int TGnuPlot::AddPlot(const TIntFltPrV& XYValV, const TGpSeriesTy& SeriesTy, const TStr& Label, const TStr& Style) {
TFltKdV XYFltValV(XYValV.Len(), 0);
for (int i = 0; i < XYValV.Len(); i++) {
XYFltValV.Add(TFltKd(TFlt(XYValV[i].Val1), TFlt(XYValV[i].Val2)));
}
return AddPlot(XYFltValV, SeriesTy, Label, Style);
}
void TSkyGridEnt::GetEntClustV(const TSkyGridBs* SkyGridBs,
const uint64& MnTm, const int& MnDocs, const int& MxDocs, const int& Clusts,
TVec<TStrFltPrV>& EntNmWgtPrVV) const {
EntNmWgtPrVV.Clr();
// create bow
PBowDocBs BowDocBs=TBowDocBs::New();
// collect documents
TIntV DocIdV; GetDocIdV(SkyGridBs, MnTm, 0, DocIdV);
DocIdV.Reverse(); DocIdV.Shuffle(TRnd(1)); DocIdV.Trunc(MxDocs);
if (DocIdV.Len()<MnDocs){return;}
for (int DocN=0; DocN<DocIdV.Len(); DocN++){
int DocId=DocIdV[DocN];
PSkyGridDoc Doc=SkyGridBs->GetDoc(DocId);
// create vector of entity-weights
TIntFltPrV WIdWgtPrV;
for (int EntN=0; EntN<Doc->GetEnts(); EntN++){
int EntId; int EntFq; Doc->GetEntNmFq(EntN, EntId, EntFq);
TStr EntNm=SkyGridBs->GetEntNm(EntId);
int EntWId=BowDocBs->AddWordStr(EntNm);
WIdWgtPrV.Add(TIntFltPr(EntWId, EntFq));
}
// create bow-document
int DId=BowDocBs->AddDoc(TInt::GetStr(DocId), TStrV(), WIdWgtPrV);
TStr DocDescStr=Doc->GetTitleStr();
BowDocBs->PutDocDescStr(DId, DocDescStr);
}
// k-means clustering
PBowSim BowSim=TBowSim::New(bstCos); // similarity object
TBowWordWgtType WordWgtType=bwwtNrmTFIDF; // define weighting
PBowDocPart BowDocPart=TBowClust::GetKMeansPart(
TNotify::StdNotify, // log output
BowDocBs, // document data
BowSim, // similarity function
TRnd(1), // random generator
Clusts, // number of clusters
1, // trials per k-means
1, // convergence epsilon for k-means
1, // min. documents per cluster
WordWgtType, // word weighting
0, // cut-word-weights percentage
0); // minimal word frequency
EntNmWgtPrVV.Clr();
for (int ClustN=0; ClustN<BowDocPart->GetClusts(); ClustN++){
PBowDocPartClust Clust=BowDocPart->GetClust(ClustN);
TStrFltPrV WordStrWgtPrV;
Clust->GetTopWordStrWgtPrV(BowDocBs, 25, 0.5, WordStrWgtPrV);
EntNmWgtPrVV.Add(WordStrWgtPrV);
}
//BowDocPart->SaveTxt("Clusts.Txt", BowDocBs, true, 25, 0.5, false);
}
TStr TStrUtil::GetStr(const TIntFltPrV& IntFltPrV, const TStr& FieldDelimiterStr,
const TStr& DelimiterStr, const TStr& FmtStr) {
TChA ResChA;
for (int i = 0; i < IntFltPrV.Len(); i++) {
if (!ResChA.Empty()) { ResChA += DelimiterStr; }
ResChA += IntFltPrV[i].Val1.GetStr();
ResChA += FieldDelimiterStr;
ResChA += TFlt::GetStr(IntFltPrV[i].Val2, FmtStr);
}
return ResChA;
}
int TAGMFast::MLEGradAscentParallel(const double& Thres, const int& MaxIter, const int ChunkNum, const int ChunkSize, const TStr PlotNm, const double StepAlpha, const double StepBeta) {
//parallel
time_t InitTime = time(NULL);
uint64 StartTm = TSecTm::GetCurTm().GetAbsSecs();
TExeTm ExeTm, CheckTm;
double PrevL = Likelihood(true);
TIntFltPrV IterLV;
int PrevIter = 0;
int iter = 0;
TIntV NIdxV(F.Len(), 0);
