情感分析_积极消极词库
import jieba
import numpy as np
# 打开词典⽂件，返回列表
def open_dict(Dict='hahah',path = 'C:\E\Textming\Textming/'):
path = path + '%s.txt' %Dict
dictionary = open(path, 'r', encoding='utf-8')
dict = []驾考流程
for word in dictionary:
word = word.strip('\n')
dict.append(word)
return dict
def judgeodd(num):
if num % 2 == 0:
return 'even'
el:
return 'odd'
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')
# print('deny_word',deny_word)
# print('posdict',posdict)
# print('negdict',negdict)
# print('degree_word',degree_word)
mostdict = degree_word[degree_word.index('extreme')+1: degree_word.index('very')] #权重4，即在情感前乘以3 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
# print('mostdict',mostdict)
# print('verydict',verydict)
# print('moredict',moredict)
# print('ishdict',ishdict)
def ntiment_score_list(datat):
g_ntence = datat.split('。')
print('g_ntence',g_ntence)
count1 = []
count2 = []
for n in g_ntence: # 循环遍历每⼀个评论
gtmp = jieba.lcut(n, cut_all=Fal) # 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 gtmp:
if word in posdict: # 判断词语是否是情感词
poscount +=1
c = 0#否定词个数
for w in gtmp[a:i]: # 扫描情感词前的程度词
if w in mostdict:
poscount *= 4.0
中秋佳节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，奇数
poscount *= -1.0
poscount2 += poscount
poscount = 0
poscount3 = poscount + poscount2 + poscount3
poscount2 = 0
el:
poscount3 = poscount + poscount2 + poscount3
poscount = 0
a = i+1十三陵陵园
打台球技巧
elif word in negdict: # 消极情感的分析，与上⾯⼀致
negcount += 1
d = 0#否定词的个数
for w in gtmp[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 deny_word:
d += 1
if judgeodd(d) == 'odd':
negcount *= -1.0
negcount2 += negcount
negcount = 0
negcount3 = negcount + negcount2 + negcount3
negcount2 = 0
el:
el:
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 gtmp[::-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
# 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:
生日发红包neg_count = -pos_count
pos_count = -neg_count
同形反应
el:
pos_count = poscount3
neg_count = negcount3
# print('[pos_count,neg_count]',[pos_count,neg_count])
count1.append([pos_count,neg_count])
count2.append(count1)
count1=[]
# print('count2',count2)
return count2写海的作文
def ntiment_score(nti_score_list):
score = []
for review in nti_score_list:
score_array = np.array(review)
Pos = np.sum(score_array[:,0])
美国恐怖片
Neg = np.sum(score_array[:,1])
AvgPos = np.mean(score_array[:,0])
AvgPos = float('%.lf' % AvgPos)
AvgNeg = np.mean(score_array[:, 1])
AvgNeg = float('%.1f' % AvgNeg)
StdPos = np.std(score_array[:, 0])
StdPos = float('%.1f' % StdPos)
StdNeg = np.std(score_array[:, 1])
StdNeg = float('%.1f' % StdNeg)
score.append([Pos,Neg,AvgPos,AvgNeg,StdPos,StdNeg])
return score
data = '⽤了⼏天⼜来评价的，⼿机⼀点也不卡，玩荣耀的什么的不是问题，充电快，电池够⼤，玩游戏可以玩⼏个⼩时，待机应该可以两三天吧，很赞' fun1=ntiment_score_list(data)
print(ntiment_score(fun1))#[[13.5, 45.0, 0.0, 1.1, 0.2, 1.0]]，[Pos,Neg,AvgPos,AvgNeg,StdPos,StdNeg]
转载于:/hapyygril/p/9970567.html
