refactor system types in library

Add new test taken from join_fit in FImdlp python
Update instructions in README

CPPFImdlp.cpp

@@ -128,8 +128,8 @@ namespace mdlp {
             // Cutpoints are always on boundaries (definition 2)
             if (y[indices[idx]] == y[indices[idx - 1]])
                 continue;
-            entropy_left = precision_t(idx - start) / static_cast<float>(elements) * metrics.entropy(start, idx);
-            entropy_right = precision_t(end - idx) / static_cast<float>(elements) * metrics.entropy(idx, end);
+            entropy_left = precision_t(idx - start) / static_cast<precision_t>(elements) * metrics.entropy(start, idx);
+            entropy_right = precision_t(end - idx) / static_cast<precision_t>(elements) * metrics.entropy(idx, end);
             if (entropy_left + entropy_right < minEntropy) {
                 minEntropy = entropy_left + entropy_right;
                 candidate = idx;
@@ -155,8 +155,8 @@ namespace mdlp {
         ent1 = metrics.entropy(start, cut);
         ent2 = metrics.entropy(cut, end);
         ig = metrics.informationGain(start, cut, end);
-        delta = static_cast<float>(log2(pow(3, precision_t(k)) - 2) -
-                                   (precision_t(k) * ent - precision_t(k1) * ent1 - precision_t(k2) * ent2));
+        delta = static_cast<precision_t>(log2(pow(3, precision_t(k)) - 2) -
+                                         (precision_t(k) * ent - precision_t(k1) * ent1 - precision_t(k2) * ent2));
         precision_t term = 1 / N * (log2(N - 1) + delta);
         return ig > term;
     }

README.md

@@ -24,9 +24,8 @@ To run the sample, just execute the following commands:
 
 ```bash
 cd sample
-mkdir build
+cmake -B build
 cd build
-cmake ..
 make
 ./sample -f iris -m 2
 ./sample -h
@@ -34,7 +33,7 @@ make
 
 ## Test
 
-To run the tests, execute the following commands:
+To run the tests and see coverage (llvm & gcovr have to be installed), execute the following commands:
 
 ```bash
 cd tests

tests/ArffFiles.cpp

@@ -27,7 +27,7 @@ string ArffFiles::getClassType() const {
     return classType;
 }
 
-vector<vector<float>> &ArffFiles::getX() {
+vector<mdlp::samples_t> &ArffFiles::getX() {
     return X;
 }
 
@@ -80,7 +80,7 @@ void ArffFiles::load(const string &fileName, bool classLast) {
 }
 
 void ArffFiles::generateDataset(bool classLast) {
-    X = vector<vector<float>>(attributes.size(), vector<float>(lines.size()));
+    X = vector<mdlp::samples_t>(attributes.size(), mdlp::samples_t(lines.size()));
     auto yy = vector<string>(lines.size(), "");
     int labelIndex = classLast ? static_cast<int>(attributes.size()) : 0;
     for (size_t i = 0; i < lines.size(); i++) {

tests/ArffFiles.h

@@ -3,6 +3,7 @@
 
 #include <string>
 #include <vector>
+#include "../typesFImdlp.h"
 
 using namespace std;
 
@@ -12,7 +13,7 @@ private:
     vector<pair<string, string>> attributes;
     string className;
     string classType;
-    vector<vector<float>> X;
+    vector<mdlp::samples_t> X;
     vector<int> y;
 
     void generateDataset(bool);
@@ -32,7 +33,7 @@ public:
 
     static string trim(const string &);
 
-    vector<vector<float>> &getX();
+    vector<mdlp::samples_t> &getX();
 
     vector<int> &getY();
 

tests/FImdlp_unittest.cpp

@@ -111,6 +111,16 @@ namespace mdlp {
         EXPECT_THROW_WITH_MESSAGE(testDepth.fit(X, y), invalid_argument, "max_depth must be greater than 0");
     }
 
+    TEST_F(TestFImdlp, JoinFit) {
+        samples_t X_ = {1, 2, 2, 3, 4, 2, 3};
+        labels_t y_ = {0, 0, 1, 2, 3, 4, 5};
+        cutPoints_t expected = {1.5f, 2.5f};
+        fit(X_, y_);
+        auto computed = getCutPoints();
+        EXPECT_EQ(computed.size(), expected.size());
+        checkCutPoints(computed, expected);
+    }
+
     TEST_F(TestFImdlp, FitErrorMaxCutPoints) {
         auto testmin = CPPFImdlp(2, 10, -1);
         auto testmax = CPPFImdlp(3, 0, 200);

tests/Metrics_unittest.cpp

@@ -30,6 +30,14 @@ namespace mdlp {
         ASSERT_NEAR(0.468996f, entropy(0, 10), precision);
     }
 
+    TEST_F(TestMetrics, EntropyDouble) {
+        y = {0, 0, 1, 2, 3};
+        samples_t expected_entropies = {0.0, 0.0, 0.91829583, 1.5, 1.4575424759098898};
+        for (auto idx = 0; idx < y.size(); ++idx) {
+            ASSERT_NEAR(expected_entropies[idx], entropy(0, idx + 1), precision);
+        }
+    }
+
     TEST_F(TestMetrics, InformationGain) {
         ASSERT_NEAR(1, informationGain(0, 5, 10), precision);
         ASSERT_NEAR(1, informationGain(0, 5, 10), precision); // For cache

typesFImdlp.h

@@ -1,5 +1,6 @@
 #ifndef TYPES_H
 #define TYPES_H
+
 #include <vector>
 #include <map>
 #include <stdexcept>