CvDTree* mushroom_create_dtree( const CvMat* data, const CvMat* missing,
const CvMat* responses, float p_weight )
{
CvDTree* dtree;
CvMat* var_type;
int i, hr1 = 0, hr2 = 0, p_total = 0;
float priors[] = { 1, p_weight };
var_type = cvCreateMat( data->cols + 1, 1, CV_8U );
cvSet( var_type, cvScalarAll(CV_VAR_CATEGORICAL) ); // all the variables are categorical
dtree = new CvDTree;
dtree->train( data, CV_ROW_SAMPLE, responses, 0, 0, var_type, missing,
CvDTreeParams( 8, // max depth
10, // min sample count
0, // regression accuracy: N/A here
true, // compute surrogate split, as we have missing data
15, // max number of categories (use sub-optimal algorithm for larger numbers)
10, // the number of cross-validation folds
true, // use 1SE rule => smaller tree
true, // throw away the pruned tree branches
priors // the array of priors, the bigger p_weight, the more attention
// to the poisonous mushrooms
// (a mushroom will be judjed to be poisonous with bigger chance)
));
// compute hit-rate on the training database, demonstrates predict usage.
for( i = 0; i < data->rows; i++ )
{
CvMat sample, mask;
cvGetRow( data, &sample, i );
cvGetRow( missing, &mask, i );
double r = dtree->predict( &sample, &mask )->value;
int d = fabs(r - responses->data.fl[i]) >= FLT_EPSILON;
if( d )
{
if( r != 'p' )
hr1++;
else
hr2++;
}
p_total += responses->data.fl[i] == 'p';
}
printf( "Results on the training database:\n"
"\tPoisonous mushrooms mis-predicted: %d (%g%%)\n"
"\tFalse-alarms: %d (%g%%)\n", hr1, (double)hr1*100/p_total,
hr2, (double)hr2*100/(data->rows - p_total) );
cvReleaseMat( &var_type );
return dtree;
}
int main()
{
const int train_sample_count = 300;
//#define LEPIOTA
#ifdef LEPIOTA
const char* filename = "../../../OpenCV_SVN/samples/c/agaricus-lepiota.data";
#else
const char* filename = "../../../OpenCV_SVN/samples/c/waveform.data";
#endif
CvDTree dtree;
CvBoost boost;
CvRTrees rtrees;
CvERTrees ertrees;
CvMLData data;
CvTrainTestSplit spl( train_sample_count );
data.read_csv( filename );
#ifdef LEPIOTA
data.set_response_idx( 0 );
#else
data.set_response_idx( 21 );
data.change_var_type( 21, CV_VAR_CATEGORICAL );
#endif
data.set_train_test_split( &spl );
printf("======DTREE=====\n");
dtree.train( &data, CvDTreeParams( 10, 2, 0, false, 16, 0, false, false, 0 ));
print_result( dtree.calc_error( &data, CV_TRAIN_ERROR), dtree.calc_error( &data ), dtree.get_var_importance() );
#ifdef LEPIOTA
printf("======BOOST=====\n");
boost.train( &data, CvBoostParams(CvBoost::DISCRETE, 100, 0.95, 2, false, 0));
print_result( boost.calc_error( &data, CV_TRAIN_ERROR ), boost.calc_error( &data ), 0 );
#endif
printf("======RTREES=====\n");
rtrees.train( &data, CvRTParams( 10, 2, 0, false, 16, 0, true, 0, 100, 0, CV_TERMCRIT_ITER ));
print_result( rtrees.calc_error( &data, CV_TRAIN_ERROR), rtrees.calc_error( &data ), rtrees.get_var_importance() );
printf("======ERTREES=====\n");
ertrees.train( &data, CvRTParams( 10, 2, 0, false, 16, 0, true, 0, 100, 0, CV_TERMCRIT_ITER ));
print_result( ertrees.calc_error( &data, CV_TRAIN_ERROR), ertrees.calc_error( &data ), ertrees.get_var_importance() );
return 0;
}
