Add report output to main

src/BayesNet/KDB.cc

@@ -35,7 +35,6 @@ namespace bayesnet {
         }
         // 2. Compute class conditional mutual information I(Xi;XjIC), f or each
         auto conditionalEdgeWeights = metrics.conditionalEdge();
-        cout << "Conditional edge weights: " << conditionalEdgeWeights << endl;
         // 3. Let the used variable list, S, be empty.
         vector<int> S;
         // 4. Let the DAG network being constructed, BN, begin with a single

src/BayesNet/KDBNew.cc

@@ -10,15 +10,12 @@ namespace bayesnet {
         className = className_;
         Xf = X_;
         y = y_;
-        model.initialize();
         // Fills vectors Xv & yv with the data from tensors X_ (discretized) & y
         fit_local_discretization(states, y);
         generateTensorXFromVector();
         // We have discretized the input data
-        // 1st we need to fit the model to build the normal TAN structure, TAN::fit initializes the base Bayesian network
-        cout << "KDBNew: Fitting model" << endl;
+        // 1st we need to fit the model to build the normal KDB structure, KDB::fit initializes the base Bayesian network
         KDB::fit(KDB::Xv, KDB::yv, features, className, states);
-        cout << "KDBNew: Model fitted" << endl;
         localDiscretizationProposal(states, model);
         generateTensorXFromVector();
         Tensor ytmp = torch::transpose(y.view({ y.size(0), 1 }), 0, 1);
@@ -26,20 +23,10 @@ namespace bayesnet {
         model.fit(KDB::Xv, KDB::yv, features, className);
         return *this;
     }
-    void KDBNew::train()
-    {
-        KDB::train();
-    }
     Tensor KDBNew::predict(Tensor& X)
     {
-        auto Xtd = torch::zeros_like(X, torch::kInt32);
-        for (int i = 0; i < X.size(0); ++i) {
-            auto Xt = vector<float>(X[i].data_ptr<float>(), X[i].data_ptr<float>() + X.size(1));
-            auto Xd = discretizers[features[i]]->transform(Xt);
-            Xtd.index_put_({ i }, torch::tensor(Xd, torch::kInt32));
-        }
-        cout << "KDBNew Xtd: " << Xtd.sizes() << endl;
-        return KDB::predict(Xtd);
+        auto Xt = prepareX(X);
+        return KDB::predict(Xt);
     }
     vector<string> KDBNew::graph(const string& name)
     {

src/BayesNet/KDBNew.h

@@ -13,7 +13,6 @@ namespace bayesnet {
         KDBNew& fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states) override;
         vector<string> graph(const string& name = "KDB") override;
         Tensor predict(Tensor& X) override;
-        void train() override;
         static inline string version() { return "0.0.1"; };
     };
 }

src/BayesNet/Proposal.cc

@@ -47,25 +47,25 @@ namespace bayesnet {
             //
             //
             //
-            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
-        //     for (auto index : indicesToReDiscretize) {
-        //         auto Xt_ptr = Xf.index({ index }).data_ptr<float>();
-        //         auto Xt = vector<float>(Xt_ptr, Xt_ptr + Xf.size(1));
-        //         Xv[index] = discretizers[pFeatures[index]]->transform(Xt);
+            // 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[pFeatures[index]] = xStates;
-        //     }
-        // }
+            // states[feature] = xStates;
+        }
+        if (upgrade) {
+            // Discretize again X (only the affected indices) with the new fitted discretizers
+            for (auto index : indicesToReDiscretize) {
+                auto Xt_ptr = Xf.index({ index }).data_ptr<float>();
+                auto Xt = vector<float>(Xt_ptr, Xt_ptr + Xf.size(1));
+                Xv[index] = discretizers[pFeatures[index]]->transform(Xt);
+                auto xStates = vector<int>(discretizers[pFeatures[index]]->getCutPoints().size() + 1);
+                iota(xStates.begin(), xStates.end(), 0);
+                //Update new states of the feature/node
+                states[pFeatures[index]] = xStates;
+            }
+        }
     }
     void Proposal::fit_local_discretization(map<string, vector<int>>& states, torch::Tensor& y)
     {
@@ -89,4 +89,14 @@ namespace bayesnet {
         iota(yStates.begin(), yStates.end(), 0);
         states[pClassName] = yStates;
     }
+    torch::Tensor Proposal::prepareX(torch::Tensor& X)
+    {
+        auto Xtd = torch::zeros_like(X, torch::kInt32);
+        for (int i = 0; i < X.size(0); ++i) {
+            auto Xt = vector<float>(X[i].data_ptr<float>(), X[i].data_ptr<float>() + X.size(1));
+            auto Xd = discretizers[pFeatures[i]]->transform(Xt);
+            Xtd.index_put_({ i }, torch::tensor(Xd, torch::kInt32));
+        }
+        return Xtd;
+    }
 }

