本文整理汇总了Python中gensim.models.LdaModel.print_topics方法的典型用法代码示例。如果您正苦于以下问题：Python LdaModel.print_topics方法的具体用法？Python LdaModel.print_topics怎么用？Python LdaModel.print_topics使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类gensim.models.LdaModel的用法示例。
在下文中一共展示了LdaModel.print_topics方法的4个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: lda
# 需要导入模块: from gensim.models import LdaModel [as 别名]
# 或者: from gensim.models.LdaModel import print_topics [as 别名]
def lda():
# remove stop words
stopwords = codecs.open('../conf/stop_words_ch.txt', mode='r', encoding='utf8').readlines()
stopwords = [ w.strip() for w in stopwords ]
fp = codecs.open('D:\\nlp\corpora\segs.txt', mode='r', encoding='utf8')
train = []
for line in fp:
line = line.split()
train.append([ w for w in line if w not in stopwords ])
dictionary = corpora.Dictionary(train)
corpus = [ dictionary.doc2bow(text) for text in train ]
lda = LdaModel(corpus=corpus, id2word=dictionary, num_topics=100)
lda.print_topics(30)
# print topic id=20
lda.print_topic(20)
# save/load model
lda.save('D:\\nlp\corpora\news.model')示例2: dictionary
# 需要导入模块: from gensim.models import LdaModel [as 别名]
# 或者: from gensim.models.LdaModel import print_topics [as 别名]
print 'Saving dictionary (%s)...' % DICT
dictionary.save(DICT)
print 'Building bag-of-words corpus ...'
bow_corpus = [ dictionary.doc2bow(t) for t in texts ]
print 'Serializing corpus (%s) ...' % BOW
MmCorpus.serialize(BOW, bow_corpus)
size = len(bow_corpus) * 4 / 5
training = bow_corpus[:size]
testing = bow_corpus[size:]
print 'Training LDA w/ %d topics on first %d texts ...' % (Num_Topics, len(training))
lda = LdaModel(training, id2word=dictionary, num_topics=Num_Topics, passes=5, iterations = 1000)
print 'Saving LDA model (%s) ...' % NSFLDA
lda.save(NSFLDA)
print 'Random subset of topics:'
print '\n'.join(lda.print_topics())
print 'Computing perplexity on %d held-out documents ...' % len(testing)
perplexity = 2 ** -(lda.log_perplexity(testing))
print 'Perplexity: %.2f' % perplexity
示例3: unpickle
# 需要导入模块: from gensim.models import LdaModel [as 别名]
# 或者: from gensim.models.LdaModel import print_topics [as 别名]
#
# logging.info('combine report and wiki dictionary...')
# wiki_to_report = report_dict.merge_with(wiki_dict)
# merged_dict = report_dict
#
# logging.info('combine report and wiki corpus...')
# merged_corpus = wiki_to_report[wiki_corpus].corpus + report_corpus
logging.info('generate wiki corpus...')
wiki_txt = unpickle('data/txt/processed_wiki.pkl')
wiki_corpus = [report_dict.doc2bow(wiki) for wiki in wiki_txt]
logging.info('combine report and wiki corpus...')
merged_corpus = wiki_corpus + report_corpus
# compute TFIDF
# logging.info('compute TFIDF...')
# tfidf = TfidfModel(dictionary=report_dict, id2word=report_dict)
# perform LDA
logging.info('perform LDA...')
if use_wiki is True:
lda = LdaModel(corpus=merged_corpus, id2word=report_dict, num_topics=num_topics, passes=passes,
iterations=iterations, alpha='auto', chunksize=chunksize)
lda.save('result/model_wiki.lda')
lda.print_topics(topics=num_topics, topn=10)
else:
lda = LdaModel(corpus=report_corpus, id2word=report_dict, num_topics=num_topics, passes=passes,
iterations=iterations, alpha='auto', chunksize=chunksize)
lda.save('result/model.lda')
lda.print_topics(topics=num_topics, topn=10)
示例4: print
# 需要导入模块: from gensim.models import LdaModel [as 别名]
# 或者: from gensim.models.LdaModel import print_topics [as 别名]
# stemming process
print(count)
# print(List)
# counts = Counter(List)
# print(counts)
print(documentInfo)
train_set = documentInfo
# construct training corpus
dictionary = Dictionary(train_set)
corpus = [dictionary.doc2bow(text) for text in train_set]
print(corpus)
print(dictionary)
# train lda model
lda = LdaModel(corpus=corpus, id2word=dictionary, num_topics=30)
print(lda)
print(lda.print_topics(5))
#
# def lda_test(train_set):
# # train corpus
# dictionary = Dictionary(train_set)
# corpus = [dictionary.doc2bow(text) for text in train_set]
# print(corpus)
# print(dictionary)
# # lda model training
# lda = LdaModel(corpus=corpus, id2word=dictionary, num_topics=50)
# print(lda)
# return (lda.print_topics(50))