Solve voting vector error

.vscode/launch.json

@@ -27,15 +27,15 @@
                 "-m",
                 "AODE",
                 "-p",
-                "/Users/rmontanana/Code/discretizbench/datasets",
+                "/home/rmontanana/Code/discretizbench/datasets",
                 "--stratified",
                 "-d",
-                "letter",
+                "mfeat-morphological",
                 "--discretize"
                 // "--hyperparameters",
                 // "{\"repeatSparent\": true, \"maxModels\": 12}"
             ],
-            "cwd": "/Users/rmontanana/Code/discretizbench",
+            "cwd": "/home/rmontanana/Code/discretizbench",
         },
         {
             "type": "lldb",

CMakeLists.txt

@@ -1,7 +1,7 @@
 cmake_minimum_required(VERSION 3.20)
 
 project(BayesNet
-  VERSION 0.1.0
+  VERSION 0.2.0
   DESCRIPTION "Bayesian Network and basic classifiers Library."
   HOMEPAGE_URL "https://github.com/rmontanana/bayesnet"
   LANGUAGES CXX
@@ -40,8 +40,7 @@ if (CODE_COVERAGE)
     enable_testing()
     include(CodeCoverage)
     MESSAGE("Code coverage enabled")
-    set(CMAKE_C_FLAGS " ${CMAKE_C_FLAGS} -fprofile-arcs -ftest-coverage")
+    set(CMAKE_CXX_FLAGS " ${CMAKE_CXX_FLAGS} -fprofile-arcs -ftest-coverage -O0")
-    set(CMAKE_CXX_FLAGS " ${CMAKE_CXX_FLAGS} -fprofile-arcs -ftest-coverage")
     SET(GCC_COVERAGE_LINK_FLAGS " ${GCC_COVERAGE_LINK_FLAGS} -lgcov --coverage")
 endif (CODE_COVERAGE)
 

data/_TAN_cpp_accuracy__.json

@@ -1 +0,0 @@
-null

src/BayesNet/Classifier.cc

@@ -13,7 +13,7 @@ namespace bayesnet {
         m = dataset.size(1);
         n = dataset.size(0) - 1;
         checkFitParameters();
-        auto n_classes = states[className].size();
+        auto n_classes = states.at(className).size();
         metrics = Metrics(dataset, features, className, n_classes);
         model.initialize();
         buildModel(weights);

src/BayesNet/Ensemble.cc

@@ -17,9 +17,13 @@ namespace bayesnet {
     {
         auto y_pred_ = y_pred.accessor<int, 2>();
         vector<int> y_pred_final;
+        int numClasses = states.at(className).size();
+        // y_pred is m x n_models with the prediction of every model for each sample
         for (int i = 0; i < y_pred.size(0); ++i) {
-            vector<double> votes(y_pred.size(1), 0);
+            // votes store in each index (value of class) the significance added by each model
-            for (int j = 0; j < y_pred.size(1); ++j) {
+            // i.e. votes[0] contains how much value has the value 0 of class. That value is generated by the models predictions
+            vector<double> votes(numClasses, 0.0);
+            for (int j = 0; j < n_models; ++j) {
                 votes[y_pred_[i][j]] += significanceModels[j];
             }
             // argsort in descending order
@@ -34,22 +38,17 @@ namespace bayesnet {
             throw logic_error("Ensemble has not been fitted");
         }
         Tensor y_pred = torch::zeros({ X.size(1), n_models }, kInt32);
-        // //Create a threadpool
+        auto threads{ vector<thread>() };
-        // auto threads{ vector<thread>() };
+        mutex mtx;
-        // mutex mtx;
-        // for (auto i = 0; i < n_models; ++i) {
-        //     threads.push_back(thread([&, i]() {
-        //         auto ypredict = models[i]->predict(X);
-        //         lock_guard<mutex> lock(mtx);
-        //         y_pred.index_put_({ "...", i }, ypredict);
-        //         }));
-        //     Hacer voting aquí ? ? ?
-        // }
-        // for (auto& thread : threads) {
-        //     thread.join();
-        // }
         for (auto i = 0; i < n_models; ++i) {
-            y_pred.index_put_({ "...", i }, models[i]->predict(X));
+            threads.push_back(thread([&, i]() {
+                auto ypredict = models[i]->predict(X);
+                lock_guard<mutex> lock(mtx);
+                y_pred.index_put_({ "...", i }, ypredict);
+                }));
+        }
+        for (auto& thread : threads) {
+            thread.join();
         }
         return torch::tensor(voting(y_pred));
     }

src/BayesNet/Network.cc

@@ -299,25 +299,19 @@ namespace bayesnet {
     vector<double> Network::exactInference(map<string, int>& evidence)
     {
         vector<double> result(classNumStates, 0.0);
-        // vector<thread> threads;
+        vector<thread> threads;
-        // mutex mtx;
+        mutex mtx;
-        // for (int i = 0; i < classNumStates; ++i) {
-        //     threads.emplace_back([this, &result, &evidence, i, &mtx]() {
-        //         auto completeEvidence = map<string, int>(evidence);
-        //         completeEvidence[getClassName()] = i;
-        //         double factor = computeFactor(completeEvidence);
-        //         lock_guard<mutex> lock(mtx);
-        //         result[i] = factor;
-        //         });
-        // }
-        // for (auto& thread : threads) {
-        //     thread.join();
-        // }
         for (int i = 0; i < classNumStates; ++i) {
-            auto completeEvidence = map<string, int>(evidence);
+            threads.emplace_back([this, &result, &evidence, i, &mtx]() {
-            completeEvidence[getClassName()] = i;
+                auto completeEvidence = map<string, int>(evidence);
-            double factor = computeFactor(completeEvidence);
+                completeEvidence[getClassName()] = i;
-            result[i] = factor;
+                double factor = computeFactor(completeEvidence);
+                lock_guard<mutex> lock(mtx);
+                result[i] = factor;
+                });
+        }
+        for (auto& thread : threads) {
+            thread.join();
         }
         // Normalize result
         double sum = accumulate(result.begin(), result.end(), 0.0);

