Load Dict form disk Returns: senti_word: senti word dict (BosonNLP) not_word: not word dict （情感极性词典.zip） degree_word: de

Load Dict form disk Returns: senti_word: senti word dict (BosonNLP) not_word: not word dict （情感极性词典.zip） degree_word: de

Turn a sentence into tokenized word list and remove stop-word Using jieba to tokenize Chinese. Args: sentence: A string. Return

将sentence中的繁体字转为简体字 :param sentence: 待转换的句子 :return: 将句子中繁体字转换为简体字之后的句子

Function does are number of Jobs: 1- Creates a word to index mapping 2- Creates a word to vector mapping 3- Transform

Function does are number of Jobs: 1- Creates a word to index mapping 2- Creates a word to vector mapping 3- Transforms the Tr

Find the location of Sentiment words, Not words, and Degree words The idea is pretty much naive, iterate every word to find the location of Senti

Find the location of Sentiment words, Not words, and Degree words The idea is pretty much naive, iterate every word to find the location of Senti

匹配微博内容和微博评论数据，并将明显的广告微博剔除 Args: comment_example: [ {'_id': 'C_4322161898716112', 'crawl_time': '2019-06-01 20:35:36', 'weibo_

Compute the sentiment score of this sentence 基于词典的情感分析算法 Args: senti_word: BosonNLP not_word: not word location dict （情感

Compute the sentiment score of this sentence 基于词典的情感分析算法 Args: senti_word: BosonNLP not_word: not word location dict （情感

Turn a sentence into tokenized word list and remove stop-word Using jieba to tokenize Chinese. Args: sentence: A string. Return

将sentence中的繁体字转为简体字 :param sentence: 待转换的句子 :return: 将句子中繁体字转换为简体字之后的句子

Function does are number of Jobs: 1- Creates a word to index mapping 2- Creates a word to vector mapping 3- Transform

Words become integers

Words become integers

Words become integers

:param text: string :return: [[tokenize1,tokenize2..]] list of list

:param text: string :return: [[tokenize1,tokenize2..]] list of list

将时间显示从2018/1/1 23:59:59 转化为2018-01-01 :param string: 如2018/1/1 23:59:59 :return: string: 如2018/1/1