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

Fix BinDisc quantile mistakes (#9)

Browse Source 
* Fix BinDisc quantile mistakes

* Fix FImdlp tests

* Fix tests, samples and remove uneeded support files

* Add coypright header to sources
Fix coverage report
Add coverage badge to README

* Update sonar github action

* Move sources to a folder and change ArffFiles files to library

* Add recursive submodules to github action
This commit is contained in:
Ricardo Montañana Gómez
2024-07-04 17:27:39 +02:00
committed by GitHub
parent 7b0673fd4b
commit e36d9af8f9
35 changed files with 1383 additions and 923 deletions
Download Patch File Download Diff File Expand all files Collapse all files

214
tests/Discretizer_unittest.cpp
View File

@@ -1,11 +1,17 @@
// ****************************************************************
// SPDX - FileCopyrightText: Copyright 2024 Ricardo Montañana Gómez
// SPDX - FileType: SOURCE
// SPDX - License - Identifier: MIT
// ****************************************************************
#include <fstream>
#include <string>
#include <iostream>
#include <ArffFiles.hpp>
#include "gtest/gtest.h"
#include "ArffFiles.h"
#include "../Discretizer.h"
#include "../BinDisc.h"
#include "../CPPFImdlp.h"
#include "Discretizer.h"
#include "BinDisc.h"
#include "CPPFImdlp.h"
namespace mdlp {
const float margin = 1e-4;
@@ -20,7 +26,15 @@ namespace mdlp {
return "../../tests/datasets/";
}
const std::string data_path = set_data_path();
const labels_t iris_quantile = { 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 2, 1, 1, 1, 1, 1, 1, 1, 0, 1, 0, 0, 0, 1, 1, 0, 0, 1, 1, 1, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 1, 0, 1, 0, 1, 0, 3, 3, 3, 1, 3, 1, 2, 0, 3, 1, 0, 2, 2, 2, 1, 3, 1, 2, 2, 1, 2, 2, 2, 2, 3, 3, 3, 3, 2, 1, 1, 1, 2, 2, 1, 2, 3, 2, 1, 1, 1, 2, 2, 0, 1, 1, 1, 2, 1, 1, 2, 2, 3, 2, 3, 3, 0, 3, 3, 3, 3, 3, 3, 1, 2, 3, 3, 3, 3, 2, 3, 1, 3, 2, 3, 3, 2, 2, 3, 3, 3, 3, 3, 2, 2, 3, 2, 3, 2, 3, 3, 3, 2, 3, 3, 3, 2, 3, 2, 2 };
TEST(Discretizer, Version)
{
Discretizer* disc = new BinDisc(4, strategy_t::UNIFORM);
auto version = disc->version();
delete disc;
std::cout << "Version computed: " << version;
EXPECT_EQ("1.2.3", version);
}
TEST(Discretizer, BinIrisUniform)
{
ArffFiles file;
@@ -43,12 +57,198 @@ namespace mdlp {
auto y = labels_t();
disc->fit(X[0], y);
auto Xt = disc->transform(X[0]);
labels_t expected = { 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 2, 1, 1, 1, 1, 1, 1, 1, 0, 1, 0, 0, 0, 1, 1, 0, 0, 1, 1, 1, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 1, 0, 1, 0, 1, 0, 3, 3, 3, 1, 3, 1, 2, 0, 3, 1, 0, 2, 2, 2, 1, 3, 1, 2, 2, 1, 2, 2, 2, 2, 3, 3, 3, 3, 2, 1, 1, 1, 2, 2, 1, 2, 3, 2, 1, 1, 1, 2, 2, 0, 1, 1, 1, 2, 1, 1, 2, 2, 3, 2, 3, 3, 0, 3, 3, 3, 3, 3, 3, 1, 2, 3, 3, 3, 3, 2, 3, 1, 3, 2, 3, 3, 2, 2, 3, 3, 3, 3, 3, 2, 2, 3, 2, 3, 2, 3, 3, 3, 2, 3, 3, 3, 2, 3, 2, 2 };
delete disc;
EXPECT_EQ(expected, Xt);
EXPECT_EQ(iris_quantile, Xt);
}
TEST(Discretizer, BinIrisQuantileTorch)
{
ArffFiles file;
Discretizer* disc = new BinDisc(4, strategy_t::QUANTILE);
file.load(data_path + "iris.arff", true);
auto X = file.getX();
auto y = file.getY();
auto X_torch = torch::tensor(X[0], torch::kFloat32);
auto yt = torch::tensor(y, torch::kInt32);
disc->fit_t(X_torch, yt);
torch::Tensor Xt = disc->transform_t(X_torch);
delete disc;
EXPECT_EQ(iris_quantile.size(), Xt.size(0));
for (int i = 0; i < iris_quantile.size(); ++i) {
EXPECT_EQ(iris_quantile.at(i), Xt[i].item<int>());
}
}
TEST(Discretizer, BinIrisQuantileTorchFit_transform)
{
ArffFiles file;
Discretizer* disc = new BinDisc(4, strategy_t::QUANTILE);
file.load(data_path + "iris.arff", true);
auto X = file.getX();
auto y = file.getY();
auto X_torch = torch::tensor(X[0], torch::kFloat32);
auto yt = torch::tensor(y, torch::kInt32);
torch::Tensor Xt = disc->fit_transform_t(X_torch, yt);
delete disc;
EXPECT_EQ(iris_quantile.size(), Xt.size(0));
for (int i = 0; i < iris_quantile.size(); ++i) {
EXPECT_EQ(iris_quantile.at(i), Xt[i].item<int>());
}
}
TEST(Discretizer, FImdlpIris)
{
auto labelsq = {
1,
0,
0,
0,
0,
1,
0,
0,
0,
0,
1,
0,
0,
0,
2,
1,
1,
1,
1,
1,
1,
1,
0,
1,
0,
0,
0,
1,
1,
0,
0,
1,
1,
1,
0,
0,
1,
0,
0,
1,
0,
0,
0,
0,
1,
0,
1,
0,
1,
0,
3,
3,
3,
1,
3,
1,
2,
0,
3,
1,
0,
2,
2,
2,
1,
3,
1,
2,
2,
1,
2,
2,
2,
2,
3,
3,
3,
3,
2,
1,
1,
1,
2,
2,
1,
2,
3,
2,
1,
1,
1,
2,
2,
0,
1,
1,
1,
2,
1,
1,
2,
2,
3,
2,
3,
3,
0,
3,
3,
3,
3,
3,
3,
1,
2,
3,
3,
3,
3,
2,
3,
1,
3,
2,
3,
3,
2,
2,
3,
3,
3,
3,
3,
2,
2,
3,
2,
3,
2,
3,
3,
3,
2,
3,
3,
3,
2,
3,
2,
2,
};
labels_t expected = {
5, 3, 4, 4, 5, 5, 5, 5, 2, 4, 5, 5, 3, 3, 5, 5, 5, 5, 5, 5, 5, 5,
5, 4, 5, 3, 5, 5, 5, 4, 4, 5, 5, 5, 4, 4, 5, 4, 3, 5, 5, 0, 4, 5,