mysvmclassifier.cpp

本程序是一本很经典的知识响亮基的源代码 学起来比较方便 请大家使用

    ai=a->words;
    while (ai->wnum) {
	(*sumi)=(*ai);
	sumi->weight*=(CFLOAT)factor;
	if(sumi->weight != 0)
	  sumi++;
	ai++;
    }
    sumi->wnum=0;

    vec=create_svector(sum,a->userdefined,a->factor);
    free(sum);

    return(vec);
}

int CMySVMClassifier::featvec_eq(SVECTOR *a, SVECTOR *b)
     /* tests two sparse vectors for equality */
{
    register SVMWORD *ai,*bj;
    ai=a->words;
    bj=b->words;
    while (ai->wnum && bj->wnum) {
      if(ai->wnum > bj->wnum) {
	if((CFLOAT)(bj->weight) != 0)
	  return(0);
	bj++;
      }
      else if (ai->wnum < bj->wnum) {
	if((CFLOAT)(ai->weight) != 0)
	  return(0);
	ai++;
      }
      else {
	if((CFLOAT)(ai->weight) != (CFLOAT)(bj->weight)) 
	  return(0);
	ai++;
	bj++;
      }
    }
    return(1);
}

double CMySVMClassifier::model_length_s(MODEL *model, KERNEL_PARM *kernel_parm) 
     /* compute length of weight vector */
{
  register long i,j;
  register double sum=0,alphai;
  register DOC *supveci;

  for(i=1;i<model->sv_num;i++) {  
    alphai=model->alpha[i];
    supveci=model->supvec[i];
    for(j=1;j<model->sv_num;j++) {
      sum+=alphai*model->alpha[j]
	   *kernel(kernel_parm,supveci,model->supvec[j]);
    }
  }
  return(sqrt(sum));
}

void CMySVMClassifier::clear_vector_n(double *vec, long int n)
{
  register long i;
  for(i=0;i<=n;i++) vec[i]=0;
}

void CMySVMClassifier::add_vector_ns(double *vec_n, SVECTOR *vec_s, double faktor)
{
  register SVMWORD *ai;
  ai=vec_s->words;
  while (ai->wnum) {
    vec_n[ai->wnum]+=(faktor*ai->weight);
    ai++;
  }
}

double CMySVMClassifier::sprod_ns(double *vec_n, SVECTOR *vec_s)
{
  register double sum=0;
  register SVMWORD *ai;
  ai=vec_s->words;
  while (ai->wnum) {
    sum+=(vec_n[ai->wnum]*ai->weight);
    ai++;
  }
  return(sum);
}

void CMySVMClassifier::add_weight_vector_to_linear_model(MODEL *model)
     /* compute weight vector in linear case and add to model */
{
  long i;
  SVECTOR *f;

  model->lin_weights=(double *)my_malloc(sizeof(double)*(model->totwords+1));
  clear_vector_n(model->lin_weights,model->totwords);
  for(i=1;i<model->sv_num;i++) {
    for(f=(model->supvec[i])->fvec;f;f=f->next)  
      add_vector_ns(model->lin_weights,f,f->factor*model->alpha[i]);
  }
}


DOC* CMySVMClassifier::create_example(long docnum, long queryid, long slackid, 
		    double costfactor, SVECTOR *fvec)
{
  DOC *example;
  example = (DOC *)my_malloc(sizeof(DOC));
  example->docnum=docnum;
  example->queryid=queryid;
  example->slackid=slackid;
  example->costfactor=costfactor;
  example->fvec=fvec;
  return(example);
}

void CMySVMClassifier::free_example(DOC *example, long deep)
{
  if(example) {
    if(deep) {
      if(example->fvec)
	free_svector(example->fvec);
    }
    free(example);
  }
}

void CMySVMClassifier::write_model(char *modelfile, MODEL *model)
{
  FILE *modelfl;
  long j,i,sv_num;
  SVECTOR *v;

  if(verbosity>=1) {
    printf("Writing model file..."); fflush(stdout);
  }
  if ((modelfl = fopen (modelfile, "w")) == NULL)
  { perror (modelfile); exit (1); }
  fprintf(modelfl,"SVM-light Version %s\n",VERSION);
  fprintf(modelfl,"%ld # kernel type\n",
	  model->kernel_parm.kernel_type);
  fprintf(modelfl,"%ld # kernel parameter -d \n",
	  model->kernel_parm.poly_degree);
  fprintf(modelfl,"%.8g # kernel parameter -g \n",
	  model->kernel_parm.rbf_gamma);
  fprintf(modelfl,"%.8g # kernel parameter -s \n",
	  model->kernel_parm.coef_lin);
  fprintf(modelfl,"%.8g # kernel parameter -r \n",
	  model->kernel_parm.coef_const);
  fprintf(modelfl,"%s# kernel parameter -u \n",model->kernel_parm.custom);
  fprintf(modelfl,"%ld # highest feature index \n",model->totwords);
  fprintf(modelfl,"%ld # number of training documents \n",model->totdoc);
 
