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

Fix XSpode predict

Browse Source
This commit is contained in:
Ricardo Montañana Gómez
2025-03-10 11:18:04 +01:00
parent 06621ea361
commit ca54f799ee
6 changed files with 310 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
tests/CMakeLists.txt
View File

@@ -18,6 +18,7 @@ if(ENABLE_TESTING)
add_test(NAME WA2DE COMMAND TestBayesNet "[WA2DE]")
add_test(NAME BoostA2DE COMMAND TestBayesNet "[BoostA2DE]")
add_test(NAME BoostAODE COMMAND TestBayesNet "[BoostAODE]")
add_test(NAME XBAODE COMMAND TestBayesNet "[XBAODE]")
add_test(NAME Classifier COMMAND TestBayesNet "[Classifier]")
add_test(NAME Ensemble COMMAND TestBayesNet "[Ensemble]")
add_test(NAME FeatureSelection COMMAND TestBayesNet "[FeatureSelection]")

18
tests/TestBayesModels.cc
View File

@@ -12,6 +12,7 @@
#include "bayesnet/classifiers/KDB.h"
#include "bayesnet/classifiers/TAN.h"
#include "bayesnet/classifiers/SPODE.h"
#include "bayesnet/classifiers/XSPODE.h"
#include "bayesnet/classifiers/TANLd.h"
#include "bayesnet/classifiers/KDBLd.h"
#include "bayesnet/classifiers/SPODELd.h"
@@ -26,26 +27,27 @@ 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}, {{"diabetes", "SPODE"}, 0.802083}, {{"diabetes", "TAN"}, 0.821615},
{{"diabetes", "AODE"}, 0.82161}, {{"diabetes", "KDB"}, 0.852865}, {{"diabetes", "XSPODE"}, 0.802083}, {{"diabetes", "SPODE"}, 0.802083}, {{"diabetes", "TAN"}, 0.821615},
{{"diabetes", "AODELd"}, 0.8125f}, {{"diabetes", "KDBLd"}, 0.80208f}, {{"diabetes", "SPODELd"}, 0.7890625f}, {{"diabetes", "TANLd"}, 0.803385437f}, {{"diabetes", "BoostAODE"}, 0.83984f},
// Ecoli
{{"ecoli", "AODE"}, 0.889881}, {{"ecoli", "KDB"}, 0.889881}, {{"ecoli", "SPODE"}, 0.880952}, {{"ecoli", "TAN"}, 0.892857},
{{"ecoli", "AODE"}, 0.889881}, {{"ecoli", "KDB"}, 0.889881}, {{"ecoli", "XSPODE"}, 0.880952}, {{"ecoli", "SPODE"}, 0.880952}, {{"ecoli", "TAN"}, 0.892857},
{{"ecoli", "AODELd"}, 0.875f}, {{"ecoli", "KDBLd"}, 0.880952358f}, {{"ecoli", "SPODELd"}, 0.839285731f}, {{"ecoli", "TANLd"}, 0.848214269f}, {{"ecoli", "BoostAODE"}, 0.89583f},
// Glass
{{"glass", "AODE"}, 0.79439}, {{"glass", "KDB"}, 0.827103}, {{"glass", "SPODE"}, 0.775701}, {{"glass", "TAN"}, 0.827103},
{{"glass", "AODE"}, 0.79439}, {{"glass", "KDB"}, 0.827103}, {{"glass", "XSPODE"}, 0.775701}, {{"glass", "SPODE"}, 0.775701}, {{"glass", "TAN"}, 0.827103},
{{"glass", "AODELd"}, 0.799065411f}, {{"glass", "KDBLd"}, 0.82710278f}, {{"glass", "SPODELd"}, 0.780373812f}, {{"glass", "TANLd"}, 0.869158864f}, {{"glass", "BoostAODE"}, 0.84579f},
// Iris
{{"iris", "AODE"}, 0.973333}, {{"iris", "KDB"}, 0.973333}, {{"iris", "SPODE"}, 0.973333}, {{"iris", "TAN"}, 0.973333},
{{"iris", "AODE"}, 0.973333}, {{"iris", "KDB"}, 0.973333}, {{"iris", "XSPODE"}, 0.973333}, {{"iris", "SPODE"}, 0.973333}, {{"iris", "TAN"}, 0.973333},
{{"iris", "AODELd"}, 0.973333}, {{"iris", "KDBLd"}, 0.973333}, {{"iris", "SPODELd"}, 0.96f}, {{"iris", "TANLd"}, 0.97333f}, {{"iris", "BoostAODE"}, 0.98f}
};
std::map<std::string, bayesnet::BaseClassifier*> models{
{"AODE", new bayesnet::AODE()}, {"AODELd", new bayesnet::AODELd()},
{"BoostAODE", new bayesnet::BoostAODE()},
{"KDB", new bayesnet::KDB(2)}, {"KDBLd", new bayesnet::KDBLd(2)},
{"SPODE", new bayesnet::SPODE(1)}, {"SPODELd", new bayesnet::SPODELd(1)},
{"XSPODE", new bayesnet::XSpode(1)}, {"SPODE", new bayesnet::SPODE(1)}, {"SPODELd", new bayesnet::SPODELd(1)},
{"TAN", new bayesnet::TAN()}, {"TANLd", new bayesnet::TANLd()}
};
std::string name = GENERATE("AODE", "AODELd", "KDB", "KDBLd", "SPODE", "SPODELd", "TAN", "TANLd");
// std::string name = GENERATE("AODE", "AODELd", "KDB", "KDBLd", "SPODE", "XSPODE", "SPODELd", "TAN", "TANLd");
std::string name = GENERATE("XSPODE");
auto clf = models[name];
SECTION("Test " + name + " classifier")
@@ -54,8 +56,12 @@ TEST_CASE("Test Bayesian Classifiers score & version", "[Models]")
auto clf = models[name];
auto discretize = name.substr(name.length() - 2) != "Ld";
auto raw = RawDatasets(file_name, discretize);
if (name == "XSPODE") {
std::cout << "Fitting XSPODE" << std::endl;
}
clf->fit(raw.Xt, raw.yt, raw.features, raw.className, raw.states, raw.smoothing);
auto score = clf->score(raw.Xt, raw.yt);
std::cout << "Classifier: " << name << " File: " << file_name << " Score: " << score << " expected = " << scores[{file_name, name}] << std::endl;
INFO("Classifier: " << name << " File: " << file_name);
REQUIRE(score == Catch::Approx(scores[{file_name, name}]).epsilon(raw.epsilon));
REQUIRE(clf->getStatus() == bayesnet::NORMAL);

