一个使用gensim实现的非常简单的LDA。你可以在这里找到更多信息:
https://radimrehurek.com/gensim/tutorial.html
希望能对你有所帮助。
from nltk.corpus import stopwords
from nltk.tokenize import RegexpTokenizer
from nltk.stem import RSLPStemmer
from gensim import corpora, models
import gensim
st = RSLPStemmer()
texts = []
doc1 = "Veganism is both the practice of abstaining from the use of animal products, particularly in diet, and an associated philosophy that rejects the commodity status of animals"
doc2 = "A follower of either the diet or the philosophy is known as a vegan."
doc3 = "Distinctions are sometimes made between several categories of veganism."
doc4 = "Dietary vegans refrain from ingesting animal products. This means avoiding not only meat but also egg and dairy products and other animal-derived foodstuffs."
doc5 = "Some dietary vegans choose to wear clothing that includes animal products (for example, leather or wool)."
docs = [doc1, doc2, doc3, doc4, doc5]
for i in docs:
tokens = word_tokenize(i.lower())
stopped_tokens = [w for w in tokens if not w in stopwords.words('english')]
stemmed_tokens = [st.stem(i) for i in stopped_tokens]
texts.append(stemmed_tokens)
dictionary = corpora.Dictionary(texts)
corpus = [dictionary.doc2bow(text) for text in texts]
ldamodel = gensim.models.ldamodel.LdaModel(corpus, num_topics=2, id2word = dictionary, passes=20)
print(ldamodel.print_topics(num_topics=2, num_words=4))
[(0, u'0.066*动物 + 0.065*, + 0.047*产品 + 0.028*哲学'), (1, u'0.085*. + 0.047*产品 + 0.028*膳食 + 0.028*素食')]
gensim
,你可以非常容易地通过pip install
安装它。这是主题页面:https://radimrehurek.com/gensim/tut2.html。关于你实际的问题,看起来...哦不,等等我找到了。 - Eugene