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

Fix CFS merit computation error

Browse Source
This commit is contained in:
Ricardo Montañana Gómez
2025-06-01 13:54:18 +02:00
parent da357ac5ba
commit ad72bb355b
6 changed files with 164 additions and 137 deletions
Download Patch File Download Diff File Expand all files Collapse all files

75
tests/TestBoostAODE.cc
View File

@@ -11,32 +11,35 @@
#include "TestUtils.h"
#include "bayesnet/ensembles/BoostAODE.h"
TEST_CASE("Feature_select CFS", "[BoostAODE]") {
TEST_CASE("Feature_select CFS", "[BoostAODE]")
{
auto raw = RawDatasets("glass", true);
auto clf = bayesnet::BoostAODE();
clf.setHyperparameters({{"select_features", "CFS"}});
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()[0] == "Used features in initialization: 9 of 9 with CFS");
REQUIRE(clf.getNotes()[1] == "Number of models: 9");
}
TEST_CASE("Feature_select IWSS", "[BoostAODE]") {
TEST_CASE("Feature_select IWSS", "[BoostAODE]")
{
auto raw = RawDatasets("glass", true);
auto clf = bayesnet::BoostAODE();
clf.setHyperparameters({{"select_features", "IWSS"}, {"threshold", 0.5}});
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()[0] == "Used features in initialization: 9 of 9 with IWSS");
REQUIRE(clf.getNotes()[1] == "Number of models: 9");
}
TEST_CASE("Feature_select FCBF", "[BoostAODE]") {
TEST_CASE("Feature_select FCBF", "[BoostAODE]")
{
auto raw = RawDatasets("glass", true);
auto clf = bayesnet::BoostAODE();
clf.setHyperparameters({{"select_features", "FCBF"}, {"threshold", 1e-7}});
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);
@@ -44,26 +47,28 @@ TEST_CASE("Feature_select FCBF", "[BoostAODE]") {
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", "[BoostAODE]") {
TEST_CASE("Test used features in train note and score", "[BoostAODE]")
{
auto raw = RawDatasets("diabetes", true);
auto clf = bayesnet::BoostAODE(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()[0] == "Used features in initialization: 7 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));
REQUIRE(score == Catch::Approx(0.8046875f).epsilon(raw.epsilon));
REQUIRE(scoret == Catch::Approx(0.8046875f).epsilon(raw.epsilon));
}
TEST_CASE("Voting vs proba", "[BoostAODE]") {
TEST_CASE("Voting vs proba", "[BoostAODE]")
{
auto raw = RawDatasets("iris", true);
auto clf = bayesnet::BoostAODE(false);
clf.fit(raw.Xv, raw.yv, raw.features, raw.className, raw.states, raw.smoothing);
@@ -71,7 +76,7 @@ TEST_CASE("Voting vs proba", "[BoostAODE]") {
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));
@@ -81,17 +86,18 @@ TEST_CASE("Voting vs proba", "[BoostAODE]") {
REQUIRE(clf.dump_cpt().size() == 7004);
REQUIRE(clf.topological_order() == std::vector<std::string>());
}
TEST_CASE("Order asc, desc & random", "[BoostAODE]") {
TEST_CASE("Order asc, desc & random", "[BoostAODE]")
{
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"}) {
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::BoostAODE();
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);
@@ -100,7 +106,8 @@ TEST_CASE("Order asc, desc & random", "[BoostAODE]") {
REQUIRE(scoret == Catch::Approx(scores[order]).epsilon(raw.epsilon));
}
}
TEST_CASE("Oddities", "[BoostAODE]") {
TEST_CASE("Oddities", "[BoostAODE]")
{
auto clf = bayesnet::BoostAODE();
auto raw = RawDatasets("iris", true);
auto bad_hyper = nlohmann::json{
@@ -109,34 +116,35 @@ TEST_CASE("Oddities", "[BoostAODE]") {
{{"maxTolerance", 0}},
{{"maxTolerance", 7}},
};
for (const auto &hyper : bad_hyper.items()) {
for (const auto& hyper : bad_hyper.items()) {
INFO("BoostAODE hyper: " << hyper.value().dump());
REQUIRE_THROWS_AS(clf.setHyperparameters(hyper.value()), std::invalid_argument);
}
REQUIRE_THROWS_AS(clf.setHyperparameters({{"maxTolerance", 0}}), 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()) {
for (const auto& hyper : bad_hyper_fit.items()) {
INFO("BoostAODE 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);
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()) {
for (const auto& hyper : bad_hyper_fit2.items()) {
INFO("BoostAODE hyper: " << hyper.value().dump());
REQUIRE_THROWS_AS(clf.setHyperparameters(hyper.value()), std::invalid_argument);
}
}
TEST_CASE("Bisection Best", "[BoostAODE]") {
TEST_CASE("Bisection Best", "[BoostAODE]")
{
auto clf = bayesnet::BoostAODE();
auto raw = RawDatasets("kdd_JapaneseVowels", true, 1200, true, false);
clf.setHyperparameters({
@@ -145,7 +153,7 @@ TEST_CASE("Bisection Best", "[BoostAODE]") {
{"convergence", true},
{"block_update", false},
{"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);
@@ -156,7 +164,8 @@ TEST_CASE("Bisection Best", "[BoostAODE]") {
REQUIRE(score == Catch::Approx(0.991666675f).epsilon(raw.epsilon));
REQUIRE(scoret == Catch::Approx(0.991666675f).epsilon(raw.epsilon));
}
TEST_CASE("Bisection Best vs Last", "[BoostAODE]") {
TEST_CASE("Bisection Best vs Last", "[BoostAODE]")
{
auto raw = RawDatasets("kdd_JapaneseVowels", true, 1500, true, false);
auto clf = bayesnet::BoostAODE(true);
auto hyperparameters = nlohmann::json{
@@ -176,7 +185,8 @@ TEST_CASE("Bisection Best vs Last", "[BoostAODE]") {
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", "[BoostAODE]") {
TEST_CASE("Block Update", "[BoostAODE]")
{
auto clf = bayesnet::BoostAODE();
auto raw = RawDatasets("mfeat-factors", true, 500);
clf.setHyperparameters({
@@ -184,7 +194,7 @@ TEST_CASE("Block Update", "[BoostAODE]") {
{"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);
@@ -205,13 +215,14 @@ TEST_CASE("Block Update", "[BoostAODE]") {
// }
// std::cout << "Score " << score << std::endl;
}
TEST_CASE("Alphablock", "[BoostAODE]") {
TEST_CASE("Alphablock", "[BoostAODE]")
{
auto clf_alpha = bayesnet::BoostAODE();
auto clf_no_alpha = bayesnet::BoostAODE();
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);