def test_index(self): vocab = Vocabulary(need_default=True, max_size=None, min_freq=None) vocab.update(text) res = [vocab[w] for w in set(text)] self.assertEqual(len(res), len(set(res))) res = [vocab.to_index(w) for w in set(text)] self.assertEqual(len(res), len(set(res)))
def add_words_field_2_databundle(data_bundle): train_cws_field = "data/wb_cws/train_cws_word.txt" dev_cws_field = "data/wb_cws/dev_cws_word.txt" test_cws_field = "data/wb_cws/test_cws_word.txt" train_field = _read_txt(train_cws_field) dev_field = _read_txt(dev_cws_field) test_field = _read_txt(test_cws_field) # # data_bundle.get_dataset('train').add_field(field_name="raw_words", fields=train_field) data_bundle.get_dataset('dev').add_field(field_name="raw_words", fields=dev_field) data_bundle.get_dataset('test').add_field(field_name="raw_words", fields=test_field) # 添加词表 words_vocab = Vocabulary() word_list = get_corpus_words(train_cws_field, dev_cws_field, test_cws_field) words_vocab.update(word_list) data_bundle.set_vocab(words_vocab, field_name="words") # 将raw_words转换为words_id for dataset in ["train", "dev", "test"]: raw_words = list(data_bundle.get_dataset(dataset)["raw_words"]) words_ids = [] for words in raw_words: words_id = [] for word in words: words_id.append(words_vocab.to_index(word)) words_ids.append(words_id) data_bundle.get_dataset(dataset).add_field(field_name="words", fields=words_ids) data_bundle.set_input('words') data_bundle.set_ignore_type('words', flag=False) data_bundle.set_pad_val("words", 0) return data_bundle
def _generate_samples(): target = [] seq_len = [] vocab = Vocabulary(unknown=None, padding=None) for i in range(3): target_i = [] seq_len_i = 0 for j in range(1, 10): word_len = np.random.randint(1, 5) seq_len_i += word_len if word_len == 1: target_i.append('S') else: target_i.append('B') target_i.extend(['M'] * (word_len - 2)) target_i.append('E') vocab.add_word_lst(target_i) target.append(target_i) seq_len.append(seq_len_i) target_ = np.zeros((3, max(seq_len))) for i in range(3): target_i = [vocab.to_index(t) for t in target[i]] target_[i, :seq_len[i]] = target_i return target_, target, seq_len, vocab
class VocabIndexerProcessor(Processor): """ 根据DataSet创建Vocabulary,并将其用数字index。新生成的index的field会被放在new_added_filed_name, 如果没有提供 new_added_field_name, 则覆盖原有的field_name. """ def __init__(self, field_name, new_added_filed_name=None, min_freq=1, max_size=None, verbose=0, is_input=True): """ :param field_name: 从哪个field_name创建词表,以及对哪个field_name进行index操作 :param new_added_filed_name: index时,生成的index field的名称,如果不传入,则覆盖field_name. :param min_freq: 创建的Vocabulary允许的单词最少出现次数. :param max_size: 创建的Vocabulary允许的最大的单词数量 :param verbose: 0, 不输出任何信息;1,输出信息 :param bool is_input: """ super(VocabIndexerProcessor, self).__init__(field_name, new_added_filed_name) self.min_freq = min_freq self.max_size = max_size self.verbose =verbose self.is_input = is_input def construct_vocab(self, *datasets): """ 使用传入的DataSet创建vocabulary :param datasets: DataSet类型的数据,用于构建vocabulary :return: """ self.vocab = Vocabulary(min_freq=self.min_freq, max_size=self.max_size) for dataset in datasets: assert isinstance(dataset, DataSet), "Only Dataset class is allowed, not {}.".format(type(dataset)) dataset.apply(lambda ins: self.vocab.update(ins[self.field_name])) self.vocab.build_vocab() if self.verbose: print("Vocabulary Constructed, has {} items.".format(len(self.vocab))) def process(self, *datasets, only_index_dataset=None): """ 若还未建立Vocabulary,则使用dataset中的DataSet建立vocabulary;若已经有了vocabulary则使用已有的vocabulary。