基于BERT的情感分析模型_bert情感分析

目录
基于BERT的情感分析模型 1
一、 基于Transformer的词向量表示 1
各个词对 it 编码影响程度示意图 4
二、 数据收集及预处理 5

1. 数据集 5
   2.文本预处理 6
   （1）数据清洗 6
   （2）文本分词 7
   （3）过滤停用词 7
   三、 基于BERT的情感分析模型 8
   输出层示意图 12
   四、 实验 14
   1.评价指标 14
   三分类混淆矩阵 14
   2.实验结果 16
   基于BERT的情感分析模型
   一、基于Transformer的词向量表示
   Word2vec 由词义的分布式假设出发，每一个单词被映射到一个唯一的稠密向量。这显然无法处理一词多义的问题：自然语言中每个词都有可能有多个不同的意思，那么如果需要用数值表示它的意思，或至少不应该是固定的某一向量。例如：
   例 2： ①The animal didn’t cross the street because it was too tired.
   ②The animal didn’t cross the street because it was too narrow.
   通过这两个句子可以看出，其中的 it 分别指代 animal 和 street，对于我们而言很容易区分其中的区别，然而对于计算机而言却并不容易。使用传统的 Word2vec 产生的词表示是静态的，不考虑上下文的，如果对两个 it 进行向量化表示，得到的词向量是一样的，这显然是有瑕疵的。
   在介绍 Transformer 之前先来介绍一下注意力机制(Attention Mechanism)，注意力机制最早被应用于图像研究领域。它源于对人类大脑工作原理的分析，其本质上是注意力资源分配的模型。例如，当我们看图片时，我们的注意力肯定会集中在某个部分， 随着眼睛的移动，注意力又转移到图片的另一个部分。任何时刻我们的注意力分布是不一样的。Google 公司在 2017 年，将注意力机制定义为查询作用于键值的过程。注意力机制有三个主要元素：输入、查询和注意力矩阵。三者相结合，产生“注意力权重”，根据产生的权重就可以区分不同语境对目标词的重要性。文本情感分析领域内的注意力机制主要被归纳为三个模型：文本注意力、特征- 文本注意力与自注意力。这里主要介绍自注意力(self-attention)，self-attention 机制包含了不止一个特征，每个单词都依次与句子中所有的但那次相互作用。每一个单词都会通过这一系列的和计算得到一个其本身在该语境中的输出特征。所以 self-attention 的输出是多个单词的注意力特征的集合。
   本文转载自：http://www.biyezuopin.vip/onews.asp?id=16514

# coding=utf-8
# Copyright 2018 The Google AI Language Team Authors.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""BERT finetuning runner."""

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import collections
import csv
import os
import modeling
import optimization
import tokenization
import tensorflow as tf
import numpy as np
import globalvar as gl
flags = tf.flags

FLAGS = flags.FLAGS

## Required parameters
flags.DEFINE_string(
    "data_dir", None,
    "The input data dir. Should contain the .tsv files (or other data files) "
    "for the task.")

flags.DEFINE_string(
    "bert_config_file", None,
    "The config json file corresponding to the pre-trained BERT model. "
    "This specifies the model architecture.")

flags.DEFINE_string("task_name", None, "The name of the task to train.")

flags.DEFINE_string("vocab_file", None,
                    "The vocabulary file that the BERT model was trained on.")

flags.DEFINE_string(
    "output_dir", None,
    "The output directory where the model checkpoints will be written.")

## Other parameters

flags.DEFINE_string(
    "init_checkpoint", None,
    "Initial checkpoint (usually from a pre-trained BERT model).")

flags.DEFINE_bool(
    "do_lower_case", True,
    "Whether to lower case the input text. Should be True for uncased "
    "models and False for cased models.")

flags.DEFINE_integer(
    "max_seq_length", 128,
    "The maximum total input sequence length after WordPiece tokenization. "
    "Sequences longer than this will be truncated, and sequences shorter "
    "than this will be padded.")

flags.DEFINE_bool("do_train", False, "Whether to run training.")

flags.DEFINE_bool("do_eval", False, "Whether to run eval on the dev set.")

flags.DEFINE_bool(
    "do_predict", False,
    "Whether to run the model in inference mode on the test set.")

flags.DEFINE_integer("train_batch_size", 32, "Total batch size for training.")

flags.DEFINE_integer("eval_batch_size", 8, "Total batch size for eval.")

flags.DEFINE_integer("predict_batch_size", 8, "Total batch size for predict.")

flags.DEFINE_float("learning_rate", 5e-5, "The initial learning rate for Adam.")

flags.DEFINE_float("num_train_epochs", 3.0,
                   "Total number of training epochs to perform.")

flags.DEFINE_float(
    "warmup_proportion", 0.1,
    "Proportion of training to perform linear learning rate warmup for. "
    "E.g., 0.1 = 10% of training.")

