1 大纲概述
文本分类这个系列将会有十篇左右，包括基于word2vec预训练的文本分类，与及基于最新的预训练模型（ELMo，BERT等）的文本分类。总共有以下系列：
Transformer 模型
ELMo 预训练模型
BERT 预训练模型
所有代码均在textClassifier仓库中，觉得有帮助，请给个小星星。
2 数据集
数据集为IMDB 电影影评，总共有三个数据文件，在/data/rawData目录下，包括unlabeledTrainData.tsv，labeledTrainData.tsv，testData.tsv。在进行文本分类时需要有标签的数据（labeledTrainData），数据预处理如文本分类实战（一）—— word2vec预训练词向量中一样，预处理后的文件为/data/preprocess/labeledTrain.csv。
3 RCNN 模型结构
RCNN模型来源于论文Recurrent Convolutional Neural Networks for Text Classification。模型结构图如下：
RCNN 整体的模型构建流程如下：
1）利用Bi-LSTM获得上下文的信息，类似于语言模型。
2）将Bi-LSTM获得的隐层输出和词向量拼接[fwOutput, wordEmbedding, bwOutput]。
3）将拼接后的向量非线性映射到低维。
4）向量中的每一个位置的值都取所有时序上的最大值，得到最终的特征向量，该过程类似于max-pool。
5）softmax分类。
4 参数配置
import os
import csv
import time
import datetime
import random
import json
import warnings
from collections import Counter
from math import sqrt
import gensim
import pandas as pd
import numpy as np
import tensorflow as tf
from sklearn.metrics import roc_auc_score, accuracy_score, precision_score, recall_score
warnings.filterwarnings("ignore")
# 配置参数
class TrainingConfig(object):
epoches = 5
evaluateEvery = 100
checkpointEvery = 100
learningRate = 0.001
class ModelConfig(object):
embeddingSize = 200
hiddenSizes = [128] # LSTM结构的神经元个数
dropoutKeepProb = 0.5
l2RegLambda = 0.0
outputSize = 128 # 从高维映射到低维的神经元个数
class Config(object):
sequenceLength = 200 # 取了所有序列长度的均值
batchSize = 128
dataSource = "../data/preProcess/labeledTrain.csv"
stopWordSource = "../data/english"
numClasses = 2
rate = 0.8 # 训练集的比例
training = TrainingConfig()
model = ModelConfig()
# 实例化配置参数对象
config = Config()
5 生成训练数据
1）将数据加载进来，将句子分割成词表示，并去除低频词和停用词。
2）将词映射成索引表示，构建词汇-索引映射表，并保存成json的数据格式，之后做inference时可以用到。（注意，有的词可能不在word2vec的预训练词向量中，这种词直接用UNK表示）
3）从预训练的词向量模型中读取出词向量，作为初始化值输入到模型中。
4）将数据集分割成训练集和测试集
# 数据预处理的类，生成训练集和测试集
class Dataset(object):
def __init__(self, config):
self._dataSource = config.dataSource
self._stopWordSource = config.stopWordSource
self._sequenceLength = config.sequenceLength # 每条输入的序列处理为定长
self._embeddingSize = config.model.embeddingSize
self._batchSize = config.batchSize
self._rate = config.rate
self._stopWordDict = {}
self.trainReviews = []
self.trainLabels = []
self.evalReviews = []
self.evalLabels = []
self.wordEmbedding =None
self._wordToIndex = {}
self._indexToWord = {}
def _readData(self, filePath):
"""
从csv文件中读取数据集
"""
df = pd.read_csv(filePath)
labels = df["sentiment"].tolist()
review = df["review"].tolist()
reviews = [line.strip().split() for line in review]
return reviews, labels
def _reviewProcess(self, review, sequenceLength, wordToIndex):
"""
将数据集中的每条评论用index表示
wordToIndex中“pad”对应的index为0
"""
reviewVec = np.zeros((sequenceLength))
sequenceLen = sequenceLength
# 判断当前的序列是否小于定义的固定序列长度
if len(review) < sequenceLength:
sequenceLen = len(review)
for i in range(sequenceLen):
if review[i] in wordToIndex:
reviewVec[i] = wordToIndex[review[i]]
else:
reviewVec[i] = wordToIndex["UNK"]
return reviewVec
