.vscode/launch.json

@@ -46,6 +46,14 @@
             ],
             "cwd": "/Users/rmontanana/Code/discretizbench",
         },
+        {
+            "type": "lldb",
+            "request": "launch",
+            "name": "list",
+            "program": "${workspaceFolder}/build/src/Platform/list",
+            "args": [],
+            "cwd": "/Users/rmontanana/Code/discretizbench",
+        },
         {
             "name": "Build & debug active file",
             "type": "cppdbg",

.vscode/tasks.json

@@ -32,6 +32,29 @@
             ],
             "group": "build",
             "detail": "Task generated by Debugger."
+        },
+        {
+            "type": "cppbuild",
+            "label": "C/C++: g++ build active file",
+            "command": "/usr/bin/g++",
+            "args": [
+                "-fdiagnostics-color=always",
+                "-g",
+                "${file}",
+                "-o",
+                "${fileDirname}/${fileBasenameNoExtension}"
+            ],
+            "options": {
+                "cwd": "${fileDirname}"
+            },
+            "problemMatcher": [
+                "$gcc"
+            ],
+            "group": {
+                "kind": "build",
+                "isDefault": true
+            },
+            "detail": "Task generated by Debugger."
         }
     ]
 }

Makefile

@@ -15,7 +15,7 @@ dependency: ## Create a dependency graph diagram of the project (build/dependenc
 	cd build && cmake .. --graphviz=dependency.dot && dot -Tpng dependency.dot -o dependency.png
 
 build: ## Build the main and BayesNetSample
-	cmake --build build -t main -t BayesNetSample -t manage -j 32
+	cmake --build build -t main -t BayesNetSample -t manage -t list -j 32
 
 clean: ## Clean the debug info
 	@echo ">>> Cleaning Debug BayesNet ...";
@@ -35,7 +35,7 @@ release: ## Build a Release version of the project
 	@if [ -d ./build ]; then rm -rf ./build; fi
 	@mkdir build; 
 	cmake -S . -B build -D CMAKE_BUILD_TYPE=Release; \
-	cmake --build build -t main -t BayesNetSample -t manage -j 32;
+	cmake --build build -t main -t BayesNetSample -t manage -t list -j 32;
 	@echo ">>> Done";	
 
 test: ## Run tests

src/Platform/CMakeLists.txt

@@ -6,5 +6,7 @@ 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 Report.cc)
 add_executable(manage manage.cc Results.cc Report.cc)
+add_executable(list list.cc platformUtils Datasets.cc)
 target_link_libraries(main BayesNet ArffFiles mdlp "${TORCH_LIBRARIES}")
-target_link_libraries(manage "${TORCH_LIBRARIES}")
+target_link_libraries(manage "${TORCH_LIBRARIES}")
+target_link_libraries(list ArffFiles mdlp "${TORCH_LIBRARIES}")

src/Platform/Datasets.cc

@@ -24,75 +24,110 @@ namespace platform {
         transform(datasets.begin(), datasets.end(), back_inserter(result), [](const auto& d) { return d.first; });
         return result;
     }
-    vector<string> Datasets::getFeatures(string name)
+    vector<string> Datasets::getFeatures(const string& name) const
     {
-        if (datasets[name]->isLoaded()) {
+        if (datasets.at(name)->isLoaded()) {
-            return datasets[name]->getFeatures();
+            return datasets.at(name)->getFeatures();
         } else {
             throw invalid_argument("Dataset not loaded.");
         }
     }
-    map<string, vector<int>> Datasets::getStates(string name)
+    map<string, vector<int>> Datasets::getStates(const string& name) const
     {
-        if (datasets[name]->isLoaded()) {
+        if (datasets.at(name)->isLoaded()) {
-            return datasets[name]->getStates();
+            return datasets.at(name)->getStates();
         } else {
             throw invalid_argument("Dataset not loaded.");
         }
     }
-    string Datasets::getClassName(string name)
+    void Datasets::loadDataset(const string& name) const
     {
-        if (datasets[name]->isLoaded()) {
+        if (datasets.at(name)->isLoaded()) {
-            return datasets[name]->getClassName();
+            return;
+        } else {
+            datasets.at(name)->load();
+        }
+    }
+    string Datasets::getClassName(const string& name) const
+    {
+        if (datasets.at(name)->isLoaded()) {
+            return datasets.at(name)->getClassName();
         } else {
             throw invalid_argument("Dataset not loaded.");
         }
     }
-    int Datasets::getNSamples(string name)
+    int Datasets::getNSamples(const string& name) const
     {
-        if (datasets[name]->isLoaded()) {
+        if (datasets.at(name)->isLoaded()) {
-            return datasets[name]->getNSamples();
+            return datasets.at(name)->getNSamples();
         } else {
             throw invalid_argument("Dataset not loaded.");
         }
     }
-    pair<vector<vector<float>>&, vector<int>&> Datasets::getVectors(string name)
+    int Datasets::getNClasses(const string& name)
+    {
+        if (datasets.at(name)->isLoaded()) {
+            auto className = datasets.at(name)->getClassName();
+            if (discretize) {
+                auto states = getStates(name);
+                return states.at(className).size();
+            }
+            auto [Xv, yv] = getVectors(name);
+            return *max_element(yv.begin(), yv.end()) + 1;
+        } else {
+            throw invalid_argument("Dataset not loaded.");
+        }
+    }
+    vector<int> Datasets::getClassesCounts(const string& name) const
+    {
+        if (datasets.at(name)->isLoaded()) {
+            auto [Xv, yv] = datasets.at(name)->getVectors();
+            vector<int> counts(*max_element(yv.begin(), yv.end()) + 1);
+            for (auto y : yv) {
+                counts[y]++;
+            }
+            return counts;
+        } else {
+            throw invalid_argument("Dataset not loaded.");
+        }
+    }
+    pair<vector<vector<float>>&, vector<int>&> Datasets::getVectors(const string& name)
     {
         if (!datasets[name]->isLoaded()) {
             datasets[name]->load();
         }
         return datasets[name]->getVectors();
     }
-    pair<vector<vector<int>>&, vector<int>&> Datasets::getVectorsDiscretized(string name)
+    pair<vector<vector<int>>&, vector<int>&> Datasets::getVectorsDiscretized(const string& name)
     {
         if (!datasets[name]->isLoaded()) {
             datasets[name]->load();
         }
         return datasets[name]->getVectorsDiscretized();
     }
-    pair<torch::Tensor&, torch::Tensor&> Datasets::getTensors(string name)
+    pair<torch::Tensor&, torch::Tensor&> Datasets::getTensors(const string& name)
     {
         if (!datasets[name]->isLoaded()) {
             datasets[name]->load();
         }
         return datasets[name]->getTensors();
     }
-    bool Datasets::isDataset(const string& name)
+    bool Datasets::isDataset(const string& name) const
     {
         return datasets.find(name) != datasets.end();
     }
     Dataset::Dataset(const Dataset& dataset) : path(dataset.path), name(dataset.name), className(dataset.className), n_samples(dataset.n_samples), n_features(dataset.n_features), features(dataset.features), states(dataset.states), loaded(dataset.loaded), discretize(dataset.discretize), X(dataset.X), y(dataset.y), Xv(dataset.Xv), Xd(dataset.Xd), yv(dataset.yv), fileType(dataset.fileType)
     {
     }
-    string Dataset::getName()
+    string Dataset::getName() const
     {
         return name;
     }
-    string Dataset::getClassName()
+    string Dataset::getClassName() const
     {
         return className;
     }
-    vector<string> Dataset::getFeatures()
+    vector<string> Dataset::getFeatures() const
     {
         if (loaded) {
             return features;
@@ -100,7 +135,7 @@ namespace platform {
             throw invalid_argument("Dataset not loaded.");
         }
     }
-    int Dataset::getNFeatures()
+    int Dataset::getNFeatures() const
     {
         if (loaded) {
             return n_features;
@@ -108,7 +143,7 @@ namespace platform {
             throw invalid_argument("Dataset not loaded.");
         }
     }
-    int Dataset::getNSamples()
+    int Dataset::getNSamples() const
     {
         if (loaded) {
             return n_samples;
@@ -116,7 +151,7 @@ namespace platform {
             throw invalid_argument("Dataset not loaded.");
         }
     }
-    map<string, vector<int>> Dataset::getStates()
+    map<string, vector<int>> Dataset::getStates() const
     {
         if (loaded) {
             return states;