flags.DEFINE_integer("save_checkpoints_steps", 1000,
                     "How often to save the model checkpoint.")

flags.DEFINE_integer("iterations_per_loop", 1000,
                     "How many steps to make in each estimator call.")

flags.DEFINE_bool("use_tpu", False, "Whether to use TPU or GPU/CPU.")

tf.flags.DEFINE_string(
    "tpu_name", None,
    "The Cloud TPU to use for training. This should be either the name "
    "used when creating the Cloud TPU, or a grpc://ip.address.of.tpu:8470 "
    "url.")

tf.flags.DEFINE_string(
    "tpu_zone", None,
    "[Optional] GCE zone where the Cloud TPU is located in. If not "
    "specified, we will attempt to automatically detect the GCE project from "
    "metadata.")

tf.flags.DEFINE_string(
    "gcp_project", None,
    "[Optional] Project name for the Cloud TPU-enabled project. If not "
    "specified, we will attempt to automatically detect the GCE project from "
    "metadata.")

tf.flags.DEFINE_string("master", None, "[Optional] TensorFlow master URL.")

flags.DEFINE_integer(
    "num_tpu_cores", 8,
    "Only used if `use_tpu` is True. Total number of TPU cores to use.")


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


class PaddingInputExample(object):
  """Fake example so the num input examples is a multiple of the batch size.

  When running eval/predict on the TPU, we need to pad the number of examples
  to be a multiple of the batch size, because the TPU requires a fixed batch
  size. The alternative is to drop the last batch, which is bad because it means
  the entire output data won't be generated.

  We use this class instead of `None` because treating `None` as padding
  battches could cause silent errors.
  """


class InputFeatures(object):
  """A single set of features of data."""

  def __init__(self,
               input_ids,
               input_mask,
               segment_ids,
               label_id,
               is_real_example=True):
    self.input_ids = input_ids
    self.input_mask = input_mask
    self.segment_ids = segment_ids
    self.label_id = label_id
    self.is_real_example = is_real_example


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_test_examples(self, data_dir):
    """Gets a collection of `InputExample`s for prediction."""
    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 tf.gfile.Open(input_file, "r") as f:
      reader = csv.reader(f, delimiter="\t", quotechar=quotechar)
      lines = []
      for line in reader:
        lines.append(line)
      return lines

class SimProcessor(DataProcessor):
  """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."""
    file_path=os.path.join(data_dir,'train.txt')
    f = open(file_path,'r',encoding='utf-8')
    train_data=[]
    index = 0
    for line in f.readlines():
        guid = "train-%d" % (index)
        line = line.replace('\n','').split('\t')
        text_a = tokenization.convert_to_unicode(str(line[1]))
        label = str(line[2])
        train_data.append(
            InputExample(guid=guid, text_a=text_a, text_b=None, label=label))
        index = index+1
    return train_data

  def get_dev_examples(self, data_dir):
    """Gets a collection of `InputExample`s for the dev set."""
    file_path = os.path.join(data_dir, 'dev.txt')
    f = open(file_path, 'r', encoding='utf-8')
    dev_data = []
    index = 0
    for line in f.readlines():
        guid = "dev-%d" % (index)
        line = line.replace('\n', '').split('\t')
        text_a = tokenization.convert_to_unicode(str(line[1]))
        label = str(line[2])
        dev_data.append(
            InputExample(guid=guid, text_a=text_a, text_b=None, label=label))
        index = index + 1
    return dev_data

  def get_test_examples(self, data_dir):
    path = gl.get_value('val_path')
    print(path)
    """Gets a collection of `InputExample`s for prediction."""
    test_data = []
    index = 0
    val_text = gl.get_value('val_text')
    if path == '打开文件':#获取手动输入内容
        val_text = gl.get_value('val_text')
        list = val_text.split('\n');
        for line in list:
            guid = "dev-%d" % (index)
            line = line.replace('\n', '').split('\t')
            text_a = tokenization.convert_to_unicode(str(line[1]))
            label = str(1)
            test_data.append(
                InputExample(guid=guid, text_a=text_a, text_b=None, label=label))
            index = index + 1
    else:
        file_path = os.path.join(path)#获取文件输入内容
        f = open(file_path, 'r', encoding='utf-8')
        for line in f.readlines():
            guid = "dev-%d" % (index)
            line = line.replace('\n', '').split('\t')
            text_a = tokenization.convert_to_unicode(str(line[1]))
            label = str(1)
            test_data.append(
                InputExample(guid=guid, text_a=text_a, text_b=None, label=label))
            index = index + 1
    return test_data

  def get_labels(self):
    """Gets the list of labels for this data set."""
    return ["0", "1", "2"]


class XnliProcessor(DataProcessor):
  """Processor for the XNLI data set."""