234
tests/TestBoostXBAODE.cc Normal file
View File

@@ -0,0 +1,234 @@
// ***************************************************************
// SPDX-FileCopyrightText: Copyright 2024 Ricardo Montañana Gómez
// SPDX-FileType: SOURCE
// SPDX-License-Identifier: MIT
// ***************************************************************
#include <type_traits>
#include <catch2/catch_test_macros.hpp>
#include <catch2/catch_approx.hpp>
#include <catch2/generators/catch_generators.hpp>
#include <catch2/matchers/catch_matchers.hpp>
#include "bayesnet/ensembles/XBAODE.h"
#include "TestUtils.h"
TEST_CASE("Feature_select CFS", "[XBAODE]")
{
auto raw = RawDatasets("glass", true);
auto clf = bayesnet::XBAODE();
clf.setHyperparameters({ {"select_features", "CFS"} });
clf.fit(raw.Xv, raw.yv, raw.features, raw.className, raw.states, raw.smoothing);
REQUIRE(clf.getNumberOfNodes() == 90);
REQUIRE(clf.getNumberOfEdges() == 153);
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("Feature_select IWSS", "[XBAODE]")
{
auto raw = RawDatasets("glass", true);
auto clf = bayesnet::XBAODE();
clf.setHyperparameters({ {"select_features", "IWSS"}, {"threshold", 0.5 } });
clf.fit(raw.Xv, raw.yv, raw.features, raw.className, raw.states, raw.smoothing);
REQUIRE(clf.getNumberOfNodes() == 90);
REQUIRE(clf.getNumberOfEdges() == 153);
REQUIRE(clf.getNotes().size() == 2);
REQUIRE(clf.getNotes()[0] == "Used features in initialization: 4 of 9 with IWSS");
REQUIRE(clf.getNotes()[1] == "Number of models: 9");
}
TEST_CASE("Feature_select FCBF", "[XBAODE]")
{
auto raw = RawDatasets("glass", true);
auto clf = bayesnet::XBAODE();
clf.setHyperparameters({ {"select_features", "FCBF"}, {"threshold", 1e-7 } });
clf.fit(raw.Xv, raw.yv, raw.features, raw.className, raw.states, raw.smoothing);
REQUIRE(clf.getNumberOfNodes() == 90);
REQUIRE(clf.getNumberOfEdges() == 153);
REQUIRE(clf.getNotes().size() == 2);
REQUIRE(clf.getNotes()[0] == "Used features in initialization: 4 of 9 with FCBF");
REQUIRE(clf.getNotes()[1] == "Number of models: 9");
}
TEST_CASE("Test used features in train note and score", "[XBAODE]")
{
auto raw = RawDatasets("diabetes", true);
auto clf = bayesnet::XBAODE(true);
clf.setHyperparameters({
{"order", "asc"},
{"convergence", true},
{"select_features","CFS"},
});
clf.fit(raw.Xv, raw.yv, raw.features, raw.className, raw.states, raw.smoothing);
REQUIRE(clf.getNumberOfNodes() == 72);
REQUIRE(clf.getNumberOfEdges() == 120);
REQUIRE(clf.getNotes().size() == 2);
REQUIRE(clf.getNotes()[0] == "Used features in initialization: 6 of 8 with CFS");
REQUIRE(clf.getNotes()[1] == "Number of models: 8");
auto score = clf.score(raw.Xv, raw.yv);
auto scoret = clf.score(raw.Xt, raw.yt);
REQUIRE(score == Catch::Approx(0.809895813).epsilon(raw.epsilon));
REQUIRE(scoret == Catch::Approx(0.809895813).epsilon(raw.epsilon));
}
TEST_CASE("Voting vs proba", "[XBAODE]")
{
auto raw = RawDatasets("iris", true);
auto clf = bayesnet::XBAODE(false);
clf.fit(raw.Xv, raw.yv, raw.features, raw.className, raw.states, raw.smoothing);
auto score_proba = clf.score(raw.Xv, raw.yv);
auto pred_proba = clf.predict_proba(raw.Xv);
clf.setHyperparameters({
