LSTM模型---情感分析（文本评价分类）

import warnings
#控制警告错误的输出
warnings.filterwarnings(action='ignore', category=UserWarning, module='gensim')
import gensim
from gensim.models import word2vec
import jieba
import tensorflow as tf
import numpy as np
import time
#模块random包含以各种方式生成随机数的函数，其中的randint()返回一个位于指定范围内的整数
from random import randint
#shuffle() 方法将序列的所有元素随机排序。
from random import shuffle
#----------------------------------
#通过读取名字为停用词.txt的文件来返回停用词
def makeStopWord():
    with open('停用词.txt','r',encoding = 'utf-8') as f:
        lines = f.readlines()
    stopWord = []
    for line in lines:
        words = jieba.lcut(line,cut_all = False)
        for word in words:
            stopWord.append(word)
    return stopWord

def words2Array(lineList):
    linesArray=[]
    wordsArray=[]
    steps = []
    for line in lineList:
        t = 0
        p = 0
        for i in range(MAX_SIZE):#一条评价最多容纳的单词数目(25个，多退少补)
            if i<len(line):
                try:#添加每个行的每个词的词向量
                    wordsArray.append(model.wv.word_vec(line[i]))
                    p = p + 1
                except KeyError:
                    t=t+1
                    continue
            else:#一句话不够25个词的，用200维的词向量代表的词来补够
               wordsArray.append(np.array([0.0]*dimsh))
        for i in range(t):
            wordsArray.append(np.array([0.0]*dimsh))
        steps.append(p)#统计一句话包含多少个有效词（即扣除非补齐的词）
        linesArray.append(wordsArray)#从第一句话开始，每句话用25行200列的矩阵来表示，直到遍历所有的句子。
        wordsArray = []
    linesArray = np.array(linesArray)#三维矩阵
    steps = np.array(steps)#统计每一句话中的有效词放到数组中，数组的元素个数为句子的个数
    return linesArray, steps

def convert2Data(posArray, negArray, posStep, negStep):
    randIt = []
    data = []
    steps = []
    labels = []
    for i in range(len(posArray)):
        #积极评价：25*200的矩阵，有效词的个数，标签，如果是分3类，标签就为[1,0,0]
        randIt.append([posArray[i], posStep[i], [1,0]])
    for i in range(len(negArray)):#消极评价：25*200的矩阵，有效词的个数，标签
        randIt.append([negArray[i], negStep[i], [0,1]])
    shuffle(randIt)#随机混乱
    for i in range(len(randIt)):
        data.append(randIt[i][0])#每一句话的25*200的矩阵表示，放到data中
        steps.append(randIt[i][1])#每一句话的有效词的个数，放到step中
        labels.append(randIt[i][2])#每一句话的标签，放到label中
    data = np.array(data)
    steps = np.array(steps)
    return data, steps, labels

def getWords(file):
    wordList = []
    trans = []
    lineList = []
    with open(file,'r',encoding='utf-8') as f:
        lines = f.readlines()
    for line in lines:
        #去掉句子末尾的空格符
        trans = jieba.lcut(line.replace('\n',''), cut_all = False)
        for word in trans:
            if word not in stopWord:
                wordList.append(word)
        lineList.append(wordList)
        wordList = []
    return lineList

def makeData(posPath,negPath):
    #获取词汇，返回类型为[[word1,word2...],[word1,word2...],...]
    pos = getWords(posPath)
    print("The positive data's length is :",