rmontanana/BayesNet
rmontanana/BayesNet
1
0
Fork 0
Code Issues 2 Pull Requests Packages Projects Releases 3 Wiki Activity

Add notes to Classifier & Changelog

Browse Source
This commit is contained in:
Ricardo Montañana Gómez 2024-02-12 10:58:20 +01:00
parent 03f8b8653b
commit f3b8150e2c
Signed by: rmontanana
GPG Key ID: 46064262FD9A7ADE
6 changed files with 95 additions and 99 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
CHANGELOG.md Normal file
View File

@ -0,0 +1,23 @@
# Changelog
All notable changes to this project will be documented in this file.
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
## [1.0.1] - 2024-02-12
### Added
- Notes in Classifier class
- BoostAODE: Add note with used features in initialization with feature selection
- BoostAODE: Add note with the number of models
- BoostAODE: Add note with the number of features used to create models if not all features are used
- Test version number in TestBayesModels
- Add tests with feature_select and notes on BoostAODE
### Fixed
- Network predict test
- Network predict_proba test
- Network score test

2
CMakeLists.txt
View File

@ -1,7 +1,7 @@
cmake_minimum_required(VERSION 3.20)
project(BayesNet
VERSION 1.0.0
VERSION 1.0.1
DESCRIPTION "Bayesian Network and basic classifiers Library."
HOMEPAGE_URL "https://github.com/rmontanana/bayesnet"
LANGUAGES CXX

1
src/BayesNet/BoostAODE.cc
View File

@ -201,6 +201,7 @@ namespace bayesnet {
notes.push_back("Used features in train: " + std::to_string(featuresUsed.size()) + " of " + std::to_string(features.size()));
status = WARNING;
}
notes.push_back("Number of models: " + std::to_string(n_models));
}
std::vector<std::string> BoostAODE::graph(const std::string& title) const
{

2
src/BayesNet/Classifier.h
View File

@ -37,7 +37,7 @@ namespace bayesnet {
int getNumberOfStates() const override;
torch::Tensor predict(torch::Tensor& X) override;
status_t getStatus() const override { return status; }
std::string getVersion() override { return "0.2.0"; };
std::string getVersion() override { return { project_version.begin(), project_version.end() }; };
std::vector<int> predict(std::vector<std::vector<int>>& X) override;
float score(torch::Tensor& X, torch::Tensor& y) override;
float score(std::vector<std::vector<int>>& X, std::vector<int>& y) override;

30
tests/TestBayesModels.cc
View File

@ -16,6 +16,11 @@
#include "AODELd.h"
#include "TestUtils.h"
TEST_CASE("Library check version", "[BayesNet]")
{
auto clf = bayesnet::KDB(2);
REQUIRE(clf.getVersion() == "1.0.1");
}
TEST_CASE("Test Bayesian Classifiers score", "[BayesNet]")
{
map <pair<std::string, std::string>, float> scores = {
@ -139,7 +144,7 @@ TEST_CASE("Get num features & num edges", "[BayesNet]")
REQUIRE(clf.getNumberOfNodes() == 5);
REQUIRE(clf.getNumberOfEdges() == 8);
}
TEST_CASE("BoostAODE feature_select CFS")
TEST_CASE("BoostAODE feature_select CFS", "[BayesNet]")
{
auto raw = RawDatasets("glass", true);
auto clf = bayesnet::BoostAODE();
@ -147,6 +152,25 @@ TEST_CASE("BoostAODE feature_select CFS")
clf.fit(raw.Xv, raw.yv, raw.featuresv, raw.classNamev, raw.statesv);
REQUIRE(clf.getNumberOfNodes() == 90);
REQUIRE(clf.getNumberOfEdges() == 153);
REQUIRE(clf.getNotes().size() == 1);
REQUIRE(clf.getNotes().size() == 2);
REQUIRE(clf.getNotes()[0] == "Used features in initialization: 6 of 9 with CFS");
}
REQUIRE(clf.getNotes()[1] == "Number of models: 9");
}
TEST_CASE("BoostAODE test used features in train note", "[BayesNet]")
{
auto raw = RawDatasets("diabetes", true);
auto clf = bayesnet::BoostAODE();
clf.setHyperparameters({
{"ascending",true},
{"convergence", true},
{"repeatSparent",true},
{"select_features","CFS"}
});
clf.fit(raw.Xv, raw.yv, raw.featuresv, raw.classNamev, raw.statesv);
REQUIRE(clf.getNumberOfNodes() == 72);
REQUIRE(clf.getNumberOfEdges() == 120);
REQUIRE(clf.getNotes().size() == 3);
REQUIRE(clf.getNotes()[0] == "Used features in initialization: 6 of 8 with CFS");
REQUIRE(clf.getNotes()[1] == "Used features in train: 7 of 8");
REQUIRE(clf.getNotes()[2] == "Number of models: 8");
}

