Python人工智能 | 二十二.基于大连理工情感词典的情感分析和情绪计算

# coding: utf-8import pandas as pd#获取数据集f = open('庆余年220.csv',encoding='utf8')weibo_df = pd.read_csv(f)print(weibo_df.head())

# coding: utf-8import pandas as pd#-------------------------------------获取数据集---------------------------------f = open('庆余年220.csv',encoding='utf8')weibo_df = pd.read_csv(f)print(weibo_df.head())#-------------------------------------情感词典读取-------------------------------#注意：#1.词典中怒的标记(NA)识别不出被当作空值,情感分类列中的NA都给替换成NAU#2.大连理工词典中有情感分类的辅助标注(有NA),故把情感分类列改好再替换原词典中# 扩展前的词典df = pd.read_excel('大连理工大学中文情感词汇本体NAU.xlsx')print(df.head(10))df = df[['词语', '词性种类', '词义数', '词义序号', '情感分类', '强度', '极性']]df.head()

# coding: utf-8import pandas as pd#-------------------------------------获取数据集---------------------------------f = open('庆余年220.csv',encoding='utf8')weibo_df = pd.read_csv(f)print(weibo_df.head())#-------------------------------------情感词典读取-------------------------------#注意：#1.词典中怒的标记(NA)识别不出被当作空值,情感分类列中的NA都给替换成NAU#2.大连理工词典中有情感分类的辅助标注(有NA),故把情感分类列改好再替换原词典中# 扩展前的词典df = pd.read_excel('大连理工大学中文情感词汇本体NAU.xlsx')print(df.head(10))df = df[['词语', '词性种类', '词义数', '词义序号', '情感分类', '强度', '极性']]df.head()#-------------------------------------七种情绪的运用-------------------------------Happy = []Good = []Surprise = []Anger = []Sad = []Fear = []Disgust = []#df.iterrows()功能是迭代遍历每一行for idx, row in df.iterrows():    if row['情感分类'] in ['PA', 'PE']:        Happy.append(row['词语'])    if row['情感分类'] in ['PD', 'PH', 'PG', 'PB', 'PK']:        Good.append(row['词语'])     if row['情感分类'] in ['PC']:        Surprise.append(row['词语'])           if row['情感分类'] in ['NB', 'NJ', 'NH', 'PF']:        Sad.append(row['词语'])    if row['情感分类'] in ['NI', 'NC', 'NG']:        Fear.append(row['词语'])    if row['情感分类'] in ['NE', 'ND', 'NN', 'NK', 'NL']:        Disgust.append(row['词语'])    if row['情感分类'] in ['NAU']:     #修改: 原NA算出来没结果        Anger.append(row['词语'])  #正负计算不是很准 自己可以制定规则       Positive = Happy + Good + SurpriseNegative = Anger + Sad + Fear + Disgustprint('情绪词语列表整理完成')  print(Anger)

#---------------------------------------中文分词---------------------------------import jiebaimport time#添加使用者词典和停用词jieba.load_userdict("user_dict.txt")              #自定义词典stop_list = pd.read_csv('stop_words.txt',                        engine='python',                        encoding='utf-8',                        delimiter="n",                        names=['t'])['t'].tolist()def txt_cut(juzi):    return [w for w in jieba.lcut(juzi) if w not in stop_list]     #可增加len(w)>1

