Update version number

- Had to deal with duplicated values in the variables and each practical case.
- Removed unused alternative versions of the algorithm.
- Now, intervals with the same value of the variable are not taken into account for cutpoints.
- Intervals have to have more than two examples to be evaluated
- Added some more datasets to the sample

.github/workflows/build.yml

@@ -0,0 +1,30 @@
+name: Build
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+    types: [opened, synchronize, reopened]
+jobs:
+  build:
+    name: Build
+    runs-on: ubuntu-latest
+    env:
+      BUILD_WRAPPER_OUT_DIR: build_wrapper_output_directory # Directory where build-wrapper output will be placed
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          fetch-depth: 0 # Shallow clones should be disabled for a better relevancy of analysis
+      - name: Install sonar-scanner and build-wrapper
+        uses: SonarSource/sonarcloud-github-c-cpp@v1
+      - name: Run build-wrapper
+        run: |
+          mkdir build
+          cmake -S . -B build
+          build-wrapper-linux-x86-64 --out-dir ${{ env.BUILD_WRAPPER_OUT_DIR }} cmake --build build/ --config Release
+      - name: Run sonar-scanner
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          SONAR_TOKEN: ${{ secrets.SONAR_TOKEN }} # Put the name of your token here
+        run: |
+          sonar-scanner --define sonar.cfamily.build-wrapper-output="${{ env.BUILD_WRAPPER_OUT_DIR }}"

.vscode/launch.json

@@ -0,0 +1,22 @@
+{
+    // Use IntelliSense to learn about possible attributes.
+    // Hover to view descriptions of existing attributes.
+    // For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
+    "version": "0.2.0",
+    "configurations": [
+        {
+            "name": "(lldb) Launch",
+            "type": "cppdbg",
+            "request": "launch",
+            "program": "${workspaceRoot}/sample/build/sample",
+            "args": [
+                "mfeat-factors"
+            ],
+            "stopAtEntry": false,
+            "cwd": "${workspaceRoot}/sample/build/",
+            "environment": [],
+            "externalConsole": false,
+            "MIMode": "lldb"
+        }
+    ]
+}

.vscode/settings.json

@@ -0,0 +1,5 @@
+{
+    "sonarlint.connectedMode.project": {
+        "projectKey": "rmontanana_mdlp_AYZkjILJHyjW-meBaElG"
+    }
+}

.vscode/tasks.json

@@ -0,0 +1,29 @@
+{
+    "tasks": [
+        {
+            "type": "cppbuild",
+            "label": "C/C++: clang++ build active file",
+            "command": "/usr/bin/clang++",
+            "args": [
+                "-fcolor-diagnostics",
+                "-fansi-escape-codes",
+                "-g",
+                "${file}",
+                "-o",
+                "${fileDirname}/${fileBasenameNoExtension}"
+            ],
+            "options": {
+                "cwd": "${fileDirname}"
+            },
+            "problemMatcher": [
+                "$gcc"
+            ],
+            "group": {
+                "kind": "build",
+                "isDefault": true
+            },
+            "detail": "Task generated by Debugger."
+        }
+    ],
+    "version": "2.0.0"
+}

CMakeLists.txt

@@ -1,7 +1,7 @@
 cmake_minimum_required(VERSION 3.20)
 project(mdlp)
 
-set(CMAKE_CXX_STANDARD 14)
+set(CMAKE_CXX_STANDARD 11)
 
 add_library(mdlp CPPFImdlp.cpp Metrics.cpp)
 

