/*************************************************************************
Serializer: unserialization
-- ALGLIB --
Copyright 14.03.2011 by Bochkanov Sergey
*************************************************************************/
public static void dfunserialize(alglib.serializer s,
decisionforest forest)
{
int i0 = 0;
int i1 = 0;
//
// check correctness of header
//
i0 = s.unserialize_int();
alglib.ap.assert(i0 == scodes.getrdfserializationcode(), "DFUnserialize: stream header corrupted");
i1 = s.unserialize_int();
alglib.ap.assert(i1 == dffirstversion, "DFUnserialize: stream header corrupted");
//
// Unserialize data
//
forest.nvars = s.unserialize_int();
forest.nclasses = s.unserialize_int();
forest.ntrees = s.unserialize_int();
forest.bufsize = s.unserialize_int();
apserv.unserializerealarray(s, ref forest.trees);
}
/*************************************************************************
Unserialization: complex value
*************************************************************************/
public static void unserializeintegerarray(alglib.serializer s,
ref int[] v)
{
int n = 0;
int i = 0;
int t = 0;
v = new int[0];
n = s.unserialize_int();
if (n == 0)
{
return;
}
v = new int[n];
for (i = 0; i <= n - 1; i++)
{
t = s.unserialize_int();
v[i] = t;
}
}
/*************************************************************************
Serialization: complex value
*************************************************************************/
public static void serializerealmatrix(alglib.serializer s,
double[,] v,
int n0,
int n1)
{
int i = 0;
int j = 0;
if (n0 < 0)
{
n0 = alglib.ap.rows(v);
}
if (n1 < 0)
{
n1 = alglib.ap.cols(v);
}
s.serialize_int(n0);
s.serialize_int(n1);
for (i = 0; i <= n0 - 1; i++)
{
for (j = 0; j <= n1 - 1; j++)
{
s.serialize_double(v[i, j]);
}
}
}
/*************************************************************************
Serialization: complex value
*************************************************************************/
public static void serializerealarray(alglib.serializer s,
double[] v,
int n)
{
int i = 0;
if (n < 0)
{
n = alglib.ap.len(v);
}
s.serialize_int(n);
for (i = 0; i <= n - 1; i++)
{
s.serialize_double(v[i]);
}
}
/*************************************************************************
Allocation of serializer: Integer array
*************************************************************************/
public static void allocintegerarray(alglib.serializer s,
int[] v,
int n)
{
int i = 0;
if (n < 0)
{
n = alglib.ap.len(v);
}
s.alloc_entry();
for (i = 0; i <= n - 1; i++)
{
s.alloc_entry();
}
}
/*************************************************************************
Serializer: unserialization
-- ALGLIB --
Copyright 14.03.2011 by Bochkanov Sergey
*************************************************************************/
public static void kdtreeunserialize(alglib.serializer s,
kdtree tree)
{
int i0 = 0;
int i1 = 0;
//
// check correctness of header
//
i0 = s.unserialize_int();
alglib.ap.assert(i0 == scodes.getkdtreeserializationcode(), "KDTreeUnserialize: stream header corrupted");
i1 = s.unserialize_int();
alglib.ap.assert(i1 == kdtreefirstversion, "KDTreeUnserialize: stream header corrupted");
//
// Unserialize data
//
tree.n = s.unserialize_int();
tree.nx = s.unserialize_int();
tree.ny = s.unserialize_int();
tree.normtype = s.unserialize_int();
apserv.unserializerealmatrix(s, ref tree.xy);
apserv.unserializeintegerarray(s, ref tree.tags);
apserv.unserializerealarray(s, ref tree.boxmin);
apserv.unserializerealarray(s, ref tree.boxmax);
apserv.unserializeintegerarray(s, ref tree.nodes);
apserv.unserializerealarray(s, ref tree.splits);
kdtreealloctemporaries(tree, tree.n, tree.nx, tree.ny);
}
/*************************************************************************
Serialization: complex value
*************************************************************************/
public static void serializecomplex(alglib.serializer s,
complex v)
{
s.serialize_double(v.x);
s.serialize_double(v.y);
}
/*************************************************************************
Calculation of all types of errors
-- ALGLIB --
Copyright 17.02.2009 by Bochkanov Sergey
*************************************************************************/
public static void mlpeallerrorsx(mlpensemble ensemble,
double[,] densexy,
sparse.sparsematrix sparsexy,
int datasetsize,
int datasettype,
int[] idx,
int subset0,
int subset1,
int subsettype,
alglib.smp.shared_pool buf,
mlpbase.modelerrors rep)
{
int i = 0;
int j = 0;
int nin = 0;
int nout = 0;
bool iscls = new bool();
int srcidx = 0;
hpccores.mlpbuffers pbuf = null;
mlpbase.modelerrors rep0 = new mlpbase.modelerrors();
mlpbase.modelerrors rep1 = new mlpbase.modelerrors();
int i_ = 0;
int i1_ = 0;
//
// Get network information
//
nin = mlpbase.mlpgetinputscount(ensemble.network);
nout = mlpbase.mlpgetoutputscount(ensemble.network);
iscls = mlpbase.mlpissoftmax(ensemble.network);
//
// Retrieve buffer, prepare, process data, recycle buffer
//
alglib.smp.ae_shared_pool_retrieve(buf, ref pbuf);
if (iscls)
{
bdss.dserrallocate(nout, ref pbuf.tmp0);
}
else
{
bdss.dserrallocate(-nout, ref pbuf.tmp0);
}
apserv.rvectorsetlengthatleast(ref pbuf.x, nin);