#---------------------------------------中文分词---------------------------------import jiebaimport time#添加自定义词典和停用词#jieba.load_userdict("user_dict.txt")stop_list = pd.read_csv('stop_words.txt',                        engine='python',                        encoding='utf-8',                        delimiter="n",                        names=['t'])#获取重命名t列的值stop_list = stop_list['t'].tolist()def txt_cut(juzi):    return [w for w in jieba.lcut(juzi) if w not in stop_list]     #可增加len(w)>1#---------------------------------------情感计算---------------------------------def emotion_caculate(text):    positive = 0    negative = 0    anger = 0    disgust = 0    fear = 0    sad = 0    surprise = 0    good = 0    happy = 0    wordlist = txt_cut(text)    #wordlist = jieba.lcut(text)    wordset = set(wordlist)    wordfreq = []    for word in wordset:        freq = wordlist.count(word)        if word in Positive:            positive+=freq        if word in Negative:            negative+=freq        if word in Anger:            anger+=freq          if word in Disgust:            disgust+=freq        if word in Fear:            fear+=freq        if word in Sad:            sad+=freq        if word in Surprise:            surprise+=freq        if word in Good:            good+=freq        if word in Happy:            happy+=freq    emotion_info = {        'length':len(wordlist),        'positive': positive,        'negative': negative,        'anger': anger,        'disgust': disgust,        'fear':fear,        'good':good,        'sadness':sad,        'surprise':surprise,        'happy':happy,    }    indexs = ['length', 'positive', 'negative', 'anger', 'disgust','fear','sadness','surprise', 'good', 'happy']    return pd.Series(emotion_info, index=indexs)#测试text="""原著的确更吸引编剧读下去，所以跟《诛仙》系列明显感觉到编剧只看过故事大纲比，这个剧的编剧完整阅读过小说。配乐活泼俏皮，除了强硬穿越的台词轻微尴尬，最应该尴尬的感情戏反而入戏，故意模糊了陈萍萍的太监身份、太子跟长公主的暧昧关系，整体观影感受极好，很期待第二季拍大东山之役。玩弄人心的阴谋阳谋都不狗血，架空的设定能摆脱历史背景，服装道具能有更自由的发挥空间，特别喜欢庆帝的闺房。以后还是少看国产剧，太长了，还是精短美剧更适合休闲，追这个太累。王启年真是太可爱了。"""res = emotion_caculate(text)print(res)

length      83positive     7negative     6anger        0disgust      6fear         0sadness      0surprise     0good         6happy        1dtype: int64