def _genTrainEvalData(self, x, y, rate):
"""
生成训练集和验证集
"""
reviews = []
labels = []
# 遍历所有的文本，将文本中的词转换成index表示
for i in range(len(x)):
reviewVec = self._reviewProcess(x[i], self._sequenceLength, self._wordToIndex)
reviews.append(reviewVec)
labels.append([y[i]])
trainIndex = int(len(x) * rate)
trainReviews = np.asarray(reviews[:trainIndex], dtype="int64")
trainLabels = np.array(labels[:trainIndex], dtype="float32")
evalReviews = np.asarray(reviews[trainIndex:], dtype="int64")
evalLabels = np.array(labels[trainIndex:], dtype="float32")
return trainReviews, trainLabels, evalReviews, evalLabels
def _genVocabulary(self, reviews):
"""
生成词向量和词汇-索引映射字典，可以用全数据集
"""
allWords = [word for review in reviews for word in review]
# 去掉停用词
subWords = [word for word in allWords if word not in self.stopWordDict]
wordCount = Counter(subWords) # 统计词频
sortWordCount = sorted(wordCount.items(), key=lambda x: x[1], reverse=True)
# 去除低频词
words = [item[0] for item in sortWordCount if item[1] >= 5]
vocab, wordEmbedding = self._getWordEmbedding(words)
self.wordEmbedding = wordEmbedding
self._wordToIndex = dict(zip(vocab, list(range(len(vocab)))))
self._indexToWord = dict(zip(list(range(len(vocab))), vocab))
# 将词汇-索引映射表保存为json数据，之后做inference时直接加载来处理数据
with open("../data/wordJson/wordToIndex.json", "w", encoding="utf-8") as f:
json.dump(self._wordToIndex, f)
with open("../data/wordJson/indexToWord.json", "w", encoding="utf-8") as f:
json.dump(self._indexToWord, f)
def _getWordEmbedding(self, words):
"""
按照我们的数据集中的单词取出预训练好的word2vec中的词向量
"""
wordVec = gensim.models.KeyedVectors.load_word2vec_format("../word2vec/word2Vec.bin", binary=True)
vocab = []
wordEmbedding = []
# 添加 "pad" 和 "UNK",
vocab.append("pad")
vocab.append("UNK")
wordEmbedding.append(np.random.randn(self._embeddingSize))
wordEmbedding.append(np.random.randn(self._embeddingSize))
for word in words:
try:
vector = wordVec.wv[word]
vocab.append(word)
wordEmbedding.append(vector)
except:
print(word + "不存在于词向量中")
return vocab, np.array(wordEmbedding)
def _readStopWord(self, stopWordPath):
"""
读取停用词
"""
with open(stopWordPath, "r") as f:
stopWords = f.read()
stopWordList = stopWords.splitlines()
# 将停用词用列表的形式生成，之后查找停用词时会比较快
self.stopWordDict = dict(zip(stopWordList, list(range(len(stopWordList)))))
def dataGen(self):
"""
初始化训练集和验证集
"""
# 初始化停用词
self._readStopWord(self._stopWordSource)
# 初始化数据集
reviews, labels = self._readData(self._dataSource)
# 初始化词汇-索引映射表和词向量矩阵
self._genVocabulary(reviews)
# 初始化训练集和测试集
trainReviews, trainLabels, evalReviews, evalLabels = self._genTrainEvalData(reviews, labels, self._rate)
self.trainReviews = trainReviews
self.trainLabels = trainLabels
self.evalReviews = evalReviews
self.evalLabels = evalLabels
data = Dataset(config)
data.dataGen()
6 生成batch数据集
采用生成器的形式向模型输入batch数据集，（生成器可以避免将所有的数据加入到内存中）
# 输出batch数据集
def nextBatch(x, y, batchSize):
"""
生成batch数据集，用生成器的方式输出
"""
perm = np.arange(len(x))
np.random.shuffle(perm)