apserv.rvectorsetlengthatleast(ref pbuf.y, nout);
apserv.rvectorsetlengthatleast(ref pbuf.desiredy, nout);
for (i = subset0; i <= subset1 - 1; i++)
{
srcidx = -1;
if (subsettype == 0)
{
srcidx = i;
}
if (subsettype == 1)
{
srcidx = idx[i];
}
alglib.ap.assert(srcidx >= 0, "MLPEAllErrorsX: internal error");
if (datasettype == 0)
{
for (i_ = 0; i_ <= nin - 1; i_++)
{
pbuf.x[i_] = densexy[srcidx, i_];
}
}
if (datasettype == 1)
{
sparse.sparsegetrow(sparsexy, srcidx, ref pbuf.x);
}
mlpeprocess(ensemble, pbuf.x, ref pbuf.y);
if (mlpbase.mlpissoftmax(ensemble.network))
{
if (datasettype == 0)
{
pbuf.desiredy[0] = densexy[srcidx, nin];
}
if (datasettype == 1)
{
pbuf.desiredy[0] = sparse.sparseget(sparsexy, srcidx, nin);
}
}
else
{
if (datasettype == 0)
{
i1_ = (nin) - (0);
for (i_ = 0; i_ <= nout - 1; i_++)
{
pbuf.desiredy[i_] = densexy[srcidx, i_ + i1_];
}
}
if (datasettype == 1)
{
for (j = 0; j <= nout - 1; j++)
{
pbuf.desiredy[j] = sparse.sparseget(sparsexy, srcidx, nin + j);
}
}
}
bdss.dserraccumulate(ref pbuf.tmp0, pbuf.y, pbuf.desiredy);
}
bdss.dserrfinish(ref pbuf.tmp0);
rep.relclserror = pbuf.tmp0[0];
rep.avgce = pbuf.tmp0[1] / Math.Log(2);
rep.rmserror = pbuf.tmp0[2];
rep.avgerror = pbuf.tmp0[3];
rep.avgrelerror = pbuf.tmp0[4];
alglib.smp.ae_shared_pool_recycle(buf, ref pbuf);
}
/*************************************************************************
Serializer: allocation
-- ALGLIB --
Copyright 19.10.2011 by Bochkanov Sergey
*************************************************************************/
public static void mlpealloc(alglib.serializer s,
mlpensemble ensemble)
{
s.alloc_entry();
s.alloc_entry();
s.alloc_entry();
apserv.allocrealarray(s, ensemble.weights, -1);
apserv.allocrealarray(s, ensemble.columnmeans, -1);
apserv.allocrealarray(s, ensemble.columnsigmas, -1);
mlpbase.mlpalloc(s, ensemble.network);
}
/*************************************************************************
Serializer: unserialization
-- ALGLIB --
Copyright 14.03.2011 by Bochkanov Sergey
*************************************************************************/
public static void mlpunserialize(alglib.serializer s,
multilayerperceptron network)
{
int i0 = 0;
int i1 = 0;
int i = 0;
int j = 0;
int k = 0;
int fkind = 0;
double threshold = 0;
double v0 = 0;
double v1 = 0;
int nin = 0;
int nout = 0;
bool issoftmax = new bool();
int[] layersizes = new int[0];
//
// check correctness of header
//
i0 = s.unserialize_int();
alglib.ap.assert(i0 == scodes.getmlpserializationcode(), "MLPUnserialize: stream header corrupted");
i1 = s.unserialize_int();
alglib.ap.assert(i1 == mlpfirstversion, "MLPUnserialize: stream header corrupted");
//
// Create network
//
issoftmax = s.unserialize_bool();
apserv.unserializeintegerarray(s, ref layersizes);
alglib.ap.assert((alglib.ap.len(layersizes) == 2 || alglib.ap.len(layersizes) == 3) || alglib.ap.len(layersizes) == 4, "MLPUnserialize: too many hidden layers!");
nin = layersizes[0];
nout = layersizes[alglib.ap.len(layersizes) - 1];
if (alglib.ap.len(layersizes) == 2)
{
if (issoftmax)
{
mlpcreatec0(layersizes[0], layersizes[1], network);
}
else
{
mlpcreate0(layersizes[0], layersizes[1], network);
}
}
if (alglib.ap.len(layersizes) == 3)
{
if (issoftmax)
{
mlpcreatec1(layersizes[0], layersizes[1], layersizes[2], network);
}
else
{
mlpcreate1(layersizes[0], layersizes[1], layersizes[2], network);
}
}
if (alglib.ap.len(layersizes) == 4)
{
if (issoftmax)
{
mlpcreatec2(layersizes[0], layersizes[1], layersizes[2], layersizes[3], network);
}
else
{
mlpcreate2(layersizes[0], layersizes[1], layersizes[2], layersizes[3], network);
}
}
//
// Load neurons and weights
//
for (i = 1; i <= alglib.ap.len(layersizes) - 1; i++)
{
for (j = 0; j <= layersizes[i] - 1; j++)
{
fkind = s.unserialize_int();
threshold = s.unserialize_double();
mlpsetneuroninfo(network, i, j, fkind, threshold);
for (k = 0; k <= layersizes[i - 1] - 1; k++)
{
v0 = s.unserialize_double();
mlpsetweight(network, i - 1, k, i, j, v0);
}
}
}
//
// Load standartizator
//
for (j = 0; j <= nin - 1; j++)
{
v0 = s.unserialize_double();
v1 = s.unserialize_double();
mlpsetinputscaling(network, j, v0, v1);
}
for (j = 0; j <= nout - 1; j++)
{
v0 = s.unserialize_double();
v1 = s.unserialize_double();
mlpsetoutputscaling(network, j, v0, v1);
}
}
public static void mlpallerrorsx(multilayerperceptron network,
double[,] densexy,
sparse.sparsematrix sparsexy,
int datasetsize,
int datasettype,
int[] idx,
int subset0,
int subset1,
int subsettype,
alglib.smp.shared_pool buf,
modelerrors rep)
{
int nin = 0;
int nout = 0;
int wcount = 0;
int rowsize = 0;
bool iscls = new bool();
int srcidx = 0;
int cstart = 0;
int csize = 0;
int j = 0;
hpccores.mlpbuffers pbuf = null;
int len0 = 0;
int len1 = 0;
modelerrors rep0 = new modelerrors();
modelerrors rep1 = new modelerrors();
int i_ = 0;
int i1_ = 0;
alglib.ap.assert(datasetsize >= 0, "MLPAllErrorsX: SetSize<0");
alglib.ap.assert(datasettype == 0 || datasettype == 1, "MLPAllErrorsX: DatasetType is incorrect");
alglib.ap.assert(subsettype == 0 || subsettype == 1, "MLPAllErrorsX: SubsetType is incorrect");
//
// Determine network properties
//
mlpproperties(network, ref nin, ref nout, ref wcount);
iscls = mlpissoftmax(network);
//
// Split problem.