CPPFImdlp.cpp

@@ -2,14 +2,18 @@
 #include <algorithm>
 #include <set>
 #include <cmath>
+#include <limits>
 #include "CPPFImdlp.h"
 #include "Metrics.h"
+
 namespace mdlp {
-    CPPFImdlp::CPPFImdlp(int algorithm):algorithm(algorithm), indices(indices_t()), X(samples_t()), y(labels_t()), metrics(Metrics(y, indices))
+
+    CPPFImdlp::CPPFImdlp(): indices(indices_t()), X(samples_t()), y(labels_t()),
+        metrics(Metrics(y, indices))
     {
     }
-    CPPFImdlp::~CPPFImdlp()
-        = default;
+    CPPFImdlp::~CPPFImdlp() = default;
+
     CPPFImdlp& CPPFImdlp::fit(samples_t& X_, labels_t& y_)
     {
         X = X_;
@@ -18,89 +22,80 @@ namespace mdlp {
         if (X.size() != y.size()) {
             throw invalid_argument("X and y must have the same size");
         }
-        if (X.size() == 0 || y.size() == 0) {
+        if (X.empty() || y.empty()) {
             throw invalid_argument("X and y must have at least one element");
         }
         indices = sortIndices(X_, y_);
         metrics.setData(y, indices);
-        switch (algorithm) {
-            case 0:
         computeCutPoints(0, X.size());
-                break;
-            case 1:
-                computeCutPointsAlternative(0, X.size());
-                break;
-            default:
-                throw invalid_argument("algorithm must be 0 or 1");
-        }
         return *this;
     }
-    precision_t CPPFImdlp::halfWayValueCutPoint(size_t start, size_t idx)
+
+    pair<precision_t, size_t> CPPFImdlp::valueCutPoint(size_t start, size_t cut, size_t end)
     {
-        size_t idxPrev = idx - 1;
-        precision_t previous = X[indices[idxPrev]], actual = X[indices[idx]];
-        // definition 2 of the paper => X[t-1] < X[t]
-        while (idxPrev-- > start && actual == previous) {
+        size_t n, m, idxPrev = cut - 1 >= start ? cut - 1 : cut;
+        size_t idxNext = cut + 1 < end ? cut + 1 : cut;
+        bool backWall; // true if duplicates reach begining of the interval
+        precision_t previous, actual, next;
         previous = X[indices[idxPrev]];
-        }
-        return (previous + actual) / 2;
-    }
-    tuple<precision_t, size_t> CPPFImdlp::completeValueCutPoint(size_t start, size_t cut, size_t end)
-    {
-        size_t idxPrev = cut - 1;
-        precision_t previous, next, actual;
-        previous = X[indices[idxPrev]];
-        next = actual = X[indices[cut]];
-        // definition 2 of the paper => X[t-1] < X[t]
-        while (idxPrev-- > start && actual == previous) {
-            previous = X[indices[idxPrev]];
-        }
-        // get the last equal value of X in the interval
-        while (actual == X[indices[cut++]] && cut < end);
-        if (previous == actual && cut < end)
         actual = X[indices[cut]];
-        cut--;
-        return make_tuple((previous + actual) / 2, cut);
+        next = X[indices[idxNext]];
+        // definition 2 of the paper => X[t-1] < X[t]
+        // get the first equal value of X in the interval
+        while (idxPrev > start && actual == previous) {
+            previous = X[indices[--idxPrev]];
         }
+        backWall = idxPrev == start && actual == previous;
+        // get the last equal value of X in the interval
+        while (idxNext < end - 1 && actual == next) {
+            next = X[indices[++idxNext]];
+        }
+        // # of duplicates before cutpoint
+        n = cut - 1 - idxPrev;
+        // # of duplicates after cutpoint
+        m = idxNext - cut - 1;
+        // Decide which values to use
+        cut = cut + (backWall ? m + 1 : -n);
+        actual = X[indices[cut]];
+        return { (actual + previous) / 2, cut };
+    }
+
     void CPPFImdlp::computeCutPoints(size_t start, size_t end)
     {
         size_t cut;
-        tuple<precision_t, size_t> result;
-        if (end - start < 2)
+        pair<precision_t, size_t> result;
+        if (end - start < 3)
             return;
         cut = getCandidate(start, end);
         if (cut == numeric_limits<size_t>::max())
             return;
         if (mdlp(start, cut, end)) {
-            result = completeValueCutPoint(start, cut, end);
-            cut = get<1>(result);
-            cutPoints.push_back(get<0>(result));
+            result = valueCutPoint(start, cut, end);
+            cut = result.second;
+            cutPoints.push_back(result.first);
             computeCutPoints(start, cut);
             computeCutPoints(cut, end);
         }
     }
-    void CPPFImdlp::computeCutPointsAlternative(size_t start, size_t end)
-    {
-        size_t cut;
-        if (end - start < 2)
-            return;
-        cut = getCandidate(start, end);
-        if (cut == numeric_limits<size_t>::max())
-            return;
-        if (mdlp(start, cut, end)) {
-            cutPoints.push_back(halfWayValueCutPoint(start, cut));
-            computeCutPointsAlternative(start, cut);
-            computeCutPointsAlternative(cut, end);
-        }
-    }
+
     size_t CPPFImdlp::getCandidate(size_t start, size_t end)
     {
         /* Definition 1: A binary discretization for A is determined by selecting the cut point TA for which
-        E(A, TA; S) is minimal amogst all the candidate cut points. */
+        E(A, TA; S) is minimal amongst all the candidate cut points. */
         size_t candidate = numeric_limits<size_t>::max(), elements = end - start;
+        bool sameValues = true;
         precision_t entropy_left, entropy_right, minEntropy;
+        // Check if all the values of the variable in the interval are the same
+        for (size_t idx = start + 1; idx < end; idx++) {
+            if (X[indices[idx]] != X[indices[start]]) {
+                sameValues = false;
+                break;
+            }
+        }
+        if (sameValues)
+            return candidate;
         minEntropy = metrics.entropy(start, end);
-        for (auto idx = start + 1; idx < end; idx++) {
+        for (size_t idx = start + 1; idx < end; idx++) {
             // Cutpoints are always on boundaries (definition 2)
             if (y[indices[idx]] == y[indices[idx - 1]])
                 continue;
@@ -113,6 +108,7 @@ namespace mdlp {
         }
         return candidate;
     }
+
     bool CPPFImdlp::mdlp(size_t start, size_t cut, size_t end)
     {
         int k, k1, k2;
@@ -134,20 +130,22 @@ namespace mdlp {
         precision_t term = 1 / N * (log2(N - 1) + delta);
         return ig > term;
     }
+
     // Argsort from https://stackoverflow.com/questions/1577475/c-sorting-and-keeping-track-of-indexes
     indices_t CPPFImdlp::sortIndices(samples_t& X_, labels_t& y_)
     {
         indices_t idx(X_.size());
         iota(idx.begin(), idx.end(), 0);
         for (size_t i = 0; i < X_.size(); i++)
-            stable_sort(idx.begin(), idx.end(), [&X_, &y_](size_t i1, size_t i2)
-                {
-                    if (X_[i1] == X_[i2]) return y_[i1] < y_[i2];
+            stable_sort(idx.begin(), idx.end(), [&X_, &y_](size_t i1, size_t i2) {
+            if (X_[i1] == X_[i2])
+                return y_[i1] < y_[i2];
             else
                 return X_[i1] < X_[i2];
                 });
         return idx;
     }
+
     cutPoints_t CPPFImdlp::getCutPoints()
     {
         // Remove duplicates and sort

CPPFImdlp.h

@@ -3,12 +3,10 @@
 #include "typesFImdlp.h"
 #include "Metrics.h"
 #include <utility>
-#include <tuple>
 #include <string>
 namespace mdlp {
     class CPPFImdlp {
     protected:
-        int algorithm;
         indices_t indices;
         samples_t X;
         labels_t y;
@@ -17,17 +15,15 @@ namespace mdlp {
 
         static indices_t sortIndices(samples_t&, labels_t&);
         void computeCutPoints(size_t, size_t);
-        void computeCutPointsAlternative(size_t, size_t);
         bool mdlp(size_t, size_t, size_t);
         size_t getCandidate(size_t, size_t);
-        precision_t halfWayValueCutPoint(size_t, size_t);
-        tuple<precision_t, size_t> completeValueCutPoint(size_t, size_t, size_t);
+        pair<precision_t, size_t> valueCutPoint(size_t, size_t, size_t);
     public:
-        CPPFImdlp(int algorithm = 0);
+        CPPFImdlp();
         ~CPPFImdlp();
         CPPFImdlp& fit(samples_t&, labels_t&);
         samples_t getCutPoints();
-        inline string version() { return "1.0.0"; };
+        inline string version() { return "1.1.1"; };
     };
 }
 #endif

Metrics.cpp

@@ -29,8 +29,8 @@ namespace mdlp {
         labels_t counts(numClasses + 1, 0);
         if (end - start < 2)
             return 0;
-        if (entropyCache.find(make_tuple(start, end)) != entropyCache.end()) {
-            return entropyCache[make_tuple(start, end)];
+        if (entropyCache.find({ start, end }) != entropyCache.end()) {
+            return entropyCache[{start, end}];
         }
         for (auto i = &indices[start]; i != &indices[end]; ++i) {
             counts[y[*i]]++;
@@ -42,7 +42,7 @@ namespace mdlp {
                 ventropy -= p * log2(p);
             }
         }
-        entropyCache[make_tuple(start, end)] = ventropy;
+        entropyCache[{start, end}] = ventropy;
         return ventropy;
     }
     precision_t Metrics::informationGain(size_t start, size_t cut, size_t end)

sample/CMakeLists.txt

@@ -1,6 +1,6 @@
 cmake_minimum_required(VERSION 3.20)
 project(main)
 
-set(CMAKE_CXX_STANDARD 14)
+set(CMAKE_CXX_STANDARD 11)
 
 add_executable(sample sample.cpp ../tests/ArffFiles.cpp ../Metrics.cpp ../CPPFImdlp.cpp)

sample/sample.cpp

@@ -7,19 +7,21 @@
 using namespace std;
 using namespace mdlp;
 
+
 int main(int argc, char** argv)
 {
     ArffFiles file;
-    vector<string> lines;
     string path = "../../tests/datasets/";
     map<string, bool> datasets = {
             {"mfeat-factors",      true},
             {"iris",               true},
             {"letter",             true},
-        {"kdd_JapaneseVowels", false}
+            {"glass",              true},
+            {"kdd_JapaneseVowels", false},
+            {"test",               true}
     };
     if (argc != 2 || datasets.find(argv[1]) == datasets.end()) {
-        cout << "Usage: " << argv[0] << " {mfeat-factors, iris, letter, kdd_JapaneseVowels}" << endl;
+        cout << "Usage: " << argv[0] << " {mfeat-factors, glass, iris, letter, kdd_JapaneseVowels, test}" << endl;
         return 1;
     }
 