# coding: utf-8import pandas as pdimport jiebaimport time#-------------------------------------获取数据集---------------------------------f = open('庆余年220.csv',encoding='utf8')weibo_df = pd.read_csv(f)print(weibo_df.head())#-------------------------------------情感词典读取-------------------------------#注意：#1.词典中怒的标记(NA)识别不出被当作空值,情感分类列中的NA都给替换成NAU#2.大连理工词典中有情感分类的辅助标注(有NA),故把情感分类列改好再替换原词典中# 扩展前的词典df = pd.read_excel('大连理工大学中文情感词汇本体NAU.xlsx')print(df.head(10))df = df[['词语', '词性种类', '词义数', '词义序号', '情感分类', '强度', '极性']]df.head()#-------------------------------------七种情绪的运用-------------------------------Happy = []Good = []Surprise = []Anger = []Sad = []Fear = []Disgust = []#df.iterrows()功能是迭代遍历每一行for idx, row in df.iterrows():    if row['情感分类'] in ['PA', 'PE']:        Happy.append(row['词语'])    if row['情感分类'] in ['PD', 'PH', 'PG', 'PB', 'PK']:        Good.append(row['词语'])     if row['情感分类'] in ['PC']:        Surprise.append(row['词语'])           if row['情感分类'] in ['NB', 'NJ', 'NH', 'PF']:        Sad.append(row['词语'])    if row['情感分类'] in ['NI', 'NC', 'NG']:        Fear.append(row['词语'])    if row['情感分类'] in ['NE', 'ND', 'NN', 'NK', 'NL']:        Disgust.append(row['词语'])    if row['情感分类'] in ['NAU']:     #修改: 原NA算出来没结果        Anger.append(row['词语'])  #正负计算不是很准 自己可以制定规则       Positive = Happy + Good + SurpriseNegative = Anger + Sad + Fear + Disgustprint('情绪词语列表整理完成')  print(Anger)#---------------------------------------中文分词---------------------------------#添加自定义词典和停用词#jieba.load_userdict("user_dict.txt")stop_list = pd.read_csv('stop_words.txt',                        engine='python',                        encoding='utf-8',                        delimiter="n",                        names=['t'])#获取重命名t列的值stop_list = stop_list['t'].tolist()def txt_cut(juzi):    return [w for w in jieba.lcut(juzi) if w not in stop_list]     #可增加len(w)>1#---------------------------------------情感计算---------------------------------def emotion_caculate(text):    positive = 0    negative = 0    anger = 0    disgust = 0    fear = 0    sad = 0    surprise = 0    good = 0    happy = 0    anger_list = []    disgust_list = []    fear_list = []    sad_list = []    surprise_list = []    good_list = []    happy_list = []    wordlist = txt_cut(text)    #wordlist = jieba.lcut(text)    wordset = set(wordlist)    wordfreq = []    for word in wordset:        freq = wordlist.count(word)        if word in Positive:            positive+=freq        if word in Negative:            negative+=freq        if word in Anger:            anger+=freq            anger_list.append(word)        if word in Disgust:            disgust+=freq            disgust_list.append(word)        if word in Fear:            fear+=freq            fear_list.append(word)        if word in Sad:            sad+=freq            sad_list.append(word)        if word in Surprise:            surprise+=freq            surprise_list.append(word)        if word in Good:            good+=freq            good_list.append(word)        if word in Happy:            happy+=freq            happy_list.append(word)    emotion_info = {        'length':len(wordlist),        'positive': positive,        'negative': negative,        'anger': anger,        'disgust': disgust,        'fear':fear,        'good':good,        'sadness':sad,        'surprise':surprise,        'happy':happy,    }    indexs = ['length', 'positive', 'negative', 'anger', 'disgust','fear','sadness','surprise', 'good', 'happy']    #return pd.Series(emotion_info, index=indexs), anger_list, disgust_list, fear_list, sad_list, surprise_list, good_list, happy_list    return pd.Series(emotion_info, index=indexs)#测试 (res, anger_list, disgust_list, fear_list, sad_list, surprise_list, good_list, happy_list)text = """原著的确更吸引编剧读下去，所以跟《诛仙》系列明显感觉到编剧只看过故事大纲比，这个剧的编剧完整阅读过小说。配乐活泼俏皮，除了强硬穿越的台词轻微尴尬，最应该尴尬的感情戏反而入戏，故意模糊了陈萍萍的太监身份、太子跟长公主的暧昧关系，整体观影感受极好，很期待第二季拍大东山之役。玩弄人心的阴谋阳谋都不狗血，架空的设定能摆脱历史背景，服装道具能有更自由的发挥空间，特别喜欢庆帝的闺房。以后还是少看国产剧，太长了，还是精短美剧更适合休闲，追这个太累。王启年真是太可爱了。"""#res, anger, disgust, fear, sad, surprise, good, happy = emotion_caculate(text)res = emotion_caculate(text)print(res)#---------------------------------------情感计算---------------------------------start = time.time()   emotion_df = weibo_df['review'].apply(emotion_caculate)end = time.time()print(end-start)print(emotion_df.head())#输出结果output_df = pd.concat([weibo_df, emotion_df], axis=1)output_df.to_csv('庆余年220_emotion.csv',encoding='utf_8_sig', index=False)print(output_df.head())

#显示fear、negative数据集fear_content = output_df.sort_values(by='fear',ascending=False)print(fear_content)print(fear_content.iloc[0:5]['review'])negative_content = output_df.sort_values(by='negative',ascending=False)print(negative_content)print(negative_content.iloc[0:5]['review'])