  def __init__(self):
    self.language = "zh"

  def get_train_examples(self, data_dir):
    """See base class."""
    lines = self._read_tsv(
        os.path.join(data_dir, "multinli",
                     "multinli.train.%s.tsv" % self.language))
    examples = []
    for (i, line) in enumerate(lines):
      if i == 0:
        continue
      guid = "train-%d" % (i)
      text_a = tokenization.convert_to_unicode(line[0])
      text_b = tokenization.convert_to_unicode(line[1])
      label = tokenization.convert_to_unicode(line[2])
      if label == tokenization.convert_to_unicode("contradictory"):
        label = tokenization.convert_to_unicode("contradiction")
      examples.append(
          InputExample(guid=guid, text_a=text_a, text_b=text_b, label=label))
    return examples

  def get_dev_examples(self, data_dir):
    """See base class."""
    lines = self._read_tsv(os.path.join(data_dir, "xnli.dev.tsv"))
    examples = []
    for (i, line) in enumerate(lines):
      if i == 0:
        continue
      guid = "dev-%d" % (i)
      language = tokenization.convert_to_unicode(line[0])
      if language != tokenization.convert_to_unicode(self.language):
        continue
      text_a = tokenization.convert_to_unicode(line[6])
      text_b = tokenization.convert_to_unicode(line[7])
      label = tokenization.convert_to_unicode(line[1])
      examples.append(
          InputExample(guid=guid, text_a=text_a, text_b=text_b, label=label))
    return examples

  def get_labels(self):
    """See base class."""
    return ["contradiction", "entailment", "neutral"]


class MnliProcessor(DataProcessor):
  """Processor for the MultiNLI 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")

  def get_dev_examples(self, data_dir):
    """See base class."""
    return self._create_examples(
        self._read_tsv(os.path.join(data_dir, "dev_matched.tsv")),
        "dev_matched")

  def get_test_examples(self, data_dir):
    """See base class."""
    return self._create_examples(
        self._read_tsv(os.path.join(data_dir, "test_matched.tsv")), "test")

  def get_labels(self):
    """See base class."""
    return ["contradiction", "entailment", "neutral"]

  def _create_examples(self, lines, set_type):
    """Creates examples for the training and dev sets."""
    examples = []
    for (i, line) in enumerate(lines):
      if i == 0:
        continue
      guid = "%s-%s" % (set_type, tokenization.convert_to_unicode(line[0]))
      text_a = tokenization.convert_to_unicode(line[8])
      text_b = tokenization.convert_to_unicode(line[9])
      if set_type == "test":
        label = "contradiction"
      else:
        label = tokenization.convert_to_unicode(line[-1])
      examples.append(
          InputExample(guid=guid, text_a=text_a, text_b=text_b, label=label))
    return examples


class MrpcProcessor(DataProcessor):
  """Processor for the MRPC 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")

  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")

  def get_test_examples(self, data_dir):
    """See base class."""
    return self._create_examples(
        self._read_tsv(os.path.join(data_dir, "test.tsv")), "test")

  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):
      if i == 0:
        continue
      guid = "%s-%s" % (set_type, i)
      text_a = tokenization.convert_to_unicode(line[3])
      text_b = tokenization.convert_to_unicode(line[4])
      if set_type == "test":
        label = "0"
      else:
        label = tokenization.convert_to_unicode(line[0])
      examples.append(
          InputExample(guid=guid, text_a=text_a, text_b=text_b, label=label))
    return examples


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")

  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")

  def get_test_examples(self, data_dir):
    """See base class."""
    return self._create_examples(
        self._read_tsv(os.path.join(data_dir, "test.tsv")), "test")

  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):
      # Only the test set has a header
      if set_type == "test" and i == 0:
        continue
      guid = "%s-%s" % (set_type, i)
      if set_type == "test":
        text_a = tokenization.convert_to_unicode(line[1])
        label = "0"
      else:
        text_a = tokenization.convert_to_unicode(line[3])
        label = tokenization.convert_to_unicode(line[1])
      examples.append(
          InputExample(guid=guid, text_a=text_a, text_b=None, label=label))
    return examples


def convert_single_example(ex_index, example, label_list, max_seq_length,
                           tokenizer):
  """Converts a single `InputExample` into a single `InputFeatures`."""

  if isinstance(example, PaddingInputExample):
    return InputFeatures(
        input_ids=[0] * max_seq_length,
        input_mask=[0] * max_seq_length,
        segment_ids=[0] * max_seq_length,
        label_id=0,
        is_real_example=False)

  label_map = {}
  for (i, label) in enumerate(label_list):
    label_map[label] = i

  tokens_a = tokenizer.tokenize(example.text_a)
  tokens_b = None
  if example.text_b:
    tokens_b = tokenizer.tokenize(example.text_b)

  if tokens_b:
    # Modifies `tokens_a` and `tokens_b` in place so that the total
    # length is less than the specified length.
    # Account for [CLS], [SEP], [SEP] with "- 3"
    _truncate_seq_pair(tokens_a, tokens_b, max_seq_length - 3)
  else:
    # Account for [CLS] and [SEP] with "- 2"
    if len(tokens_a) > max_seq_length - 2:
      tokens_a = tokens_a[0:(max_seq_length - 2)]