//
// Splitting problem allows us to reduce effect of single-precision
// arithmetics (SSE-optimized version of MLPChunkedProcess uses single
// precision internally, but converts them to double precision after
// results are exported from HPC buffer to network). Small batches are
// calculated in single precision, results are aggregated in double
// precision, and it allows us to avoid accumulation of errors when
// we process very large batches (tens of thousands of items).
//
// NOTE: it is important to use real arithmetics for ProblemCost
// because ProblemCost may be larger than MAXINT.
//
if (subset1 - subset0 >= 2 * microbatchsize && (double)(apserv.inttoreal(subset1 - subset0) * apserv.inttoreal(wcount)) > (double)(gradbasecasecost))
{
apserv.splitlength(subset1 - subset0, microbatchsize, ref len0, ref len1);
mlpallerrorsx(network, densexy, sparsexy, datasetsize, datasettype, idx, subset0, subset0 + len0, subsettype, buf, rep0);
mlpallerrorsx(network, densexy, sparsexy, datasetsize, datasettype, idx, subset0 + len0, subset1, subsettype, buf, rep1);
rep.relclserror = (len0 * rep0.relclserror + len1 * rep1.relclserror) / (len0 + len1);
rep.avgce = (len0 * rep0.avgce + len1 * rep1.avgce) / (len0 + len1);
rep.rmserror = Math.Sqrt((len0 * math.sqr(rep0.rmserror) + len1 * math.sqr(rep1.rmserror)) / (len0 + len1));
rep.avgerror = (len0 * rep0.avgerror + len1 * rep1.avgerror) / (len0 + len1);
rep.avgrelerror = (len0 * rep0.avgrelerror + len1 * rep1.avgrelerror) / (len0 + len1);
return;
}
//
// Retrieve and prepare
//
alglib.smp.ae_shared_pool_retrieve(buf, ref pbuf);
if (iscls)
{
rowsize = nin + 1;
bdss.dserrallocate(nout, ref pbuf.tmp0);
}
else
{
rowsize = nin + nout;
bdss.dserrallocate(-nout, ref pbuf.tmp0);
}
//
// Processing
//
hpccores.hpcpreparechunkedgradient(network.weights, wcount, mlpntotal(network), nin, nout, pbuf);
cstart = subset0;
while (cstart < subset1)
{
//
// Determine size of current chunk and copy it to PBuf.XY
//
csize = Math.Min(subset1, cstart + pbuf.chunksize) - cstart;
for (j = 0; j <= csize - 1; j++)
{
srcidx = -1;
if (subsettype == 0)
{
srcidx = cstart + j;
}
if (subsettype == 1)
{
srcidx = idx[cstart + j];
}
alglib.ap.assert(srcidx >= 0, "MLPAllErrorsX: internal error");
if (datasettype == 0)
{
for (i_ = 0; i_ <= rowsize - 1; i_++)
{
pbuf.xy[j, i_] = densexy[srcidx, i_];
}
}
if (datasettype == 1)
{
sparse.sparsegetrow(sparsexy, srcidx, ref pbuf.xyrow);
for (i_ = 0; i_ <= rowsize - 1; i_++)
{
pbuf.xy[j, i_] = pbuf.xyrow[i_];
}
}
}
//
// Unpack XY and process (temporary code, to be replaced by chunked processing)
//
for (j = 0; j <= csize - 1; j++)
{
for (i_ = 0; i_ <= rowsize - 1; i_++)
{
pbuf.xy2[j, i_] = pbuf.xy[j, i_];
}
}
mlpchunkedprocess(network, pbuf.xy2, 0, csize, pbuf.batch4buf, pbuf.hpcbuf);
for (j = 0; j <= csize - 1; j++)
{
for (i_ = 0; i_ <= nin - 1; i_++)
{
pbuf.x[i_] = pbuf.xy2[j, i_];
}
i1_ = (nin) - (0);
for (i_ = 0; i_ <= nout - 1; i_++)
{
pbuf.y[i_] = pbuf.xy2[j, i_ + i1_];
}
if (iscls)
{
pbuf.desiredy[0] = pbuf.xy[j, nin];
}
else
{
i1_ = (nin) - (0);
for (i_ = 0; i_ <= nout - 1; i_++)
{
pbuf.desiredy[i_] = pbuf.xy[j, i_ + i1_];
}
}
bdss.dserraccumulate(ref pbuf.tmp0, pbuf.y, pbuf.desiredy);
}
//
// Process chunk and advance line pointer
//
cstart = cstart + pbuf.chunksize;
}
bdss.dserrfinish(ref pbuf.tmp0);
rep.relclserror = pbuf.tmp0[0];
rep.avgce = pbuf.tmp0[1] / Math.Log(2);
rep.rmserror = pbuf.tmp0[2];
rep.avgerror = pbuf.tmp0[3];
rep.avgrelerror = pbuf.tmp0[4];
//
// Recycle
//
alglib.smp.ae_shared_pool_recycle(buf, ref pbuf);
}
/*************************************************************************
Serializer: serialization
-- ALGLIB --
Copyright 14.03.2011 by Bochkanov Sergey
*************************************************************************/
public static void mlpserialize(alglib.serializer s,
multilayerperceptron network)
{
int i = 0;
int j = 0;
int k = 0;
int fkind = 0;
double threshold = 0;
double v0 = 0;
double v1 = 0;
int nin = 0;
int nout = 0;
nin = network.hllayersizes[0];
nout = network.hllayersizes[alglib.ap.len(network.hllayersizes) - 1];
s.serialize_int(scodes.getmlpserializationcode());
s.serialize_int(mlpfirstversion);
s.serialize_bool(mlpissoftmax(network));
apserv.serializeintegerarray(s, network.hllayersizes, -1);
for (i = 1; i <= alglib.ap.len(network.hllayersizes) - 1; i++)
{
for (j = 0; j <= network.hllayersizes[i] - 1; j++)
{
mlpgetneuroninfo(network, i, j, ref fkind, ref threshold);
s.serialize_int(fkind);
s.serialize_double(threshold);
for (k = 0; k <= network.hllayersizes[i - 1] - 1; k++)
{
s.serialize_double(mlpgetweight(network, i - 1, k, i, j));
}
}
}
for (j = 0; j <= nin - 1; j++)
{
mlpgetinputscaling(network, j, ref v0, ref v1);
s.serialize_double(v0);
s.serialize_double(v1);
}
for (j = 0; j <= nout - 1; j++)
{
mlpgetoutputscaling(network, j, ref v0, ref v1);
s.serialize_double(v0);
s.serialize_double(v1);
}
}