//Decision Tree
void decisiontree ( Mat & trainingData , Mat & trainingClasses , Mat & testData ,
Mat & testClasses ) {
CvDTree dtree ;
Mat var_type (3 , 1 , CV_8U ) ;
// define attributes as numerical
var_type.at < unsigned int >(0 ,0) = CV_VAR_NUMERICAL;
var_type.at < unsigned int >(0 ,1) = CV_VAR_NUMERICAL ;
// define output node as numerical
var_type.at < unsigned int >(0 ,2) = CV_VAR_NUMERICAL;
dtree.train ( trainingData , CV_ROW_SAMPLE , trainingClasses , Mat () , Mat () ,
var_type , Mat () , CvDTreeParams () ) ;
Mat predicted ( testClasses.rows , 1 , CV_32F ) ;
for ( int i = 0; i < testData.rows ; i ++) {
const Mat sample = testData.row ( i ) ;
CvDTreeNode * prediction = dtree.predict ( sample ) ;
predicted.at < float > (i , 0) = prediction->value ;
}
cout << " Accuracy_ { TREE } = " << evaluate ( predicted , testClasses ) << endl ;
plot_binary ( testData , predicted , " Predictions tree " ) ;
}
void trainFromTxt() {
FILE* fin = fopen("train.txt","r");
int N,i;
training = true;
fscanf(fin,"%i",&N);
CvMat *data = cvCreateMat(N,COLS,CV_32F);
CvMat *resp = cvCreateMat(N,1,CV_32F);
char c[10];
float *fdata,*fresp;
for(i=0; i<N; i++) {
fdata = data->data.fl + i*COLS;
fresp = resp->data.fl + i;
fscanf(fin,"%s",c);
for (int j=0; j<COLS; j++) {
fscanf(fin,"%f",&fdata[j]);
}
*fresp = (float)c[0];
}
printMatrix(data);
printMatrix(resp);
CvMat *vartype = cvCreateMat( data->cols + 1, 1, CV_8U );
unsigned char *vtype = vartype->data.ptr;
//Tipos de variables de entrada al árbol
vtype[0]=CV_VAR_NUMERICAL;
vtype[1]=CV_VAR_NUMERICAL;
vtype[2]=CV_VAR_NUMERICAL;
vtype[3]=CV_VAR_NUMERICAL;
vtype[4]=CV_VAR_CATEGORICAL; //Tipo de la salida del árbol
ptree = new CvDTree;
ptree->train(data,CV_ROW_SAMPLE,resp,0,0,vartype,0,CvDTreeParams());
}
/**
* Creates a matrix for training but feeds it from images taken of folder
* ./training; Only JPG images are taken into account and all shapes in those
* images are clasified according to the first letter of the picture.
*/
void train() {
training = true;
mostrar = (flags & SH_T) != 0;
listFiles(DIR_TR,training_image);
fillMatrix();
//printMatrix(t_data);
//printMatrix(t_resp);
CvMat *vartype = cvCreateMat( t_data->cols + 1, 1, CV_8U );
unsigned char *vtype = vartype->data.ptr;
//Tipos de variables de entrada al árbol
vtype[0]=CV_VAR_NUMERICAL;
vtype[1]=CV_VAR_NUMERICAL;
vtype[2]=CV_VAR_NUMERICAL;
vtype[3]=CV_VAR_NUMERICAL;
vtype[4]=CV_VAR_CATEGORICAL; //Tipo de la salida del árbol
if ((flags & F_CHK) != 0) {
trainMask = cvCreateMat(t_data->rows, 1, CV_8U);
unsigned char *x = trainMask->data.ptr;
CvRNG seed = cvRNG(time(0));
for (int i=0; i<t_data->rows; i++,x++) {
double p = cvRandReal(&seed);
if (p < probTrain) {
*x = 1;
} else {
*x=0;
}
}
}
ptree = new CvDTree;
ptree->train(t_data,CV_ROW_SAMPLE,t_resp,0,trainMask,vartype,0,CvDTreeParams());
}
/**
* @author JIA Pei
* @version 2009-10-04
* @brief Training
* @param data Input - input data
* @param categories Input - column vector
* @return classification time cost
*/
void CClassificationAlgs::Training(const Mat_<float>& data, const Mat_<int>& categories)
{
unsigned int NbOfSamples = data.rows;
