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

Add some tests and code quality badge

Browse Source
This commit is contained in:
Ricardo Montañana Gómez 2024-04-07 02:08:37 +02:00
parent df45fddd45
commit cb26ef2562
Signed by: rmontanana
GPG Key ID: 46064262FD9A7ADE
7 changed files with 57 additions and 26 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
README.md
View File

@ -4,6 +4,7 @@
[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](<https://opensource.org/licenses/MIT>)
![Gitea Release](https://img.shields.io/gitea/v/release/rmontanana/bayesnet?gitea_url=https://gitea.rmontanana.es:3000)
![Gitea Last Commit](https://img.shields.io/gitea/last-commit/rmontanana/bayesnet?gitea_url=https://gitea.rmontanana.es:3000&logo=gitea)
[![Codacy Badge](https://app.codacy.com/project/badge/Grade/cf3e0ac71d764650b1bf4d8d00d303b1)](https://app.codacy.com/gh/Doctorado-ML/BayesNet/dashboard?utm_source=gh&utm_medium=referral&utm_content=&utm_campaign=Badge_grade)
Bayesian Network Classifiers using libtorch from scratch

19
bayesnet/classifiers/SPODELd.cc
View File

@ -5,25 +5,23 @@ namespace bayesnet {
SPODELd& SPODELd::fit(torch::Tensor& X_, torch::Tensor& y_, const std::vector<std::string>& features_, const std::string& className_, map<std::string, std::vector<int>>& states_)
{
checkInput(X_, y_);
features = features_;
className = className_;
Xf = X_;
y = y_;
// Fills std::vectors Xv & yv with the data from tensors X_ (discretized) & y
states = fit_local_discretization(y);
// We have discretized the input data
// 1st we need to fit the model to build the normal SPODE structure, SPODE::fit initializes the base Bayesian network
SPODE::fit(dataset, features, className, states);
states = localDiscretizationProposal(states, model);
return *this;
return commonFit(features_, className_, states_);
}
SPODELd& SPODELd::fit(torch::Tensor& dataset, const std::vector<std::string>& features_, const std::string& className_, map<std::string, std::vector<int>>& states_)
{
if (!torch::is_floating_point(dataset)) {
throw std::runtime_error("Dataset must be a floating point tensor");
}
Xf = dataset.index({ torch::indexing::Slice(0, dataset.size(0) - 1), "..." }).clone();
y = dataset.index({ -1, "..." }).clone();
y = dataset.index({ -1, "..." }).clone().to(torch::kInt32);
return commonFit(features_, className_, states_);
}
SPODELd& SPODELd::commonFit(const std::vector<std::string>& features_, const std::string& className_, map<std::string, std::vector<int>>& states_)
{
features = features_;
className = className_;
// Fills std::vectors Xv & yv with the data from tensors X_ (discretized) & y
@ -34,7 +32,6 @@ namespace bayesnet {
states = localDiscretizationProposal(states, model);
return *this;
}
torch::Tensor SPODELd::predict(torch::Tensor& X)
{
auto Xt = prepareX(X);

1
bayesnet/classifiers/SPODELd.h
View File

@ -10,6 +10,7 @@ namespace bayesnet {
virtual ~SPODELd() = default;
SPODELd& fit(torch::Tensor& X, torch::Tensor& y, const std::vector<std::string>& features, const std::string& className, map<std::string, std::vector<int>>& states) override;
SPODELd& fit(torch::Tensor& dataset, const std::vector<std::string>& features, const std::string& className, map<std::string, std::vector<int>>& states) override;
SPODELd& commonFit(const std::vector<std::string>& features, const std::string& className, map<std::string, std::vector<int>>& states);
std::vector<std::string> graph(const std::string& name = "SPODE") const override;
torch::Tensor predict(torch::Tensor& X) override;
static inline std::string version() { return "0.0.1"; };

