# -*- coding: utf-8 -*-import mathimport randomimport jiebaimport codecsimport datetimeclass pLSA_lph():  def __init__(self, ntopic = 5):    self.n_doc = 0    self.n_word = 0    self.n_topic = ntopic    self.corpus = None    self.p_z_dw = None    self.p_w_z = None    self.p_z_d = None    self.likelihood = 0    self.vocab = None    self.stop_words = [u'，', u'。', u'、', u'（', u'）', u'·', u'！', u' ', u'：', u'“', u'”', u'/n']  # 每行和為1的正實數(shù)，概率分布;  def _rand_mat(self, sizex, sizey):    ret = []    for i in xrange(sizex):      ret.append([])      for _ in xrange(sizey):        ret[-1].append(random.random())      norm = sum(ret[-1])      for j in xrange(sizey):        ret[-1][j] /= norm    return ret  #從文本中計算詞頻稀疏矩陣，這里存儲模型仿照LDA  def loadCorpus(self, fn):    # 中文分詞    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)    # 切割統(tǒng)計所有出現(xiàn)的詞納入詞典    seglist = seg_list.split(" ")    self.vocab = []    for word in seglist:      if (word != u' ' and word not in self.vocab):        self.vocab.append(word)    self.n_word =len(self.vocab)    CountMatrix = []    f.seek(0, 0)    # 統(tǒng)計每個文檔中出現(xiàn)的詞頻    for line in f:      # 置零      count = [0 for i in range(len(self.vocab))]      text = line.strip()      # 但還是要先分詞      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(" ")      # 查詢詞典中的詞出現(xiàn)的詞頻      for word in seglist:        if word in self.vocab:          count[self.vocab.index(word)] += 1      CountMatrix.append(count)    f.close()    self.corpus = CountMatrix    self.n_doc = len(CountMatrix)    #初始化    self.p_z_d = self._rand_mat(self.n_topic, self.n_doc)    self.p_w_z = self._rand_mat(self.n_word, self.n_topic)    self.p_z_dw =[]    for k in range(self.n_topic):      self.p_z_dw.append(self._rand_mat(self.n_doc, self.n_word))  def _e_step(self):    for k in range(self.n_topic):      for d in range(self.n_doc):        for j in range(self.n_word):          _d_wz_zd = 0          for kk in range(self.n_topic):            _d_wz_zd += self.p_w_z[j][kk]*self.p_z_d[kk][d]          if _d_wz_zd <= 0:            _d_wz_zd = 1e-6          self.p_z_dw[k][d][j] = self.p_w_z[j][k]*self.p_z_d[k][d]/_d_wz_zd  def _m_step(self):    print "updating Pn(Wj|Zk).../r"    for j in range(self.n_word):      for k in range(self.n_topic):        _d_dw_zdw = 0        for d in range(self.n_doc):          _d_dw_zdw += self.corpus[d][j]*self.p_z_dw[k][d][j]        _d_dw_zdw_sum = 0        for jj in range(self.n_word):          _d_dw_zdw_i = 0          for d in range(self.n_doc):            _d_dw_zdw_i += self.corpus[d][jj]*self.p_z_dw[k][d][jj]          _d_dw_zdw_sum += _d_dw_zdw_i        if _d_dw_zdw_sum <= 0:          _d_dw_zdw_sum = 1e-6        self.p_w_z[j][k] = _d_dw_zdw/_d_dw_zdw_sum    print "updating Pn(Zk|Di).../r"    for k in range(self.n_topic):      for d in range(self.n_doc):        _d_dw_zdw = 0        for j in range(self.n_word):          _d_dw_zdw += self.corpus[d][j]*self.p_z_dw[k][d][j]        _d_dw_zdw_sum = 0        for kk in range(self.n_topic):          _d_dw_zdw_i = 0          for j in range(self.n_word):            _d_dw_zdw_i += self.corpus[d][j]*self.p_z_dw[kk][d][j]          _d_dw_zdw_sum += _d_dw_zdw_i        if _d_dw_zdw_sum <= 0:          _d_dw_zdw_sum = 1e-6        self.p_z_d[k][d] = _d_dw_zdw/_d_dw_zdw_sum  #計算最大似然值  def _cal_max_likelihood(self):    self.likelihood = 0    for d in range(self.n_doc):      for j in range(self.n_word):        _dP_wjdi = 0        for k in range(self.n_topic):          _dP_wjdi += self.p_w_z[j][k]*self.p_z_d[k][d]        _dP_wjdi = 1.0/self.n_doc*_dP_wjdi        self.likelihood += self.corpus[d][j]*math.log(_dP_wjdi)  #迭代訓練  def train(self, n_iter = 100, d_delta = 1e-6,log_fn = "log.log"):    itr = 0    delta =10e9    _likelihood = 0    f = open(log_fn, 'w')    while itr < n_iter and delta > d_delta:      _likelihood = self.likelihood      self._e_step()      self._m_step()      self._cal_max_likelihood()      itr += 1      delta = abs(self.likelihood - _likelihood)      t1 = datetime.datetime.now().strftime('%Y-%m-%d-%y %H:%M:%S');      f.write("%s iteration %d, max-likelihood = %.6f/n"%(t1, itr, self.likelihood))      print "%s iteration %d, max-likelihood = %.6f"%(t1, itr, self.likelihood)    f.close()  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 printWordOfTopic(self):    for k in range(self.n_topic):      print "Topic %d"%k,      for j in range(self.n_word):        print self.p_w_z[j][k],      print  def saveWordOfTopic(self,fn):    f = open(fn, 'w')    for j in range(self.n_word):      f.write(", w%d"%j)    f.write("/n")    for k in range(self.n_topic):      f.write("topic %d"%k)      for j in range(self.n_word):        f.write(", %.6f"%self.p_w_z[j][k])      f.write("/n")    f.close()  def printTopicOfDoc(self):    for d in range(self.n_doc):      print "Doc %d"%d,      for k in range(self.n_topic):        print self.p_z_d[k][d],      print  def saveTopicOfDoc(self, fn):    f = open(fn, 'w')    for k in range(self.n_topic):      f.write(", z%d" % k)    f.write("/n")    for d in range(self.n_doc):      f.write("doc %d" % d)      for k in range(self.n_topic):        f.write(", %.6f" % self.p_z_d[k][d])      f.write("/n")    f.close()

<span style="font-family: Arial, Helvetica, sans-serif; background-color: rgb(255, 255, 255);">新華社北京11月26日電中共中央總書記、國家主席習近平26日向古巴共產黨中央委員會第一書記、國務委員會主席兼部長會議主席勞爾·卡斯特羅致唁電，代表中國黨、政府、人民并以個人名義，對菲德爾·卡斯特羅同志逝世表示最沉痛的哀悼，向其家屬致以最誠摯的慰問。全文如下：驚悉古巴革命領導人菲德爾·卡斯特羅同志不幸逝世，我謹代表中國共產黨、政府、人民，并以我個人的名義，向你并通過你向古巴共產黨、政府、人民，對菲德爾·卡斯特羅同志的逝世表示最沉痛的哀悼，向其家屬致以最誠摯的慰問。菲德爾·卡斯特羅同志是古巴共產黨和古巴社會主義事業(yè)的締造者，是古巴人民的偉大領袖。他把畢生精力獻給了古巴人民爭取民族解放、維護國家主權、建設社會主義的壯麗事業(yè)，為古巴人民建立了不朽的歷史功勛，也為世界社會主義發(fā)展建立了不朽的歷史功勛。菲德爾·卡斯特羅同志是我們這個時代的偉大人物，歷史和人民將記住他。我多次同菲德爾·卡斯特羅同志見面，促膝暢談，他的真知灼見令我深受啟發(fā)，他的音容笑貌猶在眼前。我深深懷念他，中國人民深深懷念他。菲德爾·卡斯特羅同志生前致力于中古友好，密切關注和高度評價中國發(fā)展進程，在他親自關心和支持下，古巴成為第一個同新中國建交的拉美國家。建交56年來，中古關系長足發(fā)展，各領域務實合作成果豐碩，兩國人民友誼與日俱增，這都與菲德爾·卡斯特羅同志的關懷和心血密不可分。菲德爾·卡斯特羅同志的逝世是古巴和拉美人民的重大損失，不僅使古巴和拉美人民失去了一位優(yōu)秀兒子，也使中國人民失去了一位親密的同志和真誠的朋友。他的光輝形象和偉大業(yè)績將永載史冊。我相信，在主席同志堅強領導下，古巴黨、政府、人民必將繼承菲德爾·卡斯特羅同志的遺志，化悲痛為力量，在社會主義建設事業(yè)中不斷取得新的成績。中古兩黨、兩國、兩國人民友誼必將得到鞏固和發(fā)展。偉大的菲德爾·卡斯特羅同志永垂不朽?。ㄍ辏?lt;/span> 

if __name__=="__main__":  _plsa = pLSA_lph(2)  _plsa.loadCorpus(u"C://Users/Administrator/Desktop//zhongwen.txt")  _plsa.train()  _plsa.printTopicOfDoc()  _plsa.printWordOfTopic()  _plsa.saveTopicOfDoc(u"C://Users/Administrator/Desktop//topic_doc.txt")  _plsa.saveWordOfTopic(u"C://Users/Administrator/Desktop//word_topic.txt")