From 27ea3bf33854428a3a94a32f624f8b7bc28be4f3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ricardo=20Monta=C3=B1ana?= Date: Tue, 21 Mar 2023 00:53:18 +0100 Subject: [PATCH] Refactor tests --- CPPFImdlp.h | 2 +- tests/FImdlp_unittest.cpp | 287 +++++++++++++++++++------------------ tests/Metrics_unittest.cpp | 23 +-- tests/test | 3 + 4 files changed, 160 insertions(+), 155 deletions(-) diff --git a/CPPFImdlp.h b/CPPFImdlp.h index 0c0311e..6a24ca3 100644 --- a/CPPFImdlp.h +++ b/CPPFImdlp.h @@ -45,7 +45,7 @@ namespace mdlp { int get_depth() const; - inline string version() const { return "1.1.1"; }; + static inline string version() { return "1.1.1"; }; }; } #endif diff --git a/tests/FImdlp_unittest.cpp b/tests/FImdlp_unittest.cpp index 56e6c1e..3b090bb 100644 --- a/tests/FImdlp_unittest.cpp +++ b/tests/FImdlp_unittest.cpp @@ -4,6 +4,7 @@ #include #include #include "ArffFiles.h" + #define EXPECT_THROW_WITH_MESSAGE(stmt, etype, whatstring) EXPECT_THROW( \ try { \ stmt; \ @@ -14,30 +15,33 @@ throw; \ , etype) namespace mdlp { - class TestFImdlp: public CPPFImdlp, public testing::Test { + class TestFImdlp : public CPPFImdlp, public testing::Test { public: - precision_t precision = 0.000001; - TestFImdlp(): CPPFImdlp() {} + precision_t precision = 0.000001f; + + TestFImdlp() : CPPFImdlp() {} + string data_path; - void SetUp() - { - 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 }; + + void SetUp() override { + X = {4.7f, 4.7f, 4.7f, 4.7f, 4.8f, 4.8f, 4.8f, 4.8f, 4.9f, 4.95f, 5.7f, 5.3f, 5.2f, 5.1f, 5.0f, 5.6f, 5.1f, + 6.0f, 5.1f, 5.9f}; + y = {1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2}; fit(X, y); data_path = set_data_path(); } - string set_data_path() - { + + static string set_data_path() { string path = "../datasets/"; - ifstream file(path+"iris.arff"); + ifstream file(path + "iris.arff"); if (file.is_open()) { file.close(); return path; } return "../../tests/datasets/"; } - void checkSortedVector() - { + + void checkSortedVector() { indices_t testSortedIndices = sortIndices(X, y); precision_t prev = X[testSortedIndices[0]]; for (unsigned long i = 0; i < X.size(); ++i) { @@ -46,26 +50,18 @@ namespace mdlp { prev = X[testSortedIndices[i]]; } } - void checkCutPoints(cutPoints_t& computed, cutPoints_t& expected) - { + + void checkCutPoints(cutPoints_t &computed, cutPoints_t &expected) const { EXPECT_EQ(computed.size(), expected.size()); for (unsigned long i = 0; i < computed.size(); i++) { cout << "(" << computed[i] << ", " << expected[i] << ") "; EXPECT_NEAR(computed[i], expected[i], precision); } } - template - void checkVectors(std::vector const& expected, std::vector const& computed) - { - ASSERT_EQ(expected.size(), computed.size()); - for (auto i = 0; i < expected.size(); i++) { - EXPECT_NEAR(expected[i], computed[i], precision); - } - } - bool test_result(samples_t& X_, size_t cut, float midPoint, size_t limit, string title) - { + + bool test_result(const samples_t &X_, size_t cut, float midPoint, size_t limit, const string &title) { pair result; - labels_t y_ = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 }; + labels_t y_ = {0, 1, 2, 3, 4, 5, 6, 7, 8, 9}; X = X_; y = y_; indices = sortIndices(X, y); @@ -75,12 +71,13 @@ namespace mdlp { EXPECT_EQ(result.second, limit); return true; } - void test_dataset(CPPFImdlp& test, string filename, vector& expected, int