svmt.h

libsvm可视化程序

#include "stdafx.h"
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <ctype.h>
#include "svm.h"
#define Malloc(type,n) (type *)malloc((n)*sizeof(type))

void exit_with_help()
{
	printf(
	"Usage: svm-train [options] training_set_file [model_file]\n"
	"options:\n"
	"-s svm_type : set type of SVM (default 0)\n"
	"	0 -- C-SVC\n"
	"	1 -- nu-SVC\n"
	"	2 -- one-class SVM\n"
	"	3 -- epsilon-SVR\n"
	"	4 -- nu-SVR\n"
	"-t kernel_type : set type of kernel function (default 2)\n"
	"	0 -- linear: u'*v\n"
	"	1 -- polynomial: (gamma*u'*v + coef0)^degree\n"
	"	2 -- radial basis function: exp(-gamma*|u-v|^2)\n"
	"	3 -- sigmoid: tanh(gamma*u'*v + coef0)\n"
	"	4 -- precomputed kernel (kernel values in training_set_file)\n"
	"-d degree : set degree in kernel function (default 3)\n"
	"-g gamma : set gamma in kernel function (default 1/k)\n"
	"-r coef0 : set coef0 in kernel function (default 0)\n"
	"-c cost : set the parameter C of C-SVC, epsilon-SVR, and nu-SVR (default 1)\n"
	"-n nu : set the parameter nu of nu-SVC, one-class SVM, and nu-SVR (default 0.5)\n"
	"-p epsilon : set the epsilon in loss function of epsilon-SVR (default 0.1)\n"
	"-m cachesize : set cache memory size in MB (default 100)\n"
	"-e epsilon : set tolerance of termination criterion (default 0.001)\n"
	"-h shrinking: whether to use the shrinking heuristics, 0 or 1 (default 1)\n"
	"-b probability_estimates: whether to train a SVC or SVR model for probability estimates, 0 or 1 (default 0)\n"
	"-wi weight: set the parameter C of class i to weight*C, for C-SVC (default 1)\n"
	"-v n: n-fold cross validation mode\n"
	);
	exit(1);
}

void parse_command_line(char *argv, char *input_file_name, char *model_file_name);
void read_problem(const char *filename);
void do_cross_validation();

struct svm_parameter param;		// set by parse_command_line
struct svm_problem prob;		// set by read_problem
struct svm_model *model;
struct svm_node *x_space;
int cross_validation;
int nr_fold;



void do_cross_validation()
{
	int i;
	int total_correct = 0;
	double total_error = 0;
	double sumv = 0, sumy = 0, sumvv = 0, sumyy = 0, sumvy = 0;
	double *target = Malloc(double,prob.l);

	svm_cross_validation(&prob,&param,nr_fold,target);
	if(param.svm_type == EPSILON_SVR ||
	   param.svm_type == NU_SVR)
	{
		for(i=0;i<prob.l;i++)
		{
			double y = prob.y[i];
			double v = target[i];
			total_error += (v-y)*(v-y);
			sumv += v;
			sumy += y;
			sumvv += v*v;
			sumyy += y*y;
			sumvy += v*y;
		}
		printf("Cross Validation Mean squared error = %g\n",total_error/prob.l);
		printf("Cross Validation Squared correlation coefficient = %g\n",
			((prob.l*sumvy-sumv*sumy)*(prob.l*sumvy-sumv*sumy))/
			((prob.l*sumvv-sumv*sumv)*(prob.l*sumyy-sumy*sumy))
			);
	}
	else
	{
		for(i=0;i<prob.l;i++)
			if(target[i] == prob.y[i])
				++total_correct;
		printf("Cross Validation Accuracy = %g%%\n",100.0*total_correct/prob.l);
	}
	free(target);
}

void parse_command_line(char *argv, char *input_file_name, char *model_file_name)
{
	// default values
	param.svm_type = C_SVC;
	param.kernel_type = RBF;
	param.degree = 3;
	param.gamma = 0;	// 1/k
	param.coef0 = 0;
	param.nu = 0.5;
	param.cache_size = 100;
	param.C = 1;
	param.eps = 1e-3;
	param.p = 0.1;
	param.shrinking = 1;
	param.probability = 0;
	param.nr_weight = 0;
	param.weight_label = NULL;
	param.weight = NULL;
	cross_validation = 0;

	// determine filenames

	strcpy(input_file_name, argv);

	sprintf(model_file_name,"%s.model",input_file_name);
	
}

// read in a problem (in svmlight format)

void read_problem(const char *filename)
{
	int elements, max_index, i, j;
	FILE *fp = fopen(filename,"r");
	
	if(fp == NULL)
	{
		fprintf(stderr,"can't open input file %s\n",filename);
		exit(1);
	}

	prob.l = 0;
	elements = 0;
	while(1)
	{
		int c = fgetc(fp);
		switch(c)
		{
			case '\n':
				++prob.l;
				// fall through,
				// count the '-1' element
			case ':':
				++elements;
				break;
			case EOF:
				goto out;
			default:
				;
		}
	}
out:
	rewind(fp);

	prob.y = Malloc(double,prob.l);
	prob.x = Malloc(struct svm_node *,prob.l);
	x_space = Malloc(struct svm_node,elements);

	max_index = 0;
	j=0;
	for(i=0;i<prob.l;i++)
	{
		double label;
		prob.x[i] = &x_space[j];
		fscanf(fp,"%lf",&label);
		prob.y[i] = label;

		while(1)
		{
			int c;
			do {
				c = getc(fp);
				if(c=='\n') goto out2;
			} while(isspace(c));
			ungetc(c,fp);
			fscanf(fp,"%d:%lf",&(x_space[j].index),&(x_space[j].value));
			++j;
		}	
out2:
		if(j>=1 && x_space[j-1].index > max_index)
			max_index = x_space[j-1].index;
		x_space[j++].index = -1;
	}

	if(param.gamma == 0)
		param.gamma = 1.0/max_index;

	if(param.kernel_type == PRECOMPUTED)
		for(i=0;i<prob.l;i++)
		{
			if (prob.x[i][0].index != 0)
			{
				fprintf(stderr,"Wrong input format: first column must be 0:sample_serial_number\n");
				exit(1);
			}
			if ((int)prob.x[i][0].value <= 0 || (int)prob.x[i][0].value > max_index)
			{
				fprintf(stderr,"Wrong input format: sample_serial_number out of range\n");
				exit(1);
			}
		}

	fclose(fp);
}