  sv_num=1;
  for(i=1;i<model->sv_num;i++) {
    for(v=model->supvec[i]->fvec;v;v=v->next) 
      sv_num++;
  }
  fprintf(modelfl,"%ld # number of support vectors plus 1 \n",sv_num);
  fprintf(modelfl,"%.8g # threshold b, each following line is a SV (starting with alpha*y)\n",model->b);

  for(i=1;i<model->sv_num;i++) {
    for(v=model->supvec[i]->fvec;v;v=v->next) {
      fprintf(modelfl,"%.32g ",model->alpha[i]*v->factor);
      for (j=0; (v->words[j]).wnum; j++) {
	fprintf(modelfl,"%ld:%.8g ",
		(long)(v->words[j]).wnum,
		(double)(v->words[j]).weight);
      }
      fprintf(modelfl,"#%s\n",v->userdefined);
    /* NOTE: this could be made more efficient by summing the
       alpha's of identical vectors before writing them to the
       file. */
    }
  }
  fclose(modelfl);
  if(verbosity>=1) {
    printf("done\n");
  }
}


MODEL* CMySVMClassifier::read_model(char *modelfile)
{
  FILE *modelfl;
  long i,queryid,slackid;
  double costfactor;
  long max_sv,max_words,ll,wpos;
  char *line,*comment;
  SVMWORD *words;
  char version_buffer[100];
  MODEL *model;

  if(verbosity>=1) {
    printf("Reading model..."); fflush(stdout);
  }

  nol_ll(modelfile,&max_sv,&max_words,&ll); /* scan size of model file */
  max_words+=2;
  ll+=2;

  words = (SVMWORD *)my_malloc(sizeof(SVMWORD)*(max_words+10));
  line = (char *)my_malloc(sizeof(char)*ll);
  model = (MODEL *)my_malloc(sizeof(MODEL));

  if ((modelfl = fopen (modelfile, "r")) == NULL)
  { perror (modelfile); exit (1); }

  fscanf(modelfl,"SVM-light Version %s\n",version_buffer);
  if(strcmp(version_buffer,VERSION)) {
    perror ("Version of model-file does not match version of svm_classify!"); 
    exit (1); 
  }
  fscanf(modelfl,"%ld%*[^\n]\n", &model->kernel_parm.kernel_type);  
  fscanf(modelfl,"%ld%*[^\n]\n", &model->kernel_parm.poly_degree);
  fscanf(modelfl,"%lf%*[^\n]\n", &model->kernel_parm.rbf_gamma);
  fscanf(modelfl,"%lf%*[^\n]\n", &model->kernel_parm.coef_lin);
  fscanf(modelfl,"%lf%*[^\n]\n", &model->kernel_parm.coef_const);
  fscanf(modelfl,"%[^#]%*[^\n]\n", model->kernel_parm.custom);

  fscanf(modelfl,"%ld%*[^\n]\n", &model->totwords);
  fscanf(modelfl,"%ld%*[^\n]\n", &model->totdoc);
  fscanf(modelfl,"%ld%*[^\n]\n", &model->sv_num);
  fscanf(modelfl,"%lf%*[^\n]\n", &model->b);

  model->supvec = (DOC **)my_malloc(sizeof(DOC *)*model->sv_num);
  model->alpha = (double *)my_malloc(sizeof(double)*model->sv_num);
  model->index=NULL;
  model->lin_weights=NULL;

  for(i=1;i<model->sv_num;i++) {
    fgets(line,(int)ll,modelfl);
    if(!parse_document(line,words,&(model->alpha[i]),&queryid,&slackid,
		       &costfactor,&wpos,max_words,&comment)) {
      printf("\nParsing error while reading model file in SV %ld!\n%s",
	     i,line);
      exit(1);
    }
    model->supvec[i] = create_example(-1,
				      0,0,
				      0.0,
				      create_svector(words,comment,1.0));
  }
  fclose(modelfl);
  free(line);
  free(words);
  if(verbosity>=1) {
    fprintf(stdout, "OK. (%d support vectors read)\n",(int)(model->sv_num-1));
  }
  return(model);
}

MODEL* CMySVMClassifier::copy_model(MODEL *model)
{
  MODEL *newmodel;
  long  i;

  newmodel=(MODEL *)my_malloc(sizeof(MODEL));
  (*newmodel)=(*model);
  newmodel->supvec = (DOC **)my_malloc(sizeof(DOC *)*model->sv_num);
  newmodel->alpha = (double *)my_malloc(sizeof(double)*model->sv_num);
  newmodel->index = NULL; /* index is not copied */
  newmodel->supvec[0] = NULL;
  newmodel->alpha[0] = 0;
  for(i=1;i<model->sv_num;i++) {
    newmodel->alpha[i]=model->alpha[i];
    newmodel->supvec[i]=create_example(model->supvec[i]->docnum,
				       model->supvec[i]->queryid,0,
				       model->supvec[i]->costfactor,
				       copy_svector(model->supvec[i]->fvec));
  }
  if(model->lin_weights) {
    newmodel->lin_weights = (double *)my_malloc(sizeof(double)*(model->totwords+1));
    for(i=0;i<model->totwords+1;i++) 
      newmodel->lin_weights[i]=model->lin_weights[i];
  }
  return(newmodel);
}

