rmontanana/BayesNet
1
0
Fork 0
Code Issues 2 Pull Requests 1 Actions Packages Projects Releases 6 Wiki Activity

Add test to 99.1%

Browse Source
This commit is contained in:
Ricardo Montañana Gómez
2025-03-14 18:55:29 +01:00
parent 400967b4e3
commit 70c7d3dd3d
4 changed files with 101 additions and 60 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@@ -7,7 +7,7 @@
[![Security Rating](https://sonarcloud.io/api/project_badges/measure?project=rmontanana_BayesNet&metric=security_rating)](https://sonarcloud.io/summary/new_code?id=rmontanana_BayesNet)
[![Reliability Rating](https://sonarcloud.io/api/project_badges/measure?project=rmontanana_BayesNet&metric=reliability_rating)](https://sonarcloud.io/summary/new_code?id=rmontanana_BayesNet)
![Gitea Last Commit](https://img.shields.io/gitea/last-commit/rmontanana/bayesnet?gitea_url=https://gitea.rmontanana.es:3000&logo=gitea)
[![Coverage Badge](https://img.shields.io/badge/Coverage-99,0%25-green)](html/index.html)
[![Coverage Badge](https://img.shields.io/badge/Coverage-99,1%25-green)](html/index.html)
[![DOI](https://zenodo.org/badge/667782806.svg)](https://doi.org/10.5281/zenodo.14210344)
Bayesian Network Classifiers library

2
bayesnet/classifiers/KDB.cc
View File

@@ -3,7 +3,7 @@
// SPDX-FileType: SOURCE
// SPDX-License-Identifier: MIT
// ***************************************************************
#include "bayesnet/utils/bayesnetUtils.h"
#include "KDB.h"
namespace bayesnet {

3
bayesnet/classifiers/KDB.h
View File

@@ -7,15 +7,14 @@
#ifndef KDB_H
#define KDB_H
#include <torch/torch.h>
#include "bayesnet/utils/bayesnetUtils.h"
#include "Classifier.h"
namespace bayesnet {
class KDB : public Classifier {
private:
int k;
float theta;
void add_m_edges(int idx, std::vector<int>& S, torch::Tensor& weights);
protected:
void add_m_edges(int idx, std::vector<int>& S, torch::Tensor& weights);
void buildModel(const torch::Tensor& weights) override;
public:
explicit KDB(int k, float theta = 0.03);

