rmontanana/Platform
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update models versions

Browse Source
This commit is contained in:
Ricardo Montañana Gómez
2024-06-13 12:30:31 +02:00
parent e628d80f4c
commit 3d900f8c81
10 changed files with 60 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
lib/Files

Submodule lib/Files updated: dbefa02d9c...a5316928d4

8
src/common/Datasets.cpp
View File

@@ -5,6 +5,14 @@
namespace platform {
using json = nlohmann::ordered_json;
const std::string message_dataset_not_loaded = "dataset not loaded.";
Datasets::Datasets(bool discretize, std::string sfileType, std::string discretizer_algorithm) :
discretize(discretize), sfileType(sfileType), discretizer_algorithm(discretizer_algorithm)
{
if (discretizer_algorithm == "none" && discretize) {
throw std::runtime_error("Can't discretize without discretization algorithm");
}
load();
}
void Datasets::load()
{
auto sd = SourceData(sfileType);

9
src/common/Datasets.h
View File

@@ -4,14 +4,7 @@
namespace platform {
class Datasets {
public:
explicit Datasets(bool discretize, std::string sfileType, std::string discretizer_algorithm = "none") :
discretize(discretize), sfileType(sfileType), discretizer_algorithm(discretizer_algorithm)
{
if (discretizer_algorithm == "none" && discretize) {
throw std::runtime_error("Can't discretize without discretization algorithm");
}
load();
};
explicit Datasets(bool discretize, std::string sfileType, std::string discretizer_algorithm = "none");
std::vector<std::string> getNames();
bool isDataset(const std::string& name) const;
Dataset& getDataset(const std::string& name) const { return *datasets.at(name); }

27
src/common/DotEnv.h
View File

@@ -19,8 +19,8 @@ namespace platform {
{
valid =
{
{"source_data", {"Arff", "Tanveer", "Surcov"}},
{"experiment", {"discretiz", "odte", "covid"}},
{"source_data", {"Arff", "Tanveer", "Surcov", "Test"}},
{"experiment", {"discretiz", "odte", "covid", "Test"}},
{"fit_features", {"0", "1"}},
{"discretize", {"0", "1"}},
{"ignore_nan", {"0", "1"}},
@@ -31,7 +31,7 @@ namespace platform {
{"n_folds", {"5", "10"}},
{"discretize_algo", {"mdlp", "bin3u", "bin3q", "bin4u", "bin4q"}},
{"smooth_strat", {"OLD_LAPLACE", "LAPLACE", "CESTNIK"}},
{ "platform", {"any"} },
{"platform", {"any"}},
{"model", {"any"}},
{"seeds", {"any"}},
{"nodes", {"any"}},
@@ -41,8 +41,25 @@ namespace platform {
if (create) {
// For testing purposes
std::ofstream file(".env");
file << "source_data = Test" << std::endl;
file << "margin = 0.1" << std::endl;
file << "experiment=Test" << std::endl;
file << "source_data=Test" << std::endl;
file << "margin=0.1" << std::endl;
file << "score=accuracy" << std::endl;
file << "platform=um790Linux" << std::endl;
file << "n_folds=5" << std::endl;
file << "discretize_algo=mdlp" << std::endl;
file << "smooth_strat=OLD_LAPLACE" << std::endl;
file << "stratified=0" << std::endl;
file << "model=TAN" << std::endl;
file << "seeds=[271]" << std::endl;
file << "discretize=0" << std::endl;
file << "ignore_nan=0" << std::endl;
file << "nodes=Nodes" << std::endl;
file << "leaves=Edges" << std::endl;
file << "depth=States" << std::endl;
file << "fit_features=0" << std::endl;
file << "framework=bulma" << std::endl;
file << "margin=0.1" << std::endl;
file.close();
}
std::ifstream file(".env");

4
tests/CMakeLists.txt
View File

@@ -13,10 +13,10 @@ if(ENABLE_TESTING)
)
set(TEST_SOURCES_PLATFORM
TestUtils.cpp TestPlatform.cpp TestResult.cpp TestScores.cpp
${Platform_SOURCE_DIR}/src/common/Datasets.cpp ${Platform_SOURCE_DIR}/src/common/Dataset.cpp
${Platform_SOURCE_DIR}/src/common/Datasets.cpp ${Platform_SOURCE_DIR}/src/common/Dataset.cpp ${Platform_SOURCE_DIR}/src/common/Discretization.cpp
${Platform_SOURCE_DIR}/src/main/Scores.cpp
)
add_executable(${TEST_PLATFORM} ${TEST_SOURCES_PLATFORM})
target_link_libraries(${TEST_PLATFORM} PUBLIC "${TORCH_LIBRARIES}" ArffFiles mdlp Catch2::Catch2WithMain BayesNet)
target_link_libraries(${TEST_PLATFORM} PUBLIC "${TORCH_LIBRARIES}" mdlp Catch2::Catch2WithMain BayesNet)
add_test(NAME ${TEST_PLATFORM} COMMAND ${TEST_PLATFORM})
endif(ENABLE_TESTING)