得到vocabulary 后,则会index datasets与only_index_dataset。 :param datasets: DataSet类型的数据 :param only_index_dataset: DataSet, or list of DataSet. 该参数中的内容只会被用于index,不会被用于生成vocabulary。 :return: """ if len(datasets)==0 and not hasattr(self,'vocab'): raise RuntimeError("You have to construct vocabulary first. Or you have to pass datasets to construct it.") if not hasattr(self, 'vocab'): self.construct_vocab(*datasets) else: if self.verbose: print("Using constructed vocabulary with {} items.".format(len(self.vocab))) to_index_datasets = [] if len(datasets)!=0: for dataset in datasets: assert isinstance(dataset, DataSet), "Only DataSet class is allowed, not {}.".format(type(dataset)) to_index_datasets.append(dataset) if not (only_index_dataset is None): if isinstance(only_index_dataset, list): for dataset in only_index_dataset: assert isinstance(dataset, DataSet), "Only DataSet class is allowed, not {}.".format(type(dataset)) to_index_datasets.append(dataset) elif isinstance(only_index_dataset, DataSet): to_index_datasets.append(only_index_dataset) else: raise TypeError('Only DataSet or list of DataSet is allowed, not {}.'.format(type(only_index_dataset))) for dataset in to_index_datasets: assert isinstance(dataset, DataSet), "Only DataSet class is allowed, not {}.".format(type(dataset)) dataset.apply(lambda ins: [self.vocab.to_index(token) for token in ins[self.field_name]], new_field_name=self.new_added_field_name, is_input=self.is_input) # 只返回一个,infer时为了跟其他processor保持一致 if len(to_index_datasets) == 1: return to_index_datasets[0] def set_vocab(self, vocab): assert isinstance(vocab, Vocabulary), "Only fastNLP.core.Vocabulary is allowed, not {}.".format(type(vocab)) self.vocab = vocab def delete_vocab(self): del self.vocab def get_vocab_size(self): return len(self.vocab) def set_verbose(self, verbose): """ 设置processor verbose状态。 :param verbose: int, 0,不输出任何信息;1,输出vocab 信息。 :return: """ self.verbose = verbose
def process( self, paths: Union[str, Dict[str, str]], dataset_name: str = None, to_lower=False, seq_len_type: str = None, bert_tokenizer: str = None, cut_text: int = None, get_index=True, auto_pad_length: int = None, auto_pad_token: str = '<pad>', set_input: Union[list, str, bool] = True, set_target: Union[list, str, bool] = True, concat: Union[str, list, bool] = None, ) -> DataBundle: """ :param paths: str或者Dict[str, str]。如果是str,则为数据集所在的文件夹或者是全路径文件名:如果是文件夹, 则会从self.paths里面找对应的数据集名称与文件名。如果是Dict,则为数据集名称(如train、dev、test)和 对应的全路径文件名。 :param str dataset_name: 如果在paths里传入的是一个数据集的全路径文件名,那么可以用dataset_name来定义 这个数据集的名字,如果不定义则默认为train。 :param bool to_lower: 是否将文本自动转为小写。默认值为False。 :param str seq_len_type: 提供的seq_len类型,支持 ``seq_len`` :提供一个数字作为句子长度; ``mask`` : 提供一个0/1的mask矩阵作为句子长度; ``bert`` :提供segment_type_id(第一个句子为0,第二个句子为1)和 attention mask矩阵(0/1的mask矩阵)。默认值为None,即不提供seq_len :param str bert_tokenizer: bert tokenizer所使用的词表所在的文件夹路径 :param int cut_text: 将长于cut_text的内容截掉。默认为None,即不截。 :param bool get_index: 是否需要根据词表将文本转为index :param int auto_pad_length: 是否需要将文本自动pad到一定长度(超过这个长度的文本将会被截掉),默认为不会自动pad :param str auto_pad_token: 自动pad的内容 :param set_input: 如果为True,则会自动将相关的field(名字里含有Const.INPUT的)设置为input,如果为False 则不会将任何field设置为input。如果传入str或者List[str],则会根据传入的内容将相对应的field设置为input, 于此同时其他field不会被设置为input。默认值为True。 :param set_target: set_target将控制哪些field可以被设置为target,用法与set_input一致。默认值为True。 :param concat: 是否需要将两个句子拼接起来。如果为False则不会拼接。