set<int> ClassSet;
for(int i = 0; i < categories.rows; i++)
{
ClassSet.insert(categories(i, 0));
}
this->m_iNbOfCategories = ClassSet.size();
switch(this->m_iClassificationMethod)
{
case CClassificationAlgs::DecisionTree:
this->m_CVDtree.train( data,
CV_ROW_SAMPLE,
categories,
Mat(),
Mat(),
Mat(),
Mat(),
CvDTreeParams( INT_MAX, 2, 0, false, this->m_iNbOfCategories, 0, false, false, 0 ) );
break;
case CClassificationAlgs::Boost:
this->m_CVBoost.train( data,
CV_ROW_SAMPLE,
categories,
Mat(),
Mat(),
Mat(),
Mat(),
CvBoostParams(CvBoost::DISCRETE, 50, 0.95, INT_MAX, false, 0),
false );
break;
case CClassificationAlgs::RandomForest:
this->m_CVRTrees.train( data,
CV_ROW_SAMPLE,
categories,
Mat(),
Mat(),
Mat(),
Mat(),
CvRTParams( INT_MAX, 2, 0, false, this->m_iNbOfCategories, 0, true, 0, 100, 0, CV_TERMCRIT_ITER ) );
break;
case CClassificationAlgs::ExtremeRandomForest:
this->m_CVERTrees.train(data,
CV_ROW_SAMPLE,
categories,
Mat(),
Mat(),
Mat(),
Mat(),
CvRTParams( INT_MAX, 2, 0, false, this->m_iNbOfCategories, 0, true, 0, 100, 0, CV_TERMCRIT_ITER ) );
break;
case CClassificationAlgs::SVM:
this->m_CVSVM.train( data,
categories,
Mat(),
Mat(),
CvSVMParams(CvSVM::C_SVC, CvSVM::RBF,
0, 1, 0,
1, 0, 0,
NULL, cvTermCriteria(CV_TERMCRIT_ITER, 1000, 1E-6) ) );
break;
}
}
int CV_DTreeTest :: train( int test_case_idx )
{
int MAX_DEPTH, MIN_SAMPLE_COUNT, MAX_CATEGORIES, CV_FOLDS;
float REG_ACCURACY = 0;
bool USE_SURROGATE, IS_PRUNED;
const char* data_name = ((CvFileNode*)cvGetSeqElem( data_sets_names, test_case_idx ))->data.str.ptr;
// read validation params
CvFileStorage* fs = ts->get_file_storage();
CvFileNode* fnode = cvGetFileNodeByName( fs, 0, "validation" ), *fnode1 = 0;
fnode = cvGetFileNodeByName( fs, fnode, name );
fnode = cvGetFileNodeByName( fs, fnode, data_name );
fnode = cvGetFileNodeByName( fs, fnode, "model_params" );
fnode1 = cvGetFileNodeByName( fs, fnode, "max_depth" );
if ( !fnode1 )
{
ts->printf( CvTS::LOG, "MAX_DEPTH can not be read from config file" );
return CvTS::FAIL_INVALID_TEST_DATA;
}
MAX_DEPTH = fnode1->data.i;
fnode1 = cvGetFileNodeByName( fs, fnode, "min_sample_count" );
if ( !fnode1 )
{
ts->printf( CvTS::LOG, "MAX_DEPTH can not be read from config file" );
return CvTS::FAIL_INVALID_TEST_DATA;
}
MIN_SAMPLE_COUNT = fnode1->data.i;
fnode1 = cvGetFileNodeByName( fs, fnode, "use_surrogate" );
if ( !fnode1 )
{
ts->printf( CvTS::LOG, "USE_SURROGATE can not be read from config file" );
return CvTS::FAIL_INVALID_TEST_DATA;
}
USE_SURROGATE = ( fnode1->data.i!= 0);
fnode1 = cvGetFileNodeByName( fs, fnode, "max_categories" );
if ( !fnode1 )
{
ts->printf( CvTS::LOG, "MAX_CATEGORIES can not be read from config file" );
return CvTS::FAIL_INVALID_TEST_DATA;
}
MAX_CATEGORIES = fnode1->data.i;
fnode1 = cvGetFileNodeByName( fs, fnode, "cv_folds" );
if ( !fnode1 )
{
ts->printf( CvTS::LOG, "CV_FOLDS can not be read from config file" );
return CvTS::FAIL_INVALID_TEST_DATA;
}
CV_FOLDS = fnode1->data.i;
fnode1 = cvGetFileNodeByName( fs, fnode, "is_pruned" );
if ( !fnode1 )
{
ts->printf( CvTS::LOG, "IS_PRUNED can not be read from config file" );
return CvTS::FAIL_INVALID_TEST_DATA;
}
