Begin implementation

.vscode/launch.json

@@ -10,7 +10,7 @@
                 "-d",
                 "iris",
                 "-m",
-                "TAN",
+                "TANNew",
                 "-p",
                 "/Users/rmontanana/Code/discretizbench/datasets/",
                 "--tensors"
@@ -24,15 +24,12 @@
             "program": "${workspaceFolder}/build/src/Platform/main",
             "args": [
                 "-m",
-                "TAN",
+                "TANNew",
                 "-p",
                 "/Users/rmontanana/Code/discretizbench/datasets",
-                "--discretize",
                 "--stratified",
-                "--title",
-                "Debug test",
                 "-d",
-                "ionosphere"
+                "iris"
             ],
             "cwd": "${workspaceFolder}/build/src/Platform",
         },

src/BayesNet/AODE.cc

@@ -9,7 +9,7 @@ namespace bayesnet {
             models.push_back(std::make_unique<SPODE>(i));
         }
     }
-    vector<string> AODE::graph(string title)
+    vector<string> AODE::graph(const string& title)
     {
         return Ensemble::graph(title);
     }

src/BayesNet/AODE.h

@@ -9,7 +9,7 @@ namespace bayesnet {
     public:
         AODE();
         virtual ~AODE() {};
-        vector<string> graph(string title = "AODE") override;
+        vector<string> graph(const string& title = "AODE") override;
     };
 }
 #endif

src/BayesNet/BaseClassifier.h

@@ -16,7 +16,7 @@ namespace bayesnet {
         int virtual getNumberOfEdges() = 0;
         int virtual getNumberOfStates() = 0;
         vector<string> virtual show() = 0;
-        vector<string> virtual graph(string title = "") = 0;
+        vector<string> virtual graph(const string& title = "") = 0;
         virtual ~BaseClassifier() = default;
         const string inline getVersion() const { return "0.1.0"; };
     };

src/BayesNet/CMakeLists.txt

@@ -1,2 +1,3 @@
-add_library(BayesNet bayesnetUtils.cc Network.cc Node.cc BayesMetrics.cc Classifier.cc KDB.cc TAN.cc SPODE.cc Ensemble.cc AODE.cc Mst.cc)
+include_directories(${BayesNet_SOURCE_DIR}/lib/mdlp)
-target_link_libraries(BayesNet "${TORCH_LIBRARIES}")
+add_library(BayesNet bayesnetUtils.cc Network.cc Node.cc BayesMetrics.cc Classifier.cc KDB.cc TAN.cc SPODE.cc Ensemble.cc AODE.cc TANNew.cc Mst.cc)
+target_link_libraries(BayesNet mdlp "${TORCH_LIBRARIES}")

src/BayesNet/Ensemble.cc

@@ -139,7 +139,7 @@ namespace bayesnet {
         }
         return result;
     }
-    vector<string> Ensemble::graph(string title)
+    vector<string> Ensemble::graph(const string& title)
     {
         auto result = vector<string>();
         for (auto i = 0; i < n_models; ++i) {

src/BayesNet/Ensemble.h

@@ -40,7 +40,7 @@ namespace bayesnet {
         int getNumberOfEdges() override;
         int getNumberOfStates() override;
         vector<string> show() override;
-        vector<string> graph(string title) override;
+        vector<string> graph(const string& title) override;
     };
 }
 #endif

src/BayesNet/KDB.cc

@@ -79,11 +79,12 @@ namespace bayesnet {
             exit_cond = num == n_edges || candidates.size(0) == 0;
         }
     }
-    vector<string> KDB::graph(string title)
+    vector<string> KDB::graph(const string& title)
     {
+        string header{ title };
         if (title == "KDB") {
-            title += " (k=" + to_string(k) + ", theta=" + to_string(theta) + ")";
+            header += " (k=" + to_string(k) + ", theta=" + to_string(theta) + ")";
         }
-        return model.graph(title);
+        return model.graph(header);
     }
 }

src/BayesNet/KDB.h

@@ -15,7 +15,7 @@ namespace bayesnet {
     public:
         explicit KDB(int k, float theta = 0.03);
         virtual ~KDB() {};
-        vector<string> graph(string name = "KDB") override;
+        vector<string> graph(const string& name = "KDB") override;
     };
 }
 #endif