src/Platform/Datasets.h

@@ -29,15 +29,15 @@ namespace platform {
     public:
         Dataset(const string& path, const string& name, const string& className, bool discretize, fileType_t fileType) : path(path), name(name), className(className), discretize(discretize), loaded(false), fileType(fileType) {};
         explicit Dataset(const Dataset&);
-        string getName();
+        string getName() const;
-        string getClassName();
+        string getClassName() const;
-        vector<string> getFeatures();
+        vector<string> getFeatures() const;
-        map<string, vector<int>> getStates();
+        map<string, vector<int>> getStates() const;
         pair<vector<vector<float>>&, vector<int>&> getVectors();
         pair<vector<vector<int>>&, vector<int>&> getVectorsDiscretized();
         pair<torch::Tensor&, torch::Tensor&> getTensors();
-        int getNFeatures();
+        int getNFeatures() const;
-        int getNSamples();
+        int getNSamples() const;
         void load();
         const bool inline isLoaded() const { return loaded; };
     };
@@ -51,14 +51,17 @@ namespace platform {
     public:
         explicit Datasets(const string& path, bool discretize = false, fileType_t fileType = ARFF) : path(path), discretize(discretize), fileType(fileType) { load(); };
         vector<string> getNames();
-        vector<string> getFeatures(string name);
+        vector<string> getFeatures(const string& name) const;
-        int getNSamples(string name);
+        int getNSamples(const string& name) const;
-        string getClassName(string name);
+        string getClassName(const string& name) const;
-        map<string, vector<int>> getStates(string name);
+        int getNClasses(const string& name);
-        pair<vector<vector<float>>&, vector<int>&> getVectors(string name);
+        vector<int> getClassesCounts(const string& name) const;
-        pair<vector<vector<int>>&, vector<int>&> getVectorsDiscretized(string name);
+        map<string, vector<int>> getStates(const string& name) const;
-        pair<torch::Tensor&, torch::Tensor&> getTensors(string name);
+        pair<vector<vector<float>>&, vector<int>&> getVectors(const string& name);
-        bool isDataset(const string& name);
+        pair<vector<vector<int>>&, vector<int>&> getVectorsDiscretized(const string& name);
+        pair<torch::Tensor&, torch::Tensor&> getTensors(const string& name);
+        bool isDataset(const string& name) const;
+        void loadDataset(const string& name) const;
     };
 };
 

src/Platform/Paths.h

@@ -1,5 +1,6 @@
 #ifndef PATHS_H
 #define PATHS_H
+#include <string>
 namespace platform {
     class Paths {
     public:

src/Platform/Report.cc

@@ -1,6 +1,9 @@
+#include <sstream>
+#include <locale>
 #include "Report.h"
 #include "BestResult.h"
 