IS_PRUNED = (fnode1->data.i != 0);
if ( !tree->train( &data,
CvDTreeParams(MAX_DEPTH, MIN_SAMPLE_COUNT, REG_ACCURACY, USE_SURROGATE,
MAX_CATEGORIES, CV_FOLDS, false, IS_PRUNED, 0 )) )
{
ts->printf( CvTS::LOG, "in test case %d model training was failed", test_case_idx );
return CvTS::FAIL_INVALID_OUTPUT;
}
return CvTS::OK;
}
int main(int argc, char **argv)
{
float priors[] = { 1.0, 10.0 }; // Edible vs poisonos weights
CvMat *var_type;
CvMat *data; // jmh add
data = cvCreateMat(20, 30, CV_8U); // jmh add
var_type = cvCreateMat(data->cols + 1, 1, CV_8U);
cvSet(var_type, cvScalarAll(CV_VAR_CATEGORICAL)); // all these vars
// are categorical
CvDTree *dtree;
dtree = new CvDTree;
dtree->train(data, CV_ROW_SAMPLE, responses, 0, 0, var_type, missing, CvDTreeParams(8, // max depth
10, // min sample count
0, // regression accuracy: N/A here
true, // compute surrogate split,
// as we have missing data
15, // max number of categories
// (use sub-optimal algorithm for
// larger numbers)
10, // cross-validations
true, // use 1SE rule => smaller tree
true, // throw away the pruned tree branches
priors // the array of priors, the bigger
// p_weight, the more attention
// to the poisonous mushrooms
)
);
dtree->save("tree.xml", "MyTree");
dtree->clear();
dtree->load("tree.xml", "MyTree");
#define MAX_CLUSTERS 5
CvScalar color_tab[MAX_CLUSTERS];
IplImage *img = cvCreateImage(cvSize(500, 500), 8, 3);
CvRNG rng = cvRNG(0xffffffff);
color_tab[0] = CV_RGB(255, 0, 0);
color_tab[1] = CV_RGB(0, 255, 0);
color_tab[2] = CV_RGB(100, 100, 255);
color_tab[3] = CV_RGB(255, 0, 255);
color_tab[4] = CV_RGB(255, 255, 0);
cvNamedWindow("clusters", 1);
for (;;) {
int k, cluster_count = cvRandInt(&rng) % MAX_CLUSTERS + 1;
int i, sample_count = cvRandInt(&rng) % 1000 + 1;
CvMat *points = cvCreateMat(sample_count, 1, CV_32FC2);
CvMat *clusters = cvCreateMat(sample_count, 1, CV_32SC1);
/* generate random sample from multivariate
Gaussian distribution */
for (k = 0; k < cluster_count; k++) {
CvPoint center;
CvMat point_chunk;
center.x = cvRandInt(&rng) % img->width;
center.y = cvRandInt(&rng) % img->height;
cvGetRows(points, &point_chunk,
k * sample_count / cluster_count,
k == cluster_count - 1 ? sample_count :
(k + 1) * sample_count / cluster_count);
cvRandArr(&rng, &point_chunk, CV_RAND_NORMAL,
cvScalar(center.x, center.y, 0, 0),
cvScalar(img->width / 6, img->height / 6, 0, 0));
}
/* shuffle samples */
for (i = 0; i < sample_count / 2; i++) {
CvPoint2D32f *pt1 = (CvPoint2D32f *) points->data.fl +
cvRandInt(&rng) % sample_count;
CvPoint2D32f *pt2 = (CvPoint2D32f *) points->data.fl +
cvRandInt(&rng) % sample_count;
CvPoint2D32f temp;
CV_SWAP(*pt1, *pt2, temp);
}
cvKMeans2(points, cluster_count, clusters,
cvTermCriteria(CV_TERMCRIT_EPS + CV_TERMCRIT_ITER, 10, 1.0));
cvZero(img);
for (i = 0; i < sample_count; i++) {
CvPoint2D32f pt = ((CvPoint2D32f *) points->data.fl)[i];
int cluster_idx = clusters->data.i[i];
cvCircle(img, cvPointFrom32f(pt), 2,
color_tab[cluster_idx], CV_FILLED);
}
cvReleaseMat(&points);
cvReleaseMat(&clusters);
cvShowImage("clusters", img);
int key = cvWaitKey(0);
if (key == 27) // 'ESC'
break;
}
}
