def read_model_predictions(prediction_path): """Read a model's validation predictions and convert to a dictionary. Args: prediction_path: Path to read predictions from Returns: A dictionary where values are predictions, and keys are composed of the claim_id/wikipedia_url/sentence_id/scrape_type """ model_predictions = util.read_json(prediction_path) id_to_predictions = {} for pred in model_predictions['predictions']: claim_id = pred['metadata']['claim_id'] scrape_type = pred['metadata']['scrape_type'] wikipedia_url = pred['metadata']['wikipedia_url'] sentence_id = pred['metadata']['sentence_id'] identifier = make_example_id( claim_id=claim_id, wikipedia_url=wikipedia_url, sentence_id=sentence_id, scrape_type=scrape_type, ) id_to_predictions[identifier] = pred return id_to_predictions
def load_from_file(cls, filename_prefix): conf = util.read_json(filename_prefix + '.space_tokenizer') return cls(**conf)
def load_from_file(cls, filename_prefix): params = util.read_json(f'{filename_prefix}.tokenizer') bert_tokenizer = BertTokenizer(vocab_file=params['vocab_file'], do_lower_case=params['do_lower_case']) return bert_tokenizer
def load_from_file(cls, filename_prefix): conf = util.read_json(filename_prefix + '.regex_tokenizer') tokenizer_cls = conf['tokenizer_cls'] tokenizer = tokenizer_registry[tokenizer_cls].load_from_file( filename_prefix) return cls(tokenizer=tokenizer, reserved_re=conf['reserved_re'])