void TGraphCascade::TopologicalSort(TIntV& SortedNIdV) {
int Nodes = Graph.GetNodes();
SortedNIdV.Gen(Nodes, 0); // result
THash<TInt, TBool> Marks(Nodes); // nodeid -> mark map
THash<TInt,TBool> TempMarks(Nodes); // nodeid -> temp mark map
THash<TInt, TBool> Added(Nodes);
TIntV NIdV; Graph.GetNIdV(NIdV); // all node ids
// set marks
for (int NodeN = 0; NodeN < Nodes; NodeN++) {
int NodeId = NIdV[NodeN];
Marks.AddDat(NodeId, false);
TempMarks.AddDat(NodeId, false);
Added.AddDat(NodeId, false);
}
TSStack<TInt> Stack;
for (int NodeN = 0; NodeN < Nodes; NodeN++) {
int NodeId = NIdV[NodeN];
// select an unmarked node
if (!Marks.GetDat(NodeId)) {
Stack.Push(NodeId);
while (!Stack.Empty()) {
// visit TopNode
int TopNodeId = Stack.Top();
Marks.GetDat(TopNodeId) = true;
TempMarks.GetDat(TopNodeId) = true;
// add children, set their temp marks to true
TNGraph::TNodeI NI = Graph.GetNI(TopNodeId);
int Children = NI.GetOutDeg();
bool IsFinal = true;
for (int ChildN = 0; ChildN < Children; ChildN++) {
int ChildId = NI.GetOutNId(ChildN);
EAssertR(!TempMarks.GetDat(ChildId), "TGraphCascade::TopologicalSort: the graph is not a DAG!");
if (!Marks.GetDat(ChildId)) {
// unvisited node
IsFinal = false;
Stack.Push(ChildId);
}
}
if (IsFinal) {
// push TopNode to tail
if (!Added.GetDat(TopNodeId)) {
SortedNIdV.Add(TopNodeId);
Added.GetDat(TopNodeId) = true;
}
TempMarks.GetDat(TopNodeId) = false;
Stack.Pop();
}
}
}
}
SortedNIdV.Reverse();
}
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);
}
