|| || || || || || || ||

---

PredictForActiveLearn

virtual void Impala::Core::Training::Svm::PredictForActiveLearn ( Matrix::DistributedAccess &  da, Table::QuidTable *  columnQuids, Core::Table::SimilarityTableSet::SimTableType *  result   ) [inline, virtual] Deprecated: Note: Works only with kernel models. It uses a model trained from distributed kernels. Then 'patches' that so it can be fed a non-distributed kernel problem. This function is used by Ork (and Koen). In the new paradigm onw would create a custum TrainDataSrc. Of course this needs some more works as one would need to 'patch the model' Definition at line 133 of file Svm.h. References Impala::Core::Table::TableTem< Col1T, Col2T, Col3T, Col4T, Col5T, Col6T, Col7T, Col8T, Col9T >::Add(), Impala::Core::Table::QuidTable::Contains(), Impala::Core::Table::TableTem< Col1T, Col2T, Col3T, Col4T, Col5T, Col6T, Col7T, Col8T, Col9T >::Get1(), Impala::Core::Matrix::DistributedAccess::GetColumn(), Impala::Core::Matrix::DistributedAccess::GetColumnQuids(), Impala::Core::Matrix::DistributedAccess::GetColumns(), Impala::Core::Matrix::DistributedAccess::GetRowQuids(), Impala::Core::Matrix::DistributedAccess::GetRows(), ILOG_ERROR, ILOG_INFO, svm_node::index, svm_parameter::kernel_type, mModel, svm_model::param, PredictSingle(), Impala::Core::Table::Table::SetSize(), Impala::Core::Table::Table::Size(), and svm_node::value. Referenced by Impala::Application::LearnConceptFromAnnotations(). { /* this function can be used when the number of column quids is very, very small and the matrix is very big. This function will cache the whole (!) matrix part used, so the prediction is faster. WARNING: the columnQuids are the quids you have learned from! So NOT the quids to apply to; it will be applied to all quids that are available. */ if(!mModel) { ILOG_ERROR("[PredictForActiveLearn] classifier untrained\n"); return; } result->SetSize(0); ILOG_INFO("starting PredictForActiveLearn"); Table::QuidTable* rowQuids = da.GetRowQuids(); Table::QuidTable* allColumns = da.GetColumnQuids(); int rowCount = da.GetRows(); std::vector<Quid> sortedColumnQuids; std::vector<int> sortedColumnQuidIndices; std::vector<Real64*> sortedColumnQuidData; for(int i = 0; i < allColumns->Size(); i++) { if(columnQuids->Contains(allColumns->Get1(i))) { // we have this one sortedColumnQuids.push_back(allColumns->Get1(i)); sortedColumnQuidIndices.push_back(i); Real64* buf = new Real64[rowCount]; int received = da.GetColumn(i, buf, rowCount); if(received != rowCount) ILOG_ERROR("[PredictForActiveLearn] didn't receive column"); sortedColumnQuidData.push_back(buf); //ILOG_INFO("Loaded " << i << " " << allColumns->Get1(i)); } } if(sortedColumnQuids.size() != columnQuids->Size()) { ILOG_ERROR("not all column quids are in the table?!"); return; } ILOG_INFO("Done loading"); // PATCH THE MODEL mModel->param.kernel_type = PRECOMPUTED; int colCount = da.GetColumns(); struct svm_node* x = new struct svm_node[colCount + 2]; for(int i = 0; i < colCount + 2; i++) { x[i].index = 0; x[i].value = 0; } for(int i = 0; i < rowCount; i++) { x[0].index = 0; x[0].value = -1; // for predict this value is not necessary // fill it with values for(int j = 0; j < sortedColumnQuids.size(); j++) { int index = sortedColumnQuidIndices[j]; x[index].index = index; x[index].value = sortedColumnQuidData[j][i]; } x[colCount+1].index = -1; // end-of-vector marker x[colCount+1].value = 0; // not used //ILOG_INFO("predict " << i); double score = PredictSingle(x); result->Add(score); } delete x; for(int i = 0; i < sortedColumnQuidData.size(); i++) { delete sortedColumnQuidData[i]; } ILOG_INFO("done predict"); } Here is the call graph for this function:

---