/*************************************************************************
Serializer: allocation
-- ALGLIB --
Copyright 14.03.2011 by Bochkanov Sergey
*************************************************************************/
public static void mlpalloc(alglib.serializer s,
multilayerperceptron network)
{
int i = 0;
int j = 0;
int k = 0;
int fkind = 0;
double threshold = 0;
double v0 = 0;
double v1 = 0;
int nin = 0;
int nout = 0;
nin = network.hllayersizes[0];
nout = network.hllayersizes[alglib.ap.len(network.hllayersizes) - 1];
s.alloc_entry();
s.alloc_entry();
s.alloc_entry();
apserv.allocintegerarray(s, network.hllayersizes, -1);
for (i = 1; i <= alglib.ap.len(network.hllayersizes) - 1; i++)
{
for (j = 0; j <= network.hllayersizes[i] - 1; j++)
{
mlpgetneuroninfo(network, i, j, ref fkind, ref threshold);
s.alloc_entry();
s.alloc_entry();
for (k = 0; k <= network.hllayersizes[i - 1] - 1; k++)
{
s.alloc_entry();
}
}
}
for (j = 0; j <= nin - 1; j++)
{
mlpgetinputscaling(network, j, ref v0, ref v1);
s.alloc_entry();
s.alloc_entry();
}
for (j = 0; j <= nout - 1; j++)
{
mlpgetoutputscaling(network, j, ref v0, ref v1);
s.alloc_entry();
s.alloc_entry();
}
}
public static void mlpgradbatchx(multilayerperceptron network,
double[,] densexy,
sparse.sparsematrix sparsexy,
int datasetsize,
int datasettype,
int[] idx,
int subset0,
int subset1,
int subsettype,
alglib.smp.shared_pool buf,
alglib.smp.shared_pool gradbuf)
{
int nin = 0;
int nout = 0;
int wcount = 0;
int rowsize = 0;
int srcidx = 0;
int cstart = 0;
int csize = 0;
int j = 0;
double problemcost = 0;
hpccores.mlpbuffers buf2 = null;
int len0 = 0;
int len1 = 0;
hpccores.mlpbuffers pbuf = null;
smlpgrad sgrad = null;
int i_ = 0;
alglib.ap.assert(datasetsize >= 0, "MLPGradBatchX: SetSize<0");
alglib.ap.assert(datasettype == 0 || datasettype == 1, "MLPGradBatchX: DatasetType is incorrect");
alglib.ap.assert(subsettype == 0 || subsettype == 1, "MLPGradBatchX: SubsetType is incorrect");
//
// Determine network and dataset properties
//
mlpproperties(network, ref nin, ref nout, ref wcount);
if (mlpissoftmax(network))
{
rowsize = nin + 1;
}
else
{
rowsize = nin + nout;
}
//
// Split problem.
//
// Splitting problem allows us to reduce effect of single-precision
// arithmetics (SSE-optimized version of MLPChunkedGradient uses single
// precision internally, but converts them to double precision after
// results are exported from HPC buffer to network). Small batches are
// calculated in single precision, results are aggregated in double
// precision, and it allows us to avoid accumulation of errors when
// we process very large batches (tens of thousands of items).
//
// NOTE: it is important to use real arithmetics for ProblemCost
// because ProblemCost may be larger than MAXINT.
//
problemcost = subset1 - subset0;
problemcost = problemcost * wcount;
if (subset1 - subset0 >= 2 * microbatchsize && (double)(problemcost) > (double)(gradbasecasecost))
{
apserv.splitlength(subset1 - subset0, microbatchsize, ref len0, ref len1);
mlpgradbatchx(network, densexy, sparsexy, datasetsize, datasettype, idx, subset0, subset0 + len0, subsettype, buf, gradbuf);
mlpgradbatchx(network, densexy, sparsexy, datasetsize, datasettype, idx, subset0 + len0, subset1, subsettype, buf, gradbuf);
return;
}
//
// Chunked processing
//
alglib.smp.ae_shared_pool_retrieve(gradbuf, ref sgrad);
alglib.smp.ae_shared_pool_retrieve(buf, ref pbuf);
hpccores.hpcpreparechunkedgradient(network.weights, wcount, mlpntotal(network), nin, nout, pbuf);
cstart = subset0;
while (cstart < subset1)
{
//
// Determine size of current chunk and copy it to PBuf.XY
//
csize = Math.Min(subset1, cstart + pbuf.chunksize) - cstart;
for (j = 0; j <= csize - 1; j++)
{
srcidx = -1;
if (subsettype == 0)
{
srcidx = cstart + j;
}
if (subsettype == 1)
{
srcidx = idx[cstart + j];
}
alglib.ap.assert(srcidx >= 0, "MLPGradBatchX: internal error");
if (datasettype == 0)
{
for (i_ = 0; i_ <= rowsize - 1; i_++)
{
pbuf.xy[j, i_] = densexy[srcidx, i_];
}
}
if (datasettype == 1)
{
sparse.sparsegetrow(sparsexy, srcidx, ref pbuf.xyrow);
for (i_ = 0; i_ <= rowsize - 1; i_++)
{
pbuf.xy[j, i_] = pbuf.xyrow[i_];
}
}
}
//
// Process chunk and advance line pointer
//
mlpchunkedgradient(network, pbuf.xy, 0, csize, pbuf.batch4buf, pbuf.hpcbuf, ref sgrad.f, false);
cstart = cstart + pbuf.chunksize;
}
hpccores.hpcfinalizechunkedgradient(pbuf, sgrad.g);
alglib.smp.ae_shared_pool_recycle(buf, ref pbuf);
alglib.smp.ae_shared_pool_recycle(gradbuf, ref sgrad);
}
/*************************************************************************
Serializer: allocation
-- ALGLIB --
Copyright 14.03.2011 by Bochkanov Sergey
*************************************************************************/
public static void kdtreealloc(alglib.serializer s,
kdtree tree)
{
//
// Header
//
s.alloc_entry();
s.alloc_entry();
//
// Data
//
s.alloc_entry();
s.alloc_entry();
s.alloc_entry();
s.alloc_entry();