{"predict_voting",true},
});
auto score_voting = clf.score(raw.Xv, raw.yv);
auto pred_voting = clf.predict_proba(raw.Xv);
REQUIRE(score_proba == Catch::Approx(0.97333).epsilon(raw.epsilon));
REQUIRE(score_voting == Catch::Approx(0.98).epsilon(raw.epsilon));
REQUIRE(pred_voting[83][2] == Catch::Approx(1.0).epsilon(raw.epsilon));
REQUIRE(pred_proba[83][2] == Catch::Approx(0.86121525).epsilon(raw.epsilon));
REQUIRE(clf.dump_cpt() == "");
REQUIRE(clf.topological_order() == std::vector<std::string>());
}
TEST_CASE("Order asc, desc & random", "[XBAODE]")
{
auto raw = RawDatasets("glass", true);
std::map<std::string, double> scores{
{"asc", 0.83645f }, { "desc", 0.84579f }, { "rand", 0.84112 }
};
for (const std::string& order : { "asc", "desc", "rand" }) {
auto clf = bayesnet::XBAODE();
clf.setHyperparameters({
{"order", order},
{"bisection", false},
{"maxTolerance", 1},
{"convergence", false},
});
clf.fit(raw.Xv, raw.yv, raw.features, raw.className, raw.states, raw.smoothing);
auto score = clf.score(raw.Xv, raw.yv);
auto scoret = clf.score(raw.Xt, raw.yt);
INFO("XBAODE order: " << order);
REQUIRE(score == Catch::Approx(scores[order]).epsilon(raw.epsilon));
REQUIRE(scoret == Catch::Approx(scores[order]).epsilon(raw.epsilon));
}
}
TEST_CASE("Oddities", "[XBAODE]")
{
auto clf = bayesnet::XBAODE();
auto raw = RawDatasets("iris", true);
auto bad_hyper = nlohmann::json{
{ { "order", "duck" } },
{ { "select_features", "duck" } },
{ { "maxTolerance", 0 } },
{ { "maxTolerance", 7 } },
};
for (const auto& hyper : bad_hyper.items()) {
INFO("XBAODE hyper: " << hyper.value().dump());
REQUIRE_THROWS_AS(clf.setHyperparameters(hyper.value()), std::invalid_argument);
}
REQUIRE_THROWS_AS(clf.setHyperparameters({ {"maxTolerance", 0 } }), std::invalid_argument);
auto bad_hyper_fit = nlohmann::json{
{ { "select_features","IWSS" }, { "threshold", -0.01 } },
{ { "select_features","IWSS" }, { "threshold", 0.51 } },
{ { "select_features","FCBF" }, { "threshold", 1e-8 } },
{ { "select_features","FCBF" }, { "threshold", 1.01 } },
};
for (const auto& hyper : bad_hyper_fit.items()) {
INFO("XBAODE hyper: " << hyper.value().dump());
clf.setHyperparameters(hyper.value());
REQUIRE_THROWS_AS(clf.fit(raw.Xv, raw.yv, raw.features, raw.className, raw.states, raw.smoothing), std::invalid_argument);
}
auto bad_hyper_fit2 = nlohmann::json{
{ { "alpha_block", true }, { "block_update", true } },
{ { "bisection", false }, { "block_update", true } },
};
for (const auto& hyper : bad_hyper_fit2.items()) {
INFO("XBAODE hyper: " << hyper.value().dump());
REQUIRE_THROWS_AS(clf.setHyperparameters(hyper.value()), std::invalid_argument);
}
}
TEST_CASE("Bisection Best", "[XBAODE]")
{
auto clf = bayesnet::XBAODE();
auto raw = RawDatasets("kdd_JapaneseVowels", true, 1200, true, false);
clf.setHyperparameters({
{"bisection", true},
{"maxTolerance", 3},
{"convergence", true},
{"convergence_best", false},
});
clf.fit(raw.X_train, raw.y_train, raw.features, raw.className, raw.states, raw.smoothing);
REQUIRE(clf.getNumberOfNodes() == 210);
REQUIRE(clf.getNumberOfEdges() == 378);
REQUIRE(clf.getNotes().size() == 1);
