void zscore ()
{
if (!data2d)
buildData2d ();
long i, j;
for (j = 0; j < nvar; j++)
{
double cursum = 0;
double curmean = 0;
double curstd = 0;
for (i = 0; i < nsample; i++)
cursum += data2d[i][j];
curmean = cursum / nsample;
cursum = 0;
register double tmpf;
for (i = 0; i < nsample; i++)
{
tmpf = data2d[i][j] - curmean;
cursum += tmpf * tmpf;
}
curstd = (nsample == 1) ? 0 : sqrt (cursum / (nsample - 1)); //nsample -1 is an unbiased version for Gaussian
for (i = 0; i < nsample; i++)
{
data2d[i][j] = (data2d[i][j] - curmean) / curstd;
}
}
b_zscore = 1;
}
void zscore (long indExcludeColumn, int b_discretize)
{
if (!data2d)
buildData2d ();
if (!b_discretize)
return; // in this case, just generate the 2D data array
long i, j;
for (j = 0; j < nvar; j++)
{
if (j==indExcludeColumn)
{
continue; //this is useful to exclude the first column, which will be the target classification variable
}
double cursum = 0;
double curmean = 0;
double curstd = 0;
for (i = 0; i < nsample; i++)
cursum += data2d[i][j];
curmean = cursum / nsample;
cursum = 0;
register double tmpf;
for (i = 0; i < nsample; i++)
{
tmpf = data2d[i][j] - curmean;
cursum += tmpf * tmpf;
}
curstd = (nsample == 1) ? 0 : sqrt (cursum / (nsample - 1)); //nsample -1 is an unbiased version for Gaussian
for (i = 0; i < nsample; i++)
{
data2d[i][j] = (data2d[i][j] - curmean) / curstd;
}
}
b_zscore = 1;
}