@@ -42,9 +44,11 @@ int main(int argc, char** argv)
         }
         cout << y[i] << endl;
     }
-    mdlp::CPPFImdlp test = mdlp::CPPFImdlp(0);
+    mdlp::CPPFImdlp test = mdlp::CPPFImdlp();
     for (auto i = 0; i < attributes.size(); i++) {
+        auto min_max = minmax_element(X[i].begin(), X[i].end());
         cout << "Cut points for " << get<0>(attributes[i]) << endl;
+        cout << "Min: " << *min_max.first << " Max: " << *min_max.second << endl;
         cout << "--------------------------" << setprecision(3) << endl;
         test.fit(X[i], y);
         for (auto item : test.getCutPoints()) {

sonar-project.properties

@@ -0,0 +1,12 @@
+sonar.projectKey=rmontanana_mdlp
+sonar.organization=rmontanana
+
+# This is the name and version displayed in the SonarCloud UI.
+#sonar.projectName=mdlp
+#sonar.projectVersion=1.0
+
+# Path is relative to the sonar-project.properties file. Replace "\" by "/" on Windows.
+#sonar.sources=.
+
+# Encoding of the source code. Default is default system encoding
+sonar.sourceEncoding=UTF-8

tests/ArffFiles.cpp

@@ -17,7 +17,7 @@ unsigned long int ArffFiles::getSize()
 {
     return lines.size();
 }
-vector<tuple<string, string>> ArffFiles::getAttributes()
+vector<pair<string, string>> ArffFiles::getAttributes()
 {
     return attributes;
 }
@@ -50,7 +50,7 @@ void ArffFiles::load(string fileName, bool classLast)
             if (line.find("@attribute") != string::npos || line.find("@ATTRIBUTE") != string::npos) {
                 stringstream ss(line);
                 ss >> keyword >> attribute >> type;
-                attributes.push_back(make_tuple(attribute, type));
+                attributes.push_back({ attribute, type });
                 continue;
             }
             if (line[0] == '@') {

tests/ArffFiles.h

@@ -2,12 +2,11 @@
 #define ARFFFILES_H
 #include <string>
 #include <vector>
-#include <tuple>
 using namespace std;
 class ArffFiles {
 private:
     vector<string> lines;
-    vector<tuple<string, string>> attributes;
+    vector<pair<string, string>> attributes;
     string className, classType;
     vector<vector<float>> X;
     vector<int> y;
@@ -22,7 +21,7 @@ public:
     string trim(const string&);
     vector<vector<float>>& getX();
     vector<int>& getY();
-    vector<tuple<string, string>> getAttributes();
+    vector<pair<string, string>> getAttributes();
     vector<int> factorize(const vector<string>& labels_t);
 };
 #endif

tests/FImdlp_unittest.cpp

@@ -13,18 +13,13 @@ namespace mdlp {
         {
             X = { 4.7, 4.7, 4.7, 4.7, 4.8, 4.8, 4.8, 4.8, 4.9, 4.95, 5.7, 5.3, 5.2, 5.1, 5.0, 5.6, 5.1, 6.0, 5.1, 5.9 };
             y = { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2 };
-            algorithm = false;
             fit(X, y);
         }
-        void setalgorithm(bool value)
-        {
-            algorithm = value;
-        }
         void checkSortedVector()
         {
             indices_t testSortedIndices = sortIndices(X, y);
             precision_t prev = X[testSortedIndices[0]];
-            for (auto i = 0; i < X.size(); ++i) {
+            for (unsigned long i = 0; i < X.size(); ++i) {
                 EXPECT_EQ(testSortedIndices[i], indices[i]);
                 EXPECT_LE(prev, X[testSortedIndices[i]]);
                 prev = X[testSortedIndices[i]];
@@ -34,7 +29,7 @@ namespace mdlp {
         {
             int expectedSize = expected.size();
             EXPECT_EQ(cutPoints.size(), expectedSize);
-            for (auto i = 0; i < cutPoints.size(); i++) {
+            for (unsigned long i = 0; i < cutPoints.size(); i++) {
                 EXPECT_NEAR(cutPoints[i], expected[i], precision);
             }
         }
@@ -47,6 +42,19 @@ namespace mdlp {
                 EXPECT_NEAR(expected[i], computed[i], precision);
             }
         }
+        bool test_result(samples_t& X_, size_t cut, float midPoint, size_t limit, string title)
+        {
+            pair<precision_t, size_t> result;
+            labels_t y_ = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 };
+            X = X_;
+            y = y_;
+            indices = sortIndices(X, y);
+            cout << "* " << title << endl;
+            result = valueCutPoint(0, cut, 10);
+            EXPECT_NEAR(result.first, midPoint, precision);
+            EXPECT_EQ(result.second, limit);
+            return true;
+        }
     };
     TEST_F(TestFImdlp, FitErrorEmptyDataset)
     {
@@ -54,11 +62,6 @@ namespace mdlp {
         y = labels_t();
         EXPECT_THROW(fit(X, y), std::invalid_argument);
     }
-    TEST_F(TestFImdlp, FitErrorIncorrectAlgorithm)
-    {
-        algorithm = 2;
-        EXPECT_THROW(fit(X, y), std::invalid_argument);
-    }
     TEST_F(TestFImdlp, FitErrorDifferentSize)
     {
         X = { 1, 2, 3 };
@@ -83,31 +86,41 @@ namespace mdlp {
         y = { 2, 2, 1 };
         indices = { 1, 2, 0 };
     }
-    TEST_F(TestFImdlp, TestArtificialDatasetAlternative)
+    TEST_F(TestFImdlp, TestShortDatasets)
     {
-        algorithm = 1;
+        vector<precision_t> computed;
+        X = { 1 };
+        y = { 1 };
         fit(X, y);
-        computeCutPoints(0, 20);
-        cutPoints_t expected = { 5.0500001907348633 };
-        vector<precision_t> computed = getCutPoints();
         computed = getCutPoints();
-        int expectedSize = expected.size();
-        EXPECT_EQ(computed.size(), expected.size());
-        for (auto i = 0; i < computed.size(); i++) {
-            EXPECT_NEAR(computed[i], expected[i], precision);
-        }
+        EXPECT_EQ(computed.size(), 0);
+        X = { 1, 3 };
+        y = { 1, 2 };
+        fit(X, y);
+        computed = getCutPoints();
+        EXPECT_EQ(computed.size(), 0);
+        X = { 2, 4 };
+        y = { 1, 2 };
+        fit(X, y);
+        computed = getCutPoints();
+        EXPECT_EQ(computed.size(), 0);
+        X = { 1, 2, 3 };
+        y = { 1, 2, 2 };
+        fit(X, y);
+        computed = getCutPoints();
+        EXPECT_EQ(computed.size(), 1);
+        EXPECT_NEAR(computed[0], 1.5, precision);
     }
     TEST_F(TestFImdlp, TestArtificialDataset)
     {
-        algorithm = 0;
         fit(X, y);
         computeCutPoints(0, 20);
-        cutPoints_t expected = { 5.0500001907348633 };
+        cutPoints_t expected = { 5.05 };
         vector<precision_t> computed = getCutPoints();
         computed = getCutPoints();
         int expectedSize = expected.size();
         EXPECT_EQ(computed.size(), expected.size());
-        for (auto i = 0; i < computed.size(); i++) {
+        for (unsigned long i = 0; i < computed.size(); i++) {
             EXPECT_NEAR(computed[i], expected[i], precision);
         }
     }
@@ -116,44 +129,17 @@ namespace mdlp {
         ArffFiles file;
         string path = "../datasets/";
 
