public hqrndstate(hqrnd.hqrndstate obj)
{
_innerobj = obj;
}
/*************************************************************************
Builds one decision tree (internal recursive subroutine)
Parameters:
TreeBuf - large enough array, at least TreeSize
IdxBuf - at least NPoints elements
TmpBufR - at least NPoints
TmpBufR2 - at least NPoints
TmpBufI - at least NPoints
TmpBufI2 - at least NPoints+1
*************************************************************************/
private static void dfbuildtreerec(double[,] xy,
int npoints,
int nvars,
int nclasses,
int nfeatures,
int nvarsinpool,
int flags,
ref int numprocessed,
int idx1,
int idx2,
dfinternalbuffers bufs,
hqrnd.hqrndstate rs)
{
int i = 0;
int j = 0;
int k = 0;
bool bflag = new bool();
int i1 = 0;
int i2 = 0;
int info = 0;
double sl = 0;
double sr = 0;
double w = 0;
int idxbest = 0;
double ebest = 0;
double tbest = 0;
int varcur = 0;
double s = 0;
double v = 0;
double v1 = 0;
double v2 = 0;
double threshold = 0;
int oldnp = 0;
double currms = 0;
bool useevs = new bool();
//
// these initializers are not really necessary,
// but without them compiler complains about uninitialized locals
//
tbest = 0;
//
// Prepare
//
alglib.ap.assert(npoints>0);
alglib.ap.assert(idx2>=idx1);
useevs = flags/dfuseevs%2!=0;
//
// Leaf node
//
if( idx2==idx1 )
{
bufs.treebuf[numprocessed] = -1;
bufs.treebuf[numprocessed+1] = xy[bufs.idxbuf[idx1],nvars];
numprocessed = numprocessed+leafnodewidth;
return;
}
//
// Non-leaf node.
// Select random variable, prepare split:
// 1. prepare default solution - no splitting, class at random
// 2. investigate possible splits, compare with default/best
//
idxbest = -1;
if( nclasses>1 )
{
//
// default solution for classification
//
for(i=0; i<=nclasses-1; i++)
{
bufs.classibuf[i] = 0;
}
s = idx2-idx1+1;
for(i=idx1; i<=idx2; i++)
{
j = (int)Math.Round(xy[bufs.idxbuf[i],nvars]);
bufs.classibuf[j] = bufs.classibuf[j]+1;
}
ebest = 0;
for(i=0; i<=nclasses-1; i++)
{
ebest = ebest+bufs.classibuf[i]*math.sqr(1-bufs.classibuf[i]/s)+(s-bufs.classibuf[i])*math.sqr(bufs.classibuf[i]/s);
}
ebest = Math.Sqrt(ebest/(nclasses*(idx2-idx1+1)));
}
else
{
//
// default solution for regression
//
v = 0;
for(i=idx1; i<=idx2; i++)
{
v = v+xy[bufs.idxbuf[i],nvars];
}
v = v/(idx2-idx1+1);
ebest = 0;
for(i=idx1; i<=idx2; i++)
{
ebest = ebest+math.sqr(xy[bufs.idxbuf[i],nvars]-v);
}
ebest = Math.Sqrt(ebest/(idx2-idx1+1));
}
i = 0;
while( i<=Math.Min(nfeatures, nvarsinpool)-1 )
{
//
// select variables from pool
//
j = i+hqrnd.hqrnduniformi(rs, nvarsinpool-i);
k = bufs.varpool[i];
bufs.varpool[i] = bufs.varpool[j];
bufs.varpool[j] = k;
varcur = bufs.varpool[i];
//
// load variable values to working array
//
// apply EVS preprocessing: if all variable values are same,
// variable is excluded from pool.
//
// This is necessary for binary pre-splits (see later) to work.
