eluka 0.1.0

data/ext/libsvm/svm-predict.c

@@ -0,0 +1,226 @@
+#include <stdio.h>
+#include <ctype.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include "svm.h"
+
+struct svm_node *x;
+int max_nr_attr = 64;
+
+struct svm_model* model;
+int predict_probability=0;
+
+static char *line = NULL;
+static int max_line_len;
+
+static char* readline(FILE *input)
+{
+	int len;
+	
+	if(fgets(line,max_line_len,input) == NULL)
+		return NULL;
+
+	while(strrchr(line,'\n') == NULL)
+	{
+		max_line_len *= 2;
+		line = (char *) realloc(line,max_line_len);
+		len = (int) strlen(line);
+		if(fgets(line+len,max_line_len-len,input) == NULL)
+			break;
+	}
+	return line;
+}
+
+void exit_input_error(int line_num)
+{
+	fprintf(stderr,"Wrong input format at line %d\n", line_num);
+	exit(1);
+}
+
+void predict(FILE *input, FILE *output)
+{
+	int correct = 0;
+	int total = 0;
+	double error = 0;
+	double sump = 0, sumt = 0, sumpp = 0, sumtt = 0, sumpt = 0;
+
+	int svm_type=svm_get_svm_type(model);
+	int nr_class=svm_get_nr_class(model);
+	double *prob_estimates=NULL;
+	int j;
+
+	if(predict_probability)
+	{
+		if (svm_type==NU_SVR || svm_type==EPSILON_SVR)
+			printf("Prob. model for test data: target value = predicted value + z,\nz: Laplace distribution e^(-|z|/sigma)/(2sigma),sigma=%g\n",svm_get_svr_probability(model));
+		else
+		{
+			int *labels=(int *) malloc(nr_class*sizeof(int));
+			svm_get_labels(model,labels);
+			prob_estimates = (double *) malloc(nr_class*sizeof(double));
+			fprintf(output,"labels");		
+			for(j=0;j<nr_class;j++)
+				fprintf(output," %d",labels[j]);
+			fprintf(output,"\n");
+			free(labels);
+		}
+	}
+
+	max_line_len = 1024;
+	line = (char *)malloc(max_line_len*sizeof(char));
+	while(readline(input) != NULL)
+	{
+		int i = 0;
+		double target_label, predict_label;
+		char *idx, *val, *label, *endptr;
+		int inst_max_index = -1; // strtol gives 0 if wrong format, and precomputed kernel has <index> start from 0
+
+		label = strtok(line," \t");
+		target_label = strtod(label,&endptr);
+		if(endptr == label)
+			exit_input_error(total+1);
+
+		while(1)
+		{
+			if(i>=max_nr_attr-1)	// need one more for index = -1
+			{
+				max_nr_attr *= 2;
+				x = (struct svm_node *) realloc(x,max_nr_attr*sizeof(struct svm_node));
+			}
+
+			idx = strtok(NULL,":");
+			val = strtok(NULL," \t");
+
+			if(val == NULL)
+				break;
+			errno = 0;
+			x[i].index = (int) strtol(idx,&endptr,10);
+			if(endptr == idx || errno != 0 || *endptr != '\0' || x[i].index <= inst_max_index)
+				exit_input_error(total+1);
+			else
+				inst_max_index = x[i].index;
+
+			errno = 0;
+			x[i].value = strtod(val,&endptr);
+			if(endptr == val || errno != 0 || (*endptr != '\0' && !isspace(*endptr)))
+				exit_input_error(total+1);
+
+			++i;
+		}
+		x[i].index = -1;
+
+		if (predict_probability && (svm_type==C_SVC || svm_type==NU_SVC))
+		{
+			predict_label = svm_predict_probability(model,x,prob_estimates);
+			fprintf(output,"%g",predict_label);
+			for(j=0;j<nr_class;j++)
+				fprintf(output," %g",prob_estimates[j]);
+			fprintf(output,"\n");
+		}
+		else
+		{
+			predict_label = svm_predict(model,x);
+			fprintf(output,"%g\n",predict_label);
+		}
+
+		if(predict_label == target_label)
+			++correct;