apserv.allocrealmatrix(s, tree.xy, -1, -1);
apserv.allocintegerarray(s, tree.tags, -1);
apserv.allocrealarray(s, tree.boxmin, -1);
apserv.allocrealarray(s, tree.boxmax, -1);
apserv.allocintegerarray(s, tree.nodes, -1);
apserv.allocrealarray(s, tree.splits, -1);
}
/*************************************************************************
Serializer: serialization
-- ALGLIB --
Copyright 14.03.2011 by Bochkanov Sergey
*************************************************************************/
public static void mlpeserialize(alglib.serializer s,
mlpensemble ensemble)
{
s.serialize_int(scodes.getmlpeserializationcode());
s.serialize_int(mlpefirstversion);
s.serialize_int(ensemble.ensemblesize);
apserv.serializerealarray(s, ensemble.weights, -1);
apserv.serializerealarray(s, ensemble.columnmeans, -1);
apserv.serializerealarray(s, ensemble.columnsigmas, -1);
mlpbase.mlpserialize(s, ensemble.network);
}
/*************************************************************************
Serializer: serialization
-- ALGLIB --
Copyright 14.03.2011 by Bochkanov Sergey
*************************************************************************/
public static void kdtreeserialize(alglib.serializer s,
kdtree tree)
{
//
// Header
//
s.serialize_int(scodes.getkdtreeserializationcode());
s.serialize_int(kdtreefirstversion);
//
// Data
//
s.serialize_int(tree.n);
s.serialize_int(tree.nx);
s.serialize_int(tree.ny);
s.serialize_int(tree.normtype);
apserv.serializerealmatrix(s, tree.xy, -1, -1);
apserv.serializeintegerarray(s, tree.tags, -1);
apserv.serializerealarray(s, tree.boxmin, -1);
apserv.serializerealarray(s, tree.boxmax, -1);
apserv.serializeintegerarray(s, tree.nodes, -1);
apserv.serializerealarray(s, tree.splits, -1);
}
/*************************************************************************
Serializer: unserialization
-- ALGLIB --
Copyright 14.03.2011 by Bochkanov Sergey
*************************************************************************/
public static void mlpeunserialize(alglib.serializer s,
mlpensemble ensemble)
{
int i0 = 0;
int i1 = 0;
//
// check correctness of header
//
i0 = s.unserialize_int();
alglib.ap.assert(i0 == scodes.getmlpeserializationcode(), "MLPEUnserialize: stream header corrupted");
i1 = s.unserialize_int();
alglib.ap.assert(i1 == mlpefirstversion, "MLPEUnserialize: stream header corrupted");
//
// Create network
//
ensemble.ensemblesize = s.unserialize_int();
apserv.unserializerealarray(s, ref ensemble.weights);
apserv.unserializerealarray(s, ref ensemble.columnmeans);
apserv.unserializerealarray(s, ref ensemble.columnsigmas);
mlpbase.mlpunserialize(s, ensemble.network);
//
// Allocate termoraries
//
ensemble.y = new double[mlpbase.mlpgetoutputscount(ensemble.network)];
}
/*************************************************************************
Allocation of serializer: complex value
*************************************************************************/
public static void alloccomplex(alglib.serializer s,
complex v)
{
s.alloc_entry();
s.alloc_entry();
}
private static void mthreadcv(mlptrainer s,
int rowsize,
int nrestarts,
int[] folds,
int fold,
int dfold,
double[,] cvy,
alglib.smp.shared_pool pooldatacv)
{
mlpparallelizationcv datacv = null;
int i = 0;
int i_ = 0;
if (fold == dfold - 1)
{
//
// Separate set
//
alglib.smp.ae_shared_pool_retrieve(pooldatacv, ref datacv);
datacv.subsetsize = 0;
for (i = 0; i <= s.npoints - 1; i++)
{
if (folds[i] != fold)
{
datacv.subset[datacv.subsetsize] = i;
datacv.subsetsize = datacv.subsetsize + 1;
}
}
//
// Train on CV training set
//
mlptrainnetworkx(s, nrestarts, -1, datacv.subset, datacv.subsetsize, datacv.subset, 0, datacv.network, datacv.rep, true, datacv.trnpool);
datacv.ngrad = datacv.ngrad + datacv.rep.ngrad;
//
// Estimate error using CV test set
//
for (i = 0; i <= s.npoints - 1; i++)
{
if (folds[i] == fold)
{
if (s.datatype == 0)
{
for (i_ = 0; i_ <= rowsize - 1; i_++)
{
datacv.xyrow[i_] = s.densexy[i, i_];
}
}
if (s.datatype == 1)
{
sparse.sparsegetrow(s.sparsexy, i, ref datacv.xyrow);
}
mlpbase.mlpprocess(datacv.network, datacv.xyrow, ref datacv.y);
for (i_ = 0; i_ <= s.nout - 1; i_++)
{
cvy[i, i_] = datacv.y[i_];
}
}
}
alglib.smp.ae_shared_pool_recycle(pooldatacv, ref datacv);
}
else
{
alglib.ap.assert(fold < dfold - 1, "MThreadCV: internal error(Fold>DFold-1).");
mthreadcv(s, rowsize, nrestarts, folds, fold, (fold + dfold) / 2, cvy, pooldatacv);
mthreadcv(s, rowsize, nrestarts, folds, (fold + dfold) / 2, dfold, cvy, pooldatacv);
}
}
/*************************************************************************
Unserialization: complex value
*************************************************************************/
public static complex unserializecomplex(alglib.serializer s)
{
complex result = 0;
result.x = s.unserialize_double();
result.y = s.unserialize_double();
return result;
}
private static void mlptrainnetworkx(mlptrainer s,
int nrestarts,
int algokind,
int[] trnsubset,