for (int i = 0; i < F.Len(); i++) { NIdxV.Add(i); }
TIntV NIDOPTV(F.Len()); //check if a node needs optimization or not 1: does not require optimization
NIDOPTV.PutAll(0);
TVec<TIntFltH> NewF(ChunkNum * ChunkSize);
TIntV NewNIDV(ChunkNum * ChunkSize);
for (iter = 0; iter < MaxIter; iter++) {
NIdxV.Clr(false);
for (int i = 0; i < F.Len(); i++) {
if (NIDOPTV[i] == 0) { NIdxV.Add(i); }
}
IAssert (NIdxV.Len() <= F.Len());
NIdxV.Shuffle(Rnd);
// compute gradient for chunk of nodes
#pragma omp parallel for schedule(static, 1)
for (int TIdx = 0; TIdx < ChunkNum; TIdx++) {
TIntFltH GradV;
for (int ui = TIdx * ChunkSize; ui < (TIdx + 1) * ChunkSize; ui++) {
NewNIDV[ui] = -1;
if (ui > NIdxV.Len()) { continue; }
int u = NIdxV[ui]; //
//find set of candidate c (we only need to consider c to which a neighbor of u belongs to)
TUNGraph::TNodeI UI = G->GetNI(u);
TIntSet CIDSet(5 * UI.GetDeg());
TIntFltH CurFU = F[u];
for (int e = 0; e < UI.GetDeg(); e++) {
if (HOVIDSV[u].IsKey(UI.GetNbrNId(e))) { continue; }
TIntFltH& NbhCIDH = F[UI.GetNbrNId(e)];
for (TIntFltH::TIter CI = NbhCIDH.BegI(); CI < NbhCIDH.EndI(); CI++) {
CIDSet.AddKey(CI.GetKey());
}
}
if (CIDSet.Empty()) {
CurFU.Clr();
}
else {
for (TIntFltH::TIter CI = CurFU.BegI(); CI < CurFU.EndI(); CI++) { //remove the community membership which U does not share with its neighbors
if (! CIDSet.IsKey(CI.GetKey())) {
CurFU.DelIfKey(CI.GetKey());
}
}
GradientForRow(u, GradV, CIDSet);
if (Norm2(GradV) < 1e-4) { NIDOPTV[u] = 1; continue; }
double LearnRate = GetStepSizeByLineSearch(u, GradV, GradV, StepAlpha, StepBeta, 5);
if (LearnRate <= 1e-5) { NewNIDV[ui] = -2; continue; }
for (int ci = 0; ci < GradV.Len(); ci++) {
int CID = GradV.GetKey(ci);
double Change = LearnRate * GradV.GetDat(CID);
double NewFuc = CurFU.IsKey(CID)? CurFU.GetDat(CID) + Change : Change;
if (NewFuc <= 0.0) {
CurFU.DelIfKey(CID);
} else {
CurFU.AddDat(CID) = NewFuc;
}
}
CurFU.Defrag();
}
//store changes
NewF[ui] = CurFU;
NewNIDV[ui] = u;
}
}
int NumNoChangeGrad = 0;
int NumNoChangeStepSize = 0;
for (int ui = 0; ui < NewNIDV.Len(); ui++) {
int NewNID = NewNIDV[ui];
if (NewNID == -1) { NumNoChangeGrad++; continue; }
if (NewNID == -2) { NumNoChangeStepSize++; continue; }
for (TIntFltH::TIter CI = F[NewNID].BegI(); CI < F[NewNID].EndI(); CI++) {
SumFV[CI.GetKey()] -= CI.GetDat();
}
}
#pragma omp parallel for
for (int ui = 0; ui < NewNIDV.Len(); ui++) {
int NewNID = NewNIDV[ui];
if (NewNID < 0) { continue; }
F[NewNID] = NewF[ui];
}
for (int ui = 0; ui < NewNIDV.Len(); ui++) {
int NewNID = NewNIDV[ui];
if (NewNID < 0) { continue; }
for (TIntFltH::TIter CI = F[NewNID].BegI(); CI < F[NewNID].EndI(); CI++) {
SumFV[CI.GetKey()] += CI.GetDat();
}
}
// update the nodes who are optimal
for (int ui = 0; ui < NewNIDV.Len(); ui++) {
int NewNID = NewNIDV[ui];
if (NewNID < 0) { continue; }
TUNGraph::TNodeI UI = G->GetNI(NewNID);
NIDOPTV[NewNID] = 0;
for (int e = 0; e < UI.GetDeg(); e++) {
NIDOPTV[UI.GetNbrNId(e)] = 0;
}
}
int OPTCnt = 0;