  # The convention in BERT is:
  # (a) For sequence pairs:
  #  tokens:   [CLS] is this jack ##son ##ville ? [SEP] no it is not . [SEP]
  #  type_ids: 0     0  0    0    0     0       0 0     1  1  1  1   1 1
  # (b) For single sequences:
  #  tokens:   [CLS] the dog is hairy . [SEP]
  #  type_ids: 0     0   0   0  0     0 0
  #
  # Where "type_ids" are used to indicate whether this is the first
  # sequence or the second sequence. The embedding vectors for `type=0` and
  # `type=1` were learned during pre-training and are added to the wordpiece
  # embedding vector (and position vector). This is not *strictly* necessary
  # since the [SEP] token unambiguously separates the sequences, but it makes
  # it easier for the model to learn the concept of sequences.
  #
  # For classification tasks, the first vector (corresponding to [CLS]) is
  # used as the "sentence vector". Note that this only makes sense because
  # the entire model is fine-tuned.
  tokens = []
  segment_ids = []
  tokens.append("[CLS]")
  segment_ids.append(0)
  for token in tokens_a:
    tokens.append(token)
    segment_ids.append(0)
  tokens.append("[SEP]")
  segment_ids.append(0)

  if tokens_b:
    for token in tokens_b:
      tokens.append(token)
      segment_ids.append(1)
    tokens.append("[SEP]")
    segment_ids.append(1)

  input_ids = tokenizer.convert_tokens_to_ids(tokens)

  # The mask has 1 for real tokens and 0 for padding tokens. Only real
  # tokens are attended to.
  input_mask = [1] * len(input_ids)

  # Zero-pad up to the sequence length.
  while len(input_ids) < max_seq_length:
    input_ids.append(0)
    input_mask.append(0)
    segment_ids.append(0)

  assert len(input_ids) == max_seq_length
  assert len(input_mask) == max_seq_length
  assert len(segment_ids) == max_seq_length

  label_id = label_map[example.label]
  L = gl.get_value('pre_deal')
  if ex_index < 20000:
    tf.logging.info("*** Example ***")
    tf.logging.info("guid: %s" % (example.guid))
    tf.logging.info("tokens: %s" % " ".join(
        [tokenization.printable_text(x) for x in tokens]))
    tf.logging.info("input_ids: %s" % " ".join([str(x) for x in input_ids]))
    tf.logging.info("input_mask: %s" % " ".join([str(x) for x in input_mask]))
    tf.logging.info("segment_ids: %s" % " ".join([str(x) for x in segment_ids]))
    tf.logging.info("label: %s (id = %d)" % (example.label, label_id))
    output_line = "*** Example ***" + "\n" + "guid: %s" % (example.guid) + "\n" + "tokens: %s" % " ".join(
        [tokenization.printable_text(x) for x in tokens]) + "\n"+"input_ids: %s" % " ".join([str(x) for x in input_ids])+"\n"
            # output_line = "\t".join(
            #   str(class_probability)
            #  for class_probability in probabilities) +"\t"+str(np.argmax(probabilities))+ "\n"
    L=L+output_line
    gl.set_value('pre_deal',L)
    print("ok")


  feature = InputFeatures(
      input_ids=input_ids,
      input_mask=input_mask,
      segment_ids=segment_ids,
      label_id=label_id,
      is_real_example=True)
  return feature


def file_based_convert_examples_to_features(
    examples, label_list, max_seq_length, tokenizer, output_file):
  """Convert a set of `InputExample`s to a TFRecord file."""
  gl._init()
  L=''
  gl.set_value('pre_deal', L)
  writer = tf.python_io.TFRecordWriter(output_file)

  for (ex_index, example) in enumerate(examples):
    if ex_index % 10000 == 0:
      tf.logging.info("Writing example %d of %d" % (ex_index, len(examples)))

    feature = convert_single_example(ex_index, example, label_list,
                                     max_seq_length, tokenizer)

    def create_int_feature(values):
      f = tf.train.Feature(int64_list=tf.train.Int64List(value=list(values)))
      return f

    features = collections.OrderedDict()
    features["input_ids"] = create_int_feature(feature.input_ids)
    features["input_mask"] = create_int_feature(feature.input_mask)
    features["segment_ids"] = create_int_feature(feature.segment_ids)
    features["label_ids"] = create_int_feature([feature.label_id])
    features["is_real_example"] = create_int_feature(
        [int(feature.is_real_example)])

    tf_example = tf.train.Example(features=tf.train.Features(feature=features))
    writer.write(tf_example.SerializeToString())
  L = gl.get_value('pre_deal')
  output_predict_file = os.path.join(FLAGS.output_dir, "test_results_3.txt")
  with tf.gfile.GFile(output_predict_file, "w") as writer:
      writer.write(L)
  writer.close()


def file_based_input_fn_builder(input_file, seq_length, is_training,
                                drop_remainder):
  """Creates an `input_fn` closure to be passed to TPUEstimator."""

