rmontanana/mdlp
1
1
Fork 0
mirror of https://github.com/rmontanana/mdlp.git synced 2025-08-15 23:45:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add max_cutpoints Hyperparameter

Browse Source
This commit is contained in:
Ricardo Montañana Gómez
2023-03-13 01:17:04 +01:00
parent ed784736ca
commit ffb8df4d1c
7 changed files with 105 additions and 41 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
tests/ArffFiles.cpp
View File

@@ -40,11 +40,10 @@ vector<int>& ArffFiles::getY()
void ArffFiles::load(string fileName, bool classLast)
{
ifstream file(fileName);
string keyword, attribute, type;
if (file.is_open()) {
string line;
string line, keyword, attribute, type;
while (getline(file, line)) {
if (line[0] == '%' || line.empty() || line == "\r" || line == " ") {
if (line.empty() || line[0] == '%' || line == "\r" || line == " ") {
continue;
}
if (line.find("@attribute") != string::npos || line.find("@ATTRIBUTE") != string::npos) {
@@ -79,7 +78,7 @@ void ArffFiles::generateDataset(bool classLast)
X = vector<vector<float>>(attributes.size(), vector<float>(lines.size()));
vector<string> yy = vector<string>(lines.size(), "");
int labelIndex = classLast ? attributes.size() : 0;
for (int i = 0; i < lines.size(); i++) {
for (size_t i = 0; i < lines.size(); i++) {
stringstream ss(lines[i]);
string value;
int pos = 0, xIndex = 0;

47
tests/FImdlp_unittest.cpp
View File

@@ -86,13 +86,22 @@ namespace mdlp {
}
TEST_F(TestFImdlp, FitErrorMinLengtMaxDepth)
{
auto testLength = CPPFImdlp(2, 10);
auto testDepth = CPPFImdlp(3, 0);
auto testLength = CPPFImdlp(2, 10, 0);
auto testDepth = CPPFImdlp(3, 0, 0);
X = { 1, 2, 3 };
y = { 1, 2, 3 };
EXPECT_THROW(testLength.fit(X, y), invalid_argument);
EXPECT_THROW(testDepth.fit(X, y), invalid_argument);
}
TEST_F(TestFImdlp, FitErrorMaxCutPoints)
{
auto testmin = CPPFImdlp(2, 10, -1);
auto testmax = CPPFImdlp(3, 0, 200);
X = { 1, 2, 3 };
y = { 1, 2, 3 };
EXPECT_THROW(testmin.fit(X, y), invalid_argument);
EXPECT_THROW(testmax.fit(X, y), invalid_argument);
}
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 };
@@ -139,10 +148,8 @@ namespace mdlp {
TEST_F(TestFImdlp, TestArtificialDataset)
{
fit(X, y);
computeCutPoints(0, 20, 1);
cutPoints_t expected = { 5.05 };
vector<precision_t> computed = getCutPoints();
computed = getCutPoints();
int expectedSize = expected.size();
EXPECT_EQ(computed.size(), expected.size());
for (unsigned long i = 0; i < computed.size(); i++) {
@@ -194,7 +201,7 @@ namespace mdlp {
TEST_F(TestFImdlp, MaxDepth)
{
// Set max_depth to 1
auto test = CPPFImdlp(3, 1);
auto test = CPPFImdlp(3, 1, 0);
vector<cutPoints_t> expected = {
{ 5.45 },
{ 3.35 },
@@ -206,7 +213,7 @@ namespace mdlp {
}
TEST_F(TestFImdlp, MinLength)
{
auto test = CPPFImdlp(75, 100);
auto test = CPPFImdlp(75, 100, 0);
// Set min_length to 75
vector<cutPoints_t> expected = {
{ 5.45, 5.75 },
@@ -220,7 +227,33 @@ namespace mdlp {
TEST_F(TestFImdlp, MinLengthMaxDepth)
{
// Set min_length to 75
auto test = CPPFImdlp(75, 2);
auto test = CPPFImdlp(75, 2, 0);
vector<cutPoints_t> expected = {
{ 5.45, 5.75 },
{ 2.85, 3.35 },
{ 2.45, 4.75 },
{ 0.8, 1.75 }
};
int depths[] = { 2, 2, 2, 2 };
test_dataset(test, "iris", expected, depths);
}
TEST_F(TestFImdlp, MaxCutPointsInteger)
{
// Set min_length to 75
auto test = CPPFImdlp(75, 2, 1);
vector<cutPoints_t> expected = {
{ 5.45 },
{ 3.35 },
{ 2.45 },
{ 0.8}
};
int depths[] = { 1, 1, 1, 1 };
test_dataset(test, "iris", expected, depths);
}
TEST_F(TestFImdlp, MaxCutPointsFloat)
{
// Set min_length to 75
auto test = CPPFImdlp(75, 2, 0.2);
vector<cutPoints_t> expected = {
{ 5.45, 5.75 },
{ 2.85, 3.35 },

1
tests/Metrics_unittest.cpp
View File

@@ -36,6 +36,7 @@ namespace mdlp {
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);

3
tests/test
View File

@@ -13,4 +13,5 @@ rm -fr gcovr-report/* 2>/dev/null
#lcov --capture --directory ./ --output-file lcoverage/main_coverage.info
#lcov --remove lcoverage/main_coverage.info 'v1/*' '/Applications/*' '*/tests/*' --output-file lcoverage/main_coverage.info -q
#lcov --list lcoverage/main_coverage.info
gcovr --root .. --gcov-filter "CPPFImdlp.cpp" --gcov-filter "Metrics.cpp" --txt --sonarqube=gcovr-report/coverage.xml
cd ..
gcovr --gcov-filter "CPPFImdlp.cpp" --gcov-filter "Metrics.cpp" --txt --sonarqube=tests/gcovr-report/coverage.xml