-        file.load(path + "iris.arff", true);
-        int items = file.getSize();
-        vector<samples_t>& X = file.getX();
-        vector<cutPoints_t> expected = {
-            { 5.4499998092651367, 6.25 },
-            { 2.8499999046325684, 3, 3.0499999523162842, 3.3499999046325684 },
-            { 2.4500000476837158, 4.75, 5.0500001907348633 },
-            { 0.80000001192092896, 1.4500000476837158, 1.75 }
-        };
-        labels_t& y = file.getY();
-        auto attributes = file.getAttributes();
-        algorithm = 0;
-        for (auto feature = 0; feature < attributes.size(); feature++) {
-            fit(X[feature], y);
-            vector<precision_t> computed = getCutPoints();
-            EXPECT_EQ(computed.size(), expected[feature].size());
-            for (auto i = 0; i < computed.size(); i++) {
-                EXPECT_NEAR(computed[i], expected[feature][i], precision);
-            }
-        }
-    }
-    TEST_F(TestFImdlp, TestIrisAlternative)
-    {
-        ArffFiles file;
-        string path = "../datasets/";
-
         file.load(path + "iris.arff", true);
         int items = file.getSize();
         vector<samples_t>& X = file.getX();
         vector<cutPoints_t> expected = {
             { 5.4499998092651367, 5.75 },
-            { 2.8499999046325684, 3.3499999046325684 },
-            { 2.4500000476837158, 4.75 },
+            { 2.75, 2.85, 2.95, 3.05, 3.35 },
+            { 2.4500000476837158, 4.75, 5.0500001907348633 },
             { 0.80000001192092896, 1.75 }
         };
         labels_t& y = file.getY();
         auto attributes = file.getAttributes();
-        algorithm = 1;
         for (auto feature = 0; feature < attributes.size(); feature++) {
             fit(X[feature], y);
             vector<precision_t> computed = getCutPoints();
@@ -166,21 +152,30 @@ namespace mdlp {
     TEST_F(TestFImdlp, ComputeCutPointsGCase)
     {
         cutPoints_t expected;
-        algorithm = 0;
         expected = { 1.5 };
-        samples_t X_ = { 0, 1, 2, 2 };
-        labels_t y_ = { 1, 1, 1, 2 };
+        samples_t X_ = { 0, 1, 2, 2, 2 };
+        labels_t y_ = { 1, 1, 1, 2, 2 };
         fit(X_, y_);
         checkCutPoints(expected);
     }
-    TEST_F(TestFImdlp, ComputeCutPointsAlternativeGCase)
+    TEST_F(TestFImdlp, ValueCutPoint)
     {
-        cutPoints_t expected;
-        expected = { 1.5 };
-        algorithm = true;
-        samples_t X_ = { 0, 1, 2, 2 };
-        labels_t y_ = { 1, 1, 1, 2 };
-        fit(X_, y_);
-        checkCutPoints(expected);
+        // Case titles as stated in the doc
+        samples_t X1a{ 3.1, 3.2, 3.3, 3.4, 3.5, 3.6, 3.7, 3.8, 3.9, 4.0 };
+        test_result(X1a, 6, 7.3 / 2, 6, "1a");
+        samples_t X2a = { 3.1, 3.2, 3.3, 3.4, 3.7, 3.7, 3.7, 3.8, 3.9, 4.0 };
+        test_result(X2a, 6, 7.1 / 2, 4, "2a");
+        samples_t X2b = { 3.7, 3.7, 3.7, 3.7, 3.7, 3.7, 3.7, 3.8, 3.9, 4.0 };
+        test_result(X2b, 6, 7.5 / 2, 7, "2b");
+        samples_t X3a = { 3.1, 3.2, 3.3, 3.4, 3.7, 3.7, 3.7, 3.8, 3.9, 4.0 };
+        test_result(X3a, 4, 7.1 / 2, 4, "3a");
+        samples_t X3b = { 3.1, 3.2, 3.3, 3.4, 3.7, 3.7, 3.7, 3.7, 3.7, 3.7 };
+        test_result(X3b, 4, 7.1 / 2, 4, "3b");
+        samples_t X4a = { 3.1, 3.2, 3.7, 3.7, 3.7, 3.7, 3.7, 3.7, 3.9, 4.0 };
+        test_result(X4a, 4, 6.9 / 2, 2, "4a");
+        samples_t X4b = { 3.7, 3.7, 3.7, 3.7, 3.7, 3.7, 3.7, 3.8, 3.9, 4.0 };
+        test_result(X4b, 4, 7.5 / 2, 7, "4b");
+        samples_t X4c = { 3.1, 3.2, 3.7, 3.7, 3.7, 3.7, 3.7, 3.7, 3.7, 3.7 };
+        test_result(X4c, 4, 6.9 / 2, 2, "4c");
     }
 }