for (int i = 0; i < NIDOPTV.Len(); i++) { if (NIDOPTV[i] == 1) { OPTCnt++; } }
if (! PlotNm.Empty()) {
printf("\r%d iterations [%s] %d secs", iter * ChunkSize * ChunkNum, ExeTm.GetTmStr(), int(TSecTm::GetCurTm().GetAbsSecs() - StartTm));
if (PrevL > TFlt::Mn) { printf(" (%f) %d g %d s %d OPT", PrevL, NumNoChangeGrad, NumNoChangeStepSize, OPTCnt); }
fflush(stdout);
}
if ((iter - PrevIter) * ChunkSize * ChunkNum >= G->GetNodes()) {
PrevIter = iter;
double CurL = Likelihood(true);
IterLV.Add(TIntFltPr(iter * ChunkSize * ChunkNum, CurL));
printf("\r%d iterations, Likelihood: %f, Diff: %f [%d secs]", iter, CurL, CurL - PrevL, int(time(NULL) - InitTime));
fflush(stdout);
if (CurL - PrevL <= Thres * fabs(PrevL)) {
break;
}
else {
PrevL = CurL;
}
}
}
if (! PlotNm.Empty()) {
printf("\nMLE completed with %d iterations(%s secs)\n", iter, int(TSecTm::GetCurTm().GetAbsSecs() - StartTm));
TGnuPlot::PlotValV(IterLV, PlotNm + ".likelihood_Q");[]
} else {
int TAGMFast::MLEGradAscent(const double& Thres, const int& MaxIter, const TStr PlotNm, const double StepAlpha, const double StepBeta) {
time_t InitTime = time(NULL);
TExeTm ExeTm, CheckTm;
int iter = 0, PrevIter = 0;
TIntFltPrV IterLV;
TUNGraph::TNodeI UI;
double PrevL = TFlt::Mn, CurL = 0.0;
TIntV NIdxV(F.Len(), 0);
for (int i = 0; i < F.Len(); i++) { NIdxV.Add(i); }
IAssert(NIdxV.Len() == F.Len());
TIntFltH GradV;
while(iter < MaxIter) {
NIdxV.Shuffle(Rnd);
for (int ui = 0; ui < F.Len(); ui++, iter++) {
int u = NIdxV[ui]; //
//find set of candidate c (we only need to consider c to which a neighbor of u belongs to)
UI = G->GetNI(u);
TIntSet CIDSet(5 * UI.GetDeg());
for (int e = 0; e < UI.GetDeg(); e++) {
if (HOVIDSV[u].IsKey(UI.GetNbrNId(e))) { continue; }
TIntFltH& NbhCIDH = F[UI.GetNbrNId(e)];
for (TIntFltH::TIter CI = NbhCIDH.BegI(); CI < NbhCIDH.EndI(); CI++) {
CIDSet.AddKey(CI.GetKey());
}
}
for (TIntFltH::TIter CI = F[u].BegI(); CI < F[u].EndI(); CI++) { //remove the community membership which U does not share with its neighbors
if (! CIDSet.IsKey(CI.GetKey())) {
DelCom(u, CI.GetKey());
}
}
if (CIDSet.Empty()) { continue; }
GradientForRow(u, GradV, CIDSet);
if (Norm2(GradV) < 1e-4) { continue; }
double LearnRate = GetStepSizeByLineSearch(u, GradV, GradV, StepAlpha, StepBeta);
if (LearnRate == 0.0) { continue; }
for (int ci = 0; ci < GradV.Len(); ci++) {
int CID = GradV.GetKey(ci);
double Change = LearnRate * GradV.GetDat(CID);
double NewFuc = GetCom(u, CID) + Change;
if (NewFuc <= 0.0) {
DelCom(u, CID);
} else {
AddCom(u, CID, NewFuc);
}
}
if (! PlotNm.Empty() && (iter + 1) % G->GetNodes() == 0) {
IterLV.Add(TIntFltPr(iter, Likelihood(false)));
}
}
printf("\r%d iterations (%f) [%lu sec]", iter, CurL, time(NULL) - InitTime);
fflush(stdout);
if (iter - PrevIter >= 2 * G->GetNodes() && iter > 10000) {
PrevIter = iter;
CurL = Likelihood();
if (PrevL > TFlt::Mn && ! PlotNm.Empty()) {
printf("\r%d iterations, Likelihood: %f, Diff: %f", iter, CurL, CurL - PrevL);
}
fflush(stdout);