# coding=utf-8from pyecharts import options as optsfrom pyecharts.charts import WordCloudfrom pyecharts.globals import SymbolType# 数据words = [    ('背包问题', 10000),    ('大整数', 6181),    ('Karatsuba乘法算法', 4386),    ('穷举搜索', 4055),    ('傅里叶变换', 2467),    ('状态树遍历', 2244),    ('剪枝', 1868),    ('Gale-shapley', 1484),    ('最大匹配与匈牙利算法', 1112),    ('线索模型', 865),    ('关键路径算法', 847),    ('最小二乘法曲线拟合', 582),    ('二分逼近法', 555),    ('牛顿迭代法', 550),    ('Bresenham算法', 462),    ('粒子群优化', 366),    ('Dijkstra', 360),    ('A*算法', 282),    ('负极大极搜索算法', 273),    ('估值函数', 265)]# 渲染图def wordcloud_base() -> WordCloud:    c = (        WordCloud()        .add("", words, word_size_range=[20, 100], shape='diamond')  # SymbolType.ROUND_RECT        .set_global_opts(title_opts=opts.TitleOpts(title='WordCloud词云'))    )    return c# 生成图wordcloud_base().render('词云图.html')

# coding: utf-8import pandas as pdimport jiebaimport timeimport csv#-------------------------------------获取数据集---------------------------------f = open('庆余年220.csv',encoding='utf8')weibo_df = pd.read_csv(f)print(weibo_df.head())#-------------------------------------情感词典读取-------------------------------#注意：#1.词典中怒的标记(NA)识别不出被当作空值,情感分类列中的NA都给替换成NAU#2.大连理工词典中有情感分类的辅助标注(有NA),故把情感分类列改好再替换原词典中# 扩展前的词典df = pd.read_excel('大连理工大学中文情感词汇本体NAU.xlsx')print(df.head(10))df = df[['词语', '词性种类', '词义数', '词义序号', '情感分类', '强度', '极性']]df.head()#-------------------------------------七种情绪的运用-------------------------------Happy = []Good = []Surprise = []Anger = []Sad = []Fear = []Disgust = []#df.iterrows()功能是迭代遍历每一行for idx, row in df.iterrows():    if row['情感分类'] in ['PA', 'PE']:        Happy.append(row['词语'])    if row['情感分类'] in ['PD', 'PH', 'PG', 'PB', 'PK']:        Good.append(row['词语'])     if row['情感分类'] in ['PC']:        Surprise.append(row['词语'])           if row['情感分类'] in ['NB', 'NJ', 'NH', 'PF']:        Sad.append(row['词语'])    if row['情感分类'] in ['NI', 'NC', 'NG']:        Fear.append(row['词语'])    if row['情感分类'] in ['NE', 'ND', 'NN', 'NK', 'NL']:        Disgust.append(row['词语'])    if row['情感分类'] in ['NAU']:     #修改: 原NA算出来没结果        Anger.append(row['词语'])  #正负计算不是很准 自己可以制定规则       Positive = Happy + Good + SurpriseNegative = Anger + Sad + Fear + Disgustprint('情绪词语列表整理完成')  print(Anger)#---------------------------------------中文分词---------------------------------#添加自定义词典和停用词#jieba.load_userdict("user_dict.txt")stop_list = pd.read_csv('stop_words.txt',                        engine='python',                        encoding='utf-8',                        delimiter="n",                        names=['t'])#获取重命名t列的值stop_list = stop_list['t'].tolist()def txt_cut(juzi):    return [w for w in jieba.lcut(juzi) if w not in stop_list]     #可增加len(w)>1#---------------------------------------情感计算---------------------------------#文件写入c = open("Emotion_features.csv", "a+", newline='', encoding='gb18030')writer = csv.writer(c)writer.writerow(["Emotion","Word","Num"])#情感统计def emotion_caculate(text):    positive = 0    negative = 0    anger = 0    disgust = 0    fear = 0    sad = 0    surprise = 0    good = 0    happy = 0    anger_list = []    disgust_list = []    fear_list = []    sad_list = []    surprise_list = []    good_list = []    happy_list = []    wordlist = txt_cut(text)    #wordlist = jieba.lcut(text)    wordset = set(wordlist)    wordfreq = []    for word in wordset:        freq = wordlist.count(word)        tlist = []        if word in Positive:            positive+=freq        if word in Negative:            negative+=freq        if word in Anger:            anger+=freq            anger_list.append(word)            tlist.append("anger")            tlist.append(word)            tlist.append(freq)            writer.writerow(tlist)        if word in Disgust:            disgust+=freq            disgust_list.append(word)            tlist.append("disgust")            tlist.append(word)            tlist.append(freq)            writer.writerow(tlist)        if word in Fear:            fear+=freq            fear_list.append(word)            tlist.append("fear")            tlist.append(word)            tlist.append(freq)            writer.writerow(tlist)        if word in Sad:            sad+=freq            sad_list.append(word)            tlist.append("sad")            tlist.append(word)            tlist.append(freq)            writer.writerow(tlist)        if word in Surprise:            surprise+=freq            surprise_list.append(word)            tlist.append("surprise")            tlist.append(word)            tlist.append(freq)            writer.writerow(tlist)        if word in Good:            good+=freq            good_list.append(word)            tlist.append("good")            tlist.append(word)            tlist.append(freq)            writer.writerow(tlist)        if word in Happy:            happy+=freq            happy_list.append(word)            tlist.append("happy")            tlist.append(word)            tlist.append(freq)            writer.writerow(tlist)    emotion_info = {        'length':len(wordlist),        'positive': positive,        'negative': negative,        'anger': anger,        'disgust': disgust,        'fear':fear,        'good':good,        'sadness':sad,        'surprise':surprise,        'happy':happy,    }    indexs = ['length', 'positive', 'negative', 'anger', 'disgust','fear','sadness','surprise', 'good', 'happy']    #return pd.Series(emotion_info, index=indexs), anger_list, disgust_list, fear_list, sad_list, surprise_list, good_list, happy_list    return pd.Series(emotion_info, index=indexs)#---------------------------------------情感计算---------------------------------start = time.time()   emotion_df = weibo_df['review'].apply(emotion_caculate)end = time.time()print(end-start)print(emotion_df.head())#输出结果output_df = pd.concat([weibo_df, emotion_df], axis=1)output_df.to_csv('庆余年220_emotion.csv',encoding='utf_8_sig', index=False)print(output_df.head())#结束统计c.close()