depths[]) - { + + void test_dataset(CPPFImdlp &test, const string &filename, vector &expected, + vector &depths) const { ArffFiles file; file.load(data_path + filename + ".arff", true); - vector& X = file.getX(); - labels_t& y = file.getY(); + vector &X = file.getX(); + labels_t &y = file.getY(); auto attributes = file.getAttributes(); for (auto feature = 0; feature < attributes.size(); feature++) { test.fit(X[feature], y); @@ -92,202 +89,206 @@ namespace mdlp { } } }; - TEST_F(TestFImdlp, FitErrorEmptyDataset) - { + + TEST_F(TestFImdlp, FitErrorEmptyDataset) { X = samples_t(); y = labels_t(); EXPECT_THROW_WITH_MESSAGE(fit(X, y), invalid_argument, "X and y must have at least one element"); } - TEST_F(TestFImdlp, FitErrorDifferentSize) - { - X = { 1, 2, 3 }; - y = { 1, 2 }; + + TEST_F(TestFImdlp, FitErrorDifferentSize) { + X = {1, 2, 3}; + y = {1, 2}; EXPECT_THROW_WITH_MESSAGE(fit(X, y), invalid_argument, "X and y must have the same size"); } - TEST_F(TestFImdlp, FitErrorMinLengtMaxDepth) - { + + TEST_F(TestFImdlp, FitErrorMinLengtMaxDepth) { auto testLength = CPPFImdlp(2, 10, 0); auto testDepth = CPPFImdlp(3, 0, 0); - X = { 1, 2, 3 }; - y = { 1, 2, 3 }; + X = {1, 2, 3}; + y = {1, 2, 3}; EXPECT_THROW_WITH_MESSAGE(testLength.fit(X, y), invalid_argument, "min_length must be greater than 2"); EXPECT_THROW_WITH_MESSAGE(testDepth.fit(X, y), invalid_argument, "max_depth must be greater than 0"); } - TEST_F(TestFImdlp, FitErrorMaxCutPoints) - { + + TEST_F(TestFImdlp, FitErrorMaxCutPoints) { auto testmin = CPPFImdlp(2, 10, -1); auto testmax = CPPFImdlp(3, 0, 200); - X = { 1, 2, 3 }; - y = { 1, 2, 3 }; + X = {1, 2, 3}; + y = {1, 2, 3}; EXPECT_THROW_WITH_MESSAGE(testmin.fit(X, y), invalid_argument, "wrong proposed num_cuts value"); EXPECT_THROW_WITH_MESSAGE(testmax.fit(X, y), invalid_argument, "wrong proposed num_cuts value"); } - TEST_F(TestFImdlp, SortIndices) - { - X = { 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, 2, 2, 2, 2, 2 }; - indices = { 4, 3, 6, 8, 2, 1, 5, 0, 9, 7 }; + + TEST_F(TestFImdlp, SortIndices) { + X = {5.7f, 5.3f, 5.2f, 5.1f, 5.0f, 5.6f, 5.1f, 6.0f, 5.1f, 5.9f}; + y = {1, 1, 1, 1, 1, 2, 2, 2, 2, 2}; + indices = {4, 3, 6, 8, 2, 1, 5, 0, 9, 7}; checkSortedVector(); - X = { 5.77, 5.88, 5.99 }; - y = { 1, 2, 1 }; - indices = { 0, 1, 2 }; + X = {5.77f, 5.88f, 5.99f}; + y = {1, 2, 1}; + indices = {0, 1, 2}; checkSortedVector(); - X = { 5.33, 5.22, 5.11 }; - y = { 1, 2, 1 }; - indices = { 2, 1, 0 }; + X = {5.33f, 5.22f, 5.11f}; + y = {1, 2, 1}; + indices = {2, 1, 0}; checkSortedVector(); - X = { 5.33, 5.22, 5.33 }; - y = { 2, 2, 1 }; - indices = { 1, 2, 0 }; + X = {5.33f, 5.22f, 5.33f}; + y = {2, 2, 1}; + indices = {1, 2, 0}; } - TEST_F(TestFImdlp, TestShortDatasets) - { + + TEST_F(TestFImdlp, TestShortDatasets) { vector computed; - X = { 1 }; - y = { 1 }; + X = {1}; + y = {1}; fit(X, y); computed = getCutPoints(); EXPECT_EQ(computed.size(), 0); - X = { 1, 3 }; - y = { 1, 2 }; + X = {1, 3}; + y = {1, 2}; fit(X, y); computed = getCutPoints(); EXPECT_EQ(computed.size(), 0); - X = { 2, 4 }; - y = { 1, 2 }; + X = {2, 4}; + y = {1, 2}; fit(X, y); computed = getCutPoints(); EXPECT_EQ(computed.size(), 0); - X = { 1, 2, 3 }; - y = { 1, 2, 2 }; + 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) - { + + TEST_F(TestFImdlp, TestArtificialDataset) { fit(X, y); - cutPoints_t