+		error += (predict_label-target_label)*(predict_label-target_label);
+		sump += predict_label;
+		sumt += target_label;
+		sumpp += predict_label*predict_label;
+		sumtt += target_label*target_label;
+		sumpt += predict_label*target_label;
+		++total;
+	}
+	if (svm_type==NU_SVR || svm_type==EPSILON_SVR)
+	{
+		printf("Mean squared error = %g (regression)\n",error/total);
+		printf("Squared correlation coefficient = %g (regression)\n",
+		       ((total*sumpt-sump*sumt)*(total*sumpt-sump*sumt))/
+		       ((total*sumpp-sump*sump)*(total*sumtt-sumt*sumt))
+		       );
+	}
+	else
+		printf("Accuracy = %g%% (%d/%d) (classification)\n",
+		       (double)correct/total*100,correct,total);
+	if(predict_probability)
+		free(prob_estimates);
+}
+
+void exit_with_help()
+{
+	printf(
+	"Usage: svm-predict [options] test_file model_file output_file\n"
+	"options:\n"
+	"-b probability_estimates: whether to predict probability estimates, 0 or 1 (default 0); for one-class SVM only 0 is supported\n"
+	);
+	exit(1);
+}
+
+int main(int argc, char **argv)
+{
+	FILE *input, *output;
+	int i;
+
+	// parse options
+	for(i=1;i<argc;i++)
+	{
+		if(argv[i][0] != '-') break;
+		++i;
+		switch(argv[i-1][1])
+		{
+			case 'b':
+				predict_probability = atoi(argv[i]);
+				break;
+			default:
+				fprintf(stderr,"Unknown option: -%c\n", argv[i-1][1]);
+				exit_with_help();
+		}
+	}
+	if(i>=argc-2)
+		exit_with_help();
+	
+	input = fopen(argv[i],"r");
+	if(input == NULL)
+	{
+		fprintf(stderr,"can't open input file %s\n",argv[i]);
+		exit(1);
+	}
+
+	output = fopen(argv[i+2],"w");
+	if(output == NULL)
+	{
+		fprintf(stderr,"can't open output file %s\n",argv[i+2]);
+		exit(1);
+	}
+
+	if((model=svm_load_model(argv[i+1]))==0)
+	{
+		fprintf(stderr,"can't open model file %s\n",argv[i+1]);
+		exit(1);
+	}
+
+	x = (struct svm_node *) malloc(max_nr_attr*sizeof(struct svm_node));
+	if(predict_probability)
+	{
+		if(svm_check_probability_model(model)==0)
+		{
+			fprintf(stderr,"Model does not support probabiliy estimates\n");
+			exit(1);
+		}
+	}
+	else
+	{
+		if(svm_check_probability_model(model)!=0)
+			printf("Model supports probability estimates, but disabled in prediction.\n");
+	}
+	predict(input,output);
+	svm_free_and_destroy_model(&model);
+	free(x);
+	free(line);
+	fclose(input);
+	fclose(output);
+	return 0;
+}

data/ext/libsvm/svm-scale.c

@@ -0,0 +1,353 @@
+#include <float.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <ctype.h>
+#include <string.h>
+
+void exit_with_help()
+{
+	printf(
+	"Usage: svm-scale [options] data_filename\n"
+	"options:\n"
+	"-l lower : x scaling lower limit (default -1)\n"
+	"-u upper : x scaling upper limit (default +1)\n"
+	"-y y_lower y_upper : y scaling limits (default: no y scaling)\n"
+	"-s save_filename : save scaling parameters to save_filename\n"
+	"-r restore_filename : restore scaling parameters from restore_filename\n"
+	);
+	exit(1);
+}
+
+char *line = NULL;
+int max_line_len = 1024;
+double lower=-1.0,upper=1.0,y_lower,y_upper;
+int y_scaling = 0;
+double *feature_max;
+double *feature_min;
+double y_max = -DBL_MAX;
+double y_min = DBL_MAX;
+int max_index;
+long int num_nonzeros = 0;
+long int new_num_nonzeros = 0;
+
+#define max(x,y) (((x)>(y))?(x):(y))
+#define min(x,y) (((x)<(y))?(x):(y))