# coding: utf-8import csvimport pandas as pd#读取数据f = open('Emotion_features.csv')data = pd.read_csv(f)print(data.head())#统计结果groupnum = data.groupby(['Emotion']).size()print(groupnum)print("")#分组统计for groupname,grouplist in data.groupby('Emotion'):    print(groupname)    print(grouplist)

   Emotion Word  Num0     good   人心    11     good   极好    12     good   活泼    13  disgust   强硬    14  disgust   尴尬    2Emotionanger         2disgust     208fear          9good        254happy        39sad          42surprise     11dtype: int64anger    Emotion Word  Num133   anger   气愤    1382   anger   报仇    3disgust     Emotion Word  Num3    disgust   强硬    14    disgust   尴尬    28    disgust   模糊    1..       ...  ...  ...558  disgust   紧张    1560  disgust   紧张    1561  disgust   刺激    1[208 rows x 3 columns]fear    Emotion  Word  Num93     fear   鸿门宴    1111    fear    吓人    1148    fear    可怕    1170    fear  没头苍蝇    1211    fear    厉害    1290    fear  刀光剑影    1292    fear    忌惮    1342    fear  无时无刻    1559    fear    紧张    1good    Emotion Word  Num0      good   人心    11      good   极好    1..       ...  ...  ...

