BosonNLP情感词典 评论情感分析

from snownlp import SnowNLP
import pandas as pd
from collections import defaultdict
import os
import re
import jieba
import codecs
'''
#读取评论内容的.txt文件
txt = open('C:/Users/24224/Desktop/1.txt',encoding='utf-8')
text = txt.readlines()
print(text)

#确认读取文件成功，并关闭文件节省资源
print('读入成功')
txt.close()

#遍历每一条评论，得到每条评论是positive文本的概率，每条评论计算完成后输出ok确认执行成功
comments = []
comments_score = []
for i in text:
    a1 = SnowNLP(i)
    a2 = a1.sentiments
    comments.append(i)
    comments_score.append(a2)
    print('ok')

#将结果数据框存为.xlsx表格，查看结果及分布
table = pd.DataFrame(comments, comments_score)
print(table)
table.to_excel('C:/Users/24224/Desktop/emotion_analyse.xlsx', sheet_name='result')
#打分范围是[0-1]，此次定义[0,0.5]为负向评论，(0.5,1]为正向评论，观察其分布。


#基于波森情感词典计算情感值
def getscore(text):
    df = pd.read_table(r"BosonNLP_sentiment_score\BosonNLP_sentiment_score.txt", sep=" ", names=['key', 'score'])
    key = df['key'].values.tolist()
    score = df['score'].values.tolist()
    # jieba分词
    segs = jieba.lcut(text,cut_all = False) #返回list
    # 计算得分
    score_list = [score[key.index(x)] for x in segs if(x in key)]
    return sum(score_list)

#读取文件
def read_txt(filename):
    with open(filename,'r',encoding='utf-8')as f:
        txt = f.read()
    return txt
#写入文件
def write_data(filename,data):
    with open(filename,'a',encoding='utf-8')as f:
        f.write(data)

if __name__=='__main__':
    text = read_txt('C:/Users/24224/Desktop/1.txt')
    lists  = text.split('\n')
    i = 0
    for list in lists:
        if list  != '':
            sentiments = round(getscore(list),2)
            #情感值为正数，表示积极；为负数表示消极
            print(list)
            print("情感值：",sentiments)
            if sentiments > 0:
                print("机器标注情感倾向：积极\n")
                s = "机器判断情感倾向：积极\n"
            else:
                print('机器标注情感倾向：消极\n')
                s = "机器判断情感倾向：消极"+'\n'
            sentiment = '情感值：'+str(sentiments)+'\n'
            #文件写入
            filename = 'BosonNLP情感分析结果.txt'
            write_data(filename,'情感分析文本：')
            write_data(filename,list+'\n') #写入待处理文本
            write_data(filename,sentiment) #写入情感值
            #write_data(filename,al_sentiment) #写入机器判断情感倾向
            write_data(filename,s+'\n') #写入人工标注情感
            i = i+1
'''
# 生成stopword表，需要去除一些否定词和程度词汇
stopwords = set()
fr = open('停用词.txt', 'r', encoding='utf-8')

for word in fr:
    stopwords.add(word.strip())  # Python strip() 方法用于移除字符串头尾指定的字符（默认为空格或换行符）或字符序列。
# 读取否定词文件
not_word_file = open('否定词.txt', 'r+', encoding='utf-8')
not_word_list = not_word_file.readlines()
not_word_list = [w.strip() for w in not_word_list]
# 读取程度副词文件
degree_file = open('程度副词.txt', 'r+',encoding='utf-8')
degree_list = degree_file.readlines()
degree_list = [item.split(',')[0] for item in degree_list]

# 生成新的停用词表
with open('stopwords.txt', 'w', encoding='utf-8') as f:
    for word in stopwords:
        if (word not in not_word_list) and (word not in degree_list):
            f.write(word + '\n')
# jieba分词后去除停用词

def seg_word(sentence):
    seg_list = jieba.cut(sentence)
    seg_result = []
    for i in seg_list:
        seg_result.append(i)
    stopwords = set()
    with open('stopwords.txt', 'r',encoding='utf-8') as fr:
        for i in fr:
            stopwords.add(i.strip())
    return list(filter(lambda x: x not in stopwords, seg_result))