src/BayesNet/Proposal.h

@@ -5,6 +5,7 @@
 #include <torch/torch.h>
 #include "Network.h"
 #include "CPPFImdlp.h"
+#include "Classifier.h"
 
 namespace bayesnet {
     class Proposal {
@@ -12,6 +13,7 @@ namespace bayesnet {
         Proposal(vector<vector<int>>& Xv_, vector<int>& yv_, vector<string>& features_, string& className_);
         virtual ~Proposal();
     protected:
+        torch::Tensor prepareX(torch::Tensor& X);
         void localDiscretizationProposal(map<string, vector<int>>& states, Network& model);
         void fit_local_discretization(map<string, vector<int>>& states, torch::Tensor& y);
         torch::Tensor Xf; // X continuous nxm tensor

src/BayesNet/TANNew.cc

@@ -15,9 +15,7 @@ namespace bayesnet {
         generateTensorXFromVector();
         // We have discretized the input data
         // 1st we need to fit the model to build the normal TAN structure, TAN::fit initializes the base Bayesian network
-        cout << "TANNew: Fitting model" << endl;
         TAN::fit(TAN::Xv, TAN::yv, features, className, states);
-        cout << "TANNew: Model fitted" << endl;
         localDiscretizationProposal(states, model);
         generateTensorXFromVector();
         Tensor ytmp = torch::transpose(y.view({ y.size(0), 1 }), 0, 1);
@@ -27,14 +25,8 @@ namespace bayesnet {
     }
     Tensor TANNew::predict(Tensor& X)
     {
-        auto Xtd = torch::zeros_like(X, torch::kInt32);
-        for (int i = 0; i < X.size(0); ++i) {
-            auto Xt = vector<float>(X[i].data_ptr<float>(), X[i].data_ptr<float>() + X.size(1));
-            auto Xd = discretizers[features[i]]->transform(Xt);
-            Xtd.index_put_({ i }, torch::tensor(Xd, torch::kInt32));
-        }
-        cout << "TANNew Xtd: " << Xtd.sizes() << endl;
-        return TAN::predict(Xtd);
+        auto Xt = prepareX(X);
+        return TAN::predict(Xt);
     }
     vector<string> TANNew::graph(const string& name)
     {

src/Platform/CMakeLists.txt

@@ -4,5 +4,5 @@ include_directories(${BayesNet_SOURCE_DIR}/lib/Files)
 include_directories(${BayesNet_SOURCE_DIR}/lib/mdlp)
 include_directories(${BayesNet_SOURCE_DIR}/lib/argparse/include)
 include_directories(${BayesNet_SOURCE_DIR}/lib/json/include)
-add_executable(main main.cc Folding.cc platformUtils.cc Experiment.cc Datasets.cc Models.cc)
+add_executable(main main.cc Folding.cc platformUtils.cc Experiment.cc Datasets.cc Models.cc Report.cc)
 target_link_libraries(main BayesNet ArffFiles mdlp "${TORCH_LIBRARIES}")

src/Platform/Experiment.cc

@@ -1,6 +1,7 @@
 #include "Experiment.h"
 #include "Datasets.h"
 #include "Models.h"
+#include "Report.h"
 
 namespace platform {
     using json = nlohmann::json;
@@ -86,6 +87,13 @@ namespace platform {
         file.close();
     }
 
+    void Experiment::report()
+    {
+        json data = build_json();
+        Report report(data);
+        report.show();
+    }
+
     void Experiment::show()
     {
         json data = build_json();
@@ -146,11 +154,6 @@ namespace platform {
                 auto y_test = y.index({ test_t });
                 cout << nfold + 1 << ", " << flush;
                 clf->fit(X_train, y_train, features, className, states);
-                cout << endl;
-                auto lines = clf->show();
-                for (auto line : lines) {
-                    cout << line << endl;
-                }
                 nodes[item] = clf->getNumberOfNodes();
                 edges[item] = clf->getNumberOfEdges();
                 num_states[item] = clf->getNumberOfStates();

src/Platform/Experiment.h

@@ -108,6 +108,7 @@ namespace platform {
         void cross_validation(const string& path, const string& fileName);
         void go(vector<string> filesToProcess, const string& path);
         void show();
+        void report();
     };
 }
 #endif

