def sentimentExtractor(sentence): list = pn.single_review_sentiment_score(sentence) if list[0] > list[1]: return True else: return False
__author__ = 'anchengwu' #coding=utf-8 import sys sys.path.append("../../../Preprocessing module") import pos_neg_senti_dict_feature as pn import textprocessing as tp # Load dataset review = tp.get_excel_data( "../Machine learning features/seniment review set/pos_review.xlsx", 1, 1, "data") #test single dataset print pn.single_review_sentiment_score( '买过散装的粽子才来买礼盒的,礼盒很大气,比超市买的100多的还要好,配置也不错,肉的素的都有,刚煮了个蛋黄粽子很不错,米好蛋黄也黄很香,老板态度很好,还想买一份~' .decode('utf8')) #test all dataset for i in pn.all_review_sentiment_score(pn.sentence_sentiment_score(review)): print i
# 词性分析 wordList = pseg.cut(reqParamList[1]) wordFlagResult = '' for words in wordList: wordFlagResult += words.word + '$%^' + words.flag + '$%^' clientSender.publish('wordFlagResult', reqParamList[0] + '!@#' + wordFlagResult) elif item['channel'] == 'sentiments': # 情感分析 sr=pn.single_review_sentiment_score(reqParamList[1].decode('utf8')) print sr if len(sr) <= 0 : continue pos=sr[2] neg=sr[3] if (pos==0 and neg ==0):pos=0.5 elif (pos==0 and neg !=0):pos=0.1 elif (pos!=0 and neg !=0):pos=pos/(pos+neg) print pos # sentimentsResult += words.word + '$%^' + words.flag + '$%^' #基于机器学习的情感分析 s = [] s.append(reqParamList[1].decode('utf8'))
__author__ = 'anchengwu' #coding=utf-8 import sys sys.path.append("../../../Preprocessing module") import pos_neg_senti_dict_feature as pn import textprocessing as tp # Load dataset review = tp.get_excel_data("../Machine learning features/seniment review set/pos_review.xlsx", 1, 1, "data") #test single dataset print pn.single_review_sentiment_score('买过散装的粽子才来买礼盒的,礼盒很大气,比超市买的100多的还要好,配置也不错,肉的素的都有,刚煮了个蛋黄粽子很不错,米好蛋黄也黄很香,老板态度很好,还想买一份~'.decode('utf8')) #test all dataset for i in pn.all_review_sentiment_score(pn.sentence_sentiment_score(review)): print i