tests/datasets/glass.arff

@@ -0,0 +1,332 @@
+% 1. Title: Glass Identification Database
+% 
+% 2. Sources:
+%     (a) Creator: B. German
+%         -- Central Research Establishment
+%            Home Office Forensic Science Service
+%            Aldermaston, Reading, Berkshire RG7 4PN
+%     (b) Donor: Vina Spiehler, Ph.D., DABFT
+%                Diagnostic Products Corporation
+%                (213) 776-0180 (ext 3014)
+%     (c) Date: September, 1987
+% 
+% 3. Past Usage:
+%     -- Rule Induction in Forensic Science
+%        -- Ian W. Evett and Ernest J. Spiehler
+%        -- Central Research Establishment
+%           Home Office Forensic Science Service
+%           Aldermaston, Reading, Berkshire RG7 4PN
+%        -- Unknown technical note number (sorry, not listed here)
+%        -- General Results: nearest neighbor held its own with respect to the
+%              rule-based system
+% 
+% 4. Relevant Information:n
+%       Vina conducted a comparison test of her rule-based system, BEAGLE, the
+%       nearest-neighbor algorithm, and discriminant analysis.  BEAGLE is 
+%       a product available through VRS Consulting, Inc.; 4676 Admiralty Way,
+%       Suite 206; Marina Del Ray, CA 90292 (213) 827-7890 and FAX: -3189.
+%       In determining whether the glass was a type of "float" glass or not,
+%       the following results were obtained (# incorrect answers):
+% 
+%              Type of Sample                            Beagle   NN    DA
+%              Windows that were float processed (87)     10      12    21
+%              Windows that were not:            (76)     19      16    22
+% 
+%       The study of classification of types of glass was motivated by 
+%       criminological investigation.  At the scene of the crime, the glass left
+%       can be used as evidence...if it is correctly identified!
+% 
+% 5. Number of Instances: 214
+% 
+% 6. Number of Attributes: 10 (including an Id#) plus the class attribute
+%    -- all attributes are continuously valued
+% 
+% 7. Attribute Information:
+%    1. Id number: 1 to 214
+%    2. RI: refractive index
+%    3. Na: Sodium (unit measurement: weight percent in corresponding oxide, as 
+%                   are attributes 4-10)
+%    4. Mg: Magnesium
+%    5. Al: Aluminum
+%    6. Si: Silicon
+%    7. K: Potassium
+%    8. Ca: Calcium
+%    9. Ba: Barium
+%   10. Fe: Iron
+%   11. Type of glass: (class attribute)
+%       -- 1 building_windows_float_processed
+%       -- 2 building_windows_non_float_processed
+%       -- 3 vehicle_windows_float_processed
+%       -- 4 vehicle_windows_non_float_processed (none in this database)
+%       -- 5 containers
+%       -- 6 tableware
+%       -- 7 headlamps
+% 
+% 8. Missing Attribute Values: None
+% 
+% Summary Statistics:
+% Attribute:   Min     Max      Mean     SD      Correlation with class
+%  2. RI:       1.5112  1.5339   1.5184  0.0030  -0.1642
+%  3. Na:      10.73   17.38    13.4079  0.8166   0.5030
+%  4. Mg:       0       4.49     2.6845  1.4424  -0.7447
+%  5. Al:       0.29    3.5      1.4449  0.4993   0.5988
+%  6. Si:      69.81   75.41    72.6509  0.7745   0.1515
+%  7. K:        0       6.21     0.4971  0.6522  -0.0100
+%  8. Ca:       5.43   16.19     8.9570  1.4232   0.0007
+%  9. Ba:       0       3.15     0.1750  0.4972   0.5751
+% 10. Fe:       0       0.51     0.0570  0.0974  -0.1879
+% 
+% 9. Class Distribution: (out of 214 total instances)
+%     -- 163 Window glass (building windows and vehicle windows)
+%        -- 87 float processed  
+%           -- 70 building windows
+%           -- 17 vehicle windows
+%        -- 76 non-float processed
+%           -- 76 building windows
+%           -- 0 vehicle windows
+%     -- 51 Non-window glass
+%        -- 13 containers
+%        -- 9 tableware
+%        -- 29 headlamps
+% 
+% 
+% 
+%
+%
+%
+%
+% Relabeled values in attribute 'Type'
+%    From: '1'                     To: 'build wind float'    
+%    From: '2'                     To: 'build wind non-float'
+%    From: '3'                     To: 'vehic wind float'    
+%    From: '4'                     To: 'vehic wind non-float'
+%    From: '5'                     To: containers          
+%    From: '6'                     To: tableware           
+%    From: '7'                     To: headlamps           
+%
+@relation Glass
+@attribute 'RI' real
+@attribute 'Na' real
+@attribute 'Mg' real
+@attribute 'Al' real
+@attribute 'Si' real
+@attribute 'K' real
+@attribute 'Ca' real
+@attribute 'Ba' real
+@attribute 'Fe' real
+@attribute 'Type' { 'build wind float', 'build wind non-float', 'vehic wind float', 'vehic wind non-float', containers, tableware, headlamps}
+@data
+1.51793,12.79,3.5,1.12,73.03,0.64,8.77,0,0,'build wind float'
+1.51643,12.16,3.52,1.35,72.89,0.57,8.53,0,0,'vehic wind float'
+1.51793,13.21,3.48,1.41,72.64,0.59,8.43,0,0,'build wind float'
+1.51299,14.4,1.74,1.54,74.55,0,7.59,0,0,tableware
+1.53393,12.3,0,1,70.16,0.12,16.19,0,0.24,'build wind non-float'
+1.51655,12.75,2.85,1.44,73.27,0.57,8.79,0.11,0.22,'build wind non-float'
+1.51779,13.64,3.65,0.65,73,0.06,8.93,0,0,'vehic wind float'
+1.51837,13.14,2.84,1.28,72.85,0.55,9.07,0,0,'build wind float'
+1.51545,14.14,0,2.68,73.39,0.08,9.07,0.61,0.05,headlamps
+1.51789,13.19,3.9,1.3,72.33,0.55,8.44,0,0.28,'build wind non-float'
+1.51625,13.36,3.58,1.49,72.72,0.45,8.21,0,0,'build wind non-float'
+1.51743,12.2,3.25,1.16,73.55,0.62,8.9,0,0.24,'build wind non-float'
+1.52223,13.21,3.77,0.79,71.99,0.13,10.02,0,0,'build wind float'
+1.52121,14.03,3.76,0.58,71.79,0.11,9.65,0,0,'vehic wind float'
+1.51665,13.14,3.45,1.76,72.48,0.6,8.38,0,0.17,'vehic wind float'
+1.51707,13.48,3.48,1.71,72.52,0.62,7.99,0,0,'build wind non-float'
+1.51719,14.75,0,2,73.02,0,8.53,1.59,0.08,headlamps
+1.51629,12.71,3.33,1.49,73.28,0.67,8.24,0,0,'build wind non-float'
+1.51994,13.27,0,1.76,73.03,0.47,11.32,0,0,containers
+1.51811,12.96,2.96,1.43,72.92,0.6,8.79,0.14,0,'build wind non-float'
+1.52152,13.05,3.65,0.87,72.22,0.19,9.85,0,0.17,'build wind float'
+1.52475,11.45,0,1.88,72.19,0.81,13.24,0,0.34,'build wind non-float'