if (CurL - PrevL <= Thres * fabs(PrevL)) { break; }
else { PrevL = CurL; }
}
}
printf("\n");
printf("MLE for Lambda completed with %d iterations(%s)\n", iter, ExeTm.GetTmStr());
if (! PlotNm.Empty()) {
TGnuPlot::PlotValV(IterLV, PlotNm + ".likelihood_Q");
}
return iter;
}
int TAGMFast::FindComsByCV(TIntV& ComsV, const double HOFrac, const int NumThreads, const TStr PlotLFNm, const double StepAlpha, const double StepBeta) {
if (ComsV.Len() == 0) {
int MaxComs = G->GetNodes() / 5;
ComsV.Add(2);
while(ComsV.Last() < MaxComs) { ComsV.Add(ComsV.Last() * 2); }
}
TIntPrV EdgeV(G->GetEdges(), 0);
for (TUNGraph::TEdgeI EI = G->BegEI(); EI < G->EndEI(); EI++) {
EdgeV.Add(TIntPr(EI.GetSrcNId(), EI.GetDstNId()));
}
EdgeV.Shuffle(Rnd);
int MaxIterCV = 3;
TVec<TVec<TIntSet> > HoldOutSets(MaxIterCV);
if (EdgeV.Len() > 50) { //if edges are many enough, use CV
printf("generating hold out set\n");
TIntV NIdV1, NIdV2;
G->GetNIdV(NIdV1);
G->GetNIdV(NIdV2);
for (int IterCV = 0; IterCV < MaxIterCV; IterCV++) {
// generate holdout sets
HoldOutSets[IterCV].Gen(G->GetNodes());
const int HOTotal = int(HOFrac * G->GetNodes() * (G->GetNodes() - 1) / 2.0);
int HOCnt = 0;
int HOEdges = (int) TMath::Round(HOFrac * G->GetEdges());
printf("holding out %d edges...\n", HOEdges);
for (int he = 0; he < (int) HOEdges; he++) {
HoldOutSets[IterCV][EdgeV[he].Val1].AddKey(EdgeV[he].Val2);
HoldOutSets[IterCV][EdgeV[he].Val2].AddKey(EdgeV[he].Val1);
HOCnt++;
}
printf("%d Edges hold out\n", HOCnt);
while(HOCnt++ < HOTotal) {
int SrcNID = Rnd.GetUniDevInt(G->GetNodes());
int DstNID = Rnd.GetUniDevInt(G->GetNodes());
HoldOutSets[IterCV][SrcNID].AddKey(DstNID);
HoldOutSets[IterCV][DstNID].AddKey(SrcNID);
}
}
printf("hold out set generated\n");
}
TFltV HOLV(ComsV.Len());
TIntFltPrV ComsLV;
for (int c = 0; c < ComsV.Len(); c++) {
const int Coms = ComsV[c];
printf("Try number of Coms:%d\n", Coms);
NeighborComInit(Coms);
printf("Initialized\n");
if (EdgeV.Len() > 50) { //if edges are many enough, use CV
for (int IterCV = 0; IterCV < MaxIterCV; IterCV++) {
HOVIDSV = HoldOutSets[IterCV];
if (NumThreads == 1) {
printf("MLE without parallelization begins\n");
MLEGradAscent(0.05, 10 * G->GetNodes(), "", StepAlpha, StepBeta);
} else {
printf("MLE with parallelization begins\n");
MLEGradAscentParallel(0.05, 100, NumThreads, "", StepAlpha, StepBeta);
}
double HOL = LikelihoodHoldOut();
HOL = HOL < 0? HOL: TFlt::Mn;
HOLV[c] += HOL;
}
}
else {
HOVIDSV.Gen(G->GetNodes());
MLEGradAscent(0.0001, 100 * G->GetNodes(), "");
double BIC = 2 * Likelihood() - (double) G->GetNodes() * Coms * 2.0 * log ( (double) G->GetNodes());
HOLV[c] = BIC;
}
}
int EstComs = 2;
double MaxL = TFlt::Mn;
printf("\n");
for (int c = 0; c < ComsV.Len(); c++) {
ComsLV.Add(TIntFltPr(ComsV[c].Val, HOLV[c].Val));
printf("%d(%f)\t", ComsV[c].Val, HOLV[c].Val);
if (MaxL < HOLV[c]) {
MaxL = HOLV[c];
EstComs = ComsV[c];
}
}
printf("\n");
RandomInit(EstComs);
HOVIDSV.Gen(G->GetNodes());
if (! PlotLFNm.Empty()) {
