/// Generates a small-world graph using the Watts-Strogatz model.
/// We assume a circle where each node creates links to NodeOutDeg other nodes.
/// This way at the end each node is connected to 2*NodeOutDeg other nodes.
/// See: Collective dynamics of 'small-world' networks. Watts and Strogatz.
/// URL: http://research.yahoo.com/files/w_s_NATURE_0.pdf
PUNGraph GenSmallWorld(const int& Nodes, const int& NodeOutDeg, const double& RewireProb, TRnd& Rnd) {
THashSet<TIntPr> EdgeSet(Nodes*NodeOutDeg);
IAssertR(Nodes > NodeOutDeg, TStr::Fmt("Insufficient nodes for out degree, %d!", NodeOutDeg));
for (int node = 0; node < Nodes; node++) {
const int src = node;
for (int edge = 1; edge <= NodeOutDeg; edge++) {
int dst = (node+edge) % Nodes; // edge to next neighbor
if (Rnd.GetUniDev() < RewireProb) { // random edge
dst = Rnd.GetUniDevInt(Nodes);
while (dst == src || EdgeSet.IsKey(TIntPr(src, dst))) {
dst = Rnd.GetUniDevInt(Nodes); }
}
EdgeSet.AddKey(TIntPr(src, dst));
}
}
PUNGraph GraphPt = TUNGraph::New();
TUNGraph& Graph = *GraphPt;
Graph.Reserve(Nodes, EdgeSet.Len());
int node;
for (node = 0; node < Nodes; node++) {
IAssert(Graph.AddNode(node) == node);
}
for (int edge = 0; edge < EdgeSet.Len(); edge++) {
Graph.AddEdge(EdgeSet[edge].Val1, EdgeSet[edge].Val2);
}
Graph.Defrag();
return GraphPt;
}
int main() {
TLSHash LSH(7, 7, DIM, TLSHash::EUCLIDEAN);
LSH.Init();
TRnd Gen;
Gen.Randomize();
TVec<TFltV> DataV;
for (int i=0; i<1000000; i++) {
TFltV Datum;
for (int j=0; j<3; j++) {
Datum.Add(Gen.GetUniDev()*2100);
}
DataV.Add(Datum);
}
LSH.AddV(DataV);
TVec<TPair<TFltV, TFltV> > NeighborsV = LSH.GetAllCandidatePairs();
printf("Number of Candidates: %d\n", NeighborsV.Len());
NeighborsV = LSH.GetAllNearPairs();
printf("Number of Close Pairs: %d\n", NeighborsV.Len());
for (int i=0; i<NeighborsV.Len(); i++) {
outputPoint(NeighborsV[i].GetVal1());
printf(" ");
outputPoint(NeighborsV[i].GetVal2());
printf("\n");
}
return 0;
}
//Initialize positive embeddings
void InitPosEmb(TIntV& Vocab, int& Dimensions, TRnd& Rnd, TVVec<TFlt, int64>& SynPos) {
SynPos = TVVec<TFlt, int64>(Vocab.Len(),Dimensions);
for (int64 i = 0; i < SynPos.GetXDim(); i++) {
for (int j = 0; j < SynPos.GetYDim(); j++) {
SynPos(i,j) =(Rnd.GetUniDev()-0.5)/Dimensions;
}
}
}
/// Generates a random scale-free network using the Copying Model.
/// The generating process operates as follows: Node u is added to a graph, it
/// selects a random node v, and with prob Beta it links to v, with 1-Beta
/// links u links to neighbor of v. The power-law degree exponent is -1/(1-Beta).
/// See: Stochastic models for the web graph.
/// Kumar, Raghavan, Rajagopalan, Sivakumar, Tomkins, Upfal.
/// URL: http://snap.stanford.edu/class/cs224w-readings/kumar00stochastic.pdf
PNGraph GenCopyModel(const int& Nodes, const double& Beta, TRnd& Rnd) {
PNGraph GraphPt = TNGraph::New();
TNGraph& Graph = *GraphPt;
Graph.Reserve(Nodes, Nodes);
const int startNId = Graph.AddNode();
Graph.AddEdge(startNId, startNId);
for (int n = 1; n < Nodes; n++) {
const int rnd = Graph.GetRndNId();
const int NId = Graph.AddNode();
if (Rnd.GetUniDev() < Beta) {
Graph.AddEdge(NId, rnd); }
else {
const TNGraph::TNodeI NI = Graph.GetNI(rnd);
const int rnd2 = Rnd.GetUniDevInt(NI.GetOutDeg());
Graph.AddEdge(NId, NI.GetOutNId(rnd2));
}
}
return GraphPt;
}
void TTransCorpus::Shuffle(const PTransCorpus& InFirstTransCorpus,
const PTransCorpus& InSecondTransCorpus, TRnd& Rnd, const double& SwapProb,
PTransCorpus& OutFirstTransCorpus, PTransCorpus& OutSecondTransCorpus) {
// prepare new corpuses
OutFirstTransCorpus = TTransCorpus::New();
OutSecondTransCorpus = TTransCorpus::New();
// swap sentences
TIntV FirstSentIdV, SecondSentIdV;
InFirstTransCorpus->GetSentIdV(FirstSentIdV);
InSecondTransCorpus->GetSentIdV(SecondSentIdV);
for (int SentIdN = 0; SentIdN < FirstSentIdV.Len(); SentIdN++) {
// get sentence id
const int SentId = FirstSentIdV[SentIdN];
// check if id same in both cases
IAssert(SecondSentIdV[SentIdN] == SentId);
// read sentences
TStr OrgStr1 = InFirstTransCorpus->GetOrgStr(SentId);
TStr OrgStr2 = InSecondTransCorpus->GetOrgStr(SentId);
IAssert(OrgStr1 == OrgStr2 );
TStr RefTransStr1 = InFirstTransCorpus->GetRefTransStrV(SentId)[0];
TStr RefTransStr2 = InSecondTransCorpus->GetRefTransStrV(SentId)[0];
IAssert(RefTransStr1 == RefTransStr2);
TStr FirstTransStr = InFirstTransCorpus->GetTransStr(SentId);
TStr SecondTransStr = InSecondTransCorpus->GetTransStr(SentId);
// swap sentences
if (Rnd.GetUniDev() < SwapProb) {
// we swap
OutFirstTransCorpus->AddSentence(SentId, OrgStr1, SecondTransStr, RefTransStr1);
OutSecondTransCorpus->AddSentence(SentId, OrgStr1, FirstTransStr, RefTransStr1);
} else {
// no swap
OutFirstTransCorpus->AddSentence(SentId, OrgStr1, FirstTransStr, RefTransStr1);
OutSecondTransCorpus->AddSentence(SentId, OrgStr1, SecondTransStr, RefTransStr1);
}
}
}
/// R-MAT Generator. The modes is based on the recursive descent into a 2x2
/// matrix [A,B; C, 1-(A+B+C)].