  name_to_features = {
      "input_ids": tf.FixedLenFeature([seq_length], tf.int64),
      "input_mask": tf.FixedLenFeature([seq_length], tf.int64),
      "segment_ids": tf.FixedLenFeature([seq_length], tf.int64),
      "label_ids": tf.FixedLenFeature([], tf.int64),
      "is_real_example": tf.FixedLenFeature([], tf.int64),
  }

  def _decode_record(record, name_to_features):
    """Decodes a record to a TensorFlow example."""
    example = tf.parse_single_example(record, name_to_features)

    # tf.Example only supports tf.int64, but the TPU only supports tf.int32.
    # So cast all int64 to int32.
    for name in list(example.keys()):
      t = example[name]
      if t.dtype == tf.int64:
        t = tf.to_int32(t)
      example[name] = t

    return example

  def input_fn(params):
    """The actual input function."""
    batch_size = params["batch_size"]

    # For training, we want a lot of parallel reading and shuffling.
    # For eval, we want no shuffling and parallel reading doesn't matter.
    d = tf.data.TFRecordDataset(input_file)
    if is_training:
      d = d.repeat()
      d = d.shuffle(buffer_size=100)

    d = d.apply(
        tf.contrib.data.map_and_batch(
            lambda record: _decode_record(record, name_to_features),
            batch_size=batch_size,
            drop_remainder=drop_remainder))

    return d

  return input_fn


def _truncate_seq_pair(tokens_a, tokens_b, max_length):
  """Truncates a sequence pair in place to the maximum length."""

  # This is a simple heuristic which will always truncate the longer sequence
  # one token at a time. This makes more sense than truncating an equal percent
  # of tokens from each, since if one sequence is very short then each token
  # that's truncated likely contains more information than a longer sequence.
  while True:
    total_length = len(tokens_a) + len(tokens_b)
    if total_length <= max_length:
      break
    if len(tokens_a) > len(tokens_b):
      tokens_a.pop()
    else:
      tokens_b.pop()


def create_model(bert_config, is_training, input_ids, input_mask, segment_ids,
                 labels, num_labels, use_one_hot_embeddings):
  """Creates a classification model."""
  model = modeling.BertModel(
      config=bert_config,
      is_training=is_training,
      input_ids=input_ids,
      input_mask=input_mask,
      token_type_ids=segment_ids,
      use_one_hot_embeddings=use_one_hot_embeddings)

  # In the demo, we are doing a simple classification task on the entire
  # segment.
  #
  # If you want to use the token-level output, use model.get_sequence_output()
  # instead.
  output_layer = model.get_pooled_output()

  hidden_size = output_layer.shape[-1].value

  output_weights = tf.get_variable(
      "output_weights", [num_labels, hidden_size],
      initializer=tf.truncated_normal_initializer(stddev=0.02))

  output_bias = tf.get_variable(
      "output_bias", [num_labels], initializer=tf.zeros_initializer())

  with tf.variable_scope("loss"):
    if is_training:
      # I.e., 0.1 dropout
      output_layer = tf.nn.dropout(output_layer, keep_prob=0.9)

    logits = tf.matmul(output_layer, output_weights, transpose_b=True)
    logits = tf.nn.bias_add(logits, output_bias)
    probabilities = tf.nn.softmax(logits, axis=-1)
    log_probs = tf.nn.log_softmax(logits, axis=-1)

    one_hot_labels = tf.one_hot(labels, depth=num_labels, dtype=tf.float32)

    per_example_loss = -tf.reduce_sum(one_hot_labels * log_probs, axis=-1)
    loss = tf.reduce_mean(per_example_loss)

    return (loss, per_example_loss, logits, probabilities)


def model_fn_builder(bert_config, num_labels, init_checkpoint, learning_rate,
                     num_train_steps, num_warmup_steps, use_tpu,
                     use_one_hot_embeddings):
  """Returns `model_fn` closure for TPUEstimator."""

  def model_fn(features, labels, mode, params):  # pylint: disable=unused-argument
    """The `model_fn` for TPUEstimator."""