void CMySVMClassifier::free_model(MODEL *model, int deep)
{
  long i;

  if(model->supvec) {
    if(deep) {
      for(i=1;i<model->sv_num;i++) {
	free_example(model->supvec[i],1);
      }
    }
    free(model->supvec);
  }
  if(model->alpha) free(model->alpha);
  if(model->index) free(model->index);
  if(model->lin_weights) free(model->lin_weights);
  free(model);
}


void CMySVMClassifier::read_documents(char *docfile, DOC ***docs, double **label, 
		    long int *totwords, long int *totdoc)
{
  char *line,*comment;
  SVMWORD *words;
  long dnum=0,wpos,dpos=0,dneg=0,dunlab=0,queryid,slackid,max_docs;
  long max_words_doc, ll;
  double doc_label,costfactor;
  FILE *docfl;

  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 */
  (*label) = (double *)my_malloc(sizeof(double)*max_docs); /* target values */
  line = (char *)my_malloc(sizeof(char)*ll);

  if ((docfl = fopen (docfile, "r")) == NULL)
  { perror (docfile); exit (1); }

  words = (SVMWORD *)my_malloc(sizeof(SVMWORD)*(max_words_doc+10));
  if(verbosity>=1) {
    printf("Reading examples into memory..."); fflush(stdout);
  }
  dnum=0;
  (*totwords)=0;
  while((!feof(docfl)) && fgets(line,(int)ll,docfl)) {
    if(line[0] == '#') continue;  /* line contains comments */
    if(!parse_document(line,words,&doc_label,&queryid,&slackid,&costfactor,
		       &wpos,max_words_doc,&comment)) {
      printf("\nParsing error in line %ld!\n%s",dnum,line);
      exit(1);
    }
    (*label)[dnum]=doc_label;
    /* printf("docnum=%ld: Class=%f ",dnum,doc_label); */
    if(doc_label > 0) dpos++;
    if (doc_label < 0) dneg++;
    if (doc_label == 0) dunlab++;
    if((wpos>1) && ((words[wpos-2]).wnum>(*totwords))) 
      (*totwords)=(words[wpos-2]).wnum;
    if((*totwords) > MAXFEATNUM) {
      printf("\nMaximum feature number exceeds limit defined in MAXFEATNUM!\n");
      printf("LINE: %s\n",line);
      exit(1);
    }
    (*docs)[dnum] = create_example(dnum,queryid,slackid,costfactor,
				   create_svector(words,comment,1.0));
    /* printf("\nNorm=%f\n",((*docs)[dnum]->fvec)->twonorm_sq);  */
    dnum++;  
    if(verbosity>=1) {
      if((dnum % 100) == 0) {
	printf("%ld..",dnum); fflush(stdout);
      }
    }
  } 

  fclose(docfl);
  free(line);
  free(words);
  if(verbosity>=1) {
    fprintf(stdout, "OK. (%ld examples read)\n", dnum);
  }
  (*totdoc)=dnum;
}

int CMySVMClassifier::parse_document(char *line, SVMWORD *words, double *label,
		   long *queryid, long *slackid, double *costfactor,
		   long int *numwords, long int max_words_doc,
		   char **comment)
{
  register long wpos,pos;
  long wnum;
  double weight;
  int numread;
  char featurepair[1000],junk[1000];

  (*queryid)=0;
  (*slackid)=0;
  (*costfactor)=1;

  pos=0;
  (*comment)=NULL;
  while(line[pos] ) {      /* cut off comments */
    if((line[pos] == '#') && (!(*comment))) {
      line[pos]=0;
      (*comment)=&(line[pos+1]);
    }
    if(line[pos] == '\n') { /* strip the CR */
      line[pos]=0;
    }
    pos++;
  }
  if(!(*comment)) (*comment)=&(line[pos]);
  /* printf("Comment: '%s'\n",(*comment)); */

  wpos=0;
  /* check, that line starts with target value or zero, but not with
     feature pair */
  if(sscanf(line,"%s",featurepair) == EOF) return(0);
  pos=0;
  while((featurepair[pos] != ':') && featurepair[pos]) pos++;
  if(featurepair[pos] == ':') {
	perror ("Line must start with label or 0!!!\n"); 
	printf("LINE: %s\n",line);
	exit (1); 
  }
  /* read the target value */
  if(sscanf(line,"%lf",label) == EOF) return(0);
  pos=0;
  while(space_or_null((int)line[pos])) pos++;
  while((!space_or_null((int)line[pos])) && line[pos]) pos++;
  while(((numread=sscanf(line+pos,"%s",featurepair)) != EOF) && 
	(numread > 0) && 
	(wpos<max_words_doc)) {
    /* printf("%s\n",featurepair); */
    while(space_or_null((int)line[pos])) pos++;