+
+void output_target(double value);
+void output(int index, double value);
+char* readline(FILE *input);
+
+int main(int argc,char **argv)
+{
+	int i,index;
+	FILE *fp, *fp_restore = NULL;
+	char *save_filename = NULL;
+	char *restore_filename = NULL;
+
+	for(i=1;i<argc;i++)
+	{
+		if(argv[i][0] != '-') break;
+		++i;
+		switch(argv[i-1][1])
+		{
+			case 'l': lower = atof(argv[i]); break;
+			case 'u': upper = atof(argv[i]); break;
+			case 'y':
+				y_lower = atof(argv[i]);
+				++i;
+				y_upper = atof(argv[i]);
+				y_scaling = 1;
+				break;
+			case 's': save_filename = argv[i]; break;
+			case 'r': restore_filename = argv[i]; break;
+			default:
+				fprintf(stderr,"unknown option\n");
+				exit_with_help();
+		}
+	}
+
+	if(!(upper > lower) || (y_scaling && !(y_upper > y_lower)))
+	{
+		fprintf(stderr,"inconsistent lower/upper specification\n");
+		exit(1);
+	}
+	
+	if(restore_filename && save_filename)
+	{
+		fprintf(stderr,"cannot use -r and -s simultaneously\n");
+		exit(1);
+	}
+
+	if(argc != i+1) 
+		exit_with_help();
+
+	fp=fopen(argv[i],"r");
+	
+	if(fp==NULL)
+	{
+		fprintf(stderr,"can't open file %s\n", argv[i]);
+		exit(1);
+	}
+
+	line = (char *) malloc(max_line_len*sizeof(char));
+
+#define SKIP_TARGET\
+	while(isspace(*p)) ++p;\
+	while(!isspace(*p)) ++p;
+
+#define SKIP_ELEMENT\
+	while(*p!=':') ++p;\
+	++p;\
+	while(isspace(*p)) ++p;\
+	while(*p && !isspace(*p)) ++p;
+	
+	/* assumption: min index of attributes is 1 */
+	/* pass 1: find out max index of attributes */
+	max_index = 0;
+
+	if(restore_filename)
+	{
+		int idx, c;
+
+		fp_restore = fopen(restore_filename,"r");
+		if(fp_restore==NULL)
+		{
+			fprintf(stderr,"can't open file %s\n", restore_filename);
+			exit(1);
+		}
+
+		c = fgetc(fp_restore);
+		if(c == 'y')
+		{
+			readline(fp_restore);
+			readline(fp_restore);
+			readline(fp_restore);
+		}
+		readline(fp_restore);
+		readline(fp_restore);
+
+		while(fscanf(fp_restore,"%d %*f %*f\n",&idx) == 1)
+			max_index = max(idx,max_index);
+		rewind(fp_restore);
+	}
+
+	while(readline(fp)!=NULL)
+	{
+		char *p=line;
+
+		SKIP_TARGET
+
+		while(sscanf(p,"%d:%*f",&index)==1)
+		{
+			max_index = max(max_index, index);
+			SKIP_ELEMENT
+			num_nonzeros++;
+		}		
+	}
+	rewind(fp);
+	
+	feature_max = (double *)malloc((max_index+1)* sizeof(double));
+	feature_min = (double *)malloc((max_index+1)* sizeof(double));
+	
+	if(feature_max == NULL || feature_min == NULL)
+	{
+		fprintf(stderr,"can't allocate enough memory\n");
+		exit(1);
+	}
+
+	for(i=0;i<=max_index;i++)
+	{
+		feature_max[i]=-DBL_MAX;
+		feature_min[i]=DBL_MAX;
+	}
+
+	/* pass 2: find out min/max value */
+	while(readline(fp)!=NULL)
+	{
+		char *p=line;
+		int next_index=1;
+		double target;
+		double value;
+
+		sscanf(p,"%lf",&target);
+		y_max = max(y_max,target);
+		y_min = min(y_min,target);
+		
+		SKIP_TARGET
+
+		while(sscanf(p,"%d:%lf",&index,&value)==2)
+		{
+			for(i=next_index;i<index;i++)
+			{
+				feature_max[i]=max(feature_max[i],0);
+				feature_min[i]=min(feature_min[i],0);
+			}
+			
+			feature_max[index]=max(feature_max[index],value);
+			feature_min[index]=min(feature_min[index],value);
+
+			SKIP_ELEMENT
+			next_index=index+1;
+		}		
+
+		for(i=next_index;i<=max_index;i++)