TGnuPlot::PlotValV(ComsLV, PlotLFNm, "hold-out likelihood", "communities", "likelihood");
}
return EstComs;
}
/// Newton method: DEPRECATED
int TAGMFast::MLENewton(const double& Thres, const int& MaxIter, const TStr PlotNm) {
TExeTm ExeTm;
int iter = 0, PrevIter = 0;
TIntFltPrV IterLV;
double PrevL = TFlt::Mn, CurL;
TUNGraph::TNodeI UI;
TIntV NIdxV;
G->GetNIdV(NIdxV);
int CID, UID, NewtonIter;
double Fuc, PrevFuc, Grad, H;
while(iter < MaxIter) {
NIdxV.Shuffle(Rnd);
for (int ui = 0; ui < F.Len(); ui++, iter++) {
if (! PlotNm.Empty() && iter % G->GetNodes() == 0) {
IterLV.Add(TIntFltPr(iter, Likelihood(false)));
}
UID = NIdxV[ui];
//find set of candidate c (we only need to consider c to which a neighbor of u belongs to)
TIntSet CIDSet;
UI = G->GetNI(UID);
if (UI.GetDeg() == 0) { //if the node is isolated, clear its membership and skip
if (! F[UID].Empty()) { F[UID].Clr(); }
continue;
}
for (int e = 0; e < UI.GetDeg(); e++) {
if (HOVIDSV[UID].IsKey(UI.GetNbrNId(e))) { continue; }
TIntFltH& NbhCIDH = F[UI.GetNbrNId(e)];
for (TIntFltH::TIter CI = NbhCIDH.BegI(); CI < NbhCIDH.EndI(); CI++) {
CIDSet.AddKey(CI.GetKey());
}
}
for (TIntFltH::TIter CI = F[UID].BegI(); CI < F[UID].EndI(); CI++) { //remove the community membership which U does not share with its neighbors
if (! CIDSet.IsKey(CI.GetKey())) {
DelCom(UID, CI.GetKey());
}
}
if (CIDSet.Empty()) { continue; }
for (TIntSet::TIter CI = CIDSet.BegI(); CI < CIDSet.EndI(); CI++) {
CID = CI.GetKey();
//optimize for UID, CID
//compute constants
TFltV AlphaKV(UI.GetDeg());
for (int e = 0; e < UI.GetDeg(); e++) {
if (HOVIDSV[UID].IsKey(UI.GetNbrNId(e))) { continue; }
AlphaKV[e] = (1 - PNoCom) * exp(- DotProduct(UID, UI.GetNbrNId(e)) + GetCom(UI.GetNbrNId(e), CID) * GetCom(UID, CID));
IAssertR(AlphaKV[e] <= 1.0, TStr::Fmt("AlphaKV=%f, %f, %f", AlphaKV[e].Val, PNoCom.Val, GetCom(UI.GetNbrNId(e), CID)));
}
Fuc = GetCom(UID, CID);
PrevFuc = Fuc;
Grad = GradientForOneVar(AlphaKV, UID, CID, Fuc), H = 0.0;
if (Grad <= 1e-3 && Grad >= -0.1) { continue; }
NewtonIter = 0;
while (NewtonIter++ < 10) {
Grad = GradientForOneVar(AlphaKV, UID, CID, Fuc), H = 0.0;
H = HessianForOneVar(AlphaKV, UID, CID, Fuc);
if (Fuc == 0.0 && Grad <= 0.0) { Grad = 0.0; }
if (fabs(Grad) < 1e-3) { break; }
if (H == 0.0) { Fuc = 0.0; break; }
double NewtonStep = - Grad / H;
if (NewtonStep < -0.5) { NewtonStep = - 0.5; }
Fuc += NewtonStep;
if (Fuc < 0.0) { Fuc = 0.0; }
}
if (Fuc == 0.0) {
DelCom(UID, CID);
}
else {
AddCom(UID, CID, Fuc);
}
}
}
if (iter - PrevIter >= 2 * G->GetNodes() && iter > 10000) {
PrevIter = iter;
CurL = Likelihood();
if (PrevL > TFlt::Mn && ! PlotNm.Empty()) {
printf("\r%d iterations, Likelihood: %f, Diff: %f", iter, CurL, CurL - PrevL);
}
fflush(stdout);
if (CurL - PrevL <= Thres * fabs(PrevL)) { break; }
else { PrevL = CurL; }
}
}
if (! PlotNm.Empty()) {
printf("\nMLE for Lambda completed with %d iterations(%s)\n", iter, ExeTm.GetTmStr());
TGnuPlot::PlotValV(IterLV, PlotNm + ".likelihood_Q");
}
return iter;
}
