情感分析_積極消極詞庫
阿新 • • 發佈:2018-11-16
import jieba
import numpy as np
# 開啟詞典檔案,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 = []
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'
deny_word = open_dict(Dict='否定詞')
posdict = open_dict(Dict='positive')
negdict = open_dict(Dict = 'negative')
degree_word = open_dict(Dict = '程度級別詞語')
# 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')] #權重4,即在情感前乘以3
verydict = degree_word[degree_word.index('very')+1: degree_word.index('more')] #權重3
moredict = degree_word[degree_word.index('more')+1: degree_word.index('ish')]#權重2
ishdict = degree_word[degree_word.index('ish')+1: degree_word.index('last')]#權重0.5
# print('mostdict',mostdict)
# print('verydict',verydict)
# print('moredict',moredict)
# print('ishdict',ishdict)
def sentiment_score_list(dataset):
seg_sentence = dataset.split('。')
print('seg_sentence',seg_sentence)
count1 = []
count2 = []
for sen in seg_sentence: # 迴圈遍歷每一個評論
segtmp = jieba.lcut(sen, cut_all=False) # 把句子進行分詞,以列表的形式返回
i = 0 #記錄掃描到的詞的位置
a = 0 #記錄情感詞的位置
poscount = 0 # 積極詞的第一次分值
poscount2 = 0 # 積極反轉後的分值
poscount3 = 0 # 積極詞的最後分值(包括歎號的分值)
negcount = 0
negcount2 = 0
negcount3 = 0
for word in segtmp:
if word in posdict: # 判斷詞語是否是情感詞
poscount +=1
c = 0#否定詞個數
for w in segtmp[a:i]: # 掃描情感詞前的程度詞
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': # 掃描情感詞前的否定詞數,奇數
poscount *= -1.0
poscount2 += poscount
poscount = 0
poscount3 = poscount + poscount2 + poscount3
poscount2 = 0
else:
poscount3 = poscount + poscount2 + poscount3
poscount = 0
a = i+1
elif word in negdict: # 消極情感的分析,與上面一致
negcount += 1
d = 0#否定詞的個數
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 deny_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 == '!': # 判斷句子是否有感嘆號
for w2 in segtmp[::-1]: # 掃描感嘆號前的情感詞,發現後權值+2,然後退出迴圈
if w2 in posdict or negdict:
poscount3 += 2
negcount3 += 2
break
i += 1
# 以下是防止出現負數的情況
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 = -pos_count
pos_count = -neg_count
else:
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
def sentiment_score(senti_score_list):
score = []
for review in senti_score_list:
score_array = np.array(review)
Pos = np.sum(score_array[:,0])
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 = '用了幾天又來評價的,手機一點也不卡,玩榮耀的什麼的不是問題,充電快,電池夠大,玩遊戲可以玩幾個小時,待機應該可以兩三天吧,很贊'
fun1=sentiment_score_list(data)
print(sentiment_score(fun1))#[[13.5, 45.0, 0.0, 1.1, 0.2, 1.0]],[Pos,Neg,AvgPos,AvgNeg,StdPos,StdNeg]