+		{
+			feature_max[i]=max(feature_max[i],0);
+			feature_min[i]=min(feature_min[i],0);
+		}	
+	}
+
+	rewind(fp);
+
+	/* pass 2.5: save/restore feature_min/feature_max */
+	
+	if(restore_filename)
+	{
+		/* fp_restore rewinded in finding max_index */
+		int idx, c;
+		double fmin, fmax;
+		
+		if((c = fgetc(fp_restore)) == 'y')
+		{
+			fscanf(fp_restore, "%lf %lf\n", &y_lower, &y_upper);
+			fscanf(fp_restore, "%lf %lf\n", &y_min, &y_max);
+			y_scaling = 1;
+		}
+		else
+			ungetc(c, fp_restore);
+
+		if (fgetc(fp_restore) == 'x') {
+			fscanf(fp_restore, "%lf %lf\n", &lower, &upper);
+			while(fscanf(fp_restore,"%d %lf %lf\n",&idx,&fmin,&fmax)==3)
+			{
+				if(idx<=max_index)
+				{
+					feature_min[idx] = fmin;
+					feature_max[idx] = fmax;
+				}
+			}
+		}
+		fclose(fp_restore);
+	}
+	
+	if(save_filename)
+	{
+		FILE *fp_save = fopen(save_filename,"w");
+		if(fp_save==NULL)
+		{
+			fprintf(stderr,"can't open file %s\n", save_filename);
+			exit(1);
+		}
+		if(y_scaling)
+		{
+			fprintf(fp_save, "y\n");
+			fprintf(fp_save, "%.16g %.16g\n", y_lower, y_upper);
+			fprintf(fp_save, "%.16g %.16g\n", y_min, y_max);
+		}
+		fprintf(fp_save, "x\n");
+		fprintf(fp_save, "%.16g %.16g\n", lower, upper);
+		for(i=1;i<=max_index;i++)
+		{
+			if(feature_min[i]!=feature_max[i])
+				fprintf(fp_save,"%d %.16g %.16g\n",i,feature_min[i],feature_max[i]);
+		}
+		fclose(fp_save);
+	}
+	
+	/* pass 3: scale */
+	while(readline(fp)!=NULL)
+	{
+		char *p=line;
+		int next_index=1;
+		double target;
+		double value;
+		
+		sscanf(p,"%lf",&target);
+		output_target(target);
+
+		SKIP_TARGET
+
+		while(sscanf(p,"%d:%lf",&index,&value)==2)
+		{
+			for(i=next_index;i<index;i++)
+				output(i,0);
+			
+			output(index,value);
+
+			SKIP_ELEMENT
+			next_index=index+1;
+		}		
+
+		for(i=next_index;i<=max_index;i++)
+			output(i,0);
+
+		printf("\n");
+	}
+
+	if (new_num_nonzeros > num_nonzeros)
+		fprintf(stderr, 
+			"Warning: original #nonzeros %ld\n"
+			"         new      #nonzeros %ld\n"
+			"Use -l 0 if many original feature values are zeros\n",
+			num_nonzeros, new_num_nonzeros);
+
+	free(line);
+	free(feature_max);
+	free(feature_min);
+	fclose(fp);
+	return 0;
+}
+
+char* readline(FILE *input)
+{
+	int len;
+	
+	if(fgets(line,max_line_len,input) == NULL)
+		return NULL;
+
+	while(strrchr(line,'\n') == NULL)
+	{
+		max_line_len *= 2;
+		line = (char *) realloc(line, max_line_len);
+		len = (int) strlen(line);
+		if(fgets(line+len,max_line_len-len,input) == NULL)
+			break;
+	}
+	return line;
+}
+
+void output_target(double value)
+{
+	if(y_scaling)
+	{
+		if(value == y_min)
+			value = y_lower;
+		else if(value == y_max)
+			value = y_upper;
+		else value = y_lower + (y_upper-y_lower) *
+			     (value - y_min)/(y_max-y_min);
+	}
+	printf("%g ",value);
+}
+
+void output(int index, double value)
+{
+	/* skip single-valued attribute */
+	if(feature_max[index] == feature_min[index])
+		return;
+
+	if(value == feature_min[index])
+		value = lower;
+	else if(value == feature_max[index])
+		value = upper;
+	else
+		value = lower + (upper-lower) * 
+			(value-feature_min[index])/
+			(feature_max[index]-feature_min[index]);
+
+	if(value != 0)
+	{
+		printf("%d:%g ",index, value);
+		new_num_nonzeros++;
+	}
+}