bool TBagOfWords::Update(const TStrV& TokenStrV) {
// Generate Ngrams if necessary
TStrV NgramStrV;
GenerateNgrams(TokenStrV, NgramStrV);
// process tokens to update DF counts
bool UpdateP = false;
if (IsHashing()) {
// consolidate tokens and get their hashed IDs
TIntSet TokenIdH;
for (int TokenStrN = 0; TokenStrN < NgramStrV.Len(); TokenStrN++) {
const TStr& TokenStr = NgramStrV[TokenStrN];
TInt TokenId = TokenStr.GetHashTrick() % HashDim;
TokenIdH.AddKey(TokenId);
if (IsStoreHashWords()) { HashWordV[TokenId].AddKey(TokenStr); }
}
// update document counts
int KeyId = TokenIdH.FFirstKeyId();
while (TokenIdH.FNextKeyId(KeyId)) {
const int TokenId = TokenIdH.GetKey(KeyId);
// update DF
DocFqV[TokenId]++;
}
} else {
// consolidate tokens
TStrH TokenStrH;
for (int TokenStrN = 0; TokenStrN < NgramStrV.Len(); TokenStrN++) {
const TStr& TokenStr = NgramStrV[TokenStrN];
TokenStrH.AddKey(TokenStr);
}
// update document counts and update vocabulary with new tokens
int KeyId = TokenStrH.FFirstKeyId();
while (TokenStrH.FNextKeyId(KeyId)) {
// get token
const TStr& TokenStr = TokenStrH.GetKey(KeyId);
// different processing for hashing
int TokenId = TokenSet.GetKeyId(TokenStr);
if (TokenId == -1) {
// new token, remember the dimensionality change
UpdateP = true;
// remember the new token
TokenId = TokenSet.AddKey(TokenStr);
// increase document count table
const int TokenDfId = DocFqV.Add(0);
// increase also the old count table
OldDocFqV.Add(0.0);
// make sure we DF vector and TokenSet still in sync
IAssert(TokenId == TokenDfId);
IAssert(DocFqV.Len() == OldDocFqV.Len());
}
// document count update
DocFqV[TokenId]++;
}
}
// update document count
Docs++;
// tell if dimension changed
return UpdateP;
}
void TAGMFast::GradientForRow(const int UID, TIntFltH& GradU, const TIntSet& CIDSet) {
GradU.Gen(CIDSet.Len());
TFltV HOSumFV; //adjust for Fv of v hold out
if (HOVIDSV[UID].Len() > 0) {
HOSumFV.Gen(SumFV.Len());
for (int e = 0; e < HOVIDSV[UID].Len(); e++) {
for (int c = 0; c < SumFV.Len(); c++) {
HOSumFV[c] += GetCom(HOVIDSV[UID][e], c);
}
}
}
TUNGraph::TNodeI NI = G->GetNI(UID);
int Deg = NI.GetDeg();
TFltV PredV(Deg), GradV(CIDSet.Len());
TIntV CIDV(CIDSet.Len());
if (DoParallel && Deg + CIDSet.Len() > 10) {
#pragma omp parallel for schedule(static, 1)
for (int e = 0; e < Deg; e++) {
if (NI.GetNbrNId(e) == UID) { continue; }
if (HOVIDSV[UID].IsKey(NI.GetNbrNId(e))) { continue; }
PredV[e] = Prediction(UID, NI.GetNbrNId(e));
}
#pragma omp parallel for schedule(static, 1)
for (int c = 0; c < CIDSet.Len(); c++) {
int CID = CIDSet.GetKey(c);
double Val = 0.0;
for (int e = 0; e < Deg; e++) {
int VID = NI.GetNbrNId(e);
if (VID == UID) { continue; }
if (HOVIDSV[UID].IsKey(VID)) { continue; }
Val += PredV[e] * GetCom(VID, CID) / (1.0 - PredV[e]) + NegWgt * GetCom(VID, CID);
}
double HOSum = HOVIDSV[UID].Len() > 0? HOSumFV[CID].Val: 0.0;//subtract Hold out pairs only if hold out pairs exist
Val -= NegWgt * (SumFV[CID] - HOSum - GetCom(UID, CID));
CIDV[c] = CID;
GradV[c] = Val;
}
}
else {
for (int e = 0; e < Deg; e++) {
if (NI.GetNbrNId(e) == UID) { continue; }
if (HOVIDSV[UID].IsKey(NI.GetNbrNId(e))) { continue; }
PredV[e] = Prediction(UID, NI.GetNbrNId(e));
}
for (int c = 0; c < CIDSet.Len(); c++) {
int CID = CIDSet.GetKey(c);
double Val = 0.0;
for (int e = 0; e < Deg; e++) {
int VID = NI.GetNbrNId(e);
if (VID == UID) { continue; }
if (HOVIDSV[UID].IsKey(VID)) { continue; }
Val += PredV[e] * GetCom(VID, CID) / (1.0 - PredV[e]) + NegWgt * GetCom(VID, CID);
}
double HOSum = HOVIDSV[UID].Len() > 0? HOSumFV[CID].Val: 0.0;//subtract Hold out pairs only if hold out pairs exist
Val -= NegWgt * (SumFV[CID] - HOSum - GetCom(UID, CID));
CIDV[c] = CID;
GradV[c] = Val;
}
}
//add regularization
if (RegCoef > 0.0) { //L1
for (int c = 0; c < GradV.Len(); c++) {
GradV[c] -= RegCoef;
}
}
if (RegCoef < 0.0) { //L2
for (int c = 0; c < GradV.Len(); c++) {
GradV[c] += 2 * RegCoef * GetCom(UID, CIDV[c]);
}
}
for (int c = 0; c < GradV.Len(); c++) {
if (GetCom(UID, CIDV[c]) == 0.0 && GradV[c] < 0.0) { continue; }
if (fabs(GradV[c]) < 0.0001) { continue; }
GradU.AddDat(CIDV[c], GradV[c]);
}
for (int c = 0; c < GradU.Len(); c++) {
if (GradU[c] >= 10) { GradU[c] = 10; }
if (GradU[c] <= -10) { GradU[c] = -10; }
IAssert(GradU[c] >= -10);
}
}