    tf.logging.info("*** Features ***")
    for name in sorted(features.keys()):
      tf.logging.info("  name = %s, shape = %s" % (name, features[name].shape))

    input_ids = features["input_ids"]
    input_mask = features["input_mask"]
    segment_ids = features["segment_ids"]
    label_ids = features["label_ids"]
    is_real_example = None
    if "is_real_example" in features:
      is_real_example = tf.cast(features["is_real_example"], dtype=tf.float32)
    else:
      is_real_example = tf.ones(tf.shape(label_ids), dtype=tf.float32)

    is_training = (mode == tf.estimator.ModeKeys.TRAIN)

    (total_loss, per_example_loss, logits, probabilities) = create_model(
        bert_config, is_training, input_ids, input_mask, segment_ids, label_ids,
        num_labels, use_one_hot_embeddings)

    tvars = tf.trainable_variables()
    initialized_variable_names = {}
    scaffold_fn = None
    if init_checkpoint:
      (assignment_map, initialized_variable_names
      ) = modeling.get_assignment_map_from_checkpoint(tvars, init_checkpoint)
      if use_tpu:

        def tpu_scaffold():
          tf.train.init_from_checkpoint(init_checkpoint, assignment_map)
          return tf.train.Scaffold()

        scaffold_fn = tpu_scaffold
      else:
        tf.train.init_from_checkpoint(init_checkpoint, assignment_map)

    tf.logging.info("**** Trainable Variables ****")
    for var in tvars:
      init_string = ""
      if var.name in initialized_variable_names:
        init_string = ", *INIT_FROM_CKPT*"
      tf.logging.info("  name = %s, shape = %s%s", var.name, var.shape,
                      init_string)

    output_spec = None
    if mode == tf.estimator.ModeKeys.TRAIN:

      train_op = optimization.create_optimizer(
          total_loss, learning_rate, num_train_steps, num_warmup_steps, use_tpu)

      output_spec = tf.contrib.tpu.TPUEstimatorSpec(
          mode=mode,
          loss=total_loss,
          train_op=train_op,
          scaffold_fn=scaffold_fn)
    elif mode == tf.estimator.ModeKeys.EVAL:

      def metric_fn(per_example_loss, label_ids, logits, is_real_example):
        predictions = tf.argmax(logits, axis=-1, output_type=tf.int32)
        accuracy = tf.metrics.accuracy(
            labels=label_ids, predictions=predictions, weights=is_real_example)
        loss = tf.metrics.mean(values=per_example_loss, weights=is_real_example)
        return {
            "eval_accuracy": accuracy,
            "eval_loss": loss,
        }

      eval_metrics = (metric_fn,
                      [per_example_loss, label_ids, logits, is_real_example])
      output_spec = tf.contrib.tpu.TPUEstimatorSpec(
          mode=mode,
          loss=total_loss,
          eval_metrics=eval_metrics,
          scaffold_fn=scaffold_fn)
    else:
      output_spec = tf.contrib.tpu.TPUEstimatorSpec(
          mode=mode,
          predictions={"probabilities": probabilities},
          scaffold_fn=scaffold_fn)
    return output_spec

  return model_fn


# This function is not used by this file but is still used by the Colab and
# people who depend on it.
def input_fn_builder(features, seq_length, is_training, drop_remainder):
  """Creates an `input_fn` closure to be passed to TPUEstimator."""

  all_input_ids = []
  all_input_mask = []
  all_segment_ids = []
  all_label_ids = []

  for feature in features:
    all_input_ids.append(feature.input_ids)
    all_input_mask.append(feature.input_mask)
    all_segment_ids.append(feature.segment_ids)
    all_label_ids.append(feature.label_id)

  def input_fn(params):
    """The actual input function."""
    batch_size = params["batch_size"]

    num_examples = len(features)

    # This is for demo purposes and does NOT scale to large data sets. We do
    # not use Dataset.from_generator() because that uses tf.py_func which is
    # not TPU compatible. The right way to load data is with TFRecordReader.
    d = tf.data.Dataset.from_tensor_slices({
        "input_ids":
            tf.constant(
                all_input_ids, shape=[num_examples, seq_length],
                dtype=tf.int32),
        "input_mask":
            tf.constant(
                all_input_mask,
                shape=[num_examples, seq_length],
                dtype=tf.int32),
        "segment_ids":
            tf.constant(
                all_segment_ids,
                shape=[num_examples, seq_length],
                dtype=tf.int32),
        "label_ids":
            tf.constant(all_label_ids, shape=[num_examples], dtype=tf.int32),
    })

    if is_training:
      d = d.repeat()
      d = d.shuffle(buffer_size=100)

    d = d.batch(batch_size=batch_size, drop_remainder=drop_remainder)
    return d

  return input_fn


# This function is not used by this file but is still used by the Colab and
# people who depend on it.
def convert_examples_to_features(examples, label_list, max_seq_length,
                                 tokenizer):
  """Convert a set of `InputExample`s to a list of `InputFeatures`."""