+1.51841,12.93,3.74,1.11,72.28,0.64,8.96,0,0.22,'build wind non-float'
+1.51754,13.39,3.66,1.19,72.79,0.57,8.27,0,0.11,'build wind float'
+1.52058,12.85,1.61,2.17,72.18,0.76,9.7,0.24,0.51,containers
+1.51569,13.24,3.49,1.47,73.25,0.38,8.03,0,0,'build wind non-float'
+1.5159,12.82,3.52,1.9,72.86,0.69,7.97,0,0,'build wind non-float'
+1.51683,14.56,0,1.98,73.29,0,8.52,1.57,0.07,headlamps
+1.51687,13.23,3.54,1.48,72.84,0.56,8.1,0,0,'build wind non-float'
+1.5161,13.33,3.53,1.34,72.67,0.56,8.33,0,0,'vehic wind float'
+1.51674,12.87,3.56,1.64,73.14,0.65,7.99,0,0,'build wind non-float'
+1.51832,13.33,3.34,1.54,72.14,0.56,8.99,0,0,'vehic wind float'
+1.51115,17.38,0,0.34,75.41,0,6.65,0,0,tableware
+1.51645,13.44,3.61,1.54,72.39,0.66,8.03,0,0,'build wind non-float'
+1.51755,13,3.6,1.36,72.99,0.57,8.4,0,0.11,'build wind float'
+1.51571,12.72,3.46,1.56,73.2,0.67,8.09,0,0.24,'build wind float'
+1.51596,12.79,3.61,1.62,72.97,0.64,8.07,0,0.26,'build wind float'
+1.5173,12.35,2.72,1.63,72.87,0.7,9.23,0,0,'build wind non-float'
+1.51662,12.85,3.51,1.44,73.01,0.68,8.23,0.06,0.25,'build wind non-float'
+1.51409,14.25,3.09,2.08,72.28,1.1,7.08,0,0,'build wind non-float'
+1.51797,12.74,3.48,1.35,72.96,0.64,8.68,0,0,'build wind float'
+1.51806,13,3.8,1.08,73.07,0.56,8.38,0,0.12,'build wind non-float'
+1.51627,13,3.58,1.54,72.83,0.61,8.04,0,0,'build wind non-float'
+1.5159,13.24,3.34,1.47,73.1,0.39,8.22,0,0,'build wind non-float'
+1.51934,13.64,3.54,0.75,72.65,0.16,8.89,0.15,0.24,'vehic wind float'
+1.51755,12.71,3.42,1.2,73.2,0.59,8.64,0,0,'build wind float'
+1.51514,14.01,2.68,3.5,69.89,1.68,5.87,2.2,0,containers
+1.51766,13.21,3.69,1.29,72.61,0.57,8.22,0,0,'build wind float'
+1.51784,13.08,3.49,1.28,72.86,0.6,8.49,0,0,'build wind float'
+1.52177,13.2,3.68,1.15,72.75,0.54,8.52,0,0,'build wind non-float'
+1.51753,12.57,3.47,1.38,73.39,0.6,8.55,0,0.06,'build wind float'
+1.51851,13.2,3.63,1.07,72.83,0.57,8.41,0.09,0.17,'build wind non-float'
+1.51743,13.3,3.6,1.14,73.09,0.58,8.17,0,0,'build wind float'
+1.51593,13.09,3.59,1.52,73.1,0.67,7.83,0,0,'build wind non-float'
+1.5164,14.37,0,2.74,72.85,0,9.45,0.54,0,headlamps
+1.51735,13.02,3.54,1.69,72.73,0.54,8.44,0,0.07,'build wind float'
+1.52247,14.86,2.2,2.06,70.26,0.76,9.76,0,0,headlamps
+1.52099,13.69,3.59,1.12,71.96,0.09,9.4,0,0,'build wind float'
+1.51769,13.65,3.66,1.11,72.77,0.11,8.6,0,0,'vehic wind float'
+1.51846,13.41,3.89,1.33,72.38,0.51,8.28,0,0,'build wind non-float'
+1.51848,13.64,3.87,1.27,71.96,0.54,8.32,0,0.32,'build wind non-float'
+1.51905,13.6,3.62,1.11,72.64,0.14,8.76,0,0,'build wind float'
+1.51567,13.29,3.45,1.21,72.74,0.56,8.57,0,0,'build wind float'
+1.52213,14.21,3.82,0.47,71.77,0.11,9.57,0,0,'build wind float'
+1.5232,13.72,3.72,0.51,71.75,0.09,10.06,0,0.16,'build wind float'
+1.51556,13.87,0,2.54,73.23,0.14,9.41,0.81,0.01,headlamps
+1.51926,13.2,3.33,1.28,72.36,0.6,9.14,0,0.11,'build wind float'
+1.52211,14.19,3.78,0.91,71.36,0.23,9.14,0,0.37,'vehic wind float'
+1.53125,10.73,0,2.1,69.81,0.58,13.3,3.15,0.28,'build wind non-float'
+1.52152,13.05,3.65,0.87,72.32,0.19,9.85,0,0.17,'build wind float'
+1.51829,14.46,2.24,1.62,72.38,0,9.26,0,0,tableware
+1.51892,13.46,3.83,1.26,72.55,0.57,8.21,0,0.14,'build wind non-float'
+1.51888,14.99,0.78,1.74,72.5,0,9.95,0,0,tableware
+1.51829,13.24,3.9,1.41,72.33,0.55,8.31,0,0.1,'build wind non-float'
+1.523,13.31,3.58,0.82,71.99,0.12,10.17,0,0.03,'build wind float'
+1.51652,13.56,3.57,1.47,72.45,0.64,7.96,0,0,'build wind non-float'
+1.51768,12.56,3.52,1.43,73.15,0.57,8.54,0,0,'build wind float'
+1.51215,12.99,3.47,1.12,72.98,0.62,8.35,0,0.31,'build wind float'
+1.51646,13.04,3.4,1.26,73.01,0.52,8.58,0,0,'vehic wind float'
+1.51721,12.87,3.48,1.33,73.04,0.56,8.43,0,0,'build wind float'
+1.51763,12.8,3.66,1.27,73.01,0.6,8.56,0,0,'build wind float'
+1.51742,13.27,3.62,1.24,73.08,0.55,8.07,0,0,'build wind float'
+1.52127,14.32,3.9,0.83,71.5,0,9.49,0,0,'vehic wind float'
+1.51779,13.21,3.39,1.33,72.76,0.59,8.59,0,0,'build wind float'
+1.52171,11.56,1.88,1.56,72.86,0.47,11.41,0,0,containers
+1.518,13.71,3.93,1.54,71.81,0.54,8.21,0,0.15,'build wind non-float'
+1.52777,12.64,0,0.67,72.02,0.06,14.4,0,0,'build wind non-float'
+1.5175,12.82,3.55,1.49,72.75,0.54,8.52,0,0.19,'build wind float'
+1.51764,12.98,3.54,1.21,73,0.65,8.53,0,0,'build wind float'
+1.52177,13.75,1.01,1.36,72.19,0.33,11.14,0,0,'build wind non-float'
+1.51645,14.94,0,1.87,73.11,0,8.67,1.38,0,headlamps
+1.51786,12.73,3.43,1.19,72.95,0.62,8.76,0,0.3,'build wind float'
+1.52152,13.12,3.58,0.9,72.2,0.23,9.82,0,0.16,'build wind float'
+1.51937,13.79,2.41,1.19,72.76,0,9.77,0,0,tableware
+1.51514,14.85,0,2.42,73.72,0,8.39,0.56,0,headlamps
+1.52172,13.48,3.74,0.9,72.01,0.18,9.61,0,0.07,'build wind float'
+1.51732,14.95,0,1.8,72.99,0,8.61,1.55,0,headlamps
+1.5202,13.98,1.35,1.63,71.76,0.39,10.56,0,0.18,'build wind non-float'
+1.51605,12.9,3.44,1.45,73.06,0.44,8.27,0,0,'build wind non-float'
+1.51847,13.1,3.97,1.19,72.44,0.6,8.43,0,0,'build wind non-float'
+1.51761,13.89,3.6,1.36,72.73,0.48,7.83,0,0,'build wind float'
+1.51673,13.3,3.64,1.53,72.53,0.65,8.03,0,0.29,'build wind non-float'
+1.52365,15.79,1.83,1.31,70.43,0.31,8.61,1.68,0,headlamps
+1.51685,14.92,0,1.99,73.06,0,8.4,1.59,0,headlamps
+1.51658,14.8,0,1.99,73.11,0,8.28,1.71,0,headlamps
+1.51316,13.02,0,3.04,70.48,6.21,6.96,0,0,containers
+1.51709,13,3.47,1.79,72.72,0.66,8.18,0,0,'build wind non-float'
+1.51727,14.7,0,2.34,73.28,0,8.95,0.66,0,headlamps
+1.51898,13.58,3.35,1.23,72.08,0.59,8.91,0,0,'build wind float'
+1.51969,12.64,0,1.65,73.75,0.38,11.53,0,0,containers
+1.5182,12.62,2.76,0.83,73.81,0.35,9.42,0,0.2,'build wind non-float'
+1.51617,14.95,0,2.27,73.3,0,8.71,0.67,0,headlamps
+1.51911,13.9,3.73,1.18,72.12,0.06,8.89,0,0,'build wind float'
+1.51651,14.38,0,1.94,73.61,0,8.48,1.57,0,headlamps
+1.51694,12.86,3.58,1.31,72.61,0.61,8.79,0,0,'vehic wind float'
+1.52315,13.44,3.34,1.23,72.38,0.6,8.83,0,0,headlamps
+1.52068,13.55,2.09,1.67,72.18,0.53,9.57,0.27,0.17,'build wind non-float'
+1.51838,14.32,3.26,2.22,71.25,1.46,5.79,1.63,0,headlamps
