int TMultimodalGraphImplB::GetSubGraphMocked(const TIntV ModeIds) const {
int NumVerticesAndEdges = 0;
for (THash<TInt,TInt>::TIter CurI = NodeToModeMapping.BegI(); CurI < NodeToModeMapping.EndI(); CurI++) {
if (ModeIds.IsIn(CurI.GetDat())) {
NumVerticesAndEdges++;
}
}
for (int ModeIdx1 = 0; ModeIdx1 < ModeIds.Len(); ModeIdx1++) {
int ModeId1 = ModeIds.GetVal(ModeIdx1);
for (int ModeIdx2 = 0; ModeIdx2 < ModeIds.Len(); ModeIdx2++) {
int ModeId2 = ModeIds.GetVal(ModeIdx2);
TPair<TInt,TInt> ModeIdsKey = GetModeIdsKey(ModeId1, ModeId2);
if (!Graphs.IsKey(ModeIdsKey)) { continue; }
const TNGraph& Graph = Graphs.GetDat(ModeIdsKey);
for (TNGraph::TNodeI it = Graph.BegNI(); it < Graph.EndNI(); it++) {
for (int e = 0; e < it.GetOutDeg(); e++) {
NumVerticesAndEdges += it.GetOutNId(e);
}
}
}
}
return NumVerticesAndEdges;
}
TIntNNet TMultimodalGraphImplB::GetSubGraph(const TIntV ModeIds) const {
TIntNNet SubGraph = TIntNNet();
for (THash<TInt,TInt>::TIter CurI = NodeToModeMapping.BegI(); CurI < NodeToModeMapping.EndI(); CurI++) {
if (ModeIds.IsIn(CurI.GetDat())) {
SubGraph.AddNode(CurI.GetKey(), CurI.GetDat());
}
}
for (int ModeIdx1 = 0; ModeIdx1 < ModeIds.Len(); ModeIdx1++) {
int ModeId1 = ModeIds.GetVal(ModeIdx1);
for (int ModeIdx2 = 0; ModeIdx2 < ModeIds.Len(); ModeIdx2++) {
int ModeId2 = ModeIds.GetVal(ModeIdx2);
TPair<TInt,TInt> ModeIdsKey = GetModeIdsKey(ModeId1, ModeId2);
if (!Graphs.IsKey(ModeIdsKey)) { continue; }
const TNGraph& Graph = Graphs.GetDat(ModeIdsKey);
for (TNGraph::TNodeI it = Graph.BegNI(); it < Graph.EndNI(); it++) {
for (int e = 0; e < it.GetOutDeg(); e++) {
SubGraph.AddEdge(it.GetId(), it.GetOutNId(e));
}
}
}
}
printf("Number of nodes in SubGraph: %d...\n", SubGraph.GetNodes());
printf("Number of edges in SubGraph: %d...\n", SubGraph.GetEdges());
return SubGraph;
}
void TNetInfBs::GenNoisyCascade(TCascade& C, const int& TModel, const double &window, TIntPrIntH& EdgesUsed,
const double& std_waiting_time, const double& std_beta,
const double& PercRndNodes, const double& PercRndRemoval) {
TIntPrIntH EdgesUsedC; // list of used edges for a single cascade
GenCascade(C, TModel, window, EdgesUsedC, delta, std_waiting_time, std_beta);
// store keys
TIntV KeyV;
C.NIdHitH.GetKeyV(KeyV);
// store first and last time
double tbeg = TFlt::Mx, tend = TFlt::Mn;
for (int i=0; i < KeyV.Len(); i++) {
if (tbeg > C.NIdHitH.GetDat(KeyV[i]).Tm) tbeg = C.NIdHitH.GetDat(KeyV[i]).Tm;
if (tend < C.NIdHitH.GetDat(KeyV[i]).Tm) tend = C.NIdHitH.GetDat(KeyV[i]).Tm;
}
// remove PercRndRemoval% of the nodes of the cascades
if (PercRndRemoval > 0) {
for (int i=KeyV.Len()-1; i >= 0; i--) {
if (TFlt::Rnd.GetUniDev() < PercRndRemoval) {
// remove from the EdgesUsedC the ones affected by the removal
TIntPrV EdgesToRemove;