x = x[perm]
y = y[perm]
numBatches = len(x) // batchSize
for i in range(numBatches):
start = i * batchSize
end = start + batchSize
batchX = np.array(x[start: end], dtype="int64")
batchY = np.array(y[start: end], dtype="float32")
yield batchX, batchY
7 RCNN 模型
class RCNN(object):
"""
RCNN 用于文本分类
"""
def __init__(self, config, wordEmbedding):
# 定义模型的输入
self.inputX = tf.placeholder(tf.int32, [None, config.sequenceLength], name="inputX")
self.inputY = tf.placeholder(tf.float32, [None, 1], name="inputY")
self.dropoutKeepProb = tf.placeholder(tf.float32, name="dropoutKeepProb")
# 定义l2损失
l2Loss = tf.constant(0.0)
# 词嵌入层
with tf.name_scope("embedding"):
# 利用预训练的词向量初始化词嵌入矩阵
self.W = tf.Variable(tf.cast(wordEmbedding, dtype=tf.float32, name="word2vec") ,name="W")
# 利用词嵌入矩阵将输入的数据中的词转换成词向量，维度[batch_size, sequence_length, embedding_size]
self.embeddedWords = tf.nn.embedding_lookup(self.W, self.inputX)
# 定义两层双向LSTM的模型结构
with tf.name_scope("Bi-LSTM"):
fwHiddenLayers = []
bwHiddenLayers = []
for idx, hiddenSize in enumerate(config.model.hiddenSizes):
with tf.name_scope("Bi-LSTM-" + str(idx)):
# 定义前向LSTM结构
lstmFwCell = tf.nn.rnn_cell.DropoutWrapper(tf.nn.rnn_cell.LSTMCell(num_units=hiddenSize, state_is_tuple=True),
output_keep_prob=self.dropoutKeepProb)
# 定义反向LSTM结构
lstmBwCell = tf.nn.rnn_cell.DropoutWrapper(tf.nn.rnn_cell.LSTMCell(num_units=hiddenSize, state_is_tuple=True),
output_keep_prob=self.dropoutKeepProb)
fwHiddenLayers.append(lstmFwCell)
bwHiddenLayers.append(lstmBwCell)
# 实现多层的LSTM结构， state_is_tuple=True，则状态会以元祖的形式组合(h, c)，否则列向拼接
fwMultiLstm = tf.nn.rnn_cell.MultiRNNCell(cells=fwHiddenLayers, state_is_tuple=True)
bwMultiLstm = tf.nn.rnn_cell.MultiRNNCell(cells=bwHiddenLayers, state_is_tuple=True)
# 采用动态rnn，可以动态的输入序列的长度，若没有输入，则取序列的全长
# outputs是一个元祖(output_fw, output_bw)，其中两个元素的维度都是[batch_size, max_time, hidden_size],fw和bw的hidden_size一样
# self.current_state 是最终的状态，二元组(state_fw, state_bw)，state_fw=[batch_size, s]，s是一个元祖(h, c)
outputs, self.current_state = tf.nn.bidirectional_dynamic_rnn(fwMultiLstm, bwMultiLstm, self.embeddedWords, dtype=tf.float32)
fwOutput, bwOutput = outputs
with tf.name_scope("context"):
shape = [tf.shape(fwOutput)[0], 1, tf.shape(fwOutput)[2]]
self.contextLeft = tf.concat([tf.zeros(shape), fwOutput[:, :-1]], axis=1, name="contextLeft")
self.contextRight = tf.concat([bwOutput[:, 1:], tf.zeros(shape)], axis=1, name="contextRight")
# 将前向，后向的输出和最早的词向量拼接在一起得到最终的词表征
with tf.name_scope("wordRepresentation"):
self.wordRepre = tf.concat([self.contextLeft, self.embeddedWords, self.contextRight], axis=2)
wordSize = config.model.hiddenSizes[-1] * 2 + config.model.embeddingSize
with tf.name_scope("textRepresentation"):
outputSize = config.model.outputSize
textW = tf.Variable(tf.random_uniform([wordSize, outputSize], -1.0, 1.0), name="W2")
textB = tf.Variable(tf.constant(0.1, shape=[outputSize]), name="b2")