+1.51818,13.72,0,0.56,74.45,0,10.99,0,0,'build wind non-float'
+1.51769,12.45,2.71,1.29,73.7,0.56,9.06,0,0.24,'build wind float'
+1.5166,12.99,3.18,1.23,72.97,0.58,8.81,0,0.24,'build wind non-float'
+1.51589,12.88,3.43,1.4,73.28,0.69,8.05,0,0.24,'build wind float'
+1.5241,13.83,2.9,1.17,71.15,0.08,10.79,0,0,'build wind non-float'
+1.52725,13.8,3.15,0.66,70.57,0.08,11.64,0,0,'build wind non-float'
+1.52119,12.97,0.33,1.51,73.39,0.13,11.27,0,0.28,containers
+1.51748,12.86,3.56,1.27,73.21,0.54,8.38,0,0.17,'build wind float'
+1.51653,11.95,0,1.19,75.18,2.7,8.93,0,0,headlamps
+1.51623,14.14,0,2.88,72.61,0.08,9.18,1.06,0,headlamps
+1.52101,13.64,4.49,1.1,71.78,0.06,8.75,0,0,'build wind float'
+1.51763,12.61,3.59,1.31,73.29,0.58,8.5,0,0,'build wind float'
+1.51596,13.02,3.56,1.54,73.11,0.72,7.9,0,0,'build wind non-float'
+1.51674,12.79,3.52,1.54,73.36,0.66,7.9,0,0,'build wind non-float'
+1.52065,14.36,0,2.02,73.42,0,8.44,1.64,0,headlamps
+1.51768,12.65,3.56,1.3,73.08,0.61,8.69,0,0.14,'build wind float'
+1.52369,13.44,0,1.58,72.22,0.32,12.24,0,0,containers
+1.51756,13.15,3.61,1.05,73.24,0.57,8.24,0,0,'build wind float'
+1.51754,13.48,3.74,1.17,72.99,0.59,8.03,0,0,'build wind float'
+1.51711,12.89,3.62,1.57,72.96,0.61,8.11,0,0,'build wind non-float'
+1.5221,13.73,3.84,0.72,71.76,0.17,9.74,0,0,'build wind float'
+1.51594,13.09,3.52,1.55,72.87,0.68,8.05,0,0.09,'build wind non-float'
+1.51784,12.68,3.67,1.16,73.11,0.61,8.7,0,0,'build wind float'
+1.51909,13.89,3.53,1.32,71.81,0.51,8.78,0.11,0,'build wind float'
+1.51977,13.81,3.58,1.32,71.72,0.12,8.67,0.69,0,'build wind float'
+1.51666,12.86,0,1.83,73.88,0.97,10.17,0,0,containers
+1.51631,13.34,3.57,1.57,72.87,0.61,7.89,0,0,'build wind non-float'
+1.51872,12.93,3.66,1.56,72.51,0.58,8.55,0,0.12,'build wind non-float'
+1.51708,13.72,3.68,1.81,72.06,0.64,7.88,0,0,'build wind non-float'
+1.52081,13.78,2.28,1.43,71.99,0.49,9.85,0,0.17,'build wind non-float'
+1.51574,14.86,3.67,1.74,71.87,0.16,7.36,0,0.12,'build wind non-float'
+1.51813,13.43,3.98,1.18,72.49,0.58,8.15,0,0,'build wind non-float'
+1.51131,13.69,3.2,1.81,72.81,1.76,5.43,1.19,0,headlamps
+1.52227,14.17,3.81,0.78,71.35,0,9.69,0,0,'build wind float'
+1.52614,13.7,0,1.36,71.24,0.19,13.44,0,0.1,'build wind non-float'
+1.51811,13.33,3.85,1.25,72.78,0.52,8.12,0,0,'build wind non-float'
+1.51655,13.41,3.39,1.28,72.64,0.52,8.65,0,0,'vehic wind float'
+1.51751,12.81,3.57,1.35,73.02,0.62,8.59,0,0,'build wind float'
+1.51508,15.15,0,2.25,73.5,0,8.34,0.63,0,headlamps
+1.51915,12.73,1.85,1.86,72.69,0.6,10.09,0,0,containers
+1.51966,14.77,3.75,0.29,72.02,0.03,9,0,0,'build wind float'
+1.51844,13.25,3.76,1.32,72.4,0.58,8.42,0,0,'build wind non-float'
+1.52664,11.23,0,0.77,73.21,0,14.68,0,0,'build wind non-float'
+1.52172,13.51,3.86,0.88,71.79,0.23,9.54,0,0.11,'build wind float'
+1.51602,14.85,0,2.38,73.28,0,8.76,0.64,0.09,headlamps
+1.51321,13,0,3.02,70.7,6.21,6.93,0,0,containers
+1.52739,11.02,0,0.75,73.08,0,14.96,0,0,'build wind non-float'
+1.52213,14.21,3.82,0.47,71.77,0.11,9.57,0,0,'build wind float'
+1.51747,12.84,3.5,1.14,73.27,0.56,8.55,0,0,'build wind float'
+1.51839,12.85,3.67,1.24,72.57,0.62,8.68,0,0.35,'build wind non-float'
+1.51646,13.41,3.55,1.25,72.81,0.68,8.1,0,0,'build wind non-float'
+1.51609,15.01,0,2.51,73.05,0.05,8.83,0.53,0,headlamps
+1.51667,12.94,3.61,1.26,72.75,0.56,8.6,0,0,'build wind non-float'
+1.51588,13.12,3.41,1.58,73.26,0.07,8.39,0,0.19,'build wind non-float'
+1.52667,13.99,3.7,0.71,71.57,0.02,9.82,0,0.1,'build wind float'
+1.51831,14.39,0,1.82,72.86,1.41,6.47,2.88,0,headlamps
+1.51918,14.04,3.58,1.37,72.08,0.56,8.3,0,0,'build wind float'
+1.51613,13.88,1.78,1.79,73.1,0,8.67,0.76,0,headlamps
+1.52196,14.36,3.85,0.89,71.36,0.15,9.15,0,0,'build wind float'
+1.51824,12.87,3.48,1.29,72.95,0.6,8.43,0,0,'build wind float'
+1.52151,11.03,1.71,1.56,73.44,0.58,11.62,0,0,containers
+1.51969,14.56,0,0.56,73.48,0,11.22,0,0,tableware
+1.51618,13.01,3.5,1.48,72.89,0.6,8.12,0,0,'build wind non-float'
+1.51645,13.4,3.49,1.52,72.65,0.67,8.08,0,0.1,'build wind non-float'
+1.51796,13.5,3.36,1.63,71.94,0.57,8.81,0,0.09,'vehic wind float'
+1.52222,14.43,0,1,72.67,0.1,11.52,0,0.08,'build wind non-float'
+1.51783,12.69,3.54,1.34,72.95,0.57,8.75,0,0,'build wind float'
+1.51711,14.23,0,2.08,73.36,0,8.62,1.67,0,headlamps
+1.51736,12.78,3.62,1.29,72.79,0.59,8.7,0,0,'build wind float'
+1.51808,13.43,2.87,1.19,72.84,0.55,9.03,0,0,'build wind float'
+1.5167,13.24,3.57,1.38,72.7,0.56,8.44,0,0.1,'vehic wind float'
+1.52043,13.38,0,1.4,72.25,0.33,12.5,0,0,containers
+1.519,13.49,3.48,1.35,71.95,0.55,9,0,0,'build wind float'
+1.51778,13.21,2.81,1.29,72.98,0.51,9.02,0,0.09,'build wind float'
+1.51905,14,2.39,1.56,72.37,0,9.57,0,0,tableware
+1.51531,14.38,0,2.66,73.1,0.04,9.08,0.64,0,headlamps
+1.51916,14.15,0,2.09,72.74,0,10.88,0,0,tableware
+1.51841,13.02,3.62,1.06,72.34,0.64,9.13,0,0.15,'build wind non-float'
+1.5159,13.02,3.58,1.51,73.12,0.69,7.96,0,0,'build wind non-float'
+1.51593,13.25,3.45,1.43,73.17,0.61,7.86,0,0,'build wind non-float'
+1.5164,12.55,3.48,1.87,73.23,0.63,8.08,0,0.09,'build wind non-float'
+1.51663,12.93,3.54,1.62,72.96,0.64,8.03,0,0.21,'build wind non-float'
+1.5169,13.33,3.54,1.61,72.54,0.68,8.11,0,0,'build wind non-float'
+1.51869,13.19,3.37,1.18,72.72,0.57,8.83,0,0.16,'build wind float'
+1.51776,13.53,3.41,1.52,72.04,0.58,8.79,0,0,'vehic wind float'
+1.51775,12.85,3.48,1.23,72.97,0.61,8.56,0.09,0.22,'build wind float'
+1.5186,13.36,3.43,1.43,72.26,0.51,8.6,0,0,'build wind non-float'
+1.5172,13.38,3.5,1.15,72.85,0.5,8.43,0,0,'build wind float'
+1.51623,14.2,0,2.79,73.46,0.04,9.04,0.4,0.09,headlamps
+1.51618,13.53,3.55,1.54,72.99,0.39,7.78,0,0,'build wind float'
+1.51761,12.81,3.54,1.23,73.24,0.58,8.39,0,0,'build wind float'
+1.5161,13.42,3.4,1.22,72.69,0.59,8.32,0,0,'vehic wind float'
+1.51592,12.86,3.52,2.12,72.66,0.69,7.97,0,0,'build wind non-float'
+1.51613,13.92,3.52,1.25,72.88,0.37,7.94,0,0.14,'build wind non-float'
+1.51689,12.67,2.88,1.71,73.21,0.73,8.54,0,0,'build wind non-float'
+1.51852,14.09,2.19,1.66,72.67,0,9.32,0,0,tableware