src/Platform/Report.cc

@@ -0,0 +1,66 @@
+#include "Report.h"
+
+namespace platform {
+    string headerLine(const string& text)
+    {
+        int n = MAXL - text.length() - 3;
+        return "* " + text + string(n, ' ') + "*\n";
+    }
+    string Report::fromVector(const string& key)
+    {
+        string result = "";
+
+        for (auto& item : data[key]) {
+            result += to_string(item) + ", ";
+        }
+        return "[" + result.substr(0, result.length() - 2) + "]";
+    }
+    string fVector(const json& data)
+    {
+        string result = "";
+        for (const auto& item : data) {
+            result += to_string(item) + ", ";
+        }
+        return "[" + result.substr(0, result.length() - 2) + "]";
+    }
+    void Report::show()
+    {
+        header();
+        body();
+    }
+    void Report::header()
+    {
+        cout << string(MAXL, '*') << endl;
+        cout << headerLine("Report " + data["model"].get<string>() + " ver. " + data["version"].get<string>() + " with " + to_string(data["folds"].get<int>()) + " Folds cross validation and " + to_string(data["seeds"].size()) + " random seeds. " + data["date"].get<string>() + " " + data["time"].get<string>());
+        cout << headerLine(data["title"].get<string>());
+        cout << headerLine("Random seeds: " + fromVector("seeds") + " Stratified: " + (data["stratified"].get<bool>() ? "True" : "False"));
+        cout << headerLine("Execution took  " + to_string(data["duration"].get<float>()) + " seconds,   " + to_string(data["duration"].get<float>() / 3600) + " hours, on " + data["platform"].get<string>());
+        cout << headerLine("Score is " + data["score_name"].get<string>());
+        cout << string(MAXL, '*') << endl;
+        cout << endl;
+    }
+    void Report::body()
+    {
+        cout << "Dataset                        Sampl. Feat. Cls Nodes   Edges   States  Score           Time              Hyperparameters" << endl;
+        cout << "============================== ====== ===== === ======= ======= ======= =============== ================= ===============" << endl;
+        for (const auto& r : data["results"]) {
+            cout << setw(30) << left << r["dataset"].get<string>() << " ";
+            cout << setw(6) << right << r["samples"].get<int>() << " ";
+            cout << setw(5) << right << r["features"].get<int>() << " ";
+            cout << setw(3) << right << r["classes"].get<int>() << " ";
+            cout << setw(7) << right << r["nodes"].get<float>() << " ";
+            cout << setw(7) << right << r["leaves"].get<float>() << " ";
+            cout << setw(7) << right << r["depth"].get<float>() << " ";
+            cout << setw(8) << right << setprecision(6) << fixed << r["score_test"].get<double>() << "±" << setw(6) << setprecision(4) << fixed << r["score_test_std"].get<double>() << " ";
+            cout << setw(10) << right << setprecision(6) << fixed << r["test_time"].get<double>() << "±" << setw(6) << setprecision(4) << fixed << r["test_time_std"].get<double>() << " ";
+            cout << " " << r["hyperparameters"].get<string>();
+            cout << endl;
+            cout << string(MAXL, '*') << endl;
+            cout << headerLine("Train scores: " + fVector(r["scores_train"]));
+            cout << headerLine("Test  scores: " + fVector(r["scores_test"]));
+            cout << headerLine("Train  times: " + fVector(r["times_train"]));
+            cout << headerLine("Test   times: " + fVector(r["times_test"]));
+            cout << string(MAXL, '*') << endl;
+        }
+    }
+}

src/Platform/Report.h

@@ -0,0 +1,23 @@
+#ifndef REPORT_H
+#define REPORT_H
+#include <string>
+#include <iostream>
+#include <nlohmann/json.hpp>
+
+using json = nlohmann::json;
+const int MAXL = 121;
+namespace platform {
+    using namespace std;
+    class Report {
+    public:
+        explicit Report(json data_) { data = data_; };
+        virtual ~Report() = default;
+        void show();
+    private:
+        void header();
+        void body();
+        string fromVector(const string& key);
+        json data;
+    };
+};
+#endif

src/Platform/main.cc

@@ -116,7 +116,7 @@ int main(int argc, char** argv)
     if (saveResults)
         experiment.save(PATH_RESULTS);
     else
-        experiment.show();
+        experiment.report();
     cout << "Done!" << endl;
     return 0;
 }