如果为True则会在两个句子之间插入一个<sep>。 如果传入一个长度为4的list,则分别表示插在第一句开始前、第一句结束后、第二句开始前、第二句结束后的标识符。如果 传入字符串 ``bert`` ,则会采用bert的拼接方式,等价于['[CLS]', '[SEP]', '', '[SEP]']. :return: """ if isinstance(set_input, str): set_input = [set_input] if isinstance(set_target, str): set_target = [set_target] if isinstance(set_input, bool): auto_set_input = set_input else: auto_set_input = False if isinstance(set_target, bool): auto_set_target = set_target else: auto_set_target = False if isinstance(paths, str): if os.path.isdir(paths): path = { n: os.path.join(paths, self.paths[n]) for n in self.paths.keys() } else: path = { dataset_name if dataset_name is not None else 'train': paths } else: path = paths data_info = DataBundle() for data_name in path.keys(): data_info.datasets[data_name] = self._load(path[data_name]) for data_name, data_set in data_info.datasets.items(): if auto_set_input: data_set.set_input(Const.INPUTS(0), Const.INPUTS(1)) if auto_set_target: if Const.TARGET in data_set.get_field_names(): data_set.set_target(Const.TARGET) if to_lower: for data_name, data_set in data_info.datasets.items(): data_set.apply( lambda x: [w.lower() for w in x[Const.INPUTS(0)]], new_field_name=Const.INPUTS(0), is_input=auto_set_input) data_set.apply( lambda x: [w.lower() for w in x[Const.INPUTS(1)]], new_field_name=Const.INPUTS(1), is_input=auto_set_input) if bert_tokenizer is not None: if bert_tokenizer.lower() in PRETRAINED_BERT_MODEL_DIR: PRETRAIN_URL = _get_base_url('bert') model_name = PRETRAINED_BERT_MODEL_DIR[bert_tokenizer] model_url = PRETRAIN_URL + model_name model_dir = cached_path(model_url) # 检查是否存在 elif os.path.isdir(bert_tokenizer): model_dir = bert_tokenizer else: raise ValueError( f"Cannot recognize BERT tokenizer from {bert_tokenizer}.") words_vocab = Vocabulary(padding='[PAD]', unknown='[UNK]') with open(os.path.join(model_dir, 'vocab.txt'), 'r') as f: lines = f.readlines() lines = [line.strip() for line in lines] words_vocab.add_word_lst(lines) words_vocab.build_vocab() tokenizer = BertTokenizer.from_pretrained(model_dir) for data_name, data_set in data_info.datasets.items(): for fields in data_set.get_field_names(): if Const.INPUT in fields: data_set.apply( lambda x: tokenizer.tokenize(' '.join(x[fields])), new_field_name=fields, is_input=auto_set_input) if isinstance(concat, bool): concat = 'default' if concat else None if concat is not None: if isinstance(concat, str): CONCAT_MAP = { 'bert': ['[CLS]', '[SEP]', '', '[SEP]'], 'default': ['', '<sep>', '', ''] } if concat.lower() in CONCAT_MAP: concat = CONCAT_MAP[concat] else: concat = 4 * [concat] assert len(concat) == 4, \ f'Please choose a list with 4 symbols which at the beginning of first sentence ' \ f'the end of first sentence, the begin of second sentence, and the end of second' \ f'sentence. Your input is {concat}' for data_name, data_set in data_info.datasets.items(): data_set.apply( lambda x: [concat[0]] + x[Const.INPUTS(0)] + [concat[ 1]] + [concat[2]] + x[Const.INPUTS(1)] + [concat[3]], new_field_name=Const.INPUT) data_set.apply( lambda x: [w for w in x[Const.INPUT] if len(w) > 0], new_field_name=Const.INPUT, is_input=auto_set_input) if seq_len_type is not None: if seq_len_type == 'seq_len': # for data_name, data_set in data_info.datasets.items(): for fields in data_set.get_field_names(): if Const.INPUT in fields: data_set.apply(lambda x: len(x[fields]), new_field_name=fields.replace( Const.INPUT, Const.INPUT_LEN), is_input=auto_set_input) elif