# coding: utf-8import csvimport pandas as pdimport operator#------------------------------------统计结果------------------------------------#读取数据f = open('Emotion_features.csv')data = pd.read_csv(f)print(data.head())#统计结果groupnum = data.groupby(['Emotion']).size()print(groupnum)print("")#分组统计for groupname,grouplist in data.groupby('Emotion'):    print(groupname)    print(grouplist)#生成数据 word = [('A',10), ('B',9), ('C',8)] 列表+Tuplei = 0words = []counts = []while i<len(data):    if data['Emotion'][i] in "sad": #相等        k = data['Word'][i]        v = data['Num'][i]        n = 0        flag = 0        while n<len(words):            #如果两个单词相同则增加次数            if words[n]==k:                counts[n] = counts[n] + v                flag = 1                break            n = n + 1        #如果没有找到相同的特征词则添加        if flag==0:            words.append(k)            counts.append(v)    i = i + 1#添加最终数组结果result = []k = 0while k<len(words):    result.append((words[k], int(counts[k]*5)))  #注意：因数据集较少,作者扩大5倍方便绘图    k = k + 1print(result)#------------------------------------词云分析------------------------------------from pyecharts import options as optsfrom pyecharts.charts import WordCloudfrom pyecharts.globals import SymbolType# 渲染图def wordcloud_base() -> WordCloud:    c = (        WordCloud()        .add("", result, word_size_range=[5, 200], shape=SymbolType.ROUND_RECT)        .set_global_opts(title_opts=opts.TitleOpts(title='情绪词云图'))    )    return c# 生成图wordcloud_base().render('情绪词云图.html')

