Java实现的LDA隐狄利克雷分配算法源码解析

 * (C) Copyright 2005, Gregor Heinrich (gregor :: arbylon : net) (This file is  
 * part of the org.knowceans experimental software packages.)  
 */ 
/*  
 * LdaGibbsSampler is free software; you can redistribute it and/or modify it  
 * under the terms of the GNU General Public License as published by the Free  
 * Software Foundation; either version 2 of the License, or (at your option) any  
 * later version.  
 */ 
/*  
 * LdaGibbsSampler is distributed in the hope that it will be useful, but  
 * WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or  
 * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more  
 * details.  
 */ 
/*  
 * You should have received a copy of the GNU General Public License along with  
 * this program; if not, write to the Free Software Foundation, Inc., 59 Temple  
 * Place, Suite 330, Boston, MA 02111-1307 USA  
 */ 
 
/*  
 * Created on Mar 6, 2005  
 */ 
package com.xh.lda;  
 
import java.text.DecimalFormat;  
import java.text.NumberFormat;  
 
/**  

 * Gibbs sampler for estimating the best assignments of topics for words and  
 * documents in a corpus. The algorithm is introduced in Tom Griffiths' paper  
 * "Gibbs sampling in the generative model of Latent Dirichlet Allocation"  
 * (2002).  
 *   
 * @author heinrich  
 */ 
public class LdaGibbsSampler {  
 
    /**  
     * document data (term lists)  
     */ 
    int[][] documents;  
 
    /**  
     * vocabulary size  
     */ 
    int V;  
 
    /**  
     * number of topics  
     */ 
    int K;  
 
    /**  
     * Dirichlet parameter (document--topic associations)  
     */ 
    double alpha;  
 
    /**