tests/datasets/test.arff

@@ -0,0 +1,180 @@
+% 1. Title: Test Feature extracted from Glass
+% 
+
+@RELATION test
+
+@ATTRIBUTE Mg	REAL
+@ATTRIBUTE Type 	{0,1,2,3,4,5,6}
+
+@DATA
+3.5,0
+3.52,1
+1.74,2
+0.0,3
+2.85,3
+3.65,1
+2.84,0
+0.0,4
+3.9,3
+3.58,3
+3.25,3
+3.76,1
+3.45,1
+3.48,3
+0.0,4
+0.0,5
+2.96,3
+3.65,0
+0.0,3
+3.74,3
+3.66,0
+1.61,5
+3.49,3
+3.52,3
+3.54,3
+3.53,1
+3.56,3
+3.34,1
+0.0,2
+3.61,3
+3.6,0
+3.46,0
+2.72,3
+3.51,3
+3.09,3
+3.48,0
+3.8,3
+3.58,3
+3.54,1
+3.42,0
+2.68,5
+3.49,0
+3.68,3
+3.6,0
+3.59,3
+0.0,4
+3.54,0
+2.2,4
+3.59,0
+3.66,1
+3.87,3
+3.45,0
+3.82,0
+3.72,0
+3.33,0
+3.78,1
+2.24,2
+3.83,3
+0.78,2
+3.9,3
+3.58,0
+3.57,3
+3.52,0
+3.47,0
+3.48,0
+3.66,0
+3.62,0
+3.39,0
+0.0,3
+3.55,0
+1.01,3
+0.0,4
+3.43,0
+3.58,0
+0.0,4
+3.74,0
+0.0,4
+3.44,3
+3.97,3
+3.6,0
+3.64,3
+1.83,4
+0.0,4
+0.0,5
+0.0,4
+0.0,5
+0.0,4
+3.73,0
+3.58,1
+3.34,4
+2.09,3
+2.71,0
+3.18,3
+3.43,0
+3.15,3
+3.56,0
+0.0,4
+0.0,4
+4.49,0
+3.59,0
+3.56,3
+3.52,3
+0.0,4
+0.0,5
+3.61,0
+3.74,0
+3.62,3
+3.84,0
+3.67,0
+3.58,0
+0.0,5
+3.66,3
+3.68,3
+2.28,3
+3.67,3
+3.2,4
+3.81,0
+0.0,3
+3.39,1
+3.57,0
+1.85,5
+3.75,0
+3.76,3
+0.0,3
+3.86,0
+0.0,4
+0.0,5
+0.0,3
+3.5,0
+3.67,3
+3.55,3
+0.0,4
+3.61,3
+3.41,3
+3.7,0
+0.0,4
+3.58,0
+1.78,4
+3.85,0
+3.48,0
+1.71,5
+0.0,2
+3.5,3
+3.49,3
+3.36,1
+0.0,3
+3.54,0
+0.0,4
+2.87,0
+3.57,1
+3.48,0
+2.81,0
+0.0,4
+0.0,2
+3.62,3
+3.58,3
+3.45,3
+3.48,3
+3.54,3
+3.54,3
+3.37,0
+3.41,1
+3.48,0
+3.43,3
+3.5,0
+0.0,4
+3.54,0
+3.52,3
+3.52,3
+2.88,3
+2.19,2

typesFImdlp.h

@@ -2,6 +2,7 @@
 #define TYPES_H
 #include <vector>
 #include <map>
+#include <stdexcept>
 
 using namespace std;
 namespace mdlp {
@@ -10,7 +11,7 @@ namespace mdlp {
     typedef vector<int> labels_t;
     typedef vector<size_t> indices_t;
     typedef vector<precision_t> cutPoints_t;
-    typedef map<tuple<int, int>, precision_t> cacheEnt_t;
+    typedef map<pair<int, int>, precision_t> cacheEnt_t;
     typedef map<tuple<int, int, int>, precision_t> cacheIg_t;
 }
 #endif