int trnsubsetsize,
int[] valsubset,
int valsubsetsize,
mlpbase.multilayerperceptron network,
mlpreport rep,
bool isrootcall,
alglib.smp.shared_pool sessions)
{
mlpbase.modelerrors modrep = new mlpbase.modelerrors();
double eval = 0;
double ebest = 0;
int ngradbatch = 0;
int nin = 0;
int nout = 0;
int wcount = 0;
int pcount = 0;
int itbest = 0;
int itcnt = 0;
int ntype = 0;
int ttype = 0;
bool rndstart = new bool();
int i = 0;
int nr0 = 0;
int nr1 = 0;
mlpreport rep0 = new mlpreport();
mlpreport rep1 = new mlpreport();
bool randomizenetwork = new bool();
double bestrmserror = 0;
smlptrnsession psession = null;
int i_ = 0;
mlpbase.mlpproperties(network, ref nin, ref nout, ref wcount);
//
// Process root call
//
if (isrootcall)
{
//
// Check correctness of parameters
//
alglib.ap.assert(algokind == 0 || algokind == -1, "MLPTrainNetworkX: unexpected AlgoKind");
alglib.ap.assert(s.npoints >= 0, "MLPTrainNetworkX: internal error - parameter S is not initialized or is spoiled(S.NPoints<0)");
if (s.rcpar)
{
ttype = 0;
}
else
{
ttype = 1;
}
if (!mlpbase.mlpissoftmax(network))
{
ntype = 0;
}
else
{
ntype = 1;
}
alglib.ap.assert(ntype == ttype, "MLPTrainNetworkX: internal error - type of the training network is not similar to network type in trainer object");
alglib.ap.assert(s.nin == nin, "MLPTrainNetworkX: internal error - number of inputs in trainer is not equal to number of inputs in the training network.");
alglib.ap.assert(s.nout == nout, "MLPTrainNetworkX: internal error - number of outputs in trainer is not equal to number of outputs in the training network.");
alglib.ap.assert(nrestarts >= 0, "MLPTrainNetworkX: internal error - NRestarts<0.");
alglib.ap.assert(alglib.ap.len(trnsubset) >= trnsubsetsize, "MLPTrainNetworkX: internal error - parameter TrnSubsetSize more than input subset size(Length(TrnSubset)<TrnSubsetSize)");
for (i = 0; i <= trnsubsetsize - 1; i++)
{
alglib.ap.assert(trnsubset[i] >= 0 && trnsubset[i] <= s.npoints - 1, "MLPTrainNetworkX: internal error - parameter TrnSubset contains incorrect index(TrnSubset[I]<0 or TrnSubset[I]>S.NPoints-1)");
}
alglib.ap.assert(alglib.ap.len(valsubset) >= valsubsetsize, "MLPTrainNetworkX: internal error - parameter ValSubsetSize more than input subset size(Length(ValSubset)<ValSubsetSize)");
for (i = 0; i <= valsubsetsize - 1; i++)
{
alglib.ap.assert(valsubset[i] >= 0 && valsubset[i] <= s.npoints - 1, "MLPTrainNetworkX: internal error - parameter ValSubset contains incorrect index(ValSubset[I]<0 or ValSubset[I]>S.NPoints-1)");
}
//
// Train
//
randomizenetwork = nrestarts > 0;
initmlptrnsessions(network, randomizenetwork, s, sessions);
mlptrainnetworkx(s, nrestarts, algokind, trnsubset, trnsubsetsize, valsubset, valsubsetsize, network, rep, false, sessions);
//
// Choose best network
//
bestrmserror = math.maxrealnumber;
alglib.smp.ae_shared_pool_first_recycled(sessions, ref psession);
while (psession != null)
{
if ((double)(psession.bestrmserror) < (double)(bestrmserror))
{
mlpbase.mlpimporttunableparameters(network, psession.bestparameters);
bestrmserror = psession.bestrmserror;
}
alglib.smp.ae_shared_pool_next_recycled(sessions, ref psession);
}
//
// Calculate errors
//
if (s.datatype == 0)
{
mlpbase.mlpallerrorssubset(network, s.densexy, s.npoints, trnsubset, trnsubsetsize, modrep);
}
if (s.datatype == 1)
{
mlpbase.mlpallerrorssparsesubset(network, s.sparsexy, s.npoints, trnsubset, trnsubsetsize, modrep);
}
rep.relclserror = modrep.relclserror;
rep.avgce = modrep.avgce;
rep.rmserror = modrep.rmserror;
rep.avgerror = modrep.avgerror;
rep.avgrelerror = modrep.avgrelerror;
//
// Done
//
return;
}
//
// Split problem, if we have more than 1 restart
//
if (nrestarts >= 2)
{
//
// Divide problem with NRestarts into two: NR0 and NR1.
//
nr0 = nrestarts / 2;
nr1 = nrestarts - nr0;
mlptrainnetworkx(s, nr0, algokind, trnsubset, trnsubsetsize, valsubset, valsubsetsize, network, rep0, false, sessions);
mlptrainnetworkx(s, nr1, algokind, trnsubset, trnsubsetsize, valsubset, valsubsetsize, network, rep1, false, sessions);
//
// Aggregate results
//
rep.ngrad = rep0.ngrad + rep1.ngrad;
rep.nhess = rep0.nhess + rep1.nhess;
rep.ncholesky = rep0.ncholesky + rep1.ncholesky;
//
// Done :)
//
return;
}
//
// Execution with NRestarts=1 or NRestarts=0:
// * NRestarts=1 means that network is restarted from random position
// * NRestarts=0 means that network is not randomized
//
alglib.ap.assert(nrestarts == 0 || nrestarts == 1, "MLPTrainNetworkX: internal error");
rep.ngrad = 0;
rep.nhess = 0;
rep.ncholesky = 0;
alglib.smp.ae_shared_pool_retrieve(sessions, ref psession);
if (((s.datatype == 0 || s.datatype == 1) && s.npoints > 0) && trnsubsetsize != 0)
{
//
// Train network using combination of early stopping and step-size
// and step-count based criteria. Network state with best value of
// validation set error is stored in WBuf0. When validation set is
// zero, most recent state of network is stored.