for (TIntPrIntH::TIter EI = EdgesUsedC.BegI(); EI < EdgesUsedC.EndI(); EI++) {
if ( (KeyV[i]==EI.GetKey().Val1 && C.IsNode(EI.GetKey().Val2) && C.GetTm(KeyV[i]) < C.GetTm(EI.GetKey().Val2)) ||
(KeyV[i]==EI.GetKey().Val2 && C.IsNode(EI.GetKey().Val1) && C.GetTm(KeyV[i]) > C.GetTm(EI.GetKey().Val1)) ) {
EI.GetDat() = EI.GetDat()-1;
if (EI.GetDat()==0)
EdgesToRemove.Add(EI.GetKey());
}
}
for (int er=0; er<EdgesToRemove.Len(); er++)
EdgesUsedC.DelKey(EdgesToRemove[er]);
C.Del(KeyV[i]);
}
}
// defrag the hash table, otherwise other functions can crash
C.NIdHitH.Defrag();
}
// Substitute PercRndNodes% of the nodes for a random node at a random time
if (PercRndNodes > 0) {
for (int i=KeyV.Len()-1; i >= 0; i--) {
if (TFlt::Rnd.GetUniDev() < PercRndNodes) {
// remove from the EdgesUsedC the ones affected by the change
TIntPrV EdgesToRemove;
for (TIntPrIntH::TIter EI = EdgesUsedC.BegI(); EI < EdgesUsedC.EndI(); EI++) {
if ( (KeyV[i]==EI.GetKey().Val1 && C.IsNode(EI.GetKey().Val2) && C.GetTm(KeyV[i]) < C.GetTm(EI.GetKey().Val2)) ||
(KeyV[i]==EI.GetKey().Val2 && C.IsNode(EI.GetKey().Val1) && C.GetTm(KeyV[i]) > C.GetTm(EI.GetKey().Val1)) ) {
EI.GetDat() = EI.GetDat()-1;
if (EI.GetDat()==0)
EdgesToRemove.Add(EI.GetKey());
}
}
for (int er=0; er<EdgesToRemove.Len(); er++)
EdgesUsedC.DelKey(EdgesToRemove[er]);
printf("Old node n:%d t:%f --", KeyV[i].Val, C.GetTm(KeyV[i]));
C.Del(KeyV[i]);
// not repeating a label
double tnew = 0;
int keynew = -1;
do {
tnew = tbeg + TFlt::Rnd.GetUniDev()*(tend-tbeg);
keynew = Graph->GetRndNId();
} while (KeyV.IsIn(keynew));
printf("New node n:%d t:%f\n", keynew, tnew);
C.Add(keynew, tnew);
KeyV.Add(keynew);
}
}
}
// add to the aggregate list (EdgesUsed)
EdgesUsedC.Defrag();
for (int i=0; i<EdgesUsedC.Len(); i++) {
if (!EdgesUsed.IsKey(EdgesUsedC.GetKey(i))) EdgesUsed.AddDat(EdgesUsedC.GetKey(i)) = 0;
EdgesUsed.GetDat(EdgesUsedC.GetKey(i)) += 1;
}
}
PBowDocBs TFtrGenBs::LoadCsv(TStr& FNm, const int& ClassId,
const TIntV& IgnoreIdV, const int& TrainLen) {
// feature generators
PFtrGenBs FtrGenBs = TFtrGenBs::New();
// CSV parsing stuff
PSIn SIn = TFIn::New(FNm);
char SsCh = ' '; TStrV FldValV;
// read the headers and initialise the feature generators
TSs::LoadTxtFldV(ssfCommaSep, SIn, SsCh, FldValV, false);
for (int FldValN = 0; FldValN < FldValV.Len(); FldValN++) {
const TStr& FldVal = FldValV[FldValN];
if (FldValN == ClassId) {
if (FldVal == "NOM") {
FtrGenBs->PutClsFtrGen(TFtrGenNominal::New());
} else if (FldVal == "MULTI-NOM") {
FtrGenBs->PutClsFtrGen(TFtrGenMultiNom::New());
} else {
TExcept::Throw("Wrong class type '" + FldVal + "', should be NOM or MULTI-NOM!");
}
} else if (!IgnoreIdV.IsIn(FldValN)) {
if (FldVal == TFtrGenNumeric::GetType()) {
FtrGenBs->AddFtrGen(TFtrGenNumeric::New());
} else if (FldVal == TFtrGenNominal::GetType()) {
