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

Complete proposal with only discretizing numeric features

Browse Source
This commit is contained in:
Ricardo Montañana Gómez
2025-08-24 01:09:25 +02:00
parent 0c7452e35b
commit 7c01646726
9 changed files with 380 additions and 48883 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
tests/TestBayesModels.cc
View File

@@ -520,34 +520,35 @@ TEST_CASE("Test Dataset Loading", "[Datasets]")
std::cout << "| " << dataset.yt[sample].item<int>() << std::endl;
}
// Test loading a dataset
dataset = RawDatasets("adult", true);
REQUIRE(dataset.Xt.size(0) == 14);
REQUIRE(dataset.Xt.size(1) == 45222);
REQUIRE(dataset.yt.size(0) == 45222);
std::cout << "Dataset adult discretized " << std::endl;
dataset = RawDatasets("heart-statlog", true);
REQUIRE(dataset.Xt.size(0) == 13);
REQUIRE(dataset.Xt.size(1) == 270);
REQUIRE(dataset.yt.size(0) == 270);
std::cout << "Dataset heart-statlog discretized " << std::endl;
for (int sample = 0; sample < max_sample; sample++) {
for (int feature = 0; feature < 14; feature++) {
for (int feature = 0; feature < 13; feature++) {
std::cout << dataset.Xt[feature][sample].item<int>() << " ";
}
std::cout << "| " << dataset.yt[sample].item<int>() << std::endl;
}
auto features = dataset.features;
std::cout << "States:" << std::endl;
for (int i = 0; i < 14; i++) {
for (int i = 0; i < 13; i++) {
std::cout << i << " has " << dataset.states.at(features[i]).size() << " states." << std::endl;
}
dataset = RawDatasets("adult", false);
std::cout << "Dataset adult raw " << std::endl;
dataset = RawDatasets("heart-statlog", false);
std::cout << "Dataset heart-statlog raw " << std::endl;
for (int sample = 0; sample < max_sample; sample++) {
for (int feature = 0; feature < 14; feature++) {
for (int feature = 0; feature < 13; feature++) {
std::cout << dataset.Xt[feature][sample].item<float>() << " ";
}
std::cout << "| " << dataset.yt[sample].item<int>() << std::endl;
}
std::cout << "States:" << std::endl;
for (int i = 0; i < 14; i++) {
for (int i = 0; i < 13; i++) {
std::cout << i << " has " << dataset.states.at(features[i]).size() << " states." << std::endl;
}
auto clf = bayesnet::TANLd();
clf.fit(dataset.Xt, dataset.yt, dataset.features, dataset.className, dataset.states, dataset.smoothing);
std::cout << "Score: " << clf.score(dataset.Xt, dataset.yt) << std::endl;
}