78
tests/TestBayesModels.cc
View File

@@ -22,7 +22,8 @@
const std::string ACTUAL_VERSION = "1.0.6";
TEST_CASE("Test Bayesian Classifiers score & version", "[Models]") {
TEST_CASE("Test Bayesian Classifiers score & version", "[Models]")
{
map<pair<std::string, std::string>, float> scores{// Diabetes
{{"diabetes", "AODE"}, 0.82161},
{{"diabetes", "KDB"}, 0.852865},
@@ -80,7 +81,8 @@ TEST_CASE("Test Bayesian Classifiers score & version", "[Models]") {
std::string name = GENERATE("AODE", "AODELd", "KDB", "KDBLd", "SPODE", "XSPODE", "SPODELd", "TAN", "TANLd");
auto clf = models[name];
SECTION("Test " + name + " classifier") {
SECTION("Test " + name + " classifier")
{
for (const std::string& file_name : { "glass", "iris", "ecoli", "diabetes" }) {
auto clf = models[name];
auto discretize = name.substr(name.length() - 2) != "Ld";
@@ -94,13 +96,15 @@ TEST_CASE("Test Bayesian Classifiers score & version", "[Models]") {
REQUIRE(clf->getStatus() == bayesnet::NORMAL);
}
}
SECTION("Library check version") {
SECTION("Library check version")
{
INFO("Checking version of " << name << " classifier");
REQUIRE(clf->getVersion() == ACTUAL_VERSION);
}
delete clf;
}
TEST_CASE("Models features & Graph", "[Models]") {
TEST_CASE("Models features & Graph", "[Models]")
{
auto graph = std::vector<std::string>(
{ "digraph BayesNet {\nlabel=<BayesNet Test>\nfontsize=30\nfontcolor=blue\nlabelloc=t\nlayout=circo\n",
"\"class\" [shape=circle, fontcolor=red, fillcolor=lightblue, style=filled ] \n",
@@ -108,7 +112,8 @@ TEST_CASE("Models features & Graph", "[Models]") {
"\"class\" -> \"petalwidth\"", "\"petallength\" [shape=circle] \n", "\"petallength\" -> \"sepallength\"",
"\"petalwidth\" [shape=circle] \n", "\"sepallength\" [shape=circle] \n", "\"sepallength\" -> \"sepalwidth\"",
"\"sepalwidth\" [shape=circle] \n", "\"sepalwidth\" -> \"petalwidth\"", "}\n" });
SECTION("Test TAN") {
SECTION("Test TAN")
{
auto raw = RawDatasets("iris", true);
auto clf = bayesnet::TAN();
clf.fit(raw.Xv, raw.yv, raw.features, raw.className, raw.states, raw.smoothing);
@@ -121,7 +126,8 @@ TEST_CASE("Models features & Graph", "[Models]") {
"sepallength -> sepalwidth, ", "sepalwidth -> petalwidth, "});
REQUIRE(clf.graph("Test") == graph);
}
SECTION("Test TANLd") {
SECTION("Test TANLd")
{
auto clf = bayesnet::TANLd();
auto raw = RawDatasets("iris", false);
clf.fit(raw.Xt, raw.yt, raw.features, raw.className, raw.states, raw.smoothing);
@@ -135,7 +141,8 @@ TEST_CASE("Models features & Graph", "[Models]") {
REQUIRE(clf.graph("Test") == graph);
}
}
TEST_CASE("Get num features & num edges", "[Models]") {
TEST_CASE("Get num features & num edges", "[Models]")
{
auto raw = RawDatasets("iris", true);
auto clf = bayesnet::KDB(2);
clf.fit(raw.Xv, raw.yv, raw.features, raw.className, raw.states, raw.smoothing);
@@ -143,7 +150,8 @@ TEST_CASE("Get num features & num edges", "[Models]") {
REQUIRE(clf.getNumberOfEdges() == 8);
}
TEST_CASE("Model predict_proba", "[Models]") {
TEST_CASE("Model predict_proba", "[Models]")
{
std::string model = GENERATE("TAN", "SPODE", "BoostAODEproba", "BoostAODEvoting");
auto res_prob_tan = std::vector<std::vector<double>>({ {0.00375671, 0.994457, 0.00178621},
{0.00137462, 0.992734, 0.00589123},
@@ -185,7 +193,8 @@ TEST_CASE("Model predict_proba", "[Models]") {
int init_index = 78;
auto raw = RawDatasets("iris", true);
SECTION("Test " + model + " predict_proba") {
SECTION("Test " + model + " predict_proba")
{
auto clf = models[model];
clf->fit(raw.Xv, raw.yv, raw.features, raw.className, raw.states, raw.smoothing);
auto y_pred_proba = clf->predict_proba(raw.Xv);
@@ -221,7 +230,8 @@ TEST_CASE("Model predict_proba", "[Models]") {
}
}
TEST_CASE("AODE voting-proba", "[Models]") {
TEST_CASE("AODE voting-proba", "[Models]")
{
auto raw = RawDatasets("glass", true);
auto clf = bayesnet::AODE(false);
clf.fit(raw.Xv, raw.yv, raw.features, raw.className, raw.states, raw.smoothing);
@@ -238,7 +248,8 @@ TEST_CASE("AODE voting-proba", "[Models]") {
