svm_learn_main.c

机器学习文本分类的SVM算法实现

/***********************************************************************/
/*                                                                     */
/*   svm_learn_main.c                                                  */
/*                                                                     */
/*   Command line interface to the learning module of the              */
/*   Support Vector Machine.                                           */
/*                                                                     */
/*   Author: Thorsten Joachims                                         */
/*   Date: 02.07.02                                                    */
/*                                                                     */
/*   Copyright (c) 2000  Thorsten Joachims - 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 */
char restartfile[200];       /* file with initial alphas */

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



int main (int argc, char* argv[])
{  
  DOC **docs;  /* training examples */
  long totwords,totdoc,i;
  double *target;
  double *alpha_in=NULL;
  KERNEL_CACHE *kernel_cache;
  LEARN_PARM learn_parm;
  KERNEL_PARM kernel_parm;
  MODEL *model=(MODEL *)my_malloc(sizeof(MODEL));

  read_input_parameters(argc,argv,docfile,modelfile,restartfile,&verbosity,
			&learn_parm,&kernel_parm);
  read_documents(docfile,&docs,&target,&totwords,&totdoc);
  if(restartfile[0]) alpha_in=read_alphas(restartfile,totdoc);

  if(kernel_parm.kernel_type == LINEAR) { /* don't need the cache */
    kernel_cache=NULL;
  }
  else {
    /* Always get a new kernel cache. It is not possible to use the
       same cache for two different training runs */
    kernel_cache=kernel_cache_init(totdoc,learn_parm.kernel_cache_size);
  }

  if(learn_parm.type == CLASSIFICATION) {
    svm_learn_classification(docs,target,totdoc,totwords,&learn_parm,
			     &kernel_parm,kernel_cache,model,alpha_in);
  }
  else if(learn_parm.type == REGRESSION) {
    svm_learn_regression(docs,target,totdoc,totwords,&learn_parm,
			 &kernel_parm,&kernel_cache,model);
  }
  else if(learn_parm.type == RANKING) {
    svm_learn_ranking(docs,target,totdoc,totwords,&learn_parm,
		      &kernel_parm,&kernel_cache,model);
  }
  else if(learn_parm.type == OPTIMIZATION) {
    svm_learn_optimization(docs,target,totdoc,totwords,&learn_parm,
			   &kernel_parm,kernel_cache,model,alpha_in);
  }

  if(kernel_cache) {
    /* Free the memory used for the cache. */
    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'. */
  /* deep_copy_of_model=copy_model(model); */
  write_model(modelfile,model);

  free(alpha_in);
  free_model(model,0);
  for(i=0;i<totdoc;i++) 
    free_example(docs[i],1);
  free(docs);
  free(target);

  return(0);
}

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

void read_input_parameters(int argc,char *argv[],char *docfile,char *modelfile,
			   char *restartfile,long *verbosity,
			   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, "");
  strcpy (restartfile, "");
  (*verbosity)=1;
  learn_parm->biased_hyperplane=1;
  learn_parm->sharedslack=0;
  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;
  learn_parm->maxiter=100000;
  learn_parm->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 '#': i++; learn_parm->maxiter=atol(argv[i]); break;
      case 'h': i++; learn_parm->svm_iter_to_shrink=atol(argv[i]); break;
      case 'm': i++; learn_parm->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;
      case 't': i++; kernel_parm->kernel_type=atol(argv[i]); break;
      case 'd': i++; kernel_parm->poly_degree=atol(argv[i]); break;
      case 'g': i++; kernel_parm->rbf_gamma=atof(argv[i]); break;
      case 's': i++; kernel_parm->coef_lin=atof(argv[i]); break;
      case 'r': i++; kernel_parm->coef_const=atof(argv[i]); break;
      case 'u': i++; strcpy(kernel_parm->custom,argv[i]); break;
      case 'l': i++; strcpy(learn_parm->predfile,argv[i]); break;
      case 'a': i++; strcpy(learn_parm->alphafile,argv[i]); break;
      case 'y': i++; strcpy(restartfile,argv[i]); break;
      default: printf("\nUnrecognized option %s!\n\n",argv[i]);
	       print_help();
	       exit(0);
      }
  }
  if(i>=argc) {
    printf("\nNot enough input parameters!\n\n");
    wait_any_key();
    print_help();
    exit(0);
  }
  strcpy (docfile, argv[i]);
  if((i+1)<argc) {
    strcpy (modelfile, argv[i+1]);
  }
  if(learn_parm->svm_iter_to_shrink == -9999) {
    if(kernel_parm->kernel_type == LINEAR) 
      learn_parm->svm_iter_to_shrink=2;
    else
      learn_parm->svm_iter_to_shrink=100;
  }
  if(strcmp(type,"c")==0) {