expected = { 5.05 }; + cutPoints_t expected = {5.05f}; vector computed = getCutPoints(); - int expectedSize = expected.size(); EXPECT_EQ(computed.size(), expected.size()); for (unsigned long i = 0; i < computed.size(); i++) { EXPECT_NEAR(computed[i], expected[i], precision); } } - TEST_F(TestFImdlp, TestIris) - { + + TEST_F(TestFImdlp, TestIris) { vector expected = { - { 5.45, 5.75 }, - { 2.75, 2.85, 2.95, 3.05, 3.35 }, - { 2.45, 4.75, 5.05 }, - { 0.8, 1.75 } + {5.45f, 5.75f}, + {2.75f, 2.85f, 2.95f, 3.05f, 3.35f}, + {2.45f, 4.75f, 5.05f}, + {0.8f, 1.75f} }; - int depths[] = { 3, 5, 5, 5 }; + vector depths = {3, 5, 4, 3}; auto test = CPPFImdlp(); - //test_dataset(test, "iris.arff", expected, depths); + test_dataset(test, "iris", expected, depths); } - TEST_F(TestFImdlp, ComputeCutPointsGCase) - { + + TEST_F(TestFImdlp, ComputeCutPointsGCase) { cutPoints_t expected; - expected = { 1.5 }; - samples_t X_ = { 0, 1, 2, 2, 2 }; - labels_t y_ = { 1, 1, 1, 2, 2 }; + expected = {1.5}; + samples_t X_ = {0, 1, 2, 2, 2}; + labels_t y_ = {1, 1, 1, 2, 2}; fit(X_, y_); auto computed = getCutPoints(); checkCutPoints(computed, expected); } - TEST_F(TestFImdlp, ValueCutPoint) - { + + TEST_F(TestFImdlp, ValueCutPoint) { // 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"); + samples_t X1a{3.1f, 3.2f, 3.3f, 3.4f, 3.5f, 3.6f, 3.7f, 3.8f, 3.9f, 4.0f}; + test_result(X1a, 6, 7.3f / 2, 6, "1a"); + samples_t X2a = {3.1f, 3.2f, 3.3f, 3.4f, 3.7f, 3.7f, 3.7f, 3.8f, 3.9f, 4.0f}; + test_result(X2a, 6, 7.1f / 2, 4, "2a"); + samples_t X2b = {3.7f, 3.7f, 3.7f, 3.7f, 3.7f, 3.7f, 3.7f, 3.8f, 3.9f, 4.0f}; + test_result(X2b, 6, 7.5f / 2, 7, "2b"); + samples_t X3a = {3.f, 3.2f, 3.3f, 3.4f, 3.7f, 3.7f, 3.7f, 3.8f, 3.9f, 4.0f}; + test_result(X3a, 4, 7.1f / 2, 4, "3a"); + samples_t X3b = {3.1f, 3.2f, 3.3f, 3.4f, 3.7f, 3.7f, 3.7f, 3.7f, 3.7f, 3.7f}; + test_result(X3b, 4, 7.1f / 2, 4, "3b"); + samples_t X4a = {3.1f, 3.2f, 3.7f, 3.7f, 3.7f, 3.7f, 3.7f, 3.7f, 3.9f, 4.0f}; + test_result(X4a, 4, 6.9f / 2, 2, "4a"); + samples_t X4b = {3.7f, 3.7f, 3.7f, 3.7f, 3.7f, 3.7f, 3.7f, 3.8f, 3.9f, 4.0f}; + test_result(X4b, 4, 7.5f / 2, 7, "4b"); + samples_t X4c = {3.1f, 3.2f, 3.7f, 3.7f, 3.7f, 3.7f, 3.7f, 3.7f, 3.7f, 3.7f}; + test_result(X4c, 4, 6.9f / 2, 2, "4c"); } - TEST_F(TestFImdlp, MaxDepth) - { + + TEST_F(TestFImdlp, MaxDepth) { // Set max_depth to 1 auto test = CPPFImdlp(3, 1, 0); vector expected = { - { 5.45 }, - { 3.35 }, - { 2.45 }, - {0.8 } + {5.45f}, + {3.35f}, + {2.45f}, + {0.8f} }; - int depths[] = { 1, 1, 1, 1 }; + vector depths = {1, 1, 1, 1}; test_dataset(test, "iris", expected, depths); } - TEST_F(TestFImdlp, MinLength) - { + + TEST_F(TestFImdlp, MinLength) { auto test = CPPFImdlp(75, 100, 0); // Set min_length to 75 vector expected = { - { 5.45, 5.75 }, - { 2.85, 3.35 }, - { 2.45, 4.75 }, - { 0.8, 1.75 } + {5.45f, 5.75f}, + {2.85f, 3.35f}, + {2.45f, 4.75f}, + {0.8f, 1.75f} }; - int depths[] = { 3, 2, 2, 2 }; + vector depths = {3, 2, 2, 2}; test_dataset(test, "iris", expected, depths); } - TEST_F(TestFImdlp, MinLengthMaxDepth) - { + + TEST_F(TestFImdlp, MinLengthMaxDepth) { // Set min_length to 75 auto test = CPPFImdlp(75, 2, 0); vector expected = { - { 5.45, 5.75 }, - { 2.85, 3.35 }, - { 2.45, 4.75 }, - { 0.8, 1.75 } + {5.45f, 5.75f}, + {2.85f, 3.35f}, + {2.45f, 4.75f}, + {0.8f, 1.75f} }; - int