LDA模型应用实践-希拉里邮件主题分类

#coding=utf8
import numpy as np
import pandas as pd
import re
from gensim import corpora, models, similarities
import gensim
from nltk.corpus import stopwords

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()

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))
doclist = docs.values
stopwords = set(stopwords.words('english'))

texts = [[word for word in doc.lower().split() if word not in stopwords] for doc in doclist]

dictionary = corpora.Dictionary(texts)
corpus = [dictionary.doc2bow(text) for text in texts]

lda = gensim.models.ldamodel.LdaModel(corpus=corpus, id2word=dictionary, num_topics=20)


print lda.print_topics(num_topics=20, num_words=5)