src/BayesNet/Node.cc

@@ -100,7 +100,7 @@ namespace bayesnet {
         }
         int name_index = pos - features.begin();
         for (int n_sample = 0; n_sample < dataset.size(1); ++n_sample) {
-            torch::List<c10::optional<torch::Tensor>> coordinates;
+            c10::List<c10::optional<at::Tensor>> coordinates;
             coordinates.push_back(dataset.index({ name_index, n_sample }));
             for (auto parent : parents) {
                 pos = find(features.begin(), features.end(), parent->getName());
@@ -118,10 +118,10 @@ namespace bayesnet {
     }
     float Node::getFactorValue(map<string, int>& evidence)
     {
-        torch::List<c10::optional<torch::Tensor>> coordinates;
+        c10::List<c10::optional<at::Tensor>> coordinates;
         // following predetermined order of indices in the cpTable (see Node.h)
-        coordinates.push_back(torch::tensor(evidence[name]));
+        coordinates.push_back(at::tensor(evidence[name]));
-        transform(parents.begin(), parents.end(), back_inserter(coordinates), [&evidence](const auto& parent) { return torch::tensor(evidence[parent->getName()]); });
+        transform(parents.begin(), parents.end(), back_inserter(coordinates), [&evidence](const auto& parent) { return at::tensor(evidence[parent->getName()]); });
         return cpTable.index({ coordinates }).item<float>();
     }
     vector<string> Node::graph(const string& className)

src/BayesNet/Proposal.cc

@@ -53,15 +53,6 @@ namespace bayesnet {
             auto xvf_ptr = Xf.index({ index }).data_ptr<float>();
             auto xvf = vector<mdlp::precision_t>(xvf_ptr, xvf_ptr + Xf.size(1));
             discretizers[feature]->fit(xvf, yxv);
-            //
-            //
-            //
-            // auto tmp = discretizers[feature]->transform(xvf);
-            // Xv[index] = tmp;
-            // auto xStates = vector<int>(discretizers[pFeatures[index]]->getCutPoints().size() + 1);
-            // iota(xStates.begin(), xStates.end(), 0);
-            // //Update new states of the feature/node
-            // states[feature] = xStates;
         }
         if (upgrade) {
             // Discretize again X (only the affected indices) with the new fitted discretizers

src/Platform/Datasets.cc

@@ -213,10 +213,11 @@ namespace platform {
     {
         for (int i = 0; i < features.size(); ++i) {
             states[features[i]] = vector<int>(*max_element(Xd[i].begin(), Xd[i].end()) + 1);
-            iota(begin(states[features[i]]), end(states[features[i]]), 0);
+            auto item = states.at(features[i]);
+            iota(begin(item), end(item), 0);
         }
         states[className] = vector<int>(*max_element(yv.begin(), yv.end()) + 1);
-        iota(begin(states[className]), end(states[className]), 0);
+        iota(begin(states.at(className)), end(states.at(className)), 0);
     }
     void Dataset::load_arff()
     {

src/Platform/Experiment.cc

@@ -182,6 +182,7 @@ namespace platform {
                 clf.reset();
             }
             cout << "end. " << flush;
+            delete fold;
         }
         result.setScoreTest(torch::mean(accuracy_test).item<double>()).setScoreTrain(torch::mean(accuracy_train).item<double>());
         result.setScoreTestStd(torch::std(accuracy_test).item<double>()).setScoreTrainStd(torch::std(accuracy_train).item<double>());

src/Platform/platformUtils.cc

@@ -69,11 +69,12 @@ tuple<Tensor, Tensor, vector<string>, string, map<string, vector<int>>> loadData
         Xd = torch::zeros({ static_cast<int>(Xr[0].size()), static_cast<int>(Xr.size()) }, torch::kInt32);
         for (int i = 0; i < features.size(); ++i) {
             states[features[i]] = vector<int>(*max_element(Xr[i].begin(), Xr[i].end()) + 1);
-            iota(begin(states[features[i]]), end(states[features[i]]), 0);
+            auto item = states.at(features[i]);
+            iota(begin(item), end(item), 0);
             Xd.index_put_({ "...", i }, torch::tensor(Xr[i], torch::kInt32));
         }
         states[className] = vector<int>(*max_element(y.begin(), y.end()) + 1);
-        iota(begin(states[className]), end(states[className]), 0);
+        iota(begin(states.at(className)), end(states.at(className)), 0);
     } else {
         Xd = torch::zeros({ static_cast<int>(X[0].size()), static_cast<int>(X.size()) }, torch::kFloat32);
         for (int i = 0; i < features.size(); ++i) {