In [1]:
# coding:utf-8
import numpy as np
import pandas as pd
import re
In [2]:
df = pd.read_csv("HillaryEmails.csv")
# 原邮件数据中有很多Nan的值，直接扔掉。
df = df[['Id','ExtractedBodyText']].dropna()
In [3]:
def clean_email_text(text):
text = text.replace('\n'," ") #去掉新行
text = re.sub(r"-", " ", text) #把 "-" 的两个单词，分开。
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，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
In [4]:
docs = df['ExtractedBodyText']
docs = docs.apply(lambda s: clean_email_text(s))
In [5]:
docs.head(1).values
Out[5]:
把所有的邮件内容拿出来。
In [6]:
doclist = docs.values
In [7]:
from gensim import corpora, models, similarities
import gensim
In [8]:
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']
人工分词：
英文的分词，对着空白处分割就可以了。
中文的分词可以使用CoreNLP, HaNLP, 结巴分词，等等
In [9]:
texts = [[word for word in doc.lower().split() if word not in stoplist] for doc in doclist]
In [10]:
texts[0] #一封邮件分词后的结果
Out[10]:
In [11]:
dictionary = corpora.Dictionary(texts)
corpus = [dictionary.doc2bow(text) for text in texts]
In [12]:
corpus[13] #第14封邮件中，一共6个有意义的单词（经过文本预处理，并去除了停止词后）其中，36号单词出现1次，505号单词出现1次
Out[12]:
In [13]:
lda = gensim.models.ldamodel.LdaModel(corpus=corpus, id2word=dictionary, num_topics=20)
In [14]:
lda.print_topic(10, topn=5) #第10号分类，最常出现的top 5单词
Out[14]:
In [15]:
lda.print_topics(num_topics=20, num_words=5) #打印所有主题
Out[15]: