svm_learn_main.c

机器学习方法支持向量机SVM源程序

/***********************************************************************/
/*                                                                     */
/*   svm_learn_main.c                                                  */
/*                                                                     */
/*   Command line interface to the learning module of the              */
/*   Support Vector Machine.                                           */
/*                                                                     */
/*   Author: Thorsten Joachims                                         */
/*   Date: 22.07.00                                                    */
/*                                                                     */
/*   Copyright (c) 2000  Universitaet Dortmund - All rights reserved   */
/*                                                                     */
/*   This software is available for non-commercial use only. It must   */
/*   not be modified and distributed without prior permission of the   */
/*   author. The author is not responsible for implications from the   */
/*   use of this software.                                             */
/*                                                                     */
/***********************************************************************/


/* uncomment, if you want to use svm-learn out of C++ */
/* extern "C" { */
# include "svm_common.h"
# include "svm_learn.h"
/* } */

char docfile[200];           /* file with training examples */
char modelfile[200];         /* file for resulting classifier */

void   read_input_parameters(int, char **, char *, char *,long *, long *, 
			     LEARN_PARM *, KERNEL_PARM *);
void   wait_any_key();
void   print_help();
int    omain (int, char **);

void main()
{
	int  i;
	int  argc = 13;
	char** argv;

	argv = (char **)malloc(sizeof(char *)*argc);
	for (i=0;i<argc;i++)
	{
		argv[i] = (char *)malloc(sizeof(char)*128);
	}

	strcpy(argv[0],"@");
	strcpy(argv[1],"-c");
	strcpy(argv[2],"10");
	strcpy(argv[3],"-p");
	strcpy(argv[4],"1");
	strcpy(argv[5],"-t");
	strcpy(argv[6],"2");
	strcpy(argv[7],"-g");
	strcpy(argv[8],"0.01");
	strcpy(argv[9],"-m");
	strcpy(argv[10],"60");
	
	strcpy(argv[11], "f:\\8_FDNRV\\datas\\facesvm2\\smpl\\facesmpl2_1.dat");
	strcpy(argv[12], "f:\\8_FDNRV\\datas\\facesvm2\\mdl\\fmdl0r502_1.dat");
	
//	strcpy(argv[11], "f:\\8_FDNRV\\datas\\headsvm2\\smpl\\headsmplo2_1.dat");
//	strcpy(argv[12], "f:\\8_FDNRV\\datas\\headsvm2\\mdl\\hmdlr52_1.dat");
	
	//strcpy(argv[11], "f:\\8_FDNRV\\datas\\facesvm1i\\smpl\\faceicrsmpl1_12345.dat");
	//strcpy(argv[12], "f:\\8_FDNRV\\datas\\facesvm1i\\mdl\\facesvmmdl_12345.dat");	

	omain(argc, argv);

	for (i=0;i<argc;i++)
	{
		free(argv[i]);
	}
	free(argv);
}
	

int omain (int argc, char** argv)
{  
  DOC *docs;  /* training examples */
  long max_docs,max_words_doc;
  long totwords,totdoc,ll,i;
  long kernel_cache_size;
  double *target;
  KERNEL_CACHE kernel_cache;
  LEARN_PARM learn_parm;
  KERNEL_PARM kernel_parm;
  MODEL model;

  read_input_parameters(argc,argv,docfile,modelfile,&verbosity,
			&kernel_cache_size,&learn_parm,&kernel_parm);
  
  if(verbosity>=1) {
    printf("Scanning examples..."); fflush(stdout);
  }
  nol_ll(docfile,&max_docs,&max_words_doc,&ll); /* scan size of input file */
  max_words_doc+=2;
  ll+=2;
  max_docs+=2;
  if(verbosity>=1) {
    printf("done\n"); fflush(stdout);
  }

  docs = (DOC *)my_malloc(sizeof(DOC)*max_docs);         /* feature vectors */
  target = (double *)my_malloc(sizeof(double)*max_docs); /* target values */

  read_documents(docfile,docs,target,max_words_doc,ll,&totwords,&totdoc);

  if(kernel_parm.kernel_type == LINEAR) { /* don't need the cache */
    if(learn_parm.type == CLASSIFICATION) {
      svm_learn_classification(docs,target,totdoc,totwords,&learn_parm,
			       &kernel_parm,NULL,&model);
    }
    else if(learn_parm.type == REGRESSION) {
      svm_learn_regression(docs,target,totdoc,totwords,&learn_parm,
			   &kernel_parm,NULL,&model);
    }
  }
  else {
    if(learn_parm.type == CLASSIFICATION) {
      kernel_cache_init(&kernel_cache,totdoc,kernel_cache_size);
      svm_learn_classification(docs,target,totdoc,totwords,&learn_parm,
			       &kernel_parm,&kernel_cache,&model);
      kernel_cache_cleanup(&kernel_cache);
    }
    else if(learn_parm.type == REGRESSION) {
      kernel_cache_init(&kernel_cache,2*totdoc,kernel_cache_size);
      svm_learn_regression(docs,target,totdoc,totwords,&learn_parm,
			   &kernel_parm,&kernel_cache,&model);
      kernel_cache_cleanup(&kernel_cache);
    }
  }

  /* Warning: The model contains references to the original data 'docs'.
     If you want to free the original data, and only keep the model, you 
     have to make a deep copy of 'model'. */
  write_model(modelfile,&model);

  free(model.supvec);
  free(model.alpha);
  free(model.index);
  for(i=0;i<totdoc;i++) 
    free(docs[i].words);
  free(docs);
  free(target);

  return(0);
}

/*---------------------------------------------------------------------------*/

void read_input_parameters(int argc,char *argv[],char *docfile,char *modelfile,
			   long *verbosity,long *kernel_cache_size,
			   LEARN_PARM *learn_parm,KERNEL_PARM *kernel_parm)
{
  long i;
  char type[100];
  
  /* set default */
  strcpy (modelfile, "svm_model");
  strcpy (learn_parm->predfile, "trans_predictions");
  strcpy (learn_parm->alphafile, "");
  (*verbosity)=1;
  learn_parm->biased_hyperplane=1;
  learn_parm->remove_inconsistent=0;
  learn_parm->skip_final_opt_check=0;
  learn_parm->svm_maxqpsize=10;
  learn_parm->svm_newvarsinqp=0;
  learn_parm->svm_iter_to_shrink=-9999;
  (*kernel_cache_size)=40;
  learn_parm->svm_c=0.0;
  learn_parm->eps=0.1;
  learn_parm->transduction_posratio=-1.0;
  learn_parm->svm_costratio=1.0;
  learn_parm->svm_costratio_unlab=1.0;
  learn_parm->svm_unlabbound=1E-5;
  learn_parm->epsilon_crit=0.001;
  learn_parm->epsilon_a=1E-15;
  learn_parm->compute_loo=0;
  learn_parm->rho=1.0;
  learn_parm->xa_depth=0;
  kernel_parm->kernel_type=0;
  kernel_parm->poly_degree=3;
  kernel_parm->rbf_gamma=1.0;
  kernel_parm->coef_lin=1;
  kernel_parm->coef_const=1;
  strcpy(kernel_parm->custom,"empty");
  strcpy(type,"c");

  for(i=1;(i<argc) && ((argv[i])[0] == '-');i++) {
    switch ((argv[i])[1]) 
      { 
      case '?': print_help(); exit(0);
      case 'z': i++; strcpy(type,argv[i]); break;
      case 'v': i++; (*verbosity)=atol(argv[i]); break;
      case 'b': i++; learn_parm->biased_hyperplane=atol(argv[i]); break;
      case 'i': i++; learn_parm->remove_inconsistent=atol(argv[i]); break;
      case 'f': i++; learn_parm->skip_final_opt_check=!atol(argv[i]); break;
      case 'q': i++; learn_parm->svm_maxqpsize=atol(argv[i]); break;
      case 'n': i++; learn_parm->svm_newvarsinqp=atol(argv[i]); break;
      case 'h': i++; learn_parm->svm_iter_to_shrink=atol(argv[i]); break;
      case 'm': i++; (*kernel_cache_size)=atol(argv[i]); break;
      case 'c': i++; learn_parm->svm_c=atof(argv[i]); break;
      case 'w': i++; learn_parm->eps=atof(argv[i]); break;
      case 'p': i++; learn_parm->transduction_posratio=atof(argv[i]); break;
      case 'j': i++; learn_parm->svm_costratio=atof(argv[i]); break;
      case 'e': i++; learn_parm->epsilon_crit=atof(argv[i]); break;
      case 'o': i++; learn_parm->rho=atof(argv[i]); break;
      case 'k': i++; learn_parm->xa_depth=atol(argv[i]); break;
      case 'x': i++; learn_parm->compute_loo=atol(argv[i]); break;