/// See: R-MAT Generator: A Recursive Model for Graph Mining.
/// D. Chakrabarti, Y. Zhan and C. Faloutsos, in SIAM Data Mining 2004.
/// URL: http://www.cs.cmu.edu/~deepay/mywww/papers/siam04.pdf
PNGraph GenRMat(const int& Nodes, const int& Edges, const double& A, const double& B, const double& C, TRnd& Rnd) {
PNGraph GraphPt = TNGraph::New();
TNGraph& Graph = *GraphPt;
Graph.Reserve(Nodes, Edges);
IAssert(A+B+C < 1.0);
int rngX, rngY, offX, offY;
int Depth=0, Collisions=0, Cnt=0, PctDone=0;
const int EdgeGap = Edges / 100 + 1;
// sum of parameters (probabilities)
TVec<double> sumA(128, 0), sumAB(128, 0), sumAC(128, 0), sumABC(128, 0); // up to 2^128 vertices ~ 3.4e38
for (int i = 0; i < 128; i++) {
const double a = A * (Rnd.GetUniDev() + 0.5);
const double b = B * (Rnd.GetUniDev() + 0.5);
const double c = C * (Rnd.GetUniDev() + 0.5);
const double d = (1.0 - (A+B+C)) * (Rnd.GetUniDev() + 0.5);
const double abcd = a+b+c+d;
sumA.Add(a / abcd);
sumAB.Add((a+b) / abcd);
sumAC.Add((a+c) / abcd);
sumABC.Add((a+b+c) / abcd);
}
// nodes
for (int node = 0; node < Nodes; node++) {
IAssert(Graph.AddNode(-1) == node);
}
// edges
for (int edge = 0; edge < Edges; ) {
rngX = Nodes; rngY = Nodes; offX = 0; offY = 0;
Depth = 0;
// recurse the matrix
while (rngX > 1 || rngY > 1) {
const double RndProb = Rnd.GetUniDev();
if (rngX>1 && rngY>1) {
if (RndProb < sumA[Depth]) { rngX/=2; rngY/=2; }
else if (RndProb < sumAB[Depth]) { offX+=rngX/2; rngX-=rngX/2; rngY/=2; }
else if (RndProb < sumABC[Depth]) { offY+=rngY/2; rngX/=2; rngY-=rngY/2; }
else { offX+=rngX/2; offY+=rngY/2; rngX-=rngX/2; rngY-=rngY/2; }
} else
if (rngX>1) { // row vector
if (RndProb < sumAC[Depth]) { rngX/=2; rngY/=2; }
else { offX+=rngX/2; rngX-=rngX/2; rngY/=2; }
} else
if (rngY>1) { // column vector
if (RndProb < sumAB[Depth]) { rngX/=2; rngY/=2; }
else { offY+=rngY/2; rngX/=2; rngY-=rngY/2; }
} else { Fail; }
Depth++;
}
// add edge
const int NId1 = offX;
const int NId2 = offY;
if (NId1 != NId2 && ! Graph.IsEdge(NId1, NId2)) {
Graph.AddEdge(NId1, NId2);
if (++Cnt > EdgeGap) {
Cnt=0; printf("\r %d%% edges", ++PctDone); }
edge++;
} else {
Collisions++; }
}
printf("\r RMat: nodes:%d, edges:%d, Iterations:%d, Collisions:%d (%.1f%%).\n", Nodes, Edges,
Edges+Collisions, Collisions, 100*Collisions/double(Edges+Collisions));
Graph.Defrag();
return GraphPt;
}
int64 RndUnigramInt(TIntV& KTable, TFltV& UTable, TRnd& Rnd) {
TInt X = KTable[static_cast<int64>(Rnd.GetUniDev()*KTable.Len())];
double Y = Rnd.GetUniDev();
return Y < UTable[X] ? X : KTable[X];
}