//
rndstart = nrestarts != 0;
ngradbatch = 0;
eval = 0;
ebest = 0;
itbest = 0;
itcnt = 0;
mlpstarttrainingx(s, rndstart, algokind, trnsubset, trnsubsetsize, psession);
if (s.datatype == 0)
{
ebest = mlpbase.mlperrorsubset(psession.network, s.densexy, s.npoints, valsubset, valsubsetsize);
}
if (s.datatype == 1)
{
ebest = mlpbase.mlperrorsparsesubset(psession.network, s.sparsexy, s.npoints, valsubset, valsubsetsize);
}
for (i_ = 0; i_ <= wcount - 1; i_++)
{
psession.wbuf0[i_] = psession.network.weights[i_];
}
while (mlpcontinuetrainingx(s, trnsubset, trnsubsetsize, ref ngradbatch, psession))
{
if (s.datatype == 0)
{
eval = mlpbase.mlperrorsubset(psession.network, s.densexy, s.npoints, valsubset, valsubsetsize);
}
if (s.datatype == 1)
{
eval = mlpbase.mlperrorsparsesubset(psession.network, s.sparsexy, s.npoints, valsubset, valsubsetsize);
}
if ((double)(eval) <= (double)(ebest) || valsubsetsize == 0)
{
for (i_ = 0; i_ <= wcount - 1; i_++)
{
psession.wbuf0[i_] = psession.network.weights[i_];
}
ebest = eval;
itbest = itcnt;
}
if (itcnt > 30 && (double)(itcnt) > (double)(1.5 * itbest))
{
break;
}
itcnt = itcnt + 1;
}
for (i_ = 0; i_ <= wcount - 1; i_++)
{
psession.network.weights[i_] = psession.wbuf0[i_];
}
rep.ngrad = ngradbatch;
}
else
{
for (i = 0; i <= wcount - 1; i++)
{
psession.network.weights[i] = 0;
}
}
//
// Evaluate network performance and update PSession.BestParameters/BestRMSError
// (if needed).
//
if (s.datatype == 0)
{
mlpbase.mlpallerrorssubset(psession.network, s.densexy, s.npoints, trnsubset, trnsubsetsize, modrep);
}
if (s.datatype == 1)
{
mlpbase.mlpallerrorssparsesubset(psession.network, s.sparsexy, s.npoints, trnsubset, trnsubsetsize, modrep);
}
if ((double)(modrep.rmserror) < (double)(psession.bestrmserror))
{
mlpbase.mlpexporttunableparameters(psession.network, ref psession.bestparameters, ref pcount);
psession.bestrmserror = modrep.rmserror;
}
//
// Move session back to pool
//
alglib.smp.ae_shared_pool_recycle(sessions, ref psession);
}
/*************************************************************************
Unserialization: complex value
*************************************************************************/
public static void unserializerealarray(alglib.serializer s,
ref double[] v)
{
int n = 0;
int i = 0;
double t = 0;
v = new double[0];
n = s.unserialize_int();
if (n == 0)
{
return;
}
v = new double[n];
for (i = 0; i <= n - 1; i++)
{
t = s.unserialize_double();
v[i] = t;
}
}
private static void mlptrainensemblex(mlptrainer s,
mlpe.mlpensemble ensemble,
int idx0,
int idx1,
int nrestarts,
int trainingmethod,
apserv.sinteger ngrad,
bool isrootcall,
alglib.smp.shared_pool esessions)
{
int pcount = 0;
int nin = 0;
int nout = 0;
int wcount = 0;
int i = 0;
int j = 0;
int k = 0;
int trnsubsetsize = 0;
int valsubsetsize = 0;
int k0 = 0;
apserv.sinteger ngrad0 = new apserv.sinteger();
apserv.sinteger ngrad1 = new apserv.sinteger();
mlpetrnsession psession = null;
hqrnd.hqrndstate rs = new hqrnd.hqrndstate();
int i_ = 0;
int i1_ = 0;
nin = mlpbase.mlpgetinputscount(ensemble.network);
nout = mlpbase.mlpgetoutputscount(ensemble.network);
wcount = mlpbase.mlpgetweightscount(ensemble.network);
if (mlpbase.mlpissoftmax(ensemble.network))
{
pcount = nin;
}
else
{
pcount = nin + nout;
}
if (nrestarts <= 0)
{
nrestarts = 1;
}
//
// Handle degenerate case
//
if (s.npoints < 2)
{
for (i = idx0; i <= idx1 - 1; i++)
{
for (j = 0; j <= wcount - 1; j++)
{
ensemble.weights[i * wcount + j] = 0.0;
}
for (j = 0; j <= pcount - 1; j++)
{
ensemble.columnmeans[i * pcount + j] = 0.0;
ensemble.columnsigmas[i * pcount + j] = 1.0;
}
}
return;
}
//
// Process root call
//
if (isrootcall)
{
//
// Prepare:
// * prepare MLPETrnSessions
// * fill ensemble by zeros (helps to detect errors)
//
initmlpetrnsessions(ensemble.network, s, esessions);
for (i = idx0; i <= idx1 - 1; i++)
{
for (j = 0; j <= wcount - 1; j++)
{
ensemble.weights[i * wcount + j] = 0.0;
}
for (j = 0; j <= pcount - 1; j++)
{
ensemble.columnmeans[i * pcount + j] = 0.0;
ensemble.columnsigmas[i * pcount + j] = 0.0;
}
}
//
// Train in non-root mode and exit
//
mlptrainensemblex(s, ensemble, idx0, idx1, nrestarts, trainingmethod, ngrad, false, esessions);
return;
}
//
// Split problem
//
if (idx1 - idx0 >= 2)
{
k0 = (idx1 - idx0) / 2;
ngrad0.val = 0;
ngrad1.val = 0;
mlptrainensemblex(s, ensemble, idx0, idx0 + k0, nrestarts, trainingmethod, ngrad0, false, esessions);
mlptrainensemblex(s, ensemble, idx0 + k0, idx1, nrestarts, trainingmethod, ngrad1, false, esessions);
ngrad.val = ngrad0.val + ngrad1.val;
return;
}
//
// Retrieve and prepare session
//
alglib.smp.ae_shared_pool_retrieve(esessions, ref psession);
//
// Train
//
hqrnd.hqrndrandomize(rs);
for (k = idx0; k <= idx1 - 1; k++)
{
//
// Split set
//
trnsubsetsize = 0;
valsubsetsize = 0;
if (trainingmethod == 0)
{
do
{
trnsubsetsize = 0;
valsubsetsize = 0;
for (i = 0; i <= s.npoints - 1; i++)
{
if ((double)(math.randomreal()) < (double)(0.66))
{
//
// Assign sample to training set
//
psession.trnsubset[trnsubsetsize] = i;
trnsubsetsize = trnsubsetsize + 1;
}
else
{
//
// Assign sample to validation set
//
psession.valsubset[valsubsetsize] = i;
valsubsetsize = valsubsetsize + 1;
}
}
}
while (!(trnsubsetsize != 0 && valsubsetsize != 0));
}
if (trainingmethod == 1)
{
valsubsetsize = 0;
trnsubsetsize = s.npoints;
for (i = 0; i <= s.npoints - 1; i++)
{
psession.trnsubset[i] = hqrnd.hqrnduniformi(rs, s.npoints);
}
}
//
// Train
//
mlptrainnetworkx(s, nrestarts, -1, psession.trnsubset, trnsubsetsize, psession.valsubset, valsubsetsize, psession.network, psession.mlprep, true, psession.mlpsessions);
ngrad.val = ngrad.val + psession.mlprep.ngrad;
//
// Save results
//
i1_ = (0) - (k * wcount);
for (i_ = k * wcount; i_ <= (k + 1) * wcount - 1; i_++)
{
ensemble.weights[i_] = psession.network.weights[i_ + i1_];
}
i1_ = (0) - (k * pcount);
for (i_ = k * pcount; i_ <= (k + 1) * pcount - 1; i_++)
{
ensemble.columnmeans[i_] = psession.network.columnmeans[i_ + i1_];
}
i1_ = (0) - (k * pcount);
for (i_ = k * pcount; i_ <= (k + 1) * pcount - 1; i_++)
{
ensemble.columnsigmas[i_] = psession.network.columnsigmas[i_ + i1_];
}
}
//
// Recycle session
//
alglib.smp.ae_shared_pool_recycle(esessions, ref psession);
}
/*************************************************************************
Serialization: Integer array
*************************************************************************/
public static void serializeintegerarray(alglib.serializer s,
int[] v,
int n)
{
int i = 0;
if (n < 0)
{
n = alglib.ap.len(v);
}
s.serialize_int(n);
for (i = 0; i <= n - 1; i++)
{
s.serialize_int(v[i]);
}
}
/*************************************************************************
This function initializes temporaries needed for training session.
*************************************************************************/
private static void initmlptrnsessions(mlpbase.multilayerperceptron networktrained,
bool randomizenetwork,
mlptrainer trainer,
alglib.smp.shared_pool sessions)
{
int[] dummysubset = new int[0];
smlptrnsession t = new smlptrnsession();
smlptrnsession p = null;
if (alglib.smp.ae_shared_pool_is_initialized(sessions))
{
//
// Pool was already initialized.
// Clear sessions stored in the pool.
//
alglib.smp.ae_shared_pool_first_recycled(sessions, ref p);
while (p != null)
{
alglib.ap.assert(mlpbase.mlpsamearchitecture(p.network, networktrained), "InitMLPTrnSessions: internal consistency error");
p.bestrmserror = math.maxrealnumber;
alglib.smp.ae_shared_pool_next_recycled(sessions, ref p);
}
}
else
{
//
// Prepare session and seed pool
//
initmlptrnsession(networktrained, randomizenetwork, trainer, t);
alglib.smp.ae_shared_pool_set_seed(sessions, t);
}
}
/*************************************************************************
Allocation of serializer: real matrix
*************************************************************************/
public static void allocrealmatrix(alglib.serializer s,
double[,] v,
int n0,
int n1)
{
int i = 0;
int j = 0;
if (n0 < 0)
{
n0 = alglib.ap.rows(v);
}
if (n1 < 0)
{
n1 = alglib.ap.cols(v);
}
s.alloc_entry();
s.alloc_entry();
for (i = 0; i <= n0 - 1; i++)
{
for (j = 0; j <= n1 - 1; j++)
{
s.alloc_entry();
}
}
}
/*************************************************************************
This function initializes temporaries needed for training session.
*************************************************************************/
private static void initmlpetrnsessions(mlpbase.multilayerperceptron individualnetwork,
mlptrainer trainer,
alglib.smp.shared_pool sessions)
{
mlpetrnsession t = new mlpetrnsession();
if (!alglib.smp.ae_shared_pool_is_initialized(sessions))
{
initmlpetrnsession(individualnetwork, trainer, t);
alglib.smp.ae_shared_pool_set_seed(sessions, t);
}
}
/*************************************************************************
Unserialization: complex value
*************************************************************************/
public static void unserializerealmatrix(alglib.serializer s,
ref double[,] v)
{
int i = 0;
int j = 0;
int n0 = 0;
int n1 = 0;
double t = 0;
v = new double[0, 0];
n0 = s.unserialize_int();
n1 = s.unserialize_int();
if (n0 == 0 || n1 == 0)
{
return;
}
v = new double[n0, n1];
for (i = 0; i <= n0 - 1; i++)
{
for (j = 0; j <= n1 - 1; j++)
{
t = s.unserialize_double();
v[i, j] = t;
}
}
}
/*************************************************************************
Serializer: serialization
-- ALGLIB --
Copyright 14.03.2011 by Bochkanov Sergey
*************************************************************************/
public static void dfserialize(alglib.serializer s,
decisionforest forest)
{
s.serialize_int(scodes.getrdfserializationcode());
s.serialize_int(dffirstversion);
s.serialize_int(forest.nvars);
s.serialize_int(forest.nclasses);
s.serialize_int(forest.ntrees);
s.serialize_int(forest.bufsize);
apserv.serializerealarray(s, forest.trees, forest.bufsize);
}