 | >>> ddp = DDParser() |
| 425 | >>> inputs = [['百度', '是', '一家', '高科技', '公司'], ['他', '送', '了', '一本', '书']] |
| 426 | >>> ddp.parse_seg(inputs) |
| 427 | [{'word': ['百度', '是', '一家', '高科技', '公司'], 'head': [2, 0, 5, 5, 2], 'deprel': ['SBV', 'HED', 'ATT', 'ATT', 'VOB']}, |
| 428 | {'word': ['他', '送', '了', '一本', '书'], 'head': [2, 0, 2, 5, 2], 'deprel': ['SBV', 'HED', 'MT', 'ATT', 'VOB']}] |
| 429 | |
| 430 | |
| 431 | >>> ddp = DDParser(prob=True) |
| 432 | >>> inputs = [['百度', '是', '一家', '高科技', '公司']] |
| 433 | >>> ddp.parse_seg(inputs) |
| 434 | [{'word': ['百度', '是', '一家', '高科技', '公司'], 'head': [2, 0, 5, 5, 2], |
| 435 | 'deprel': ['SBV', 'HED', 'ATT', 'ATT', 'VOB'], 'prob': [1.0, 1.0, 1.0, 1.0, 1.0]}] |
| 436 | """ |
| 437 | if not inputs: |
| 438 | return |
| 439 | if all([isinstance(i, list) and i and all(i) for i in inputs]): |
| 440 | predicts = Corpus.load_word_segments(inputs, self.env.fields) |
| 441 | else: |
| 442 | logging.warning("please check the foramt of your inputs.") |
| 443 | return |
| 444 | dataset = TextDataset(predicts, [self.env.WORD, self.env.FEAT], self.args.buckets) |
| 445 | # set the data loader |
| 446 | dataset.loader = batchify( |
| 447 | dataset, |
| 448 | self.args.batch_size, |
| 449 | use_multiprocess=False, |
| 450 | sequential_sampler=True if not self.args.buckets else False, |
| 451 | ) |
| 452 | pred_arcs, pred_rels, pred_probs = epoch_predict(self.env, self.args, self.model, dataset.loader) |
| 453 | |
| 454 | if self.args.buckets: |
| 455 | indices = np.argsort(np.array([i for bucket in dataset.buckets.values() for i in bucket])) |
| 456 | else: |
| 457 | indices = range(len(pred_arcs)) |
| 458 | predicts.head = [pred_arcs[i] for i in indices] |
| 459 | predicts.deprel = [pred_rels[i] for i in indices] |
| 460 | if self.args.prob: |
| 461 | predicts.prob = [pred_probs[i] for i in indices] |
| 462 | |
| 463 | outputs = predicts.get_result() |
| 464 | if outputs[0].get("postag", None): |
| 465 | for output in outputs: |
| 466 | del output["postag"] |
| 467 | return outputs |
| 468 | |
| 469 | def _get_abs_path(self, path): |
| 470 | return os.path.normpath(os.path.join(os.path.dirname(os.path.abspath(__file__)), path)) |
nothing calls this directly
no test coverage detected