九、（1）情感分类——基于词典。评论。

九、（1）情感分类——基于词典。评论。

————数据集留言邮箱发送

# -*- coding: utf-8 -*-
"""
Created on Thu Jun 13 23:32:14 2019

@author: sun
"""
import jieba
import numpy as np


#打开词典文件，返回列表，词典文件就是包含否定词，positive，negtive，程度级别词语的文件夹
def open_dict(Dict = 'hahah', path=r'C:\Users\sun\Desktop\Textming\Textming/'):
    path = path + '%s.txt' % Dict
    dictionary = open(path, 'r', encoding='utf-8')
    dict = []
    for word in dictionary:
        word = word.strip('\n')
        dict.append(word)
    return dict



def judgeodd(num):
    if (num % 2) == 0:
        return 'even'
    else:
        return 'odd'


#注意，这里你要修改path路径。
deny_word = open_dict(Dict = '否定词')
posdict = open_dict(Dict = 'positive')
negdict = open_dict(Dict = 'negative')

degree_word = open_dict(Dict = '程度级别词语')
mostdict = degree_word[degree_word.index('extreme')+1 : degree_word.index('very')]#权重4，即在情感词前乘以4
verydict = degree_word[degree_word.index('very')+1 : degree_word.index('more')]#权重3
moredict = degree_word[degree_word.index('more')+1 : degree_word.index('ish')]#权重2
ishdict = degree_word[degree_word.index('ish')+1 : degree_word.index('last')]#权重0.5


#将测试的语句以句号分隔开。一个句号代表一条文本记录
def sentiment_score_list(dataset):
    seg_sentence = dataset.split('。')

    count1 = []
    count2 = []
    for sen in seg_sentence: #循环遍历每一个评论
        segtmp = jieba.lcut(sen, cut_all=False)  #把句子进行分词，以列表的形式返回
        i = 0 #记录扫描到的词的位置
        a = 0 #记录情感词的位置
        poscount = 0 #积极词的第一次分值
        poscount2 = 0 #积极词反转后的分值
        poscount3 = 0 #积极词的最后分值（包括叹号的分值）
        negcount = 0
        negcount2 = 0
        negcount3 = 0
        for word in segtmp:
            if word in posdict:  # 判断词语是否是情感词
                poscount += 1
                c = 0
                for w in segtmp[a:i]:  # 扫描情感词前的程度词
                    if w in mostdict:
                        poscount *= 4.0
                    elif w in verydict:
                        poscount *= 3.0
                    elif w in moredict:
                        poscount *= 2.0
                    elif w in ishdict:
                        poscount *= 0.5
                    elif w in deny_word:
                        c += 1
                if judgeodd(c) == 'odd':  # 扫描情感词前的否定词数
                    poscount *= -1.0
                    poscount2 += poscount
                    poscount = 0
                    poscount3 = poscount + poscount2 + poscount3
                    poscount2 = 0
                else:
                    poscount3 = poscount + poscount2 + poscount3
                    poscount = 0
                a = i + 1  # 情感词的位置变化

            elif word in negdict:  # 消极情感的分析，与上面一致
                negcount += 1
                d = 0
                for w in segtmp[a:i]:
                    if w in mostdict:
                        negcount *= 4.0
                    elif w in verydict:
                        negcount *= 3.0
                    elif w in moredict:
                        negcount *= 2.0
                    elif w in ishdict:
                        negcount *= 0.5
                    elif w in degree_word:
                        d += 1
                if judgeodd(d) == 'odd':
                    negcount *= -1.0
                    negcount2 += negcount
                    negcount = 0
                    negcount3 = negcount + negcount2 + negcount3
                    negcount2 = 0
                else:
                    negcount3 = negcount + negcount2 + negcount3
                    negcount = 0
                a = i + 1
            elif word == '！' or word == '!':  ##判断句子是否有感叹号
                for w2 in segtmp[::-1]:  # 扫描感叹号前的情感词，发现后权值+2，然后退出循环
                    if w2 in posdict or negdict:
                        poscount3 += 2
                        negcount3 += 2
                        break
            i += 1 # 扫描词位置前移


            # 以下是防止出现负数的情况
            pos_count = 0
            neg_count = 0
            if poscount3 < 0 and negcount3 > 0:
                neg_count += negcount3 - poscount3
                pos_count = 0
            elif negcount3 < 0 and poscount3 > 0:
                pos_count = poscount3 - negcount3
                neg_count = 0
            elif poscount3 < 0 and negcount3 < 0:
                neg_count = -poscount3
                pos_count = -negcount3
            else:
                pos_count = poscount3
                neg_count = negcount3

            count1.append([pos_count, neg_count])
        count2.append(count1)
        count1 = []

    return count2
#计算分值
def sentiment_score(senti_score_list):
    #score = []
    s=''
    w=''
    for review in senti_score_list:#senti_score_list
        #print(review)
        score_array =  np.array(review)
        #print(score_array)
        Pos = np.sum(score_array[:,0])#积极总分
        Neg = np.sum(score_array[:,1])#消极总分
        AvgPos = np.mean(score_array[:,0])#积极情感均值
        AvgPos = float('%.lf' % AvgPos)
        AvgNeg = np.mean(score_array[:, 1])#消极情感均值
        AvgNeg = float('%.1f' % AvgNeg)
        StdPos = np.std(score_array[:, 0])#积极情感方差
        StdPos = float('%.1f' % StdPos)
        StdNeg = np.std(score_array[:, 1])#消极情感方差
        StdNeg = float('%.1f' % StdNeg)
        #s+=([Pos,Neg,AvgPos,AvgNeg,StdPos,StdNeg]))
        s+='\n'+str([Pos, Neg])
        #score.append([Pos,Neg])
        res=Pos-Neg
        if res>0:
            w+='\n'+'好评'
            print ('该条评论是：好评')
        elif res<0:
            w+='\n'+'差评'
            print ('该条评论是：差评')
        else:
            w+='\n'+'中评'
            print ('该条评论是：中评')
    #print(w)
    return w


#输入数据，本想读取一个txt文本的每一行为一条记录预测，但是老是错误，如果有大佬会的话，请留言较一下我
#本代码数据是通过word生成。将所有句子以句号结尾，然后将格式改为无换行符，在替换中即可操作。下面有图
data = '你就是个王八蛋，混账玩意!你们的手机真不好用！非常生气，我非常郁。你是好人，喜欢你。产品质量不错，值的购买。你就是个王八蛋，混账玩意!你们的手机真不好用！非常生气，我非常郁。你是好人，喜欢你。你就是个王八蛋，混账玩意!你们的手机真不好用！非常生气，我非常郁。你就是个王八蛋，混账玩意!你们的手机真不好用！非常生气，我非常郁。产品质量不错，值的购买。你就是个王八蛋，混账玩意!你们的手机真不好用！非常生气，我非常郁'

print(sentiment_score(sentiment_score_list(data)))

输出结果：

测试数据格式：在word中编辑的

一共九条数据，代码预测是比较准确的，将数据改为下图放入代码的data后面就可以了：

对比图

为了便于观察，将数据整合到表格里即可：

搞定收工。

“☺☺☺ 若本篇文章对你有一丝丝帮助，请帮顶、评论点赞，谢谢。☺☺☺”

↓↓↓↓