//
for(j=idx1; j<=idx2; j++)
{
bufs.tmpbufr[j-idx1] = xy[bufs.idxbuf[j],varcur];
}
if( useevs )
{
bflag = false;
v = bufs.tmpbufr[0];
for(j=0; j<=idx2-idx1; j++)
{
if( (double)(bufs.tmpbufr[j])!=(double)(v) )
{
bflag = true;
break;
}
}
if( !bflag )
{
//
// exclude variable from pool,
// go to the next iteration.
// I is not increased.
//
k = bufs.varpool[i];
bufs.varpool[i] = bufs.varpool[nvarsinpool-1];
bufs.varpool[nvarsinpool-1] = k;
nvarsinpool = nvarsinpool-1;
continue;
}
}
//
// load labels to working array
//
if( nclasses>1 )
{
for(j=idx1; j<=idx2; j++)
{
bufs.tmpbufi[j-idx1] = (int)Math.Round(xy[bufs.idxbuf[j],nvars]);
}
}
else
{
for(j=idx1; j<=idx2; j++)
{
bufs.tmpbufr2[j-idx1] = xy[bufs.idxbuf[j],nvars];
}
}
//
// calculate split
//
if( useevs && bufs.evsbin[varcur] )
{
//
// Pre-calculated splits for binary variables.
// Threshold is already known, just calculate RMS error
//
threshold = bufs.evssplits[varcur];
if( nclasses>1 )
{
//
// classification-specific code
//
for(j=0; j<=2*nclasses-1; j++)
{
bufs.classibuf[j] = 0;
}
sl = 0;
sr = 0;
for(j=0; j<=idx2-idx1; j++)
{
k = bufs.tmpbufi[j];
if( (double)(bufs.tmpbufr[j])<(double)(threshold) )
{
bufs.classibuf[k] = bufs.classibuf[k]+1;
sl = sl+1;
}
else
{
bufs.classibuf[k+nclasses] = bufs.classibuf[k+nclasses]+1;
sr = sr+1;
}
}
alglib.ap.assert((double)(sl)!=(double)(0) && (double)(sr)!=(double)(0), "DFBuildTreeRec: something strange!");
currms = 0;
for(j=0; j<=nclasses-1; j++)
{
w = bufs.classibuf[j];
currms = currms+w*math.sqr(w/sl-1);
currms = currms+(sl-w)*math.sqr(w/sl);
w = bufs.classibuf[nclasses+j];
currms = currms+w*math.sqr(w/sr-1);
currms = currms+(sr-w)*math.sqr(w/sr);
}
currms = Math.Sqrt(currms/(nclasses*(idx2-idx1+1)));
}
else
{
//
// regression-specific code
//
sl = 0;
sr = 0;
v1 = 0;
v2 = 0;
for(j=0; j<=idx2-idx1; j++)
{
if( (double)(bufs.tmpbufr[j])<(double)(threshold) )
{
v1 = v1+bufs.tmpbufr2[j];
sl = sl+1;
}
else
{
v2 = v2+bufs.tmpbufr2[j];
sr = sr+1;
}
}
alglib.ap.assert((double)(sl)!=(double)(0) && (double)(sr)!=(double)(0), "DFBuildTreeRec: something strange!");
v1 = v1/sl;
v2 = v2/sr;
currms = 0;
for(j=0; j<=idx2-idx1; j++)
{
if( (double)(bufs.tmpbufr[j])<(double)(threshold) )
{
currms = currms+math.sqr(v1-bufs.tmpbufr2[j]);
}
else
{
currms = currms+math.sqr(v2-bufs.tmpbufr2[j]);
}
}
currms = Math.Sqrt(currms/(idx2-idx1+1));
}
info = 1;
}
else
{
//
// Generic splits
//
if( nclasses>1 )
{
dfsplitc(ref bufs.tmpbufr, ref bufs.tmpbufi, ref bufs.classibuf, idx2-idx1+1, nclasses, dfusestrongsplits, ref info, ref threshold, ref currms, ref bufs.sortrbuf, ref bufs.sortibuf);
}
else
{
dfsplitr(ref bufs.tmpbufr, ref bufs.tmpbufr2, idx2-idx1+1, dfusestrongsplits, ref info, ref threshold, ref currms, ref bufs.sortrbuf, ref bufs.sortrbuf2);
}
}
if( info>0 )
{
if( (double)(currms)<=(double)(ebest) )
{
ebest = currms;
idxbest = varcur;
tbest = threshold;
}
}
//
// Next iteration
//
i = i+1;
}
//
// to split or not to split
//
if( idxbest<0 )
{
//
// All values are same, cannot split.