12
tests/TestPlatform.cpp
View File

@@ -7,6 +7,7 @@
#include <string>
#include "TestUtils.h"
#include "folding.hpp"
#include <ArffFiles.hpp>
#include <bayesnet/classifiers/TAN.h>
#include "config.h"
@@ -14,7 +15,7 @@
TEST_CASE("Test Platform version", "[Platform]")
{
std::string version = { platform_project_version.begin(), platform_project_version.end() };
REQUIRE(version == "1.0.4");
REQUIRE(version == "1.1.0");
}
TEST_CASE("Test Folding library version", "[Folding]")
{
@@ -24,10 +25,15 @@ TEST_CASE("Test Folding library version", "[Folding]")
TEST_CASE("Test BayesNet version", "[BayesNet]")
{
std::string version = bayesnet::TAN().getVersion();
REQUIRE(version == "1.0.5.1");
REQUIRE(version == "1.0.6");
}
TEST_CASE("Test mdlp version", "[mdlp]")
{
std::string version = mdlp::CPPFImdlp::version();
REQUIRE(version == "1.1.2");
REQUIRE(version == "1.2.1");
}
TEST_CASE("Test Arff version", "[Arff]")
{
std::string version = ArffFiles().version();
REQUIRE(version == "1.1.0");
}

13
tests/TestResult.cpp
View File

@@ -13,13 +13,14 @@
TEST_CASE("ZeroR comparison in reports", "[Report]")
{
auto dotEnv = platform::DotEnv(true);
auto margin = 1e-2;
std::string dataset = "liver-disorders";
auto margin = 1e-4;
std::string dataset_name = "liver-disorders";
auto dt = platform::Datasets(false, platform::Paths::datasets());
dt.loadDataset(dataset);
std::vector<int> distribution = dt.getClassesCounts(dataset);
double nSamples = dt.getNSamples(dataset);
auto& dataset = dt.getDataset(dataset_name);
dataset.load();
std::vector<int> distribution = dataset.getClassesCounts();
double nSamples = dataset.getNSamples();
std::vector<int>::iterator maxValue = max_element(distribution.begin(), distribution.end());
double mark = *maxValue / nSamples * (1 + margin);
REQUIRE(mark == Catch::Approx(0.585507f).epsilon(1e-5));
REQUIRE(mark == Catch::Approx(0.57976811f).epsilon(margin));
}

2
tests/TestScores.cpp
View File

@@ -128,7 +128,7 @@ TEST_CASE("Confusion Matrix JSON", "[Scores]")
REQUIRE(res_json_str["Car"][1] == 2);
REQUIRE(res_json_str["Car"][2] == 3);
}
TEST_CASE("Classification Report", "[Scores]") -
TEST_CASE("Classification Report", "[Scores]")
{
std::vector<int> y_test = { 0, 2, 2, 2, 2, 0, 1, 2, 0, 2 };
std::vector<int> y_pred = { 0, 1, 2, 2, 1, 1, 1, 0, 0, 2 };

2
tests/TestUtils.h
View File

@@ -5,7 +5,7 @@
#include <vector>
#include <map>
#include <tuple>
#include "ArffFiles.h"
#include <ArffFiles.hpp>
#include "CPPFImdlp.h"
bool file_exists(const std::string& name);

16
tests/data/all.txt
View File

@@ -1,8 +1,8 @@
diabetes,class, all
ecoli,class, all
glass,Type, all
iris,class, all
kdd_JapaneseVowels,speaker, [2,3,4,5,6,7,8,9,10,11,12,13]
letter,class, all
liver-disorders,selector, all
mfeat-factors,class, all
diabetes;class;all
ecoli;class;all
glass;Type,all
iris;class;all
kdd_JapaneseVowels;speaker;[2,3,4,5,6,7,8,9,10,11,12,13]
letter;class;all
liver-disorders;selector;all
mfeat-factors;class;all