+
 namespace platform {
     string headerLine(const string& text)
     {
@@ -31,21 +34,31 @@ namespace platform {
         body();
         footer();
     }
+    struct separated : numpunct<char> {
+        char do_decimal_point() const { return ','; }
+        char do_thousands_sep() const { return '.'; }
+        string do_grouping() const { return "\03"; }
+    };
     void Report::header()
     {
+        locale mylocale(cout.getloc(), new separated);
+        locale::global(mylocale);
+        cout.imbue(mylocale);
+        stringstream oss;
         cout << Colors::MAGENTA() << 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>());
+        oss << "Execution took  " << setprecision(2) << fixed << data["duration"].get<float>() << " seconds,   " << data["duration"].get<float>() / 3600 << " hours, on " << data["platform"].get<string>();
+        cout << headerLine(oss.str());
         cout << headerLine("Score is " + data["score_name"].get<string>());
         cout << string(MAXL, '*') << endl;
         cout << endl;
     }
     void Report::body()
     {
-        cout << Colors::GREEN() << "Dataset                        Sampl. Feat. Cls Nodes   Edges   States  Score           Time               Hyperparameters" << endl;
+        cout << Colors::GREEN() << "Dataset                        Sampl. Feat. Cls Nodes     Edges     States    Score           Time               Hyperparameters" << endl;
-        cout << "============================== ====== ===== === ======= ======= ======= =============== ================== ===============" << endl;
+        cout << "============================== ====== ===== === ========= ========= ========= =============== ================== ===============" << endl;
         json lastResult;
         totalScore = 0;
         bool odd = true;
@@ -55,9 +68,9 @@ namespace platform {
             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) << setprecision(2) << fixed << r["nodes"].get<float>() << " ";
+            cout << setw(9) << setprecision(2) << fixed << r["nodes"].get<float>() << " ";
-            cout << setw(7) << setprecision(2) << fixed << r["leaves"].get<float>() << " ";
+            cout << setw(9) << setprecision(2) << fixed << r["leaves"].get<float>() << " ";
-            cout << setw(7) << setprecision(2) << fixed << r["depth"].get<float>() << " ";
+            cout << setw(9) << setprecision(2) << fixed << r["depth"].get<float>() << " ";
             cout << setw(8) << right << setprecision(6) << fixed << r["score"].get<double>() << "±" << setw(6) << setprecision(4) << fixed << r["score_std"].get<double>() << " ";
             cout << setw(11) << right << setprecision(6) << fixed << r["time"].get<double>() << "±" << setw(6) << setprecision(4) << fixed << r["time_std"].get<double>() << " ";
             try {
@@ -85,7 +98,9 @@ namespace platform {
         cout << Colors::MAGENTA() << string(MAXL, '*') << endl;
         auto score = data["score_name"].get<string>();
         if (score == BestResult::scoreName()) {
-            cout << headerLine(score + " compared to " + BestResult::title() + " .:  " + to_string(totalScore / BestResult::score()));
+            stringstream oss;
+            oss << score << " compared to " << BestResult::title() << " .:  " << totalScore / BestResult::score();
+            cout << headerLine(oss.str());
         }
         cout << string(MAXL, '*') << endl << Colors::RESET();
 

src/Platform/list.cc

@@ -0,0 +1,57 @@
+#include <iostream>
+#include <locale>
+#include "Paths.h"
+#include "Colors.h"
+#include "Datasets.h"
+
+using namespace std;
+const int BALANCE_LENGTH = 75;
+
+struct separated : numpunct<char> {
+    char do_decimal_point() const { return ','; }
+    char do_thousands_sep() const { return '.'; }
+    string do_grouping() const { return "\03"; }
+};
+
+void outputBalance(const string& balance)
+{
+    auto temp = string(balance);
+    while (temp.size() > BALANCE_LENGTH - 1) {
+        auto part = temp.substr(0, BALANCE_LENGTH);
+        cout << part << endl;
+        cout << setw(48) << " ";
+        temp = temp.substr(BALANCE_LENGTH);
+    }
+    cout << temp << endl;
+}
+
+int main(int argc, char** argv)
+{
+    auto data = platform::Datasets(platform::Paths().datasets(), false);
+    locale mylocale(cout.getloc(), new separated);
+    locale::global(mylocale);
+    cout.imbue(mylocale);
+    cout << Colors::GREEN() << "Dataset                        Sampl. Feat. Cls. Balance" << endl;
+    string balanceBars = string(BALANCE_LENGTH, '=');
+    cout << "============================== ====== ===== === " << balanceBars << endl;
+    bool odd = true;
+    for (const auto& dataset : data.getNames()) {
+        auto color = odd ? Colors::CYAN() : Colors::BLUE();
+        cout << color << setw(30) << left << dataset << " ";
+        data.loadDataset(dataset);
+        auto nSamples = data.getNSamples(dataset);
+        cout << setw(6) << right << nSamples << " ";
+        cout << setw(5) << right << data.getFeatures(dataset).size() << " ";
+        cout << setw(3) << right << data.getNClasses(dataset) << " ";
+        stringstream oss;
+        string sep = "";
+        for (auto number : data.getClassesCounts(dataset)) {
+            oss << sep << setprecision(2) << fixed << (float)number / nSamples * 100.0 << "% (" << number << ")";
+            sep = " / ";
+        }
+        outputBalance(oss.str());
+        odd = !odd;
+    }
+    cout << Colors::RESET() << endl;
+    return 0;
+}