rmontanana/mdlp
1
1
Fork 0
mirror of https://github.com/rmontanana/mdlp.git synced 2025-08-15 15:35:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

Reformat some test files

Browse Source
This commit is contained in:
Ricardo Montañana Gómez
2023-03-21 09:55:40 +01:00
parent 27ea3bf338
commit 77135739cf
2 changed files with 23 additions and 39 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
tests/ArffFiles.cpp
View File

@@ -7,43 +7,35 @@ using namespace std;
ArffFiles::ArffFiles() = default; ArffFiles::ArffFiles() = default;
vector<string> ArffFiles::getLines() const vector<string> ArffFiles::getLines() const {
{
return lines; return lines;
} }
unsigned long int ArffFiles::getSize() const unsigned long int ArffFiles::getSize() const {
{
return lines.size(); return lines.size();
} }
vector<pair<string, string>> ArffFiles::getAttributes() const vector<pair<string, string>> ArffFiles::getAttributes() const {
{
return attributes; return attributes;
} }
string ArffFiles::getClassName() const string ArffFiles::getClassName() const {
{
return className; return className;
} }
string ArffFiles::getClassType() const string ArffFiles::getClassType() const {
{
return classType; return classType;
} }
vector<vector<float>>& ArffFiles::getX() vector<vector<float>> &ArffFiles::getX() {
{
return X; return X;
} }
vector<int>& ArffFiles::getY() vector<int> &ArffFiles::getY() {
{
return y; return y;
} }
void ArffFiles::load(const string& fileName, bool classLast) void ArffFiles::load(const string &fileName, bool classLast) {
{
ifstream file(fileName); ifstream file(fileName);
if (!file.is_open()) { if (!file.is_open()) {
throw invalid_argument("Unable to open file"); throw invalid_argument("Unable to open file");
@@ -87,8 +79,7 @@ void ArffFiles::load(const string& fileName, bool classLast)
} }
void ArffFiles::generateDataset(bool classLast) void ArffFiles::generateDataset(bool classLast) {
{
X = vector<vector<float>>(attributes.size(), vector<float>(lines.size())); X = vector<vector<float>>(attributes.size(), vector<float>(lines.size()));
auto yy = vector<string>(lines.size(), ""); auto yy = vector<string>(lines.size(), "");
int labelIndex = classLast ? static_cast<int>(attributes.size()) : 0; int labelIndex = classLast ? static_cast<int>(attributes.size()) : 0;
@@ -108,21 +99,19 @@ void ArffFiles::generateDataset(bool classLast)
y = factorize(yy); y = factorize(yy);
} }
string ArffFiles::trim(const string& source) string ArffFiles::trim(const string &source) {
{
string s(source); string s(source);
s.erase(0, s.find_first_not_of(" \n\r\t")); s.erase(0, s.find_first_not_of(" \n\r\t"));
s.erase(s.find_last_not_of(" \n\r\t") + 1); s.erase(s.find_last_not_of(" \n\r\t") + 1);
return s; return s;
} }
vector<int> ArffFiles::factorize(const vector<string>& labels_t) vector<int> ArffFiles::factorize(const vector<string> &labels_t) {
{
vector<int> yy; vector<int> yy;
yy.reserve(labels_t.size()); yy.reserve(labels_t.size());
map<string, int> labelMap; map<string, int> labelMap;
int i = 0; int i = 0;
for (const string& label : labels_t) { for (const string &label: labels_t) {
if (labelMap.find(label) == labelMap.end()) { if (labelMap.find(label) == labelMap.end()) {
labelMap[label] = i++; labelMap[label] = i++;
} }

27
tests/Metrics_unittest.cpp
View File

@@ -1,44 +1,39 @@
#include "gtest/gtest.h" #include "gtest/gtest.h"
#include "../Metrics.h" #include "../Metrics.h"
namespace mdlp { namespace mdlp {
class TestMetrics: public Metrics, public testing::Test { class TestMetrics : public Metrics, public testing::Test {
public: public:
labels_t y_ = { 1, 1, 1, 1, 1, 2, 2, 2, 2, 2 }; 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 }; indices_t indices_ = {0, 1, 2, 3, 4, 5, 6, 7, 8, 9};
precision_t precision = 0.000001f; precision_t precision = 0.000001f;
TestMetrics(): Metrics(y_, indices_) {}; TestMetrics() : Metrics(y_, indices_) {};
void SetUp() override void SetUp() override {
{
setData(y_, indices_); setData(y_, indices_);
} }
}; };
TEST_F(TestMetrics, NumClasses) TEST_F(TestMetrics, NumClasses) {
{ y = {1, 1, 1, 1, 1, 1, 1, 1, 2, 1};
y = { 1, 1, 1, 1, 1, 1, 1, 1, 2, 1 };
EXPECT_EQ(1, computeNumClasses(4, 8)); EXPECT_EQ(1, computeNumClasses(4, 8));
EXPECT_EQ(2, computeNumClasses(0, 10)); EXPECT_EQ(2, computeNumClasses(0, 10));
EXPECT_EQ(2, computeNumClasses(8, 10)); EXPECT_EQ(2, computeNumClasses(8, 10));
} }
TEST_F(TestMetrics, Entropy) TEST_F(TestMetrics, Entropy) {
{
EXPECT_EQ(1, entropy(0, 10)); EXPECT_EQ(1, entropy(0, 10));
EXPECT_EQ(0, entropy(0, 5)); EXPECT_EQ(0, entropy(0, 5));
y = { 1, 1, 1, 1, 1, 1, 1, 1, 2, 1 }; y = {1, 1, 1, 1, 1, 1, 1, 1, 2, 1};
setData(y, indices); setData(y, indices);
ASSERT_NEAR(0.468996f, entropy(0, 10), precision); ASSERT_NEAR(0.468996f, entropy(0, 10), precision);
} }
TEST_F(TestMetrics, InformationGain) TEST_F(TestMetrics, InformationGain) {
{
ASSERT_NEAR(1, informationGain(0, 5, 10), precision); ASSERT_NEAR(1, informationGain(0, 5, 10), precision);
ASSERT_NEAR(1, informationGain(0, 5, 10), precision); // For cache ASSERT_NEAR(1, informationGain(0, 5, 10), precision); // For cache
y = { 1, 1, 1, 1, 1, 1, 1, 1, 2, 1 }; y = {1, 1, 1, 1, 1, 1, 1, 1, 2, 1};
setData(y, indices); setData(y, indices);
ASSERT_NEAR(0.108032f, informationGain(0, 5, 10), precision); ASSERT_NEAR(0.108032f, informationGain(0, 5, 10), precision);
} }