12
bayesnet/utils/bayesnetUtils.cc
View File

@ -10,18 +10,6 @@ namespace bayesnet {
sort(indices.begin(), indices.end(), [&nums](int i, int j) {return nums[i] > nums[j];});
return indices;
}
std::vector<std::vector<int>> tensorToVector(torch::Tensor& dtensor)
{
// convert mxn tensor to nxm std::vector
std::vector<std::vector<int>> result;
// Iterate over cols
for (int i = 0; i < dtensor.size(1); ++i) {
auto col_tensor = dtensor.index({ "...", i });
auto col = std::vector<int>(col_tensor.data_ptr<int>(), col_tensor.data_ptr<int>() + dtensor.size(0));
result.push_back(col);
}
return result;
}
std::vector<std::vector<double>> tensorToVectorDouble(torch::Tensor& dtensor)
{
// convert mxn tensor to mxn std::vector

1
bayesnet/utils/bayesnetUtils.h
View File

@ -4,7 +4,6 @@
#include <torch/torch.h>
namespace bayesnet {
std::vector<int> argsort(std::vector<double>& nums);
std::vector<std::vector<int>> tensorToVector(torch::Tensor& dtensor);
std::vector<std::vector<double>> tensorToVectorDouble(torch::Tensor& dtensor);
torch::Tensor vectorToTensor(std::vector<std::vector<int>>& vector, bool transpose = true);
}

1
gcovr.cfg
View File

@ -1,4 +1,5 @@
filter = bayesnet/
exclude-directories = build_debug/lib/
exclude = bayesnet/utils/loguru.*
print-summary = yes
sort = uncovered-percent

48
tests/TestBayesModels.cc
View File

@ -207,7 +207,7 @@ TEST_CASE("Model predict_proba", "[Models]")
}
TEST_CASE("BoostAODE voting-proba", "[Models]")
{
auto raw = RawDatasets("iris", false);
auto raw = RawDatasets("iris", true);
auto clf = bayesnet::BoostAODE(false);
clf.fit(raw.Xv, raw.yv, raw.featuresv, raw.classNamev, raw.statesv);
auto score_proba = clf.score(raw.Xv, raw.yv);
@ -224,9 +224,53 @@ TEST_CASE("BoostAODE voting-proba", "[Models]")
clf.dump_cpt();
REQUIRE(clf.topological_order() == std::vector<std::string>());
}
TEST_CASE("AODE voting-proba", "[Models]")
{
auto raw = RawDatasets("glass", true);
auto clf = bayesnet::AODE(false);
clf.fit(raw.Xv, raw.yv, raw.featuresv, raw.classNamev, raw.statesv);
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(0.79439f).epsilon(raw.epsilon));
REQUIRE(score_voting == Catch::Approx(0.78972f).epsilon(raw.epsilon));
REQUIRE(pred_voting[67][0] == Catch::Approx(0.888889).epsilon(raw.epsilon));
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]")
{
auto raw = RawDatasets("iris", false);
auto clf = bayesnet::SPODELd(0);
raw.dataset.to(torch::kFloat32);
clf.fit(raw.dataset, raw.featuresv, raw.classNamev, raw.statesv);
auto score = clf.score(raw.Xt, raw.yt);
clf.fit(raw.Xt, raw.yt, raw.featurest, raw.classNamet, raw.statest);
auto scoret = clf.score(raw.Xt, raw.yt);
REQUIRE(score == Catch::Approx(0.97333f).epsilon(raw.epsilon));
REQUIRE(scoret == Catch::Approx(0.97333f).epsilon(raw.epsilon));
}
TEST_CASE("KDB with hyperparameters", "[Models]")
{
auto raw = RawDatasets("glass", true);
auto clf = bayesnet::KDB(2);
clf.fit(raw.Xv, raw.yv, raw.featuresv, raw.classNamev, raw.statesv);
auto score = clf.score(raw.Xv, raw.yv);
clf.setHyperparameters({
{"k", 3},
{"theta", 0.7},
});
clf.fit(raw.Xv, raw.yv, raw.featuresv, raw.classNamev, raw.statesv);
auto scoret = clf.score(raw.Xv, raw.yv);
REQUIRE(score == Catch::Approx(0.827103).epsilon(raw.epsilon));
REQUIRE(scoret == Catch::Approx(0.761682).epsilon(raw.epsilon));
}
TEST_CASE("BoostAODE order asc, desc & random", "[Models]")
{
auto raw = RawDatasets("glass", true);
std::map<std::string, double> scores{
{"asc", 0.83645f }, { "desc", 0.84579f }, { "rand", 0.84112 }