136
tests/TestBayesNetwork.cc
View File

@ -25,6 +25,7 @@ TEST_CASE("Test Bayesian Network", "[BayesNet]")
auto raw = RawDatasets("iris", true);
auto net = bayesnet::Network();
double threshold = 1e-4;
SECTION("Test get features")
{
@ -167,97 +168,44 @@ TEST_CASE("Test Bayesian Network", "[BayesNet]")
REQUIRE(str[5] == "C [shape=circle] \n");
REQUIRE(str[6] == "}\n");
}
// SECTION("Test predict")
// {
// auto net = bayesnet::Network();
// net.fit(raw.Xv, raw.yv, raw.weightsv, raw.featuresv, raw.classNamev, raw.statesv);
// std::vector<std::vector<int>> test = { {1, 2, 0, 1}, {0, 1, 2, 0}, {1, 1, 1, 1}, {0, 0, 0, 0}, {2, 2, 2, 2} };
// std::vector<int> y_test = { 0, 1, 1, 0, 2 };
// auto y_pred = net.predict(test);
// REQUIRE(y_pred == y_test);
// }
// SECTION("Test predict_proba")
// {
// auto net = bayesnet::Network();
// net.fit(raw.Xv, raw.yv, raw.weightsv, raw.featuresv, raw.classNamev, raw.statesv);
// std::vector<std::vector<int>> test = { {1, 2, 0, 1}, {0, 1, 2, 0}, {1, 1, 1, 1}, {0, 0, 0, 0}, {2, 2, 2, 2} };
// auto y_test = { 0, 1, 1, 0, 2 };
// auto y_pred = net.predict(test);
// REQUIRE(y_pred == y_test);
// }
}
// SECTION("Test score")
// {
// auto net = bayesnet::Network();
// net.fit(Xd, y, weights, features, className, states);
// auto test = { {1, 2, 0, 1}, {0, 1, 2, 0}, {1, 1, 1, 1}, {0, 0, 0, 0}, {2, 2, 2, 2} };
// auto score = net.score(X, y);
// REQUIRE(score == Catch::Approx();
// }
//
//
// SECTION("Test graph")
// {
// auto net = bayesnet::Network();
// net.addNode("A");
// net.addNode("B");
// net.addNode("C");
// net.addEdge("A", "B");
// net.addEdge("A", "C");
// auto str = net.graph("Test Graph");
// REQUIRE(str.size() == 6);
// REQUIRE(str[0] == "digraph \"Test Graph\" {");
// REQUIRE(str[1] == " A -> B;");
// REQUIRE(str[2] == " A -> C;");
// REQUIRE(str[3] == " B [shape=ellipse];");
// REQUIRE(str[4] == " C [shape=ellipse];");
// REQUIRE(str[5] == "}");
// }
// SECTION("Test initialize")
// {
// auto net = bayesnet::Network();
// net.addNode("A");
// net.addNode("B");
// net.addNode("C");
// net.addEdge("A", "B");
// net.addEdge("A", "C");
// net.initialize();
// REQUIRE(net.getNodes().size() == 0);
// REQUIRE(net.getEdges().size() == 0);
// REQUIRE(net.getFeatures().size() == 0);
// REQUIRE(net.getClassNumStates() == 0);
// REQUIRE(net.getClassName().empty());
// REQUIRE(net.getStates() == 0);
// REQUIRE(net.getSamples().numel() == 0);
// }
// SECTION("Test dump_cpt")
// {
// auto net = bayesnet::Network();
// net.addNode("A");
// net.addNode("B");
// net.addNode("C");
// net.addEdge("A", "B");
// net.addEdge("A", "C");
// net.setClassName("C");
// net.setStates({ {"A", {0, 1}}, {"B", {0, 1}}, {"C", {0, 1, 2}} });
// net.fit({ {0, 0}, {0, 1}, {1, 0}, {1, 1} }, { 0, 1, 1, 2 }, {}, { "A", "B" }, "C", { {"A", {0, 1}}, {"B", {0, 1}}, {"C", {0, 1, 2}} });
// net.dump_cpt();
// // TODO: Check that the file was created and contains the expected data
// }
// SECTION("Test version")
// {
// auto net = bayesnet::Network();
// REQUIRE(net.version() == "0.2.0");
// }
// }
// }
SECTION("Test predict")
{
auto net = bayesnet::Network();
buildModel(net, raw.featuresv, raw.classNamev);
net.fit(raw.Xv, raw.yv, raw.weightsv, raw.featuresv, raw.classNamev, raw.statesv);
std::vector<std::vector<int>> test = { {1, 2, 0, 1, 1}, {0, 1, 2, 0, 1}, {0, 0, 0, 0, 1}, {2, 2, 2, 2, 1} };
std::vector<int> y_test = { 2, 2, 0, 2, 1 };
auto y_pred = net.predict(test);
REQUIRE(y_pred == y_test);
}
SECTION("Test predict_proba")
{
auto net = bayesnet::Network();
buildModel(net, raw.featuresv, raw.classNamev);
net.fit(raw.Xv, raw.yv, raw.weightsv, raw.featuresv, raw.classNamev, raw.statesv);
std::vector<std::vector<int>> test = { {1, 2, 0, 1, 1}, {0, 1, 2, 0, 1}, {0, 0, 0, 0, 1}, {2, 2, 2, 2, 1} };
std::vector<std::vector<double>> y_test = {
{0.450237, 0.0866621, 0.463101},
{0.244443, 0.0925922, 0.662964},
{0.913441, 0.0125857, 0.0739732},
{0.450237, 0.0866621, 0.463101},
{0.0135226, 0.971726, 0.0147519}
};
auto y_pred = net.predict_proba(test);
REQUIRE(y_pred.size() == 5);
REQUIRE(y_pred[0].size() == 3);
for (int i = 0; i < y_pred.size(); ++i) {
for (int j = 0; j < y_pred[i].size(); ++j) {
REQUIRE(y_pred[i][j] == Catch::Approx(y_test[i][j]).margin(threshold));
}
}
}
SECTION("Test score")
{
auto net = bayesnet::Network();
buildModel(net, raw.featuresv, raw.classNamev);
net.fit(raw.Xv, raw.yv, raw.weightsv, raw.featuresv, raw.classNamev, raw.statesv);
auto score = net.score(raw.Xv, raw.yv);
REQUIRE(score == Catch::Approx(0.97333333).margin(threshold));
}
}