def school_weibo_dict_analysis(schoolname):
weibo_content_results = pickle.load(open('dict weibo data\\%s_seg_weibo_new.pkl' % (schoolname), 'r'))
cuted_weibo = []
meaning_count = 0
positive_count = 0
negative_count = 0
for cell in weibo_content_results:
if cell[1] == 1:
cuted_weibo.append(tp.cut_sentences_2(cell[0]))
#pass
else:
meaning_count += 1
single_weibo_count = []
for index,weibo in enumerate(cuted_weibo):
single_weibo_count = []
for sent in weibo:
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
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
elif word == '!'.decode('utf-8') or word == '！'.decode('utf-8'):
for w2 in seg_sent[::-1]:
if w2 in posdict:
poscount += 2
break
elif w2 in negdict:
negcount += 2
break
i += 1
single_weibo_count.append(transform_to_positive_num(poscount, negcount, 0, 0, 0))
[pos_count, neg_count] = judge_weibo(single_weibo_count)
#print index, pos_count, neg_count
if pos_count > neg_count:
positive_count += 1
elif pos_count < neg_count:
negative_count += 1
else:
meaning_count += 1
end_results = [positive_count, negative_count, meaning_count]
pickle.dump(end_results, open('dict weibo data\\%s_end_results.pkl' % schoolname, 'w'))
print end_results
return end_results
def all_weibo_sentence_sentiment_score(schoolname, weiboid=None):
weibo_content_results = tp.get_one_weibo_data(schoolname, weiboid)
cuted_weibo = []
upvotes = []
forwards = []
reviews = []
weiboid = None
for cell in weibo_content_results:
cuted_weibo.append(tp.cut_sentences_2(cell[0]))
upvotes.append(int(cell[1]))
forwards.append(int(cell[2]))
reviews.append(int(cell[3]))
weiboid = cell[4]
'''
print cell[0] #微博内容
'''
#print cell[1], #点赞数量
#print cell[2] #转发数量
#print cell[3] #评论数量
single_weibo_count = []
all_weibo_count = []
for index,weibo in enumerate(cuted_weibo):
for sent in weibo:
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
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
elif word == '!'.decode('utf-8') or word == '！'.decode('utf-8'):
for w2 in seg_sent[::-1]:
if w2 in posdict:
poscount += 2
break
elif w2 in negdict:
negcount += 2
break
i += 1
single_weibo_count.append(transform_to_positive_num(poscount, negcount, upvotes[index], forwards[index], reviews[index])) #[[s1_score], [s2_score], ...]
all_weibo_count.append(single_weibo_count) # [[[s11_score], [s12_score], ...], [[s21_score], [s22_score], ...], ...]
single_weibo_count = []
return all_weibo_count, weiboid
def single_weibo_sentiment_score(weibo):
single_weibo_senti_score = []
cuted_weibo = tp.cut_sentences_2(weibo) # 切分成一个个小句子的list
for sent in cuted_weibo:
print '', sent
seg_sent = tp.segmentation(sent, 'list') # 分词，返回单词列表
i = 0 # word position counter
s = 0 # sentiment word position
poscount = 0 # count a positive word
negcount = 0 # count a negative word
for word in seg_sent:
print '', word
if word in posdict:
poscount += 1
for w in seg_sent[s:i]:
poscount = match(w, poscount)
a = i + 1
elif word in negdict:
negcount += 1
for w in seg_sent[s:i]:
negcount = match(w, negcount)
a = i + 1
# Match "！" in the weibo, every "！" has a weight of +2
elif word == "!".decode('utf-8') or word == "！".decode('utf-8'):
for w2 in seg_sent[::-1]:
if w2 in posdict:
poscount += 2
break
elif w2 in negdict:
negcount += 2
break
i += 1
print 'positive and negative',poscount, negcount
single_weibo_senti_score.append(transform_to_positive_num(poscount, negcount))
weibo_sentiment_score = sumup_sentence_sentiment_score(single_weibo_senti_score)
for i in single_weibo_senti_score:
print i
return weibo_sentiment_score
