Add google test and fix metrics

fimdlp/Metrics.cpp

@@ -1,4 +1,5 @@
 #include "Metrics.h"
+#include <set>
 namespace mdlp
 {
     Metrics::Metrics()
@@ -6,33 +7,29 @@ namespace mdlp
     }
     int Metrics::numClasses(std::vector<int> &y, std::vector<size_t> indices, size_t start, size_t end)
     {
-        int nClasses = 1;
-        int yAnt = y.at(start);
+        std::set<int> numClasses;
         for (auto i = start; i < end; ++i)
         {
-            if (y.at(i) != yAnt)
-            {
-                nClasses++;
-                yAnt = y.at(i);
-            }
+            numClasses.insert(y[indices[i]]);
         }
-        return nClasses;
+        return numClasses.size();
     }
     float Metrics::entropy(std::vector<int> &y, std::vector<size_t> &indices, size_t start, size_t end, int nClasses)
     {
         float entropy = 0;
         int nElements = 0;
-        std::vector<int> counts(nClasses, 0);
+        std::vector<int> counts(nClasses + 1, 0);
         for (auto i = &indices[start]; i != &indices[end]; ++i)
         {
             counts[y[*i]]++;
             nElements++;
         }
-        for (auto i = 0; i < nClasses; i++)
+        for (auto count : counts)
         {
-            if (counts[i] > 0)
+            if (count > 0)
             {
-                float p = (float)counts[i] / nElements;
+
+                float p = (float)count / nElements;
                 entropy -= p * log2(p);
             }
         }

fimdlp/test.cpp

@@ -1,18 +0,0 @@
-#include "CPPFImdlp.h"
-#include <iostream>
-
-using namespace mdlp;
-int main(int argc, char *argv[], char *envp[])
-{
-    {
-        CPPFImdlp fimdlp = CPPFImdlp(true);
-        std::vector<float> X = {1, 2, 3, 4, 5, 6, 7, 8, 9, 10};
-        std::vector<int> y = {1, 1, 1, 1, 1, 1, 1, 1, 1, 1};
-        fimdlp.computeCutPoints(X, y);
-        for (struct CutPointBody cutPt : fimdlp.getCutPoints())
-        {
-            std::cout << cutPt << std::endl;
-        }
-        return 0;
-    }
-}

fimdlp/test/CMakeLists.txt

@@ -0,0 +1,30 @@
+cmake_minimum_required(VERSION 3.14)
+project(FImdlp)
+
+# GoogleTest requires at least C++14
+set(CMAKE_CXX_STANDARD 14)
+
+include(FetchContent)
+FetchContent_Declare(
+  googletest
+  URL https://github.com/google/googletest/archive/03597a01ee50ed33e9dfd640b249b4be3799d395.zip
+)
+# For Windows: Prevent overriding the parent project's compiler/linker settings
+set(gtest_force_shared_crt ON CACHE BOOL "" FORCE)
+FetchContent_MakeAvailable(googletest)
+
+enable_testing()
+
+add_executable(
+  Metrics_unittest
+  ../Metrics.cpp
+  Metrics_unittest.cc
+)
+target_link_libraries(
+  Metrics_unittest
+  GTest::gtest_main
+)
+
+include(GoogleTest)
+gtest_discover_tests(Metrics_unittest)
+

fimdlp/test/Metrics_unittest.cc

@@ -0,0 +1,23 @@
+#include "gtest/gtest.h"
+#include "../Metrics.h"
+namespace
+{
+    TEST(MetricTest, NumClasses)
+    {
+        std::vector<int> y = {1, 1, 1, 1, 1, 1, 1, 1, 2, 1};
+        std::vector<size_t> indices = {0, 1, 2, 3, 4, 5, 6, 7, 8, 9};
+        EXPECT_EQ(1, mdlp::Metrics::numClasses(y, indices, 4, 8));
+        EXPECT_EQ(2, mdlp::Metrics::numClasses(y, indices, 0, 10));
+        EXPECT_EQ(2, mdlp::Metrics::numClasses(y, indices, 8, 10));
+    }
+    TEST(MetricTest, Entropy)
+    {
+        std::vector<int> y = {1, 1, 1, 1, 1, 2, 2, 2, 2, 2};
+        std::vector<size_t> indices = {0, 1, 2, 3, 4, 5, 6, 7, 8, 9};
+        EXPECT_EQ(1, mdlp::Metrics::entropy(y, indices, 0, 10, 2));
+        EXPECT_EQ(0, mdlp::Metrics::entropy(y, indices, 0, 5, 1));
+        std::vector<int> yz = {1, 1, 1, 1, 1, 1, 1, 1, 2, 1};
+        ASSERT_NEAR(0.468996, mdlp::Metrics::entropy(yz, indices, 0, 10, 2), 0.000001);
+    }
+
+}

fimdlp/test/test.sh

@@ -0,0 +1,4 @@
+cmake -S . -B build
+cmake --build build
+cd build
+ctest --output-on-failure