bert的实现-数据预处理

1、引入参数代码
需要那个参数再回来查看

parser = argparse.ArgumentParser()
    ## Required parameters
    parser.add_argument("--data_dir",
                        default=None,
                        type=str,
                        required=True,
                        help="The input data dir. Should contain the .tsv files (or other data files) for the task.")
    parser.add_argument("--bert_model", default=None, type=str, required=True,
                        help="Bert pre-trained model selected in the list: bert-base-uncased, "
                        "bert-large-uncased, bert-base-cased, bert-large-cased, bert-base-multilingual-uncased, "
                        "bert-base-multilingual-cased, bert-base-chinese.")
    parser.add_argument("--task_name",
                        default=None,
                        type=str,
                        required=True,
                        help="The name of the task to train.")
    parser.add_argument("--output_dir",
                        default=None,
                        type=str,
                        required=True,
                        help="The output directory where the model predictions and checkpoints will be written.")
                        #输出的地址

    ## Other parameters
    parser.add_argument("--max_seq_length",
                        default=128,
                        type=int,
                        help="The maximum total input sequence length after WordPiece tokenization. \n"
                             "Sequences longer than this will be truncated, and sequences shorter \n"
                             "than this will be padded.")
    parser.add_argument("--do_train",
                        action='store_true',
                        help="Whether to run training.")
    parser.add_argument("--do_eval",
                        action='store_true',
                        help="Whether to run eval on the dev set.")
    parser.add_argument("--do_lower_case",
                        action='store_true',
                        help="Set this flag if you are using an uncased model.")
    parser.add_argument("--train_batch_size",
                        default=32,
                        type=int,
                        help="Total batch size for training.")
    parser.add_argument("--eval_batch_size",
                        default=8,
                        type=int,
                        help="Total batch size for eval.")
    parser.add_argument("--learning_rate",
                        default=5e-5,
                        type=float,
                        help="The initial learning rate for Adam.")
    parser.add_argument("--num_train_epochs",
                        default=3.0,
                        type=float,
                        help="Total number of training epochs to perform.")
    parser.add_argument("--warmup_proportion",
                        default=0.1,
                        type=float,
                        help="Proportion of training to perform linear learning rate warmup for. "
                             "E.g., 0.1 = 10%% of training.")
    parser.add_argument("--no_cuda",
                        action='store_true',
                        help="Whether not to use CUDA when available")
                        #有cuda时候你是否选择关闭cuda
    parser.add_argument("--local_rank",
                        type=int,
                        default=-1,
                        help="local_rank for distributed training on gpus")
                        #是否进行分布式训练：
    parser.add_argument('--seed',
                        type=int,
                        default=42,
                        help="random seed for initialization")
    parser.add_argument('--gradient_accumulation_steps',
                        type=int,
                        default=1,
                        help="Number of updates steps to accumulate before performing a backward/update pass.")
                        #执行向后/更新过程之前要累积的更新步骤数。
                        
    parser.add_argument('--fp16',
                        action='store_true',
                        help="Whether to use 16-bit float precision instead of 32-bit")
    parser.add_argument('--loss_scale',
                        type=float, default=0,
                        help="Loss scaling to improve fp16 numeric stability. Only used when fp16 set to True.\n"
                             "0 (default value): dynamic loss scaling.\n"
                             "Positive power of 2: static loss scaling value.\n")

    args = parser.parse_args()

2、三个标准数据集的预处理函数，打包成字典

 processors = {
        "cola": ColaProcessor,
        "mnli": MnliProcessor,
        "mrpc": MrpcProcessor,
    }

    num_labels_task = {
        "cola": 2,
        "mnli": 3,
        "mrpc": 2,
    }

3、调用gpu，没有gpu就调用cpu进行训练

	if args.local_rank == -1 or args.no_cuda:
	        device = torch.device("cuda" if torch.cuda.is_available() and not args.no_cuda else "cpu")
	        #如果有cuda且不需要关闭cuda就使用gpu，不然就用cpu
	        n_gpu = torch.cuda.device_count()
	        #计算有几个gpu，多gpu进行分布式训练
    else:
        torch.cuda.set_device(args.local_rank)
        device = torch.device("cuda", args.local_rank)
        n_gpu = 1
        # Initializes the distributed backend which will take care of sychronizing nodes/GPUs
        torch.distributed.init_process_group(backend='nccl')
    logger.info("device: {} n_gpu: {}, distributed training: {}, 16-bits training: {}".format(
        device, n_gpu, bool(args.local_rank != -1), args.fp16))

