自然语言处理(NLP) 六：主题建模_nlp六 model

import warnings
warnings.filterwarnings('ignore',category=UserWarning)
import nltk.tokenize as tk 
import nltk.corpus as nc 
import nltk.stem.snowball as sb 
import gensim.models.ldamodel as gm 
import gensim.corpora as gc 

doc = []
with open('/Users/youkechaung/Desktop/算法/数据分析/AI/day02/day02/data/topic.txt','r') as f:
    for line in f.readlines():
        doc.append(line[:-1])
        #除去了换行符
tokenizer = tk.RegexpTokenizer(r'\w+')
#建立一个正则表达式的分词器，以单词的形式进行拆词，但是不要标点符号
#the  as 等词为stopwords,高频但是不重要
stopwords = nc.stopwords.words('english')
stemmer = sb.SnowballStemmer('english')
lines_tokens = []
for line in doc:
    tokens = tokenizer.tokenize(line.lower())
    line_tokens = []
    for token in tokens:
        if token not in stopwords:
            token = stemmer.stem(token)
            line_tokens.append(token)
    lines_tokens.append(line_tokens)
dic = gc.Dictionary(lines_tokens)
bow = []
for line_tokens in lines_tokens:
    row = dic.doc2bow(line_tokens)
    bow.append(row)
print(bow)

n_topics = 2
#隐含狄利克雷分布，主题建模器
model = gm.LdaModel(bow,num_topics=n_topics,id2word=dic,passes=25)
topics = model.print_topics(num_topics=n_topics,num_words=4)
print(topics)


























1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66