  features = []
  for (ex_index, example) in enumerate(examples):
    if ex_index % 10000 == 0:
      tf.logging.info("Writing example %d of %d" % (ex_index, len(examples)))

    feature = convert_single_example(ex_index, example, label_list,
                                     max_seq_length, tokenizer)

    features.append(feature)
  return features

def run(_):
  tf.logging.set_verbosity(tf.logging.INFO)

  processors = {
      "cola": ColaProcessor,
      "mnli": MnliProcessor,
      "mrpc": MrpcProcessor,
      "xnli": XnliProcessor,
      "sim" : SimProcessor,
  }

  tokenization.validate_case_matches_checkpoint(FLAGS.do_lower_case,
                                                FLAGS.init_checkpoint)

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

  bert_config = modeling.BertConfig.from_json_file(FLAGS.bert_config_file)

  if FLAGS.max_seq_length > bert_config.max_position_embeddings:
    raise ValueError(
        "Cannot use sequence length %d because the BERT model "
        "was only trained up to sequence length %d" %
        (FLAGS.max_seq_length, bert_config.max_position_embeddings))

  tf.gfile.MakeDirs(FLAGS.output_dir)

  task_name = FLAGS.task_name.lower()

  if task_name not in processors:
    raise ValueError("Task not found: %s" % (task_name))

  processor = processors[task_name]()

  label_list = processor.get_labels()

  tokenizer = tokenization.FullTokenizer(
      vocab_file=FLAGS.vocab_file, do_lower_case=FLAGS.do_lower_case)

  tpu_cluster_resolver = None
  if FLAGS.use_tpu and FLAGS.tpu_name:
    tpu_cluster_resolver = tf.contrib.cluster_resolver.TPUClusterResolver(
        FLAGS.tpu_name, zone=FLAGS.tpu_zone, project=FLAGS.gcp_project)

  is_per_host = tf.contrib.tpu.InputPipelineConfig.PER_HOST_V2
  run_config = tf.contrib.tpu.RunConfig(
      cluster=tpu_cluster_resolver,
      master=FLAGS.master,
      model_dir=FLAGS.output_dir,
      save_checkpoints_steps=FLAGS.save_checkpoints_steps,
      tpu_config=tf.contrib.tpu.TPUConfig(
          iterations_per_loop=FLAGS.iterations_per_loop,
          num_shards=FLAGS.num_tpu_cores,
          per_host_input_for_training=is_per_host))

  train_examples = None
  num_train_steps = None
  num_warmup_steps = None
  if FLAGS.do_train:
    train_examples = processor.get_train_examples(FLAGS.data_dir)
    num_train_steps = int(
        len(train_examples) / FLAGS.train_batch_size * FLAGS.num_train_epochs)
    num_warmup_steps = int(num_train_steps * FLAGS.warmup_proportion)

  model_fn = model_fn_builder(
      bert_config=bert_config,
      num_labels=len(label_list),
      init_checkpoint=FLAGS.init_checkpoint,
      learning_rate=FLAGS.learning_rate,
      num_train_steps=num_train_steps,
      num_warmup_steps=num_warmup_steps,
      use_tpu=FLAGS.use_tpu,
      use_one_hot_embeddings=FLAGS.use_tpu)

  # If TPU is not available, this will fall back to normal Estimator on CPU
  # or GPU.
  estimator = tf.contrib.tpu.TPUEstimator(
      use_tpu=FLAGS.use_tpu,
      model_fn=model_fn,
      config=run_config,
      train_batch_size=FLAGS.train_batch_size,
      eval_batch_size=FLAGS.eval_batch_size,
      predict_batch_size=FLAGS.predict_batch_size)

  if FLAGS.do_train:
    train_file = os.path.join(FLAGS.output_dir, "train.tf_record")
    file_based_convert_examples_to_features(
        train_examples, label_list, FLAGS.max_seq_length, tokenizer, train_file)
    tf.logging.info("***** Running training *****")
    tf.logging.info("  Num examples = %d", len(train_examples))
    tf.logging.info("  Batch size = %d", FLAGS.train_batch_size)
    tf.logging.info("  Num steps = %d", num_train_steps)
    train_input_fn = file_based_input_fn_builder(
        input_file=train_file,
        seq_length=FLAGS.max_seq_length,
        is_training=True,
        drop_remainder=True)
    estimator.train(input_fn=train_input_fn, max_steps=num_train_steps)

  if FLAGS.do_eval:
    eval_examples = processor.get_dev_examples(FLAGS.data_dir)
    num_actual_eval_examples = len(eval_examples)
    if FLAGS.use_tpu:
      # TPU requires a fixed batch size for all batches, therefore the number
      # of examples must be a multiple of the batch size, or else examples
      # will get dropped. So we pad with fake examples which are ignored
      # later on. These do NOT count towards the metric (all tf.metrics
      # support a per-instance weight, and these get a weight of 0.0).
      while len(eval_examples) % FLAGS.eval_batch_size != 0:
        eval_examples.append(PaddingInputExample())

    eval_file = os.path.join(FLAGS.output_dir, "eval.tf_record")
    file_based_convert_examples_to_features(
        eval_examples, label_list, FLAGS.max_seq_length, tokenizer, eval_file)

    tf.logging.info("***** Running evaluation *****")
    tf.logging.info("  Num examples = %d (%d actual, %d padding)",
                    len(eval_examples), num_actual_eval_examples,
                    len(eval_examples) - num_actual_eval_examples)
    tf.logging.info("  Batch size = %d", FLAGS.eval_batch_size)