depths[] = { 2, 2, 2, 2 }; + vector depths = {2, 2, 2, 2}; test_dataset(test, "iris", expected, depths); } - TEST_F(TestFImdlp, MaxCutPointsInteger) - { + + TEST_F(TestFImdlp, MaxCutPointsInteger) { // Set min_length to 75 auto test = CPPFImdlp(75, 2, 1); vector expected = { - { 5.45 }, - { 3.35 }, - { 2.45 }, - { 0.8} + {5.45f}, + {3.35f}, + {2.45f}, + {0.8f} }; - int depths[] = { 1, 1, 1, 1 }; + vector depths = {1, 1, 1, 1}; test_dataset(test, "iris", expected, depths); } - TEST_F(TestFImdlp, MaxCutPointsFloat) - { + + TEST_F(TestFImdlp, MaxCutPointsFloat) { // Set min_length to 75 - auto test = CPPFImdlp(75, 2, 0.2); + auto test = CPPFImdlp(75, 2, 0.2f); vector expected = { - { 5.45, 5.75 }, - { 2.85, 3.35 }, - { 2.45, 4.75 }, - { 0.8, 1.75 } + {5.45f, 5.75f}, + {2.85f, 3.35f}, + {2.45f, 4.75f}, + {0.8f, 1.75f} }; - int depths[] = { 2, 2, 2, 2 }; + vector depths = {2, 2, 2, 2}; test_dataset(test, "iris", expected, depths); } - TEST_F(TestFImdlp, ProposedCuts) - { - vector> proposed_list = { { 0.1, 2}, { 0.5, 10}, {0.07, 1}, {1, 1}, {2, 2} }; - size_t expected, computed; - for (auto proposed_item : proposed_list) { + + TEST_F(TestFImdlp, ProposedCuts) { + vector> proposed_list = {{0.1f, 2}, + {0.5f, 10}, + {0.07f, 1}, + {1.0f, 1}, + {2.0f, 2}}; + size_t expected; + size_t computed; + for (auto proposed_item: proposed_list) { tie(proposed_cuts, expected) = proposed_item; computed = compute_max_num_cut_points(); ASSERT_EQ(expected, computed); diff --git a/tests/Metrics_unittest.cpp b/tests/Metrics_unittest.cpp index e7d6f8b..5cd73d6 100644 --- a/tests/Metrics_unittest.cpp +++ b/tests/Metrics_unittest.cpp @@ -5,19 +5,18 @@ namespace mdlp { class TestMetrics: public Metrics, public testing::Test { public: - labels_t y; - samples_t X; - indices_t indices; - precision_t precision = 0.000001; + labels_t y_ = { 1, 1, 1, 1, 1, 2, 2, 2, 2, 2 }; + indices_t indices_ = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 }; + precision_t precision = 0.000001f; - TestMetrics(): Metrics(y, indices) {} - void SetUp() + TestMetrics(): Metrics(y_, indices_) {}; + + void SetUp() override { - y = { 1, 1, 1, 1, 1, 2, 2, 2, 2, 2 }; - indices = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 }; - setData(y, indices); + setData(y_, indices_); } }; + TEST_F(TestMetrics, NumClasses) { y = { 1, 1, 1, 1, 1, 1, 1, 1, 2, 1 }; @@ -25,20 +24,22 @@ namespace mdlp { EXPECT_EQ(2, computeNumClasses(0, 10)); EXPECT_EQ(2, computeNumClasses(8, 10)); } + TEST_F(TestMetrics, Entropy) { EXPECT_EQ(1, entropy(0, 10)); EXPECT_EQ(0, entropy(0, 5)); y = { 1, 1, 1, 1, 1, 1, 1, 1, 2, 1 }; setData(y, indices); - ASSERT_NEAR(0.468996, entropy(0, 10), precision); + ASSERT_NEAR(0.468996f, entropy(0, 10), precision); } + TEST_F(TestMetrics, InformationGain) { ASSERT_NEAR(1, informationGain(0, 5, 10), precision); ASSERT_NEAR(1, informationGain(0, 5, 10), precision); // For cache y = { 1, 1, 1, 1, 1, 1, 1, 1, 2, 1 }; setData(y, indices); - ASSERT_NEAR(0.108032, informationGain(0, 5, 10), precision); + ASSERT_NEAR(0.108032f, informationGain(0, 5, 10), precision); } } diff --git a/tests/test b/tests/test index 4180150..33fde47 100755 --- a/tests/test +++ b/tests/test @@ -1,6 +1,9 @@ if [ -d build ] ; then rm -fr build fi +if [ -d gcovr-report ] ; then + rm -fr gcovr-report +fi cmake -S . -B build -Wno-dev cmake --build build cd build