lda模型实战
# -*- coding: utf-8 -*- """ Created on Tue Dec 8 00:02:27 2020 @author: Administrator """ import numpy as np import pandas as pd import re # 数据加载 df = pd.read_csv("../input/HillaryEmails.csv") # 原邮件数据中有很多Nan的值,直接扔了。 df = df[['Id','ExtractedBodyText']].dropna() #文本预处理 def clean_email_text(text): text = text.replace(' '," ") #新行,我们是不需要的 text = re.sub(r"-", " ", text) #把 "-" 的两个单词,分开。(比如:july-edu ==> july edu) text = re.sub(r"d+/d+/d+", "", text) #日期,对主体模型没什么意义 text = re.sub(r"[0-2]?[0-9]:[0-6][0-9]", "", text) #时间,没意义 text = re.sub(r"[w]+@[.w]+", "", text) #邮件地址,没意义 text = re.sub(r"/[a-zA-Z]*[://]*[A-Za-z0-9-_]+.+[A-Za-z0-9./%&=?-_]+/i", "", text) #网址,没意义 pure_text = '' # 以防还有其他特殊字符(数字)等等,我们直接把他们loop一遍,过滤掉 for letter in text: # 只留下字母和空格 if letter.isalpha() or letter==' ': pure_text += letter # 再把那些去除特殊字符后落单的单词,直接排除。 # 我们就只剩下有意义的单词了。 text = ' '.join(word for word in pure_text.split() if len(word)>1) return text docs = df['ExtractedBodyText'] docs = docs.apply(lambda s: clean_email_text(s)) docs.head(1).values doclist = docs.values # LDA模型构建 from gensim import corpora, models, similarities import gensim ''' 为了免去讲解安装NLTK等等的麻烦,我这里直接手写一下停止词列表: 这些词在不同语境中指代意义完全不同,但是在不同主题中的出现概率是几乎一致的。 所以要去除,否则对模型的准确性有影响 ''' stoplist = ['very', 'ourselves', 'am', 'doesn', 'through', 'me', 'against', 'up', 'just', 'her', 'ours', 'couldn', 'because', 'is', 'isn', 'it', 'only', 'in', 'such', 'too', 'mustn', 'under', 'their', 'if', 'to', 'my', 'himself', 'after', 'why', 'while', 'can', 'each', 'itself', 'his', 'all', 'once', 'herself', 'more', 'our', 'they', 'hasn', 'on', 'ma', 'them', 'its', 'where', 'did', 'll', 'you', 'didn', 'nor', 'as', 'now', 'before', 'those', 'yours', 'from', 'who', 'was', 'm', 'been', 'will', 'into', 'same', 'how', 'some', 'of', 'out', 'with', 's', 'being', 't', 'mightn', 'she', 'again', 'be', 'by', 'shan', 'have', 'yourselves', 'needn', 'and', 'are', 'o', 'these', 'further', 'most', 'yourself', 'having', 'aren', 'here', 'he', 'were', 'but', 'this', 'myself', 'own', 'we', 'so', 'i', 'does', 'both', 'when', 'between', 'd', 'had', 'the', 'y', 'has', 'down', 'off', 'than', 'haven', 'whom', 'wouldn', 'should', 've', 'over', 'themselves', 'few', 'then', 'hadn', 'what', 'until', 'won', 'no', 'about', 'any', 'that', 'for', 'shouldn', 'don', 'do', 'there', 'doing', 'an', 'or', 'ain', 'hers', 'wasn', 'weren', 'above', 'a', 'at', 'your', 'theirs', 'below', 'other', 'not', 're', 'him', 'during', 'which'] # 中文的分词稍微复杂点儿,具体可以百度:CoreNLP, HaNLP, 结巴分词,等等 texts = [[word for word in doc.lower().split() if word not in stoplist] for doc in doclist] texts[0] # 语料库构建 dictionary = corpora.Dictionary(texts) corpus = [dictionary.doc2bow(text) for text in texts] #词袋模型 corpus[13] lda = gensim.models.ldamodel.LdaModel(corpus=corpus, id2word=dictionary, num_topics=20) #第十主题/分类,最常出现词 lda.print_topic(10, topn=5) #所有主题top5词 lda.print_topics(num_topics=20, num_words=5) #文本主题 lda.get_document_topics(bow) #词主题 lda.get_term_topics(word_id)