    if args.gradient_accumulation_steps < 1:
    #执行向后/更新过程之前要累积的更新步骤数，如果小于1是错误的
        raise ValueError("Invalid gradient_accumulation_steps parameter: {}, should be >= 1".format(
                            args.gradient_accumulation_steps))

    args.train_batch_size = int(args.train_batch_size / args.gradient_accumulation_steps)
	#设置随机种子使得实验结果可以浮现
    random.seed(args.seed)
    np.random.seed(args.seed)
    torch.manual_seed(args.seed)
    #如果有gpu，也要设置随机种子
    if n_gpu > 0:
        torch.cuda.manual_seed_all(args.seed)

4、进行判断，只有训练和预测两个过程，二选其一；以及训练阶段输出列表不能已经建立完整

  if not args.do_train and not args.do_eval:
        raise ValueError("At least one of `do_train` or `do_eval` must be True.")

  if os.path.exists(args.output_dir) and os.listdir(args.output_dir) and args.do_train:
        raise ValueError("Output directory ({}) already exists and is not empty.".format(args.output_dir))
    os.makedirs(args.output_dir, exist_ok=True)

5、数据集的样子

数据集里第一列是label，CoLA中label一共是2类：0和1。第三列是文本训练集。每个训练集的数据中只有一句话。

6、提取数据文本和label。同时，guid给每一条数据都加上一个单独的id。

class DataProcessor(object):
    """Base class for data converters for sequence classification data sets."""

    def get_train_examples(self, data_dir):
        """Gets a collection of `InputExample`s for the train set."""
        raise NotImplementedError()

    def get_dev_examples(self, data_dir):
        """Gets a collection of `InputExample`s for the dev set."""
        raise NotImplementedError()

    def get_labels(self):
        """Gets the list of labels for this data set."""
        raise NotImplementedError()

    @classmethod
    def _read_tsv(cls, input_file, quotechar=None):
        """Reads a tab separated value file."""
        with open(input_file, "r", encoding='utf-8') as f:
            reader = csv.reader(f, delimiter="\t", quotechar=quotechar)
            lines = []
            for line in reader:
                lines.append(line)
            return lines

class ColaProcessor(DataProcessor):
    """Processor for the CoLA data set (GLUE version)."""

    def get_train_examples(self, data_dir):
        """See base class."""
        return self._create_examples(
            self._read_tsv(os.path.join(data_dir, "train.tsv")), "train")
	#读入train.tsv的文件，保存到train为文件名的文件中
    def get_dev_examples(self, data_dir):
        """See base class."""
        return self._create_examples(
            self._read_tsv(os.path.join(data_dir, "dev.tsv")), "dev")
	#读入dev.tsv的文件，保存到dev为文件名的文件中
    def get_labels(self):
        """See base class."""
        return ["0", "1"]

    def _create_examples(self, lines, set_type):
        """Creates examples for the training and dev sets."""
        examples = []
        for (i, line) in enumerate(lines):
            guid = "%s-%s" % (set_type, i)
            text_a = line[3]
            label = line[1]
            examples.append(
                InputExample(guid=guid, text_a=text_a, text_b=None, label=label))
        return examples
#返回带有id、文本和标签的样本
class InputExample(object):
    """A single training/test example for simple sequence classification."""

    def __init__(self, guid, text_a, text_b=None, label=None):
        """Constructs a InputExample.
        Args:
            guid: Unique id for the example.
            text_a: string. The untokenized text of the first sequence. For single
            sequence tasks, only this sequence must be specified.
            text_b: (Optional) string. The untokenized text of the second sequence.
            Only must be specified for sequence pair tasks.
            label: (Optional) string. The label of the example. This should be
            specified for train and dev examples, but not for test examples.
        """
        self.guid = guid
        self.text_a = text_a
        self.text_b = text_b
        self.label = label

补充：

read_csv() 读入逗号分隔文件；
read_csv2() 读取分号分隔文件；
read_tsv() 读取制表符分隔文件；
read_delim() 读取使用任意分隔符的文件

7、调用预训练的分词器

    tokenizer = BertTokenizer.from_pretrained(args.bert_model, do_lower_case=args.do_lower_case)