# tf.einsum可以指定维度的消除运算
self.textRepre = tf.tanh(tf.einsum(‘aij,jk->aik‘, self.wordRepre, textW) + textB)
# 做max-pool的操作，将时间步的维度消失
output = tf.reduce_max(self.textRepre, axis=1)
# 全连接层的输出
with tf.name_scope("output"):
outputW = tf.get_variable(
"outputW",
shape=[outputSize, 1],
initializer=tf.contrib.layers.xavier_initializer())
outputB= tf.Variable(tf.constant(0.1, shape=[1]), name="outputB")
l2Loss += tf.nn.l2_loss(outputW)
l2Loss += tf.nn.l2_loss(outputB)
self.predictions = tf.nn.xw_plus_b(output, outputW, outputB, name="predictions")
self.binaryPreds = tf.cast(tf.greater_equal(self.predictions, 0.5), tf.float32, name="binaryPreds")
# 计算二元交叉熵损失
with tf.name_scope("loss"):
losses = tf.nn.sigmoid_cross_entropy_with_logits(logits=self.predictions, labels=self.inputY)
self.loss = tf.reduce_mean(losses) + config.model.l2RegLambda * l2Loss
8 定义计算metrics的函数
# 定义性能指标函数
def mean(item):
return sum(item) / len(item)
def genMetrics(trueY, predY, binaryPredY):
"""
生成acc和auc值
"""
auc = roc_auc_score(trueY, predY)
accuracy = accuracy_score(trueY, binaryPredY)
precision = precision_score(trueY, binaryPredY)
recall = recall_score(trueY, binaryPredY)
return round(accuracy, 4), round(auc, 4), round(precision, 4), round(recall, 4)
9 训练模型
在训练时，我们定义了tensorBoard的输出，并定义了两种模型保存的方法。
# 训练模型
# 生成训练集和验证集
trainReviews = data.trainReviews
trainLabels = data.trainLabels
evalReviews = data.evalReviews
evalLabels = data.evalLabels
wordEmbedding = data.wordEmbedding
# 定义计算图
with tf.Graph().as_default():
session_conf = tf.ConfigProto(allow_soft_placement=True, log_device_placement=False)
session_conf.gpu_options.allow_growth=True
session_conf.gpu_options.per_process_gpu_memory_fraction = 0.9 # 配置gpu占用率
sess = tf.Session(config=session_conf)
# 定义会话
with sess.as_default():
lstm = RCNN(config, wordEmbedding)
globalStep = tf.Variable(0, name="globalStep", trainable=False)
# 定义优化函数，传入学习速率参数
optimizer = tf.train.AdamOptimizer(config.training.learningRate)
# 计算梯度,得到梯度和变量
gradsAndVars = optimizer.compute_gradients(lstm.loss)
# 将梯度应用到变量下，生成训练器
trainOp = optimizer.apply_gradients(gradsAndVars, global_step=globalStep)
# 用summary绘制tensorBoard
gradSummaries = []
for g, v in gradsAndVars:
if g is not None:
tf.summary.histogram("{}/grad/hist".format(v.name), g)
tf.summary.scalar("{}/grad/sparsity".format(v.name), tf.nn.zero_fraction(g))
outDir = os.path.abspath(os.path.join(os.path.curdir, "summarys"))
print("Writing to {}\n".format(outDir))
lossSummary = tf.summary.scalar("loss", lstm.loss)
summaryOp = tf.summary.merge_all()
trainSummaryDir = os.path.join(outDir, "train")
trainSummaryWriter = tf.summary.FileWriter(trainSummaryDir, sess.graph)
evalSummaryDir = os.path.join(outDir, "eval")
evalSummaryWriter = tf.summary.FileWriter(evalSummaryDir, sess.graph)
# 初始化所有变量
saver = tf.train.Saver(tf.global_variables(), max_to_keep=5)
# 保存模型的一种方式，保存为pb文件
builder = tf.saved_model.builder.SavedModelBuilder("../model/Bi-LSTM/savedModel")