REQUIRE(pred_proba[67][0] == Catch::Approx(0.702184).epsilon(raw.epsilon));
REQUIRE(clf.topological_order() == std::vector<std::string>());
}
TEST_CASE("SPODELd dataset", "[Models]") {
TEST_CASE("SPODELd dataset", "[Models]")
{
auto raw = RawDatasets("iris", false);
auto clf = bayesnet::SPODELd(0);
// raw.dataset.to(torch::kFloat32);
@@ -249,7 +260,8 @@ TEST_CASE("SPODELd dataset", "[Models]") {
REQUIRE(score == Catch::Approx(0.97333f).epsilon(raw.epsilon));
REQUIRE(scoret == Catch::Approx(0.97333f).epsilon(raw.epsilon));
}
TEST_CASE("KDB with hyperparameters", "[Models]") {
TEST_CASE("KDB with hyperparameters", "[Models]")
{
auto raw = RawDatasets("glass", true);
auto clf = bayesnet::KDB(2);
clf.fit(raw.Xv, raw.yv, raw.features, raw.className, raw.states, raw.smoothing);
@@ -263,12 +275,14 @@ TEST_CASE("KDB with hyperparameters", "[Models]") {
REQUIRE(score == Catch::Approx(0.827103).epsilon(raw.epsilon));
REQUIRE(scoret == Catch::Approx(0.761682).epsilon(raw.epsilon));
}
TEST_CASE("Incorrect type of data for SPODELd", "[Models]") {
TEST_CASE("Incorrect type of data for SPODELd", "[Models]")
{
auto raw = RawDatasets("iris", true);
auto clf = bayesnet::SPODELd(0);
REQUIRE_THROWS_AS(clf.fit(raw.dataset, raw.features, raw.className, raw.states, raw.smoothing), std::runtime_error);
}
TEST_CASE("Predict, predict_proba & score without fitting", "[Models]") {
TEST_CASE("Predict, predict_proba & score without fitting", "[Models]")
{
auto clf = bayesnet::AODE();
auto raw = RawDatasets("iris", true);
std::string message = "Ensemble has not been fitted";
@@ -285,7 +299,8 @@ TEST_CASE("Predict, predict_proba & score without fitting", "[Models]") {
REQUIRE_THROWS_WITH(clf.score(raw.Xv, raw.yv), message);
REQUIRE_THROWS_WITH(clf.score(raw.Xt, raw.yt), message);
}
TEST_CASE("TAN & SPODE with hyperparameters", "[Models]") {
TEST_CASE("TAN & SPODE with hyperparameters", "[Models]")
{
auto raw = RawDatasets("iris", true);
auto clf = bayesnet::TAN();
clf.setHyperparameters({
@@ -302,7 +317,8 @@ TEST_CASE("TAN & SPODE with hyperparameters", "[Models]") {
auto score2 = clf2.score(raw.Xv, raw.yv);
REQUIRE(score2 == Catch::Approx(0.973333).epsilon(raw.epsilon));
}
TEST_CASE("TAN & SPODE with invalid hyperparameters", "[Models]") {
TEST_CASE("TAN & SPODE with invalid hyperparameters", "[Models]")
{
auto raw = RawDatasets("iris", true);
auto clf = bayesnet::TAN();
clf.setHyperparameters({
@@ -317,11 +333,14 @@ TEST_CASE("TAN & SPODE with invalid hyperparameters", "[Models]") {
REQUIRE_THROWS_AS(clf2.fit(raw.Xv, raw.yv, raw.features, raw.className, raw.states, raw.smoothing),
std::invalid_argument);
}
TEST_CASE("Check proposal checkInput", "[Models]") {
TEST_CASE("Check proposal checkInput", "[Models]")
{
class testProposal : public bayesnet::Proposal {
public:
testProposal(torch::Tensor& dataset_, std::vector<std::string>& features_, std::string& className_)
: Proposal(dataset_, features_, className_) {}
: Proposal(dataset_, features_, className_)
{
}
void test_X_y(const torch::Tensor& X, const torch::Tensor& y) { checkInput(X, y); }
};
auto raw = RawDatasets("iris", true);
@@ -337,3 +356,26 @@ TEST_CASE("Check proposal checkInput", "[Models]") {
INFO("X and y are correct");
REQUIRE_NOTHROW(clf.test_X_y(X, y));
}
TEST_CASE("Check KDB loop detection", "[Models]")
{
class testKDB : public bayesnet::KDB {
public:
testKDB() : KDB(2, 0) {}
void test_add_m_edges(std::vector<std::string> features_, int idx, std::vector<int>& S, torch::Tensor& weights)
{
features = features_;
add_m_edges(idx, S, weights);
}
};
auto clf = testKDB();
auto features = std::vector<std::string>{ "A", "B", "C" };
int idx = 0;
std::vector<int> S = { 0 };
torch::Tensor weights = torch::tensor({
{ 1.0, 10.0, 0.0 }, // row0 -> picks col1
{ 0.0, 1.0, 10.0 }, // row1 -> picks col2
{ 10.0, 0.0, 1.0 }, // row2 -> picks col0
});
REQUIRE_NOTHROW(clf.test_add_m_edges(features, 0, S, weights));
REQUIRE_NOTHROW(clf.test_add_m_edges(features, 1, S, weights));
}