REQUIRE(clf.getNotes().at(0) == "Number of models: 14");
auto score = clf.score(raw.X_test, raw.y_test);
auto scoret = clf.score(raw.X_test, raw.y_test);
REQUIRE(score == Catch::Approx(0.991666675f).epsilon(raw.epsilon));
REQUIRE(scoret == Catch::Approx(0.991666675f).epsilon(raw.epsilon));
}
TEST_CASE("Bisection Best vs Last", "[XBAODE]")
{
auto raw = RawDatasets("kdd_JapaneseVowels", true, 1500, true, false);
auto clf = bayesnet::XBAODE(true);
auto hyperparameters = nlohmann::json{
{"bisection", true},
{"maxTolerance", 3},
{"convergence", true},
{"convergence_best", true},
};
clf.setHyperparameters(hyperparameters);
clf.fit(raw.X_train, raw.y_train, raw.features, raw.className, raw.states, raw.smoothing);
auto score_best = clf.score(raw.X_test, raw.y_test);
REQUIRE(score_best == Catch::Approx(0.980000019f).epsilon(raw.epsilon));
// Now we will set the hyperparameter to use the last accuracy
hyperparameters["convergence_best"] = false;
clf.setHyperparameters(hyperparameters);
clf.fit(raw.X_train, raw.y_train, raw.features, raw.className, raw.states, raw.smoothing);
auto score_last = clf.score(raw.X_test, raw.y_test);
REQUIRE(score_last == Catch::Approx(0.976666689f).epsilon(raw.epsilon));
}
TEST_CASE("Block Update", "[XBAODE]")
{
auto clf = bayesnet::XBAODE();
auto raw = RawDatasets("mfeat-factors", true, 500);
clf.setHyperparameters({
{"bisection", true},
{"block_update", true},
{"maxTolerance", 3},
{"convergence", true},
});
clf.fit(raw.X_train, raw.y_train, raw.features, raw.className, raw.states, raw.smoothing);
REQUIRE(clf.getNumberOfNodes() == 868);
REQUIRE(clf.getNumberOfEdges() == 1724);
REQUIRE(clf.getNotes().size() == 3);
REQUIRE(clf.getNotes()[0] == "Convergence threshold reached & 15 models eliminated");
REQUIRE(clf.getNotes()[1] == "Used features in train: 19 of 216");
REQUIRE(clf.getNotes()[2] == "Number of models: 4");
auto score = clf.score(raw.X_test, raw.y_test);
auto scoret = clf.score(raw.X_test, raw.y_test);
REQUIRE(score == Catch::Approx(0.99f).epsilon(raw.epsilon));
REQUIRE(scoret == Catch::Approx(0.99f).epsilon(raw.epsilon));
//
// std::cout << "Number of nodes " << clf.getNumberOfNodes() << std::endl;
// std::cout << "Number of edges " << clf.getNumberOfEdges() << std::endl;
// std::cout << "Notes size " << clf.getNotes().size() << std::endl;
// for (auto note : clf.getNotes()) {
// std::cout << note << std::endl;
// }
// std::cout << "Score " << score << std::endl;
}
TEST_CASE("Alphablock", "[XBAODE]")
{
auto clf_alpha = bayesnet::XBAODE();
auto clf_no_alpha = bayesnet::XBAODE();
auto raw = RawDatasets("diabetes", true);
clf_alpha.setHyperparameters({
{"alpha_block", true},
});
clf_alpha.fit(raw.X_train, raw.y_train, raw.features, raw.className, raw.states, raw.smoothing);
clf_no_alpha.fit(raw.X_train, raw.y_train, raw.features, raw.className, raw.states, raw.smoothing);
auto score_alpha = clf_alpha.score(raw.X_test, raw.y_test);
auto score_no_alpha = clf_no_alpha.score(raw.X_test, raw.y_test);
REQUIRE(score_alpha == Catch::Approx(0.720779f).epsilon(raw.epsilon));
REQUIRE(score_no_alpha == Catch::Approx(0.733766f).epsilon(raw.epsilon));
}