作用：

1. 个替换原文本中符号，
2. 检测元文本中的单词是否在预训练字典中
3. 将单词替换成字典中对应的id
4. 对文本的长度进行padding

class BertTokenizer(object):
    """Runs end-to-end tokenization: punctuation splitting + wordpiece"""

    def __init__(self, vocab_file, do_lower_case=True, max_len=None,
                 never_split=("[UNK]", "[SEP]", "[PAD]", "[CLS]", "[MASK]")):
        #判断vocab_file是否为文件，也就决定了它是否能被加载
        if not os.path.isfile(vocab_file):
            raise ValueError(
                "Can't find a vocabulary file at path '{}'. To load the vocabulary from a Google pretrained "
                "model use `tokenizer = BertTokenizer.from_pretrained(PRETRAINED_MODEL_NAME)`".format(vocab_file))
        #加载词汇表
        self.vocab = load_vocab(vocab_file)
        #建立词汇和编号的对应关系词典
        self.ids_to_tokens = collections.OrderedDict(
            [(ids, tok) for tok, ids in self.vocab.items()])
        #加载分词器
        self.basic_tokenizer = BasicTokenizer(do_lower_case=do_lower_case,
                                              never_split=never_split)
        self.wordpiece_tokenizer = WordpieceTokenizer(vocab=self.vocab)
        self.max_len = max_len if max_len is not None else int(1e12)

    def tokenize(self, text):
    #	进行分词
        split_tokens = []
        for token in self.basic_tokenizer.tokenize(text):
            for sub_token in self.wordpiece_tokenizer.tokenize(token):
                split_tokens.append(sub_token)
        return split_tokens

    def convert_tokens_to_ids(self, tokens):
        """Converts a sequence of tokens into ids using the vocab."""
        #用词典将token转化为序列
        ids = []
        for token in tokens:
            ids.append(self.vocab[token])
        if len(ids) > self.max_len:
            raise ValueError(
                "Token indices sequence length is longer than the specified maximum "
                " sequence length for this BERT model ({} > {}). Running this"
                " sequence through BERT will result in indexing errors".format(len(ids), self.max_len)
            )
        return ids

    def convert_ids_to_tokens(self, ids):
        """Converts a sequence of ids in wordpiece tokens using the vocab."""
        #通过self.ids_to_tokens（里面建立好的词典）将id转化为token
        tokens = []
        for i in ids:
            tokens.append(self.ids_to_tokens[i])
        return tokens
 	#通过类方法加载预训练模型
    @classmethod
    def from_pretrained(cls, pretrained_model_name, cache_dir=None, *inputs, **kwargs):
        """
        Instantiate a PreTrainedBertModel from a pre-trained model file.
        Download and cache the pre-trained model file if needed.
        """
        #内部保存着已有的预训练模型的下载地址
        if pretrained_model_name in PRETRAINED_VOCAB_ARCHIVE_MAP:
            vocab_file = PRETRAINED_VOCAB_ARCHIVE_MAP[pretrained_model_name]
        else:
            vocab_file = pretrained_model_name
       	#os.listdir()用于返回一个由文件名和目录名组成的列表
        if os.path.isdir(vocab_file):
            vocab_file = os.path.join(vocab_file, VOCAB_NAME)
        # redirect to the cache, if necessary
        try:
            resolved_vocab_file = cached_path(vocab_file, cache_dir=cache_dir)
        except FileNotFoundError:
            logger.error(
                "Model name '{}' was not found in model name list ({}). "
                "We assumed '{}' was a path or url but couldn't find any file "
                "associated to this path or url.".format(
                    pretrained_model_name,
                    ', '.join(PRETRAINED_VOCAB_ARCHIVE_MAP.keys()),
                    vocab_file))
            return None
        if resolved_vocab_file == vocab_file:
            logger.info("loading vocabulary file {}".format(vocab_file))
        else:
            logger.info("loading vocabulary file {} from cache at {}".format(
                vocab_file, resolved_vocab_file))
        if pretrained_model_name in PRETRAINED_VOCAB_POSITIONAL_EMBEDDINGS_SIZE_MAP:
            # if we're using a pretrained model, ensure the tokenizer wont index sequences longer
            # than the number of positional embeddings
            max_len = PRETRAINED_VOCAB_POSITIONAL_EMBEDDINGS_SIZE_MAP[pretrained_model_name]
            kwargs['max_len'] = min(kwargs.get('max_len', int(1e12)), max_len)
        # Instantiate tokenizer.
        tokenizer = cls(resolved_vocab_file, *inputs, **kwargs)
        return tokenizer