# coding: utf-8import sysimport gzipfrom collections import defaultdictfrom itertools import productimport jiebaimport csvimport pandas as pdclass Struct(object):    def __init__(self, word, sentiment, pos,value, class_value):        self.word = word        self.sentiment = sentiment        self.pos = pos        self.value = value        self.class_value = class_valueclass Result(object):    def __init__(self,score, score_words,not_word, degree_word ):        self.score = score        self.score_words = score_words        self.not_word = not_word        self.degree_word = degree_wordclass Score(object):        # 七个情感大类对应的小类简称: 尊敬        score_class = {'乐':['PA','PE'],                       '好':['PD','PH', 'PG','PB','PK'],                       '怒':['NA' ],                       '哀':['NB','NJ','NH', 'PF'],                       '惧':['NI', 'NC', 'NG'],                       '恶':['NE', 'ND', 'NN','NK','NL'],                       '惊':['PC']                       }        # 大连理工大学 -> ICTPOS 3.0        POS_MAP = {            'noun': 'n',            'verb': 'v',            'adj': 'a',            'adv': 'd',            'nw': 'al',  # 网络用语            'idiom': 'al',            'prep': 'p',        }        # 否定词        NOT_DICT = set(['不','不是','不大', '没', '无', '非', '莫', '弗', '毋',                        '勿', '未', '否', '别', '無', '休'])        def __init__(self, sentiment_dict_path, degree_dict_path, stop_dict_path ):            self.sentiment_struct,self.sentiment_dict = self.load_sentiment_dict(sentiment_dict_path)            self.degree_dict = self.load_degree_dict(degree_dict_path)            self.stop_words = self.load_stop_words(stop_dict_path)        def load_stop_words(self, stop_dict_path):            stop_words = [w for w in open(stop_dict_path).readlines()]            #print (stop_words[:100])            return stop_words        def remove_stopword(self, words):            words = [w for w in words if w not in self.stop_words]            return words        def load_degree_dict(self, dict_path):            """读取程度副词词典            Args:                dict_path: 程度副词词典路径. 格式为 wordtdegree                           所有的词可以分为6个级别，分别对应极其, 很, 较, 稍, 欠, 超           Returns:                返回 dict = {word: degree}            """            degree_dict = {}            with open(dict_path, 'r', encoding='UTF-8') as f:                for line in f:                    line = line.strip()                    word, degree = line.split('t')                    degree = float(degree)                    degree_dict[word] = degree            return degree_dict        def load_sentiment_dict(self, dict_path):            """读取情感词词典            Args:                dict_path: 情感词词典路径. 格式请看 README.md            Returns:                返回 dict = {(word, postag): 极性}            """            sentiment_dict = {}            sentiment_struct = []            with open(dict_path, 'r', encoding='UTF-8') as f:            #with gzip.open(dict_path) as f:                for index, line in enumerate(f):                    if index == 0:  # title,即第一行的标题                        continue                    items = line.split('t')                    word = items[0]                    pos = items[1]                    sentiment=items[4]                    intensity = items[5]  # 1, 3, 5, 7, 9五档, 9表示强度最大, 1为强度最小.                    polar = items[6]      # 极性                    # 将词性转为 ICTPOS 词性体系                    pos = self.__class__.POS_MAP[pos]                    intensity = int(intensity)                    polar = int(polar)                    # 转换情感倾向的表现形式, 负数为消极, 0 为中性, 正数为积极                    # 数值绝对值大小表示极性的强度 // 分成3类，极性：褒(+1)、中(0)、贬(-1)；强度为权重值                    value = None                    if polar == 0:            # neutral                        value = 0                    elif polar == 1:          # positive                        value = intensity                    elif polar == 2:          # negtive                        value = -1 * intensity                    else:  # invalid                        continue                    #key = (word, pos, sentiment )                    key = word                    sentiment_dict[key] = value                    #找对应的大类                    for item in self.score_class.items():                        key = item[0]                        values = item[1]                        #print(key)                        #print(value)                        for x in values:                            if (sentiment==x):                                class_value = key # 如果values中包含，则获取key                    sentiment_struct.append(Struct(word, sentiment, pos,value, class_value))            return  sentiment_struct, sentiment_dict        def findword(self, text): #查找文本中包含哪些情感词            word_list = []            for item in self.sentiment_struct:                if item.word in text:                    word_list.append(item)            return word_list        def classify_words(self, words):            # 这3个键是词的序号(索引)            sen_word = {}                             not_word = {}            degree_word = {}            # 找到对应的sent, not, degree;      words 是分词后的列表            for index, word in enumerate(words):                if word in self.sentiment_dict and word not in self.__class__.NOT_DICT and word not in self.degree_dict:                    sen_word[index] = self.sentiment_dict[word]                elif word in self.