seq_len_type == 'mask': for data_name, data_set in data_info.datasets.items(): for fields in data_set.get_field_names(): if Const.INPUT in fields: data_set.apply(lambda x: [1] * len(x[fields]), new_field_name=fields.replace( Const.INPUT, Const.INPUT_LEN), is_input=auto_set_input) elif seq_len_type == 'bert': for data_name, data_set in data_info.datasets.items(): if Const.INPUT not in data_set.get_field_names(): raise KeyError( f'Field ``{Const.INPUT}`` not in {data_name} data set: ' f'got {data_set.get_field_names()}') data_set.apply(lambda x: [0] * (len(x[Const.INPUTS(0)]) + 2) + [1] * (len(x[Const.INPUTS(1)]) + 1), new_field_name=Const.INPUT_LENS(0), is_input=auto_set_input) data_set.apply(lambda x: [1] * len(x[Const.INPUT_LENS(0)]), new_field_name=Const.INPUT_LENS(1), is_input=auto_set_input) if auto_pad_length is not None: cut_text = min( auto_pad_length, cut_text if cut_text is not None else auto_pad_length) if cut_text is not None: for data_name, data_set in data_info.datasets.items(): for fields in data_set.get_field_names(): if (Const.INPUT in fields) or ((Const.INPUT_LEN in fields) and (seq_len_type != 'seq_len')): data_set.apply(lambda x: x[fields][:cut_text], new_field_name=fields, is_input=auto_set_input) data_set_list = [d for n, d in data_info.datasets.items()] assert len(data_set_list) > 0, f'There are NO data sets in data info!' if bert_tokenizer is None: words_vocab = Vocabulary(padding=auto_pad_token) words_vocab = words_vocab.from_dataset( *[d for n, d in data_info.datasets.items() if 'train' in n], field_name=[ n for n in data_set_list[0].get_field_names() if (Const.INPUT in n) ], no_create_entry_dataset=[ d for n, d in data_info.datasets.items() if 'train' not in n ]) target_vocab = Vocabulary(padding=None, unknown=None) target_vocab = target_vocab.from_dataset( *[d for n, d in data_info.datasets.items() if 'train' in n], field_name=Const.TARGET) data_info.vocabs = { Const.INPUT: words_vocab, Const.TARGET: target_vocab } if get_index: for data_name, data_set in data_info.datasets.items(): for fields in data_set.get_field_names(): if Const.INPUT in fields: data_set.apply( lambda x: [words_vocab.to_index(w) for w in x[fields]], new_field_name=fields, is_input=auto_set_input) if Const.TARGET in data_set.get_field_names(): data_set.apply( lambda x: target_vocab.to_index(x[Const.TARGET]), new_field_name=Const.TARGET, is_input=auto_set_input, is_target=auto_set_target) if auto_pad_length is not None: if seq_len_type == 'seq_len': raise RuntimeError( f'the sequence will be padded with the length {auto_pad_length}, ' f'so the seq_len_type cannot be `{seq_len_type}`!') for data_name, data_set in data_info.datasets.items(): for fields in data_set.get_field_names(): if Const.INPUT in fields: data_set.apply( lambda x: x[fields] + [words_vocab.to_index(words_vocab.padding)] * (auto_pad_length - len(x[fields])), new_field_name=fields, is_input=auto_set_input) elif (Const.INPUT_LEN in fields) and (seq_len_type != 'seq_len'): data_set.apply(lambda x: x[fields] + [0] * (auto_pad_length - len(x[fields])), new_field_name=fields, is_input=auto_set_input) for data_name, data_set in data_info.datasets.items(): if isinstance(set_input, list): data_set.set_input(*[ inputs for inputs in set_input if inputs in data_set.get_field_names() ]) if isinstance(set_target, list): data_set.set_target(*[ target for target in set_target if target in data_set.get_field_names() ]) return data_info