src/BayesNet/SPODE.cc

@@ -17,7 +17,7 @@ namespace bayesnet {
             }
         }
     }
-    vector<string> SPODE::graph(string name )
+    vector<string> SPODE::graph(const string& name)
     {
         return model.graph(name);
     }

src/BayesNet/SPODE.h

@@ -11,7 +11,7 @@ namespace bayesnet {
     public:
         explicit SPODE(int root);
         virtual ~SPODE() {};
-        vector<string> graph(string name = "SPODE") override;
+        vector<string> graph(const string& name = "SPODE") override;
     };
 }
 #endif

src/BayesNet/TAN.cc

@@ -34,7 +34,7 @@ namespace bayesnet {
             model.addEdge(className, feature);
         }
     }
-    vector<string> TAN::graph(string title)
+    vector<string> TAN::graph(const string& title)
     {
         return model.graph(title);
     }

src/BayesNet/TAN.h

@@ -11,7 +11,7 @@ namespace bayesnet {
     public:
         TAN();
         virtual ~TAN() {};
-        vector<string> graph(string name = "TAN") override;
+        vector<string> graph(const string& name = "TAN") override;
     };
 }
 #endif

src/BayesNet/TANNew.cc

@@ -0,0 +1,23 @@
+#include "TANNew.h"
+
+namespace bayesnet {
+    using namespace std;
+    TANNew::TANNew() : TAN(), discretizer{ mdlp::CPPFImdlp() } {}
+    TANNew::~TANNew() {}
+    TANNew& TANNew::fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states)
+    {
+        /*
+        Hay que discretizar los datos de entrada y luego en predict discretizar también con el mmismo modelo, hacer un transform solamente.
+        */
+        TAN::fit(X, y, features, className, states);
+        return *this;
+    }
+    void TANNew::train()
+    {
+        TAN::train();
+    }
+    vector<string> TANNew::graph(const string& name)
+    {
+        return TAN::graph(name);
+    }
+}

src/BayesNet/TANNew.h

@@ -0,0 +1,21 @@
+#ifndef TANNEW_H
+#define TANNEW_H
+#include "TAN.h"
+#include "CPPFImdlp.h"
+
+namespace bayesnet {
+    using namespace std;
+    class TANNew : public TAN {
+    private:
+        mdlp::CPPFImdlp discretizer;
+    public:
+        TANNew();
+        virtual ~TANNew();
+        void train() override;
+        TANNew& fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states) override;
+        vector<string> graph(const string& name = "TAN") override;
+        static inline string version() { return "0.0.1"; };
+    };
+}
+
+#endif // !TANNEW_H

src/Platform/Datasets.cc

@@ -207,9 +207,9 @@ namespace platform {
         if (discretize) {
             Xd = discretizeDataset(Xv, yv);
             computeStates();
-            n_samples = Xd[0].size();
-            n_features = Xd.size();
         }
+        n_samples = Xv[0].size();
+        n_features = Xv.size();
         loaded = true;
     }
     void Dataset::buildTensors()

src/Platform/Experiment.cc

@@ -104,7 +104,7 @@ namespace platform {
 
     void Experiment::cross_validation(const string& path, const string& fileName)
     {
-        auto datasets = platform::Datasets(path, true, platform::ARFF);
+        auto datasets = platform::Datasets(path, discretized, platform::ARFF);
         // Get dataset
         auto [X, y] = datasets.getTensors(fileName);
         auto states = datasets.getStates(fileName);

src/Platform/Models.h

@@ -6,6 +6,7 @@
 #include "TAN.h"
 #include "KDB.h"
 #include "SPODE.h"
+#include "TANNew.h"
 namespace platform {
     class Models {
     private:

src/Platform/modelRegister.h

@@ -2,6 +2,8 @@
 #define MODEL_REGISTER_H
 static platform::Registrar registrarT("TAN",
     [](void) -> bayesnet::BaseClassifier* { return new bayesnet::TAN();});
+static platform::Registrar registrarTN("TANNew",
+    [](void) -> bayesnet::BaseClassifier* { return new bayesnet::TANNew();});
 static platform::Registrar registrarS("SPODE",
     [](void) -> bayesnet::BaseClassifier* { return new bayesnet::SPODE(2);});
 static platform::Registrar registrarK("KDB",