added ability to read files with different space count

pull/13383/head
Maria Dimashova 13 years ago
parent 7a3786bad9
commit 14ca8ed03c
  1. 25
      modules/ml/src/data.cpp

@ -161,8 +161,21 @@ int CvMLData::read_csv(const char* filename)
fclose(file);
return -1;
}
for( ptr = buf; *ptr != '\0'; ptr++ )
cols_count += (*ptr == delimiter);
ptr = buf;
while( *ptr == ' ' )
ptr++;
for( ; *ptr != '\0'; )
{
if(*ptr == delimiter || *ptr == ' ')
{
cols_count++;
ptr++;
while( *ptr == ' ' ) ptr++;
}
else
ptr++;
}
if ( cols_count == 0)
{
@ -204,7 +217,7 @@ int CvMLData::read_csv(const char* filename)
str_to_flt_elem( token, el_ptr[cols_count-1], type);
var_types_ptr[cols_count-1] |= type;
cvSeqPush( seq, el_ptr );
if( !fgets_chomp( buf, M, file ) || !strchr( buf, delimiter ) )
if( !fgets_chomp( buf, M, file ) )
break;
}
fclose(file);
@ -606,7 +619,7 @@ void CvMLData::set_train_test_split( const CvTrainTestSplit * spl)
CV_ERROR( CV_StsBadArg, "train samples count is not correct" );
train_sample_portion = train_sample_portion <= FLT_EPSILON ||
1 - train_sample_portion <= FLT_EPSILON ? 1 : train_sample_portion;
train_sample_count = cvFloor( train_sample_portion * sample_count );
train_sample_count = std::max(1, cvFloor( train_sample_portion * sample_count ));
}
if ( train_sample_count == sample_count )
@ -625,8 +638,10 @@ void CvMLData::set_train_test_split( const CvTrainTestSplit * spl)
for (int i = 0; i < sample_count; i++ )
sample_idx[i] = i;
train_sample_idx = cvCreateMatHeader( 1, train_sample_count, CV_32SC1 );
test_sample_idx = cvCreateMatHeader( 1, test_sample_count, CV_32SC1 );
*train_sample_idx = cvMat( 1, train_sample_count, CV_32SC1, &sample_idx[0] );
CV_Assert(test_sample_count > 0);
test_sample_idx = cvCreateMatHeader( 1, test_sample_count, CV_32SC1 );
*test_sample_idx = cvMat( 1, test_sample_count, CV_32SC1, &sample_idx[train_sample_count] );
}

Loading…
Cancel
Save