    # This tells the estimator to run through the entire set.
    eval_steps = None
    # However, if running eval on the TPU, you will need to specify the
    # number of steps.
    if FLAGS.use_tpu:
      assert len(eval_examples) % FLAGS.eval_batch_size == 0
      eval_steps = int(len(eval_examples) // FLAGS.eval_batch_size)

    eval_drop_remainder = True if FLAGS.use_tpu else False
    eval_input_fn = file_based_input_fn_builder(
        input_file=eval_file,
        seq_length=FLAGS.max_seq_length,
        is_training=False,
        drop_remainder=eval_drop_remainder)

    result = estimator.evaluate(input_fn=eval_input_fn, steps=eval_steps)

    output_eval_file = os.path.join(FLAGS.output_dir, "eval_results.txt")
    with tf.gfile.GFile(output_eval_file, "w") as writer:
      tf.logging.info("***** Eval results *****")
      for key in sorted(result.keys()):
        tf.logging.info("  %s = %s", key, str(result[key]))
        writer.write("%s = %s\n" % (key, str(result[key])))

  if FLAGS.do_predict:
    predict_examples = processor.get_test_examples(FLAGS.data_dir)
    num_actual_predict_examples = len(predict_examples)
    if FLAGS.use_tpu:
      # TPU requires a fixed batch size for all batches, therefore the number
      # of examples must be a multiple of the batch size, or else examples
      # will get dropped. So we pad with fake examples which are ignored
      # later on.
      while len(predict_examples) % FLAGS.predict_batch_size != 0:
        predict_examples.append(PaddingInputExample())

    predict_file = os.path.join(FLAGS.output_dir, "predict.tf_record")#把数据转化为tf_record格式输出
    file_based_convert_examples_to_features(predict_examples, label_list,
                                            FLAGS.max_seq_length, tokenizer,
                                            predict_file)

    tf.logging.info("***** Running prediction*****")
    tf.logging.info("  Num examples = %d (%d actual, %d padding)",
                    len(predict_examples), num_actual_predict_examples,
                    len(predict_examples) - num_actual_predict_examples)
    tf.logging.info("  Batch size = %d", FLAGS.predict_batch_size)

    predict_drop_remainder = True if FLAGS.use_tpu else False
    predict_input_fn = file_based_input_fn_builder(
        input_file=predict_file,
        seq_length=FLAGS.max_seq_length,
        is_training=False,
        drop_remainder=predict_drop_remainder)

    result = estimator.predict(input_fn=predict_input_fn)

    output_predict_file = os.path.join(FLAGS.output_dir, "test_results_1.txt")
    with tf.gfile.GFile(output_predict_file, "w") as writer:
      num_written_lines = 0
      tf.logging.info("***** Predict results *****")
      for (i, prediction) in enumerate(result):
        probabilities = prediction["probabilities"]
        if i >= num_actual_predict_examples:
          break
        index = np.argmax(probabilities)
        if index == 0:
            output_line = str(i+1)+"\t"+predict_examples[i].text_a+"\t"+"无情感倾向"+ "\n"
        elif index == 1:
            output_line = str(i+1)+"\t"+predict_examples[i].text_a+"\t"+"正向情感倾向"+ "\n"
        elif index == 2:
            output_line = str(i+1)+"\t"+predict_examples[i].text_a+"\t"+"负向情感倾向"+ "\n"
        #output_line = "\t".join(
         #   str(class_probability)
          #  for class_probability in probabilities) +"\t"+str(np.argmax(probabilities))+ "\n"
        writer.write(output_line)
        num_written_lines += 1
    assert num_written_lines == num_actual_predict_examples
    print("ok")



def runn():
    flags.mark_flag_as_required("data_dir")
    flags.mark_flag_as_required("task_name")
    flags.mark_flag_as_required("vocab_file")
    flags.mark_flag_as_required("bert_config_file")
    flags.mark_flag_as_required("output_dir")
    tf.app.run(run)


if __name__ == "__main__":
  flags.mark_flag_as_required("data_dir")
  flags.mark_flag_as_required("task_name")
  flags.mark_flag_as_required("vocab_file")
  flags.mark_flag_as_required("bert_config_file")
  flags.mark_flag_as_required("output_dir")
  tf.app.run(run)

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087