//
bufs.treebuf[numprocessed] = -1;
if( nclasses>1 )
{
//
// Select random class label (randomness allows us to
// approximate distribution of the classes)
//
bufs.treebuf[numprocessed+1] = (int)Math.Round(xy[bufs.idxbuf[idx1+hqrnd.hqrnduniformi(rs, idx2-idx1+1)],nvars]);
}
else
{
//
// Select average (for regression task).
//
v = 0;
for(i=idx1; i<=idx2; i++)
{
v = v+xy[bufs.idxbuf[i],nvars]/(idx2-idx1+1);
}
bufs.treebuf[numprocessed+1] = v;
}
numprocessed = numprocessed+leafnodewidth;
}
else
{
//
// we can split
//
bufs.treebuf[numprocessed] = idxbest;
bufs.treebuf[numprocessed+1] = tbest;
i1 = idx1;
i2 = idx2;
while( i1<=i2 )
{
//
// Reorder indices so that left partition is in [Idx1..I1-1],
// and right partition is in [I2+1..Idx2]
//
if( (double)(xy[bufs.idxbuf[i1],idxbest])<(double)(tbest) )
{
i1 = i1+1;
continue;
}
if( (double)(xy[bufs.idxbuf[i2],idxbest])>=(double)(tbest) )
{
i2 = i2-1;
continue;
}
j = bufs.idxbuf[i1];
bufs.idxbuf[i1] = bufs.idxbuf[i2];
bufs.idxbuf[i2] = j;
i1 = i1+1;
i2 = i2-1;
}
oldnp = numprocessed;
numprocessed = numprocessed+innernodewidth;
dfbuildtreerec(xy, npoints, nvars, nclasses, nfeatures, nvarsinpool, flags, ref numprocessed, idx1, i1-1, bufs, rs);
bufs.treebuf[oldnp+2] = numprocessed;
dfbuildtreerec(xy, npoints, nvars, nclasses, nfeatures, nvarsinpool, flags, ref numprocessed, i2+1, idx2, bufs, rs);
}
}
/*************************************************************************
Unsets HQRNDState structure
*************************************************************************/
private static void unsetstate(hqrnd.hqrndstate state)
{
state.s1 = 0;
state.s2 = 0;
state.v = 0;
state.magicv = 0;
}
/*************************************************************************
Builds one decision tree. Just a wrapper for the DFBuildTreeRec.
*************************************************************************/
private static void dfbuildtree(double[,] xy,
int npoints,
int nvars,
int nclasses,
int nfeatures,
int nvarsinpool,
int flags,
dfinternalbuffers bufs,
hqrnd.hqrndstate rs)
{
int numprocessed = 0;
int i = 0;
alglib.ap.assert(npoints>0);
//
// Prepare IdxBuf. It stores indices of the training set elements.
// When training set is being split, contents of IdxBuf is
// correspondingly reordered so we can know which elements belong
// to which branch of decision tree.
//
for(i=0; i<=npoints-1; i++)
{
bufs.idxbuf[i] = i;
}
//
// Recursive procedure
//
numprocessed = 1;
dfbuildtreerec(xy, npoints, nvars, nclasses, nfeatures, nvarsinpool, flags, ref numprocessed, 0, npoints-1, bufs, rs);
bufs.treebuf[0] = numprocessed;
}