__class__.NOT_DICT and word not in self.degree_dict:                    not_word[index] = -1                elif word in self.degree_dict:                    degree_word[index] = self.degree_dict[word]            return sen_word, not_word, degree_word        def get2score_position(self, words):            sen_word, not_word, degree_word =  self.classify_words(words)   # 是字典            score = 0            start = 0            # 存所有情感词、否定词、程度副词的位置(索引、序号)的列表            sen_locs = sen_word.keys()            not_locs = not_word.keys()            degree_locs = degree_word.keys()            senloc = -1            # 遍历句子中所有的单词words，i为单词的绝对位置            for i in range(0, len(words)):                if i in sen_locs:                    W = 1  # 情感词间权重重置                    not_locs_index = 0                    degree_locs_index = 0                    # senloc为情感词位置列表的序号,之前的sen_locs是情感词再分词后列表中的位置序号                    senloc += 1                    #score += W * float(sen_word[i])                    if (senloc==0): # 第一个情感词,前面是否有否定词，程度词                        start = 0                    elif senloc < len(sen_locs):  # 和前面一个情感词之间，是否有否定词,程度词                        # j为绝对位置                        start = previous_sen_locs                    for j in range(start,i): # 词间的相对位置                        # 如果有否定词                        if j in not_locs:                            W *= -1                            not_locs_index=j                        # 如果有程度副词                        elif j in degree_locs:                            W *= degree_word[j]                            degree_locs_index=j                        # 判断否定词和程度词的位置：1）否定词在前，程度词减半(加上正值)；不是很   2）否定词在后，程度增强（不变），很不是                    if ((not_locs_index>0) and (degree_locs_index>0 )):                        if (not_locs_index < degree_locs_index ):                            degree_reduce = (float(degree_word[degree_locs_index]/2))                            W +=degree_reduce                            #print (W)                    score += W * float(sen_word[i])  # 直接添加该情感词分数                    #print(score)                    previous_sen_locs = i            return score        #感觉get2score用处不是很大        def get2score(self, text):            word_list = self.findword(text)  ##查找文本中包含哪些正负情感词，然后分别分别累计它们的数值            pos_score = 0            pos_word = []            neg_score = 0            neg_word=[]            for word in word_list:                if (word.value>0):                    pos_score = pos_score + word.value                    pos_word.append(word.word)                else:                    neg_score = neg_score+word.value                    neg_word.append(word.word)            print ("pos_score=%d; neg_score=%d" %(pos_score, neg_score))            #print('pos_word',pos_word)            #print('neg_word',neg_word)        def getscore(self, text):            word_list = self.findword(text)  ##查找文本中包含哪些情感词            # 增加程度副词+否定词            not_w = 1            not_word = []            for notword in self.__class__.NOT_DICT:  # 否定词                if notword in text:                    not_w = not_w * -1                    not_word.append(notword)            degree_word = []            for degreeword in self.degree_dict.keys():                if degreeword in text:                    degree = self.degree_dict[degreeword]                    #polar = polar + degree if polar > 0 else polar - degree                    degree_word.append(degreeword)            # 7大类找对应感情大类的词语，分别统计分数= 词极性*词权重            result = []            for key in self.score_class.keys(): #区分7大类                score = 0                score_words = []                for word in word_list:                    if (key == word.class_value):                        score = score + word.value                        score_words.append(word.word)                if score > 0:                    score = score + degree                elif score<0:                    score = score - degree  # 看分数>0，程度更强；分数<0,程度减弱？                score = score * not_w                x = '{}_score={}; word={}; nor_word={}; degree_word={};'.format(key, score, score_words,not_word, degree_word)                print (x)                result.append(x)                #key + '_score=%d; word=%s; nor_word=%s; degree_word=%s;'% (score, score_words,not_word, degree_word))            return resultif __name__ == '__main__':    sentiment_dict_path = "sentiment_words_chinese.tsv"     degree_dict_path = "degree_dict.txt"    stop_dict_path = "stop_words.txt"    #文件读取    f = open('庆余年220.csv',encoding='utf8')    data = pd.read_csv(f)    #文件写入    c = open("Result.csv", "a+", newline='', encoding='gb18030')    writer = csv.writer(c)    writer.writerow(["no","review","score"])    #分句功能 否定词程度词位置判断    score = Score(sentiment_dict_path, degree_dict_path, stop_dict_path )    n = 1    for temp in data['review']:        tlist = []        words = [x for x in jieba.cut(temp)] #分词        #print(words)             words_ = score.remove_stopword(words)        print(words_)        #分词->情感词间是否有否定词/程度词+前后顺序->分数累加        result = score.get2score_position(words_)          print(result)        tlist.append(str(n))        tlist.append(words)        tlist.append(str(result))        writer.writerow(tlist)        n = n + 1        #句子-> 整句判断否定词/程度词 -> 分正负词        #score.get2score(temp)         #score.getscore(text)    c.close()

# -*- coding: utf-8 -*-from snownlp import SnowNLPs1 = SnowNLP(u"我今天很开心")print(u"s1情感分数:")print(s1.sentiments)s2 = SnowNLP(u"我今天很沮丧")print(u"s2情感分数:")print(s2.sentiments)s3 = SnowNLP(u"大傻瓜，你脾气真差，动不动就打人")print(u"s3情感分数:")print(s3.sentiments)

s1情感分数:0.842040189791s2情感分数:0.648537121839s3情感分数:0.049546727538

# -*- coding: utf-8 -*-from snownlp import SnowNLPimport codecsimport osimport pandas as pd#获取情感分数f = open('庆余年220.csv',encoding='utf8')data = pd.read_csv(f)sentimentslist = []for i in data['review']:    s = SnowNLP(i)    print(s.sentiments)    sentimentslist.append(s.sentiments)#区间转换为[-0.5, 0.5]result = []i = 0while i<len(sentimentslist):    result.append(sentimentslist[i]-0.5)    i = i + 1#可视化画图import matplotlib.pyplot as pltimport numpy as npplt.plot(np.arange(0, 220, 1), result, 'k-')plt.xlabel('Number')plt.ylabel('Sentiment')plt.title('Analysis of Sentiments')plt.show()