FtrGenBs->AddFtrGen(TFtrGenNominal::New());
} else if (FldVal == TFtrGenToken::GetType()) {
FtrGenBs->AddFtrGen(TFtrGenToken::New(
TSwSet::New(swstNone), TStemmer::New(stmtNone)));
} else if (FldVal == TFtrGenSparseNumeric::GetType()) {
FtrGenBs->AddFtrGen(TFtrGenSparseNumeric::New());
} else if (FldVal == TFtrGenMultiNom::GetType()) {
FtrGenBs->AddFtrGen(TFtrGenMultiNom::New());
} else {
TExcept::Throw("Wrong type '" + FldVal + "'!");
}
}
}
const int Flds = FldValV.Len();
// read the lines and feed them to the feature generators
int Recs = 0;
while (!SIn->Eof()) {
if (Recs == TrainLen) { break; }
Recs++; printf("%7d\r", Recs);
TSs::LoadTxtFldV(ssfCommaSep, SIn, SsCh, FldValV, false);
// make sure line still has the same number of fields as the header
EAssertR(FldValV.Len() == Flds,
TStr::Fmt("Wrong number of fields in line %d! Found %d and expected %d!",
Recs + 1, FldValV.Len(), Flds));
// go over lines
try {
TStrV FtrValV;
for (int FldValN = 0; FldValN < FldValV.Len(); FldValN++) {
const TStr& FldVal = FldValV[FldValN];
if (FldValN == ClassId) {
FtrGenBs->UpdateCls(FldVal);
} else if (!IgnoreIdV.IsIn(FldValN)) {
FtrValV.Add(FldVal);
}
}
FtrGenBs->Update(FtrValV);
} catch (PExcept Ex) {
TExcept::Throw(TStr::Fmt("Error in line %d: '%s'!",
Recs+1, Ex->GetMsgStr().CStr()));
}
}
// read the file again and feed it to the training set
PBowDocBs BowDocBs = FtrGenBs->MakeBowDocBs();
// we read and ignore the headers since we parsed them already
SIn = TFIn::New(FNm); SsCh = ' ';
TSs::LoadTxtFldV(ssfCommaSep, SIn, SsCh, FldValV, false);
// read the lines and feed them to the training set
Recs = 0;
while (!SIn->Eof()){
Recs++; printf("%7d\r", Recs);
TSs::LoadTxtFldV(ssfCommaSep, SIn, SsCh, FldValV, false);
// make sure line still has the same number of fields as the header
EAssertR(FldValV.Len() == Flds,
TStr::Fmt("Wrong number of fields in line %s! Found %d and expected %d!",
Recs + 1, FldValV.Len(), Flds));
// go over lines and construct the sparse vector
TStrV FtrValV; TStr ClsFtrVal;
try {
for (int FldValN = 0; FldValN < FldValV.Len(); FldValN++) {
const TStr& FldVal = FldValV[FldValN];
if (FldValN == ClassId) {
ClsFtrVal = FldVal;
} else if (!IgnoreIdV.IsIn(FldValN)) {
FtrValV.Add(FldVal);
}
}
} catch (PExcept Ex) {
TExcept::Throw(TStr::Fmt("Error in line %d: '%s'!",
Recs+1, Ex->GetMsgStr().CStr()));
}
// add the feature vector to trainsets
FtrGenBs->AddBowDoc(BowDocBs, TStr::Fmt("Line-%d", Recs), FtrValV, ClsFtrVal);
}
// prepare training and testing doc ids
TIntV AllDIdV; BowDocBs->GetAllDIdV(AllDIdV); IAssert(AllDIdV.IsSorted());
TIntV TrainDIdV = AllDIdV; TrainDIdV.Trunc(TrainLen);
BowDocBs->PutTrainDIdV(TrainDIdV);
TIntV TestDIdV = AllDIdV; TestDIdV.Minus(TrainDIdV);
BowDocBs->PutTestDIdV(TestDIdV);
return BowDocBs;
}