sess.run(tf.global_variables_initializer())
def trainStep(batchX, batchY):
"""
训练函数
"""
feed_dict = {
lstm.inputX: batchX,
lstm.inputY: batchY,
lstm.dropoutKeepProb: config.model.dropoutKeepProb
}
_, summary, step, loss, predictions, binaryPreds = sess.run(
[trainOp, summaryOp, globalStep, lstm.loss, lstm.predictions, lstm.binaryPreds],
feed_dict)
timeStr = datetime.datetime.now().isoformat()
acc, auc, precision, recall = genMetrics(batchY, predictions, binaryPreds)
print("{}, step: {}, loss: {}, acc: {}, auc: {}, precision: {}, recall: {}".format(timeStr, step, loss, acc, auc, precision, recall))
trainSummaryWriter.add_summary(summary, step)
def devStep(batchX, batchY):
"""
验证函数
"""
feed_dict = {
lstm.inputX: batchX,
lstm.inputY: batchY,
lstm.dropoutKeepProb: 1.0
}
summary, step, loss, predictions, binaryPreds = sess.run(
[summaryOp, globalStep, lstm.loss, lstm.predictions, lstm.binaryPreds],
feed_dict)
acc, auc, precision, recall = genMetrics(batchY, predictions, binaryPreds)
evalSummaryWriter.add_summary(summary, step)
return loss, acc, auc, precision, recall
for i in range(config.training.epoches):
# 训练模型
print("start training model")
for batchTrain in nextBatch(trainReviews, trainLabels, config.batchSize):
trainStep(batchTrain[0], batchTrain[1])
currentStep = tf.train.global_step(sess, globalStep)
if currentStep % config.training.evaluateEvery == 0:
print("\nEvaluation:")
losses = []
accs = []
aucs = []
precisions = []
recalls = []
for batchEval in nextBatch(evalReviews, evalLabels, config.batchSize):
loss, acc, auc, precision, recall = devStep(batchEval[0], batchEval[1])
losses.append(loss)
accs.append(acc)
aucs.append(auc)
precisions.append(precision)
recalls.append(recall)
time_str = datetime.datetime.now().isoformat()
print("{}, step: {}, loss: {}, acc: {}, auc: {}, precision: {}, recall: {}".format(time_str, currentStep, mean(losses),
mean(accs), mean(aucs), mean(precisions),
mean(recalls)))
if currentStep % config.training.checkpointEvery == 0:
# 保存模型的另一种方法，保存checkpoint文件
path = saver.save(sess, "../model/Bi-LSTM/model/my-model", global_step=currentStep)
print("Saved model checkpoint to {}\n".format(path))
inputs = {"inputX": tf.saved_model.utils.build_tensor_info(lstm.inputX),
"keepProb": tf.saved_model.utils.build_tensor_info(lstm.dropoutKeepProb)}
outputs = {"binaryPreds": tf.saved_model.utils.build_tensor_info(lstm.binaryPreds)}
prediction_signature = tf.saved_model.signature_def_utils.build_signature_def(inputs=inputs, outputs=outputs,
method_name=tf.saved_model.signature_constants.PREDICT_METHOD_NAME)
legacy_init_op = tf.group(tf.tables_initializer(), name="legacy_init_op")
builder.add_meta_graph_and_variables(sess, [tf.saved_model.tag_constants.SERVING],
signature_def_map={"predict": prediction_signature}, legacy_init_op=legacy_init_op)
builder.save()
原文地址：https://www.cnblogs.com/jiangxinyang/p/10208290.html
时间： 2024-10-09 04:44:10