# 找出文本中的情感词、否定词和程度副词

def classify_words(word_list):
    # 读取情感词典文件
    sen_file = open('BosonNLP_sentiment_score\BosonNLP_sentiment_score.txt', 'r+', encoding='utf-8')
    # 获取词典文件内容
    sen_list = sen_file.readlines()
    # 创建情感字典
    sen_dict = defaultdict()
    # 读取词典每一行的内容，将其转换成字典对象，key为情感词，value为其对应的权重
    for i in sen_list:
        if len(i.split(' ')) == 2:
            sen_dict[i.split(' ')[0]] = i.split(' ')[1]
    # 读取否定词文件

    not_word_file = open('否定词.txt', 'r+', encoding='utf-8')
    not_word_list = not_word_file.readlines()
    # 读取程度副词文件
    degree_file = open('程度副词.txt', 'r+', encoding='utf-8')
    degree_list = degree_file.readlines()
    degree_dict = defaultdict()
    for i in degree_list:
        degree_dict[i.split(',')[0]] = i.split(',')[0]
    sen_word = dict()
    not_word = dict()
    degree_word = dict()
    # 分类
    for i in range(len(word_list)):
        word = word_list[i]
        if word in sen_dict.keys() and word not in not_word_list and word not in degree_dict.keys():
            # 找出分词结果中在情感字典中的词
            sen_word[i] = sen_dict[word]
        elif word in not_word_list and word not in degree_dict.keys():
            # 分词结果中在否定词列表中的词
            not_word[i] = -1
        elif word in degree_dict.keys():
            # 分词结果中在程度副词中的词
            degree_word[i] = degree_dict[word]
    # 关闭打开的文件
    sen_file.close()
    not_word_file.close()
    degree_file.close()
    # 返回分类结果
    return sen_word, not_word, degree_word

# 计算情感词的分数
def score_sentiment(sen_word, not_word, degree_word, seg_result):
    # 权重初始化为1
    W = 1
    score = 0
    # 情感词下标初始化
    sentiment_index = -1
    # 情感词的位置下标集合
    sentiment_index_list = list(sen_word.keys())
    # 遍历分词结果
    for i in range(0, len(seg_result)):
        # 如果是情感词
        if i in sen_word.keys():
            # 权重*情感词得分
            score += W * float(sen_word[i])
            # 情感词下标加一，获取下一个情感词的位置
            sentiment_index += 1
            if sentiment_index < len(sentiment_index_list) - 1:
                # 判断当前的情感词与下一个情感词之间是否有程度副词或否定词
                for j in range(sentiment_index_list[sentiment_index], sentiment_index_list[sentiment_index + 1]):
                    # 更新权重，如果有否定词，权重取反
                    if j in not_word.keys():
                        W *= -1
                    elif j in degree_word.keys():
                        W *= float(degree_word[j])
        # 定位到下一个情感词
        if sentiment_index < len(sentiment_index_list) - 1:
            i = sentiment_index_list[sentiment_index + 1]
    return score


# 计算得分
def sentiment_score(sentence):
    # 1.对文档分词
    seg_list = seg_word(sentence)
    # 2.将分词结果转换成字典，找出情感词、否定词和程度副词
    sen_word, not_word, degree_word = classify_words(seg_list)
    # 3.计算得分
    score = score_sentiment(sen_word, not_word, degree_word, seg_list)
    return score
#读取文件
def read_txt(filename):
    with open(filename,'r',encoding='utf-8')as f:
        txt = f.read()
    return txt
def write_data(filename,data):
    with open(filename,'a',encoding='utf-8')as f:
        f.write(data)
#基于波森情感词典计算情感值
text = read_txt('C:/Users/24224/Desktop/1.txt')
lists  = text.split('\n')
i = 0
for l in lists:
    if l  != '':
        sentiments =sentiment_score(l)
            #情感值为正数，表示积极；为负数表示消极
        print("情感值：",sentiments)
        if sentiments > 0:
            print(l)
            print("机器标注情感倾向：积极\n")
            s = "机器判断情感倾向：积极\n"
        else:
            print(l)
            print('机器标注情感倾向：消极\n')
            s = "机器判断情感倾向：消极"+'\n'
        sentiment = '情感值：'+str(sentiments)+'\n'
            #文件写入
        filename = 'BosonNLP情感分析结果.txt'
        write_data(filename,'情感分析文本：')
        write_data(filename,l+'\n') #写入待处理文本
        write_data(filename,sentiment) #写入情感值
            #write_data(filename,al_sentiment) #写入机器判断情感倾向
        write_data(filename,s+'\n') #写入人工标注情感
        i = i+1