Python_LDA实现方法详解 实现方法详解 主要介绍了Python_LDA实现方法详解，具有一定参考价值，需要的朋友可以了解下。 LDA(Latent Dirichlet allocation)模型是一种常用而用途广泛地概率主题模型。其实现一般通过Variational inference和Gibbs Samping实现。作者在提出LDA模型时给出了其变分推理的C源码（后续贴出C++改编的类），这里贴出基于Python的第三方 模块改写的LDA类及实现。 #coding:utf-8 import numpy as np import lda import lda.datasets import jieba import codecs class LDA_v20161130(): def __init__(self, topics=2): self.n_topic = topics self.corpus = None self.vocab = None self.ppCountMatrix = None self.stop_words = [u'，', u'。', u'、', u'（', u'）', u'·', u'！', u' ', u'：', u'“', u'”', u'\n'] self.model = None def loadCorpusFromFile(self, fn): # 中文分词 f = open(fn, 'r') text = f.readlines() text = r' '.join(text) seg_generator = jieba.cut(text) seg_list = [i for i in seg_generator if i not in self.stop_words] seg_list = r' '.join(seg_list) # 切割统计所有出现的词纳入词典 seglist = seg_list.split(" ") self.vocab = [] for word in seglist: if (word != u' ' and word not in self.vocab): self.vocab.append(word) CountMatrix = [] f.seek(0, 0) # 统计每个文档中出现的词频 for line in f: # 置零 count = np.zeros(len(self.vocab),dtype=np.int) text = line.strip() # 但还是要先分词 seg_generator = jieba.cut(text) seg_list = [i for i in seg_generator if i not in self.stop_words] seg_list = r' '.join(seg_list) seglist = seg_list.split(" ") # 查询词典中的词出现的词频 for word in seglist: if word in self.vocab: count[self.vocab.index(word)] += 1 CountMatrix.append(count) f.close() #self.ppCountMatrix = (len(CountMatrix), len(self.vocab)) self.ppCountMatrix = np.array(CountMatrix) print "load corpus from %s success!"%fn def setStopWords(self, word_list): self.stop_words = word_list def fitModel(self, n_iter = 1500, _alpha = 0.1, _eta = 0.01): self.model = lda.LDA(n_topics=self.n_topic, n_iter=n_iter, alpha=_alpha, eta= _eta, random_state= 1) self.model.fit(self.ppCountMatrix) def printTopic_Word(self, n_top_word = 8): for i, topic_dist in enumerate(self.model.topic_word_): topic_words = np.array(self.vocab)[np.argsort(topic_dist)][:-(n_top_word + 1):-1] print "Topic:",i,"\t", for word in topic_words: print word, print def printDoc_Topic(self): for i in range(len(self.ppCountMatrix)): print ("Doc %d:((top topic:%s) topic distribution:%s)"%(i, self.model.doc_topic_[i].argmax(),self.model.doc_topic_[i])) def printVocabulary(self): print "vocabulary:" for word in self.vocab: print word, print def saveVocabulary(self, fn): f = codecs.open(fn, 'w', 'utf-8') 

for word in self.vocab: f.write("%s\n"%word) f.close() def saveTopic_Words(self, fn, n_top_word = -1): if n_top_word==-1: n_top_word = len(self.vocab) f = codecs.open(fn, 'w', 'utf-8') for i, topic_dist in enumerate(self.model.topic_word_): topic_words = np.array(self.vocab)[np.argsort(topic_dist)][:-(n_top_word + 1):-1] f.write( "Topic:%d\t"%i) for word in topic_words: f.write("%s "%word) f.write("\n") f.close() def saveDoc_Topic(self, fn): f = codecs.open(fn, 'w', 'utf-8') for i in range(len(self.ppCountMatrix)): f.write("Doc %d:((top topic:%s) topic distribution:%s)\n" % (i, self.model.doc_topic_[i].argmax(), self.model.doc_topic_[i])) f.close() 算法实现demo： 例如，抓取BBC川普当选的新闻作为语料，输入以下代码： if __name__=="__main__": _lda = LDA_v20161130(topics=20) stop = [u'!', u'@', u'#', u',',u'.',u'/',u';',u' ',u'[',u']',u'$',u'%',u'^',u'&',u'*',u'(',u')', u'"',u':',u'<',u'>',u'?',u'{',u'}',u'=',u'+',u'_',u'-',u''''''] _lda.setStopWords(stop) _lda.loadCorpusFromFile(u'C:\\Users\Administrator\Desktop\\BBC.txt') _lda.fitModel(n_iter=1500) _lda.printTopic_Word(n_top_word=10) _lda.printDoc_Topic() _lda.saveVocabulary(u'C:\\Users\Administrator\Desktop\\vocab.txt') _lda.saveTopic_Words(u'C:\\Users\Administrator\Desktop\\topic_word.txt') _lda.saveDoc_Topic(u'C:\\Users\Administrator\Desktop\\doc_topic.txt') 因为语料全部为英文，因此这里的stop_words全部设置为英文符号，主题设置20个，迭代1500次。结果显示，文档148篇， 词典1347词，总词数4174，在i3的电脑上运行17s。 Topic_words部分输出如下： Topic: 0 to will and of he be trumps the what policy Topic: 1 he would in said not no with mr this but Topic: 2 for or can some whether have change health obamacare insurance Topic: 3 the to that president as of us also first all Topic: 4 trump to when with now were republican mr office presidential Topic: 5 the his trump from uk who president to american house Topic: 6 a to that was it by issue vote while marriage Topic: 7 the to of an are they which by could from Topic: 8 of the states one votes planned won two new clinton Topic: 9 in us a use for obama law entry new interview Topic: 10 and on immigration has that there website vetting action given Doc_Topic部分输出如下： Doc 0:((top topic:4) topic distribution:[ 0.02972973 0.0027027 0.0027027 0.16486486 0.32702703 0.19189189 0.0027027 0.0027027 0.02972973 0.0027027 0.02972973 0.0027027 0.0027027 0.0027027 0.02972973 0.0027027 0.02972973 0.0027027 0.13783784 0.0027027 ]) Doc 1:((top topic:18) topic distribution:[ 0.21 0.01 0.01 0.01 0.01 0.01 0.01 0.01 0.11 0.01 0.01 0.01 0.01 0.01 0.01 0.01 0.01 0.01 0.31 0.21]) Doc 2:((top topic:18) topic distribution:[ 0.02075472 0.00188679 0.03962264 0.00188679 0.00188679 0.00188679 0.00188679 0.15283019 0.00188679 0.02075472 0.00188679 0.24716981 0.00188679 0.07735849 0.00188679 0.00188679 0.00188679 0.00188679 0.41698113 0.00188679]) 当然，对于英文语料，需要排除大部分的虚词以及常用无意义词，例如it, this, there, that...在实际操作中，需要合理地设置参 数。 换中文语料尝试，采用习大大就卡斯特罗逝世发表的吊唁文章和朴槿惠辞职的新闻。 Topic: 0 的 同志 和 人民 卡斯特罗 菲德尔 古巴 他 了 我 Topic: 1 在 朴槿惠 向 表示 总统 对 将 的 月 国民 

Doc 0:((top topic:0) topic distribution:[ 0.91714123 0.08285877]) Doc 1:((top topic:1) topic distribution:[ 0.09200666 0.90799334]) 还是存在一些虚词，例如“的”，“和”，“了”，“对”等词的干扰，但是大致来说，两则新闻的主题分布很明显，效果还不赖。 总结总结 以上就是本文关于Python_LDA实现方法详解的全部内容，希望对大家有所帮助。感兴趣的朋友可以继续参阅本站： python+mongodb数据抓取详细介绍、Python探索之创建二叉树、Python探索之修改Python搜索路径等，有什么问题可以随 时留言，欢迎大家一起交流讨论。感谢朋友们对本站的支持！