当前位置:首页 >> 脚本专栏

Python_LDA实现方法详解

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'"color: #008080">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!