def fenci1(comments, storePath, filter=False):
stopwords = tp.loadTextWords(os.getcwd() +
"\Dictionary\stopword\stopwords.txt")
for comment in comments:
seg_result = tp.segmentation(comment, 'str')
seg_list = tp.segmentation(comment, 'list')
if (filter == True):
seg_filter = [
word for word in seg_list
if word not in stopwords and word != ' '
]
seg_result = " ".join(seg_filter)
print(seg_result)
with codecs.open(storePath, 'a+', 'utf-8') as f:
f.writelines(seg_result + "\n")
def cut_sentences_words(self, review):
sent_words = []
cuted_review = tp.cut_sentence_2(review)
for sent in cuted_review:
seg_sent = tp.segmentation(sent, 'list')
#seg_sent = self.stop_word_filter(seg_sent)
sent_words.append(seg_sent)
return sent_words
def get_single_sent_count(cuted_sents):
single_review_senti_score = []
for sent in cuted_sents:
seg_sent = tp.segmentation(sent, 'list')
i = 0 # word position counter
a = 0 # sentiment word position
poscount = 0 # count a positive word
negcount = 0 # count a negative word
#match 用于表示程度
for word in seg_sent:
if word in posdict:
poscount += 1
for w in seg_sent[a:i]:
poscount = match(w, poscount)
a = i + 1
elif word in negdict:
negcount += 1
for w in seg_sent[a:i]:
negcount = match(w, negcount)
a = i + 1
# Match "!" in the review, every "!" has a weight of +2
elif word == "！".decode('utf8') or word == "!".decode('utf8'):
for w2 in seg_sent[::-1]:
if w2 in posdict:
poscount += 2
break
elif w2 in negdict:
negcount += 2
break
i += 1
single_review_senti_score.append(
transform_to_positive_num(poscount, negcount))
return single_review_senti_score
def single_review_sentiment_score(weibo_sent):
single_review_senti_score = []
all_word = []
cuted_review = tp.cut_sentence(weibo_sent) # 句子切分，单独对每个句子进行分析
for sent in cuted_review:
seg_sent = tp.segmentation(sent) # 分词
seg_sent = tp.del_stopwords(seg_sent)[:]
#print(seg_sent)
i = 0 # 记录扫描到的词的位置
s = 0 # 记录情感词的位置
poscount = 0 # 记录该分句中的积极情感得分
negcount = 0 # 记录该分句中的消极情感得分
mark1_count = 0
mark2_count = 0
for word in seg_sent: # 逐词分析
all_word.append(word)
if word in posdict: # 如果是积极情感词
# print "posword:", word
poscount += 1 # 积极得分+1
for w in seg_sent[s:i]:
poscount = match(w, poscount)
# print "poscount:", poscount
s = i + 1 # 记录情感词的位置变化
elif word in negdict: # 如果是消极情感词
# print "negword:", word
negcount += 1
for w in seg_sent[s:i]:
negcount = match(w, negcount)
# print "negcount:", negcount
s = i + 1
# 如果是感叹号，表示已经到本句句尾
# elif word == "！" :
elif word.encode('UTF-8') == "? " or word.encode('UTF-8') == " ？":
mark1_count += 1
elif word.encode('UTF-8') == "！" or word.encode('UTF-8') == "！":
mark2_count += 1
for w2 in seg_sent[::-1]: # 倒序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:
poscount += 1
break
elif w2 in negdict:
negcount += 1
break
i += 1
#print (negcount)
single_review_senti_score.append(
transform_to_positive_num(poscount, negcount)) # 对得分做最后处理
#print("poscount,negcount,?, ！", poscount, negcount, mark1_count, mark2_count)
#return single_review_senti_score
#print ("lenth:%d"%(len(all_word)))
su = len(all_word)
pos_result, neg_result = 0, 0 # 分别记录积极情感总得分和消极情感总得分
sentlength = len(single_review_senti_score)
#wordlength = len(all_word)
#print ("该回答共有%d 分句,共有%d 个分词" %(sentlength,wordlength))
#print ("该回答共有%d个词" %wordlength)
pos_score = []
neg_score = []
for res1, res2 in single_review_senti_score: # 每个分句循环累加
pos_result += res1
neg_result += res2
pos_score.append(pos_result)
neg_score.append(neg_result)
# print pos_result, neg_result
result1 = (pos_result - neg_result) # 简单计算该语句的得分
result2 = (pos_result + neg_result)
try:
result = result1 / result2 #利用林乐模型计算语调
tone = round(result, 3)
#print (tone)
#return result
except Exception as e:
tone = 0
#return result
res = 0
if tone > 0.0:
res = 1
elif tone < 0.0:
res = 2
#print ("susu:%d xue:%d" %(pos_result,neg_result))
return pos_result, neg_result, tone, su