biasedrandomwalk.h File Reference

This graph shows which files directly or indirectly include this file:

Go to the source code of this file.

Typedefs
typedef TNodeEDatNet< TIntIntVFltVPrH, TFlt >	TWNet
typedef TPt< TWNet >	PWNet

Functions
void	PreprocessTransitionProbs (PWNet &InNet, const double &ParamP, const double &ParamQ, const bool &verbose)
	Preprocesses transition probabilities for random walks. Has to be called once before SimulateWalk calls. More...
void	SimulateWalk (PWNet &InNet, int64 StartNId, const int &WalkLen, TRnd &Rnd, TIntV &Walk)
	Simulates one walk and writes it into Walk vector. More...
int64	PredictMemoryRequirements (PWNet &InNet)

Typedef Documentation

typedef TPt<TWNet> PWNet

Definition at line 5 of file biasedrandomwalk.h.

typedef TNodeEDatNet<TIntIntVFltVPrH, TFlt> TWNet

Definition at line 4 of file biasedrandomwalk.h.

Function Documentation

int64 PredictMemoryRequirements

(

PWNet &

InNet

)

Definition at line 119 of file biasedrandomwalk.cpp.

References TNodeEDatNet< TNodeData, TEdgeData >::TNodeI::GetOutDeg().

                                              {
  int64 MemNeeded = 0;
  for (TWNet::TNodeI NI = InNet->BegNI(); NI < InNet->EndNI(); NI++) {
    for (int64 i = 0; i < NI.GetOutDeg(); i++) {
      TWNet::TNodeI CurrI = InNet->GetNI(NI.GetNbrNId(i));
      MemNeeded += CurrI.GetOutDeg()*(sizeof(TInt) + sizeof(TFlt));
    }
  }
  return MemNeeded;
}

Here is the call graph for this function:

void PreprocessTransitionProbs	(	PWNet &	InNet,
		const double &	ParamP,
		const double &	ParamQ,
		const bool &	verbose
	)

Preprocesses transition probabilities for random walks. Has to be called once before SimulateWalk calls.

Definition at line 97 of file biasedrandomwalk.cpp.

References TVec< TVal, TSizeTy >::Add(), TNodeEDatNet< TNodeData, TEdgeData >::TNodeI::GetDat(), TNodeEDatNet< TNodeData, TEdgeData >::TNodeI::GetOutDeg(), TVec< TVal, TSizeTy >::Len(), and PreprocessNode().

Referenced by node2vec().

                                                                                                              {
  for (TWNet::TNodeI NI = InNet->BegNI(); NI < InNet->EndNI(); NI++) {
    InNet->SetNDat(NI.GetId(),TIntIntVFltVPrH());
  }
  for (TWNet::TNodeI NI = InNet->BegNI(); NI < InNet->EndNI(); NI++) {
    for (int64 i = 0; i < NI.GetOutDeg(); i++) {                    //allocating space in advance to avoid issues with multithreading
      TWNet::TNodeI CurrI = InNet->GetNI(NI.GetNbrNId(i));
      CurrI.GetDat().AddDat(NI.GetId(),TPair<TIntV,TFltV>(TIntV(CurrI.GetOutDeg()),TFltV(CurrI.GetOutDeg())));
    }
  }
  int64 NCnt = 0;
  TIntV NIds;
  for (TWNet::TNodeI NI = InNet->BegNI(); NI < InNet->EndNI(); NI++) {
    NIds.Add(NI.GetId());
  }
#pragma omp parallel for schedule(dynamic)
  for (int64 i = 0; i < NIds.Len(); i++) {
    PreprocessNode(InNet, ParamP, ParamQ, InNet->GetNI(NIds[i]), NCnt, Verbose);
  }
  if(Verbose){ printf("\n"); }
}

Here is the call graph for this function:

Here is the caller graph for this function:

void SimulateWalk	(	PWNet &	InNet,
		int64	StartNId,
		const int &	WalkLen,
		TRnd &	Rnd,
		TIntV &	Walk
	)

Simulates one walk and writes it into Walk vector.

Definition at line 131 of file biasedrandomwalk.cpp.

References TVec< TVal, TSizeTy >::Add(), AliasDrawInt(), TRnd::GetUniDevInt(), TVec< TVal, TSizeTy >::Last(), TVec< TVal, TSizeTy >::LastLast(), and TVec< TVal, TSizeTy >::Len().

Referenced by node2vec().

                                                                                             {
  WalkV.Add(StartNId);
  if (WalkLen == 1) { return; }
  if (InNet->GetNI(StartNId).GetOutDeg() == 0) { return; }
  WalkV.Add(InNet->GetNI(StartNId).GetNbrNId(Rnd.GetUniDevInt(InNet->GetNI(StartNId).GetOutDeg())));
  while (WalkV.Len() < WalkLen) {
    int64 Dst = WalkV.Last();
    int64 Src = WalkV.LastLast();
    if (InNet->GetNI(Dst).GetOutDeg() == 0) { return; }
    int64 Next = AliasDrawInt(InNet->GetNDat(Dst).GetDat(Src),Rnd);
    WalkV.Add(InNet->GetNI(Dst).GetNbrNId(Next));
  }
}

Here is the call graph for this function:

Here is the caller graph for this function: