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

Add tests to 90% coverage

Browse Source
This commit is contained in:
Ricardo Montañana Gómez
2025-03-14 14:53:22 +01:00
parent c234308701
commit 400967b4e3
14 changed files with 943 additions and 463 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
bayesnet/classifiers/Proposal.cc
View File

@@ -11,7 +11,7 @@ namespace bayesnet {
Proposal::~Proposal()
{
for (auto& [key, value] : discretizers) {
delete value;
delete value;
}
}
void Proposal::checkInput(const torch::Tensor& X, const torch::Tensor& y)
@@ -126,4 +126,4 @@ namespace bayesnet {
}
return yy;
}
}
}

487
bayesnet/ensembles/Boost.cc
View File

@@ -3,255 +3,266 @@
// SPDX-FileType: SOURCE
// SPDX-License-Identifier: MIT
// ***************************************************************
#include <folding.hpp>
#include "Boost.h"
#include "bayesnet/feature_selection/CFS.h"
#include "bayesnet/feature_selection/FCBF.h"
#include "bayesnet/feature_selection/IWSS.h"
#include "Boost.h"
#include <folding.hpp>
namespace bayesnet {
Boost::Boost(bool predict_voting) : Ensemble(predict_voting)
{
validHyperparameters = { "alpha_block", "order", "convergence", "convergence_best", "bisection", "threshold", "maxTolerance",
"predict_voting", "select_features", "block_update" };
Boost::Boost(bool predict_voting) : Ensemble(predict_voting) {
validHyperparameters = {"alpha_block", "order", "convergence", "convergence_best", "bisection",
"threshold", "maxTolerance", "predict_voting", "select_features", "block_update"};
}
void Boost::setHyperparameters(const nlohmann::json &hyperparameters_) {
auto hyperparameters = hyperparameters_;
if (hyperparameters.contains("order")) {
std::vector<std::string> algos = {Orders.ASC, Orders.DESC, Orders.RAND};
order_algorithm = hyperparameters["order"];
if (std::find(algos.begin(), algos.end(), order_algorithm) == algos.end()) {
throw std::invalid_argument("Invalid order algorithm, valid values [" + Orders.ASC + ", " + Orders.DESC +
", " + Orders.RAND + "]");
}
hyperparameters.erase("order");
}
void Boost::setHyperparameters(const nlohmann::json& hyperparameters_)
{
auto hyperparameters = hyperparameters_;
if (hyperparameters.contains("order")) {
std::vector<std::string> algos = { Orders.ASC, Orders.DESC, Orders.RAND };
order_algorithm = hyperparameters["order"];
if (std::find(algos.begin(), algos.end(), order_algorithm) == algos.end()) {
throw std::invalid_argument("Invalid order algorithm, valid values [" + Orders.ASC + ", " + Orders.DESC + ", " + Orders.RAND + "]");
}
hyperparameters.erase("order");
}
if (hyperparameters.contains("alpha_block")) {
alpha_block = hyperparameters["alpha_block"];
hyperparameters.erase("alpha_block");
}
if (hyperparameters.contains("convergence")) {
convergence = hyperparameters["convergence"];
hyperparameters.erase("convergence");
}
if (hyperparameters.contains("convergence_best")) {
convergence_best = hyperparameters["convergence_best"];
hyperparameters.erase("convergence_best");
}
if (hyperparameters.contains("bisection")) {
bisection = hyperparameters["bisection"];
hyperparameters.erase("bisection");
}
if (hyperparameters.contains("threshold")) {
threshold = hyperparameters["threshold"];
hyperparameters.erase("threshold");
}
if (hyperparameters.contains("maxTolerance")) {
maxTolerance = hyperparameters["maxTolerance"];
if (maxTolerance < 1 || maxTolerance > 6)
throw std::invalid_argument("Invalid maxTolerance value, must be greater in [1, 6]");
hyperparameters.erase("maxTolerance");
}
if (hyperparameters.contains("predict_voting")) {
predict_voting = hyperparameters["predict_voting"];
hyperparameters.erase("predict_voting");
}
if (hyperparameters.contains("select_features")) {
auto selectedAlgorithm = hyperparameters["select_features"];
std::vector<std::string> algos = { SelectFeatures.IWSS, SelectFeatures.CFS, SelectFeatures.FCBF };
selectFeatures = true;
select_features_algorithm = selectedAlgorithm;
if (std::find(algos.begin(), algos.end(), selectedAlgorithm) == algos.end()) {
throw std::invalid_argument("Invalid selectFeatures value, valid values [" + SelectFeatures.IWSS + ", " + SelectFeatures.CFS + ", " + SelectFeatures.FCBF + "]");
}
hyperparameters.erase("select_features");
}
if (hyperparameters.contains("block_update")) {
block_update = hyperparameters["block_update"];
hyperparameters.erase("block_update");
}
if (block_update && alpha_block) {
throw std::invalid_argument("alpha_block and block_update cannot be true at the same time");
}
if (block_update && !bisection) {
throw std::invalid_argument("block_update needs bisection to be true");
}
Classifier::setHyperparameters(hyperparameters);
if (hyperparameters.contains("alpha_block")) {
alpha_block = hyperparameters["alpha_block"];
hyperparameters.erase("alpha_block");
}
void Boost::buildModel(const torch::Tensor& weights)
{
// Models shall be built in trainModel
models.clear();
significanceModels.clear();
n_models = 0;
// Prepare the validation dataset
auto y_ = dataset.index({ -1, "..." });
if (convergence) {
// Prepare train & validation sets from train data
auto fold = folding::StratifiedKFold(5, y_, 271);
auto [train, test] = fold.getFold(0);
auto train_t = torch::tensor(train);
auto test_t = torch::tensor(test);
// Get train and validation sets
X_train = dataset.index({ torch::indexing::Slice(0, dataset.size(0) - 1), train_t });
y_train = dataset.index({ -1, train_t });
X_test = dataset.index({ torch::indexing::Slice(0, dataset.size(0) - 1), test_t });
y_test = dataset.index({ -1, test_t });
dataset = X_train;
m = X_train.size(1);
auto n_classes = states.at(className).size();
// Build dataset with train data
buildDataset(y_train);
metrics = Metrics(dataset, features, className, n_classes);
} else {
// Use all data to train
X_train = dataset.index({ torch::indexing::Slice(0, dataset.size(0) - 1), "..." });
y_train = y_;
}
if (hyperparameters.contains("convergence")) {
convergence = hyperparameters["convergence"];
hyperparameters.erase("convergence");
}
std::vector<int> Boost::featureSelection(torch::Tensor& weights_)
{
int maxFeatures = 0;
if (select_features_algorithm == SelectFeatures.CFS) {
featureSelector = new CFS(dataset, features, className, maxFeatures, states.at(className).size(), weights_);
} else if (select_features_algorithm == SelectFeatures.IWSS) {
if (threshold < 0 || threshold >0.5) {
throw std::invalid_argument("Invalid threshold value for " + SelectFeatures.IWSS + " [0, 0.5]");
}
featureSelector = new IWSS(dataset, features, className, maxFeatures, states.at(className).size(), weights_, threshold);
} else if (select_features_algorithm == SelectFeatures.FCBF) {
if (threshold < 1e-7 || threshold > 1) {
throw std::invalid_argument("Invalid threshold value for " + SelectFeatures.FCBF + " [1e-7, 1]");
}
featureSelector = new FCBF(dataset, features, className, maxFeatures, states.at(className).size(), weights_, threshold);
}
featureSelector->fit();
auto featuresUsed = featureSelector->getFeatures();
delete featureSelector;
return featuresUsed;
if (hyperparameters.contains("convergence_best")) {
convergence_best = hyperparameters["convergence_best"];
hyperparameters.erase("convergence_best");
}
std::tuple<torch::Tensor&, double, bool> Boost::update_weights(torch::Tensor& ytrain, torch::Tensor& ypred, torch::Tensor& weights)
{
bool terminate = false;
double alpha_t = 0;
auto mask_wrong = ypred != ytrain;
auto mask_right = ypred == ytrain;
auto masked_weights = weights * mask_wrong.to(weights.dtype());
double epsilon_t = masked_weights.sum().item<double>();
// std::cout << "epsilon_t: " << epsilon_t << " count wrong: " << mask_wrong.sum().item<int>() << " count right: " << mask_right.sum().item<int>() << std::endl;
if (epsilon_t > 0.5) {
// Inverse the weights policy (plot ln(wt))
// "In each round of AdaBoost, there is a sanity check to ensure that the current base
// learner is better than random guess" (Zhi-Hua Zhou, 2012)
terminate = true;
} else {
double wt = (1 - epsilon_t) / epsilon_t;
alpha_t = epsilon_t == 0 ? 1 : 0.5 * log(wt);
// Step 3.2: Update weights for next classifier
// Step 3.2.1: Update weights of wrong samples
weights += mask_wrong.to(weights.dtype()) * exp(alpha_t) * weights;
// Step 3.2.2: Update weights of right samples
weights += mask_right.to(weights.dtype()) * exp(-alpha_t) * weights;
// Step 3.3: Normalise the weights
double totalWeights = torch::sum(weights).item<double>();
weights = weights / totalWeights;
}
return { weights, alpha_t, terminate };
if (hyperparameters.contains("bisection")) {
bisection = hyperparameters["bisection"];
hyperparameters.erase("bisection");
}
std::tuple<torch::Tensor&, double, bool> Boost::update_weights_block(int k, torch::Tensor& ytrain, torch::Tensor& weights)
{
/* Update Block algorithm
k = # of models in block
n_models = # of models in ensemble to make predictions
n_models_bak = # models saved
models = vector of models to make predictions
models_bak = models not used to make predictions
significances_bak = backup of significances vector
if (hyperparameters.contains("threshold")) {
threshold = hyperparameters["threshold"];
hyperparameters.erase("threshold");
}
if (hyperparameters.contains("maxTolerance")) {
maxTolerance = hyperparameters["maxTolerance"];
if (maxTolerance < 1 || maxTolerance > 6)
throw std::invalid_argument("Invalid maxTolerance value, must be greater in [1, 6]");
hyperparameters.erase("maxTolerance");
}
if (hyperparameters.contains("predict_voting")) {
predict_voting = hyperparameters["predict_voting"];
hyperparameters.erase("predict_voting");
}
if (hyperparameters.contains("select_features")) {
auto selectedAlgorithm = hyperparameters["select_features"];
std::vector<std::string> algos = {SelectFeatures.IWSS, SelectFeatures.CFS, SelectFeatures.FCBF};
selectFeatures = true;
select_features_algorithm = selectedAlgorithm;
if (std::find(algos.begin(), algos.end(), selectedAlgorithm) == algos.end()) {
throw std::invalid_argument("Invalid selectFeatures value, valid values [" + SelectFeatures.IWSS + ", " +
SelectFeatures.CFS + ", " + SelectFeatures.FCBF + "]");
}
hyperparameters.erase("select_features");
}
if (hyperparameters.contains("block_update")) {
block_update = hyperparameters["block_update"];
hyperparameters.erase("block_update");
}
if (block_update && alpha_block) {
throw std::invalid_argument("alpha_block and block_update cannot be true at the same time");
}
if (block_update && !bisection) {
throw std::invalid_argument("block_update needs bisection to be true");
}
Classifier::setHyperparameters(hyperparameters);
}
void Boost::add_model(std::unique_ptr<Classifier> model, double significance) {
models.push_back(std::move(model));
n_models++;
significanceModels.push_back(significance);
}
void Boost::remove_last_model() {
models.pop_back();
significanceModels.pop_back();
n_models--;
}
void Boost::buildModel(const torch::Tensor &weights) {
// Models shall be built in trainModel
models.clear();
significanceModels.clear();
n_models = 0;
// Prepare the validation dataset
auto y_ = dataset.index({-1, "..."});
if (convergence) {
// Prepare train & validation sets from train data
auto fold = folding::StratifiedKFold(5, y_, 271);
auto [train, test] = fold.getFold(0);
auto train_t = torch::tensor(train);
auto test_t = torch::tensor(test);
// Get train and validation sets
X_train = dataset.index({torch::indexing::Slice(0, dataset.size(0) - 1), train_t});
y_train = dataset.index({-1, train_t});
X_test = dataset.index({torch::indexing::Slice(0, dataset.size(0) - 1), test_t});
y_test = dataset.index({-1, test_t});
dataset = X_train;
m = X_train.size(1);
auto n_classes = states.at(className).size();
// Build dataset with train data
buildDataset(y_train);
metrics = Metrics(dataset, features, className, n_classes);
} else {
// Use all data to train
X_train = dataset.index({torch::indexing::Slice(0, dataset.size(0) - 1), "..."});
y_train = y_;
}
}
std::vector<int> Boost::featureSelection(torch::Tensor &weights_) {
int maxFeatures = 0;
if (select_features_algorithm == SelectFeatures.CFS) {
featureSelector = new CFS(dataset, features, className, maxFeatures, states.at(className).size(), weights_);
} else if (select_features_algorithm == SelectFeatures.IWSS) {
if (threshold < 0 || threshold > 0.5) {
throw std::invalid_argument("Invalid threshold value for " + SelectFeatures.IWSS + " [0, 0.5]");
}
featureSelector =
new IWSS(dataset, features, className, maxFeatures, states.at(className).size(), weights_, threshold);
} else if (select_features_algorithm == SelectFeatures.FCBF) {
if (threshold < 1e-7 || threshold > 1) {
throw std::invalid_argument("Invalid threshold value for " + SelectFeatures.FCBF + " [1e-7, 1]");
}
featureSelector =
new FCBF(dataset, features, className, maxFeatures, states.at(className).size(), weights_, threshold);
}
featureSelector->fit();
auto featuresUsed = featureSelector->getFeatures();
delete featureSelector;
return featuresUsed;
}
std::tuple<torch::Tensor &, double, bool> Boost::update_weights(torch::Tensor &ytrain, torch::Tensor &ypred,
torch::Tensor &weights) {
bool terminate = false;
double alpha_t = 0;
auto mask_wrong = ypred != ytrain;
auto mask_right = ypred == ytrain;
auto masked_weights = weights * mask_wrong.to(weights.dtype());
double epsilon_t = masked_weights.sum().item<double>();
// std::cout << "epsilon_t: " << epsilon_t << " count wrong: " << mask_wrong.sum().item<int>() << " count right: "
// << mask_right.sum().item<int>() << std::endl;
if (epsilon_t > 0.5) {
// Inverse the weights policy (plot ln(wt))
// "In each round of AdaBoost, there is a sanity check to ensure that the current base
// learner is better than random guess" (Zhi-Hua Zhou, 2012)
terminate = true;
} else {
double wt = (1 - epsilon_t) / epsilon_t;
alpha_t = epsilon_t == 0 ? 1 : 0.5 * log(wt);
// Step 3.2: Update weights for next classifier
// Step 3.2.1: Update weights of wrong samples
weights += mask_wrong.to(weights.dtype()) * exp(alpha_t) * weights;
// Step 3.2.2: Update weights of right samples
weights += mask_right.to(weights.dtype()) * exp(-alpha_t) * weights;
// Step 3.3: Normalise the weights
double totalWeights = torch::sum(weights).item<double>();
weights = weights / totalWeights;
}
return {weights, alpha_t, terminate};
}
std::tuple<torch::Tensor &, double, bool> Boost::update_weights_block(int k, torch::Tensor &ytrain,
torch::Tensor &weights) {
/* Update Block algorithm
k = # of models in block
n_models = # of models in ensemble to make predictions
n_models_bak = # models saved
models = vector of models to make predictions
models_bak = models not used to make predictions
significances_bak = backup of significances vector
Case list
A) k = 1, n_models = 1 => n = 0 , n_models = n + k
B) k = 1, n_models = n + 1 => n_models = n + k
C) k > 1, n_models = k + 1 => n= 1, n_models = n + k
D) k > 1, n_models = k => n = 0, n_models = n + k
E) k > 1, n_models = k + n => n_models = n + k
Case list
A) k = 1, n_models = 1 => n = 0 , n_models = n + k
B) k = 1, n_models = n + 1 => n_models = n + k
C) k > 1, n_models = k + 1 => n= 1, n_models = n + k
D) k > 1, n_models = k => n = 0, n_models = n + k
E) k > 1, n_models = k + n => n_models = n + k
A, D) n=0, k > 0, n_models == k
1. n_models_bak <- n_models
2. significances_bak <- significances
3. significances = vector(k, 1)
4. Don’t move any classifiers out of models
5. n_models <- k
6. Make prediction, compute alpha, update weights
7. Don’t restore any classifiers to models
8. significances <- significances_bak
9. Update last k significances
10. n_models <- n_models_bak
A, D) n=0, k > 0, n_models == k
1. n_models_bak <- n_models
2. significances_bak <- significances
3. significances = vector(k, 1)
4. Don’t move any classifiers out of models
5. n_models <- k
6. Make prediction, compute alpha, update weights
7. Don’t restore any classifiers to models
8. significances <- significances_bak
9. Update last k significances
10. n_models <- n_models_bak
B, C, E) n > 0, k > 0, n_models == n + k
1. n_models_bak <- n_models
2. significances_bak <- significances
3. significances = vector(k, 1)
4. Move first n classifiers to models_bak
5. n_models <- k
6. Make prediction, compute alpha, update weights
7. Insert classifiers in models_bak to be the first n models
8. significances <- significances_bak
9. Update last k significances
10. n_models <- n_models_bak
*/
//
// Make predict with only the last k models
//
std::unique_ptr<Classifier> model;
std::vector<std::unique_ptr<Classifier>> models_bak;
// 1. n_models_bak <- n_models 2. significances_bak <- significances
auto significance_bak = significanceModels;
auto n_models_bak = n_models;
// 3. significances = vector(k, 1)
significanceModels = std::vector<double>(k, 1.0);
// 4. Move first n classifiers to models_bak
// backup the first n_models - k models (if n_models == k, don't backup any)
for (int i = 0; i < n_models - k; ++i) {
model = std::move(models[0]);
models.erase(models.begin());
models_bak.push_back(std::move(model));
}
assert(models.size() == k);
// 5. n_models <- k
n_models = k;
// 6. Make prediction, compute alpha, update weights
auto ypred = predict(X_train);
//
// Update weights
//
double alpha_t;
bool terminate;
std::tie(weights, alpha_t, terminate) = update_weights(y_train, ypred, weights);
//
// Restore the models if needed
//
// 7. Insert classifiers in models_bak to be the first n models
// if n_models_bak == k, don't restore any, because none of them were moved
if (k != n_models_bak) {
// Insert in the same order as they were extracted
int bak_size = models_bak.size();
for (int i = 0; i < bak_size; ++i) {
model = std::move(models_bak[bak_size - 1 - i]);
models_bak.erase(models_bak.end() - 1);
models.insert(models.begin(), std::move(model));
}
}
// 8. significances <- significances_bak
significanceModels = significance_bak;
//
// Update the significance of the last k models
//
// 9. Update last k significances
for (int i = 0; i < k; ++i) {
significanceModels[n_models_bak - k + i] = alpha_t;
}
// 10. n_models <- n_models_bak
n_models = n_models_bak;
return { weights, alpha_t, terminate };
B, C, E) n > 0, k > 0, n_models == n + k
1. n_models_bak <- n_models
2. significances_bak <- significances
3. significances = vector(k, 1)
4. Move first n classifiers to models_bak
5. n_models <- k
6. Make prediction, compute alpha, update weights
7. Insert classifiers in models_bak to be the first n models
8. significances <- significances_bak
9. Update last k significances
10. n_models <- n_models_bak
*/
//
// Make predict with only the last k models
//
std::unique_ptr<Classifier> model;
std::vector<std::unique_ptr<Classifier>> models_bak;
// 1. n_models_bak <- n_models 2. significances_bak <- significances
auto significance_bak = significanceModels;
auto n_models_bak = n_models;
// 3. significances = vector(k, 1)
significanceModels = std::vector<double>(k, 1.0);
// 4. Move first n classifiers to models_bak
// backup the first n_models - k models (if n_models == k, don't backup any)
for (int i = 0; i < n_models - k; ++i) {
model = std::move(models[0]);
models.erase(models.begin());
models_bak.push_back(std::move(model));
}
}
assert(models.size() == k);
// 5. n_models <- k
n_models = k;
// 6. Make prediction, compute alpha, update weights
auto ypred = predict(X_train);
//
// Update weights
//
double alpha_t;
bool terminate;
std::tie(weights, alpha_t, terminate) = update_weights(y_train, ypred, weights);
//
// Restore the models if needed
//
// 7. Insert classifiers in models_bak to be the first n models
// if n_models_bak == k, don't restore any, because none of them were moved
if (k != n_models_bak) {
// Insert in the same order as they were extracted
int bak_size = models_bak.size();
for (int i = 0; i < bak_size; ++i) {
model = std::move(models_bak[bak_size - 1 - i]);
models_bak.erase(models_bak.end() - 1);
models.insert(models.begin(), std::move(model));
}
}
// 8. significances <- significances_bak
significanceModels = significance_bak;
//
// Update the significance of the last k models
//
// 9. Update last k significances
for (int i = 0; i < k; ++i) {
significanceModels[n_models_bak - k + i] = alpha_t;
}
// 10. n_models <- n_models_bak
n_models = n_models_bak;
return {weights, alpha_t, terminate};
}
} // namespace bayesnet

7
bayesnet/ensembles/Boost.h
View File

@@ -34,6 +34,11 @@ namespace bayesnet {
void buildModel(const torch::Tensor& weights) override;
std::tuple<torch::Tensor&, double, bool> update_weights(torch::Tensor& ytrain, torch::Tensor& ypred, torch::Tensor& weights);
std::tuple<torch::Tensor&, double, bool> update_weights_block(int k, torch::Tensor& ytrain, torch::Tensor& weights);
void add_model(std::unique_ptr<Classifier> model, double significance);
void remove_last_model();
//
// Attributes
//
torch::Tensor X_train, y_train, X_test, y_test;
// Hyperparameters
bool bisection = true; // if true, use bisection stratety to add k models at once to the ensemble
@@ -49,4 +54,4 @@ namespace bayesnet {
bool alpha_block = false; // if true, the alpha is computed with the ensemble built so far and the new model
};
}
#endif
#endif

4
bayesnet/ensembles/BoostAODE.cc
View File

@@ -6,10 +6,10 @@
#include <random>
#include <set>
#include <functional>
#include <limits.h>
#include <tuple>
#include "BoostAODE.h"
#include "bayesnet/classifiers/SPODE.h"
#include <loguru.hpp>
#include <loguru.cpp>
@@ -180,4 +180,4 @@ namespace bayesnet {
{
return Ensemble::graph(title);
}
}
}

3
bayesnet/ensembles/BoostAODE.h
View File

@@ -8,7 +8,6 @@
#define BOOSTAODE_H
#include <string>
#include <vector>
#include "bayesnet/classifiers/SPODE.h"
#include "Boost.h"
namespace bayesnet {
@@ -23,4 +22,4 @@ namespace bayesnet {
std::vector<int> initializeModels(const Smoothing_t smoothing);
};
}
#endif
#endif

168
bayesnet/ensembles/XBA2DE.cc Normal file
View File

@@ -0,0 +1,168 @@
// ***************************************************************
// SPDX-FileCopyrightText: Copyright 2025 Ricardo Montañana Gómez
// SPDX-FileType: SOURCE
// SPDX-License-Identifier: MIT
// ***************************************************************
#include <folding.hpp>
#include <limits.h>
#include "XBA2DE.h"
#include "bayesnet/classifiers/XSPnDE.h"
#include "bayesnet/utils/TensorUtils.h"
namespace bayesnet {
XBA2DE::XBA2DE(bool predict_voting) : Boost(predict_voting) {}
std::vector<int> XBA2DE::initializeModels(const Smoothing_t smoothing) {
torch::Tensor weights_ = torch::full({m}, 1.0 / m, torch::kFloat64);
std::vector<int> featuresSelected = featureSelection(weights_);
if (featuresSelected.size() < 2) {
notes.push_back("No features selected in initialization");
status = ERROR;
return std::vector<int>();
}
for (int i = 0; i < featuresSelected.size() - 1; i++) {
for (int j = i + 1; j < featuresSelected.size(); j++) {
std::unique_ptr<Classifier> model = std::make_unique<XSpnde>(featuresSelected[i], featuresSelected[j]);
model->fit(dataset, features, className, states, weights_, smoothing);
add_model(std::move(model), 1.0);
}
}
notes.push_back("Used features in initialization: " + std::to_string(featuresSelected.size()) + " of " +
std::to_string(features.size()) + " with " + select_features_algorithm);
return featuresSelected;
}
void XBA2DE::trainModel(const torch::Tensor &weights, const Smoothing_t smoothing) {
//
// Logging setup
//
// loguru::set_thread_name("XBA2DE");
// loguru::g_stderr_verbosity = loguru::Verbosity_OFF;
// loguru::add_file("boostA2DE.log", loguru::Truncate, loguru::Verbosity_MAX);
// Algorithm based on the adaboost algorithm for classification
// as explained in Ensemble methods (Zhi-Hua Zhou, 2012)
X_train_ = TensorUtils::to_matrix(X_train);
y_train_ = TensorUtils::to_vector<int>(y_train);
if (convergence) {
X_test_ = TensorUtils::to_matrix(X_test);
y_test_ = TensorUtils::to_vector<int>(y_test);
}
fitted = true;
double alpha_t = 0;
torch::Tensor weights_ = torch::full({m}, 1.0 / m, torch::kFloat64);
bool finished = false;
std::vector<int> featuresUsed;
if (selectFeatures) {
featuresUsed = initializeModels(smoothing);
if (featuresUsed.size() == 0) {
return;
}
auto ypred = predict(X_train);
std::tie(weights_, alpha_t, finished) = update_weights(y_train, ypred, weights_);
// Update significance of the models
for (int i = 0; i < n_models; ++i) {
significanceModels[i] = alpha_t;
}
if (finished) {
return;
}
}
int numItemsPack = 0; // The counter of the models inserted in the current pack
// Variables to control the accuracy finish condition
double priorAccuracy = 0.0;
double improvement = 1.0;
double convergence_threshold = 1e-4;
int tolerance = 0; // number of times the accuracy is lower than the convergence_threshold
// Step 0: Set the finish condition
// epsilon sub t > 0.5 => inverse the weights policy
// validation error is not decreasing
// run out of features
bool ascending = order_algorithm == Orders.ASC;
std::mt19937 g{173};
std::vector<std::pair<int, int>> pairSelection;
while (!finished) {
// Step 1: Build ranking with mutual information
pairSelection = metrics.SelectKPairs(weights_, featuresUsed, ascending, 0); // Get all the pairs sorted
if (order_algorithm == Orders.RAND) {
std::shuffle(pairSelection.begin(), pairSelection.end(), g);
}
int k = bisection ? pow(2, tolerance) : 1;
int counter = 0; // The model counter of the current pack
// VLOG_SCOPE_F(1, "counter=%d k=%d featureSelection.size: %zu", counter, k, featureSelection.size());
while (counter++ < k && pairSelection.size() > 0) {
auto feature_pair = pairSelection[0];
pairSelection.erase(pairSelection.begin());
std::unique_ptr<Classifier> model;
model = std::make_unique<XSpnde>(feature_pair.first, feature_pair.second);
model->fit(dataset, features, className, states, weights_, smoothing);
alpha_t = 0.0;
if (!block_update) {
auto ypred = model->predict(X_train);
// Step 3.1: Compute the classifier amout of say
std::tie(weights_, alpha_t, finished) = update_weights(y_train, ypred, weights_);
}
// Step 3.4: Store classifier and its accuracy to weigh its future vote
numItemsPack++;
models.push_back(std::move(model));
significanceModels.push_back(alpha_t);
n_models++;
// VLOG_SCOPE_F(2, "numItemsPack: %d n_models: %d featuresUsed: %zu", numItemsPack, n_models,
// featuresUsed.size());
}
if (block_update) {
std::tie(weights_, alpha_t, finished) = update_weights_block(k, y_train, weights_);
}
if (convergence && !finished) {
auto y_val_predict = predict(X_test);
double accuracy = (y_val_predict == y_test).sum().item<double>() / (double)y_test.size(0);
if (priorAccuracy == 0) {
priorAccuracy = accuracy;
} else {
improvement = accuracy - priorAccuracy;
}
if (improvement < convergence_threshold) {
// VLOG_SCOPE_F(3, " (improvement<threshold) tolerance: %d numItemsPack: %d improvement: %f prior: %f
// current: %f", tolerance, numItemsPack, improvement, priorAccuracy, accuracy);
tolerance++;
} else {
// VLOG_SCOPE_F(3, "* (improvement>=threshold) Reset. tolerance: %d numItemsPack: %d improvement: %f
// prior: %f current: %f", tolerance, numItemsPack, improvement, priorAccuracy, accuracy);
tolerance = 0; // Reset the counter if the model performs better
numItemsPack = 0;
}
if (convergence_best) {
// Keep the best accuracy until now as the prior accuracy
priorAccuracy = std::max(accuracy, priorAccuracy);
} else {
// Keep the last accuray obtained as the prior accuracy
priorAccuracy = accuracy;
}
}
// VLOG_SCOPE_F(1, "tolerance: %d featuresUsed.size: %zu features.size: %zu", tolerance, featuresUsed.size(),
// features.size());
finished = finished || tolerance > maxTolerance || pairSelection.size() == 0;
}
if (tolerance > maxTolerance) {
if (numItemsPack < n_models) {
notes.push_back("Convergence threshold reached & " + std::to_string(numItemsPack) + " models eliminated");
// VLOG_SCOPE_F(4, "Convergence threshold reached & %d models eliminated of %d", numItemsPack, n_models);
for (int i = 0; i < numItemsPack; ++i) {
significanceModels.pop_back();
models.pop_back();
n_models--;
}
} else {
notes.push_back("Convergence threshold reached & 0 models eliminated");
// VLOG_SCOPE_F(4, "Convergence threshold reached & 0 models eliminated n_models=%d numItemsPack=%d",
// n_models, numItemsPack);
}
}
if (pairSelection.size() > 0) {
notes.push_back("Pairs not used in train: " + std::to_string(pairSelection.size()));
status = WARNING;
}
notes.push_back("Number of models: " + std::to_string(n_models));
}
std::vector<std::string> XBA2DE::graph(const std::string &title) const { return Ensemble::graph(title); }
} // namespace bayesnet

28
bayesnet/ensembles/XBA2DE.h Normal file
View File

@@ -0,0 +1,28 @@
// ***************************************************************
// SPDX-FileCopyrightText: Copyright 2025 Ricardo Montañana Gómez
// SPDX-FileType: SOURCE
// SPDX-License-Identifier: MIT
// ***************************************************************
#ifndef XBA2DE_H
#define XBA2DE_H
#include <string>
#include <vector>
#include "Boost.h"
namespace bayesnet {
class XBA2DE : public Boost {
public:
explicit XBA2DE(bool predict_voting = false);
virtual ~XBA2DE() = default;
std::vector<std::string> graph(const std::string& title = "XBA2DE") const override;
std::string getVersion() override { return version; };
protected:
void trainModel(const torch::Tensor& weights, const Smoothing_t smoothing) override;
private:
std::vector<int> initializeModels(const Smoothing_t smoothing);
std::vector<std::vector<int>> X_train_, X_test_;
std::vector<int> y_train_, y_test_;
std::string version = "0.9.7";
};
}
#endif

10
bayesnet/ensembles/XBAODE.cc
View File

@@ -15,16 +15,6 @@ XBAODE::XBAODE() : Boost(false) {
validHyperparameters = {"alpha_block", "order", "convergence", "convergence_best", "bisection",
"threshold", "maxTolerance", "predict_voting", "select_features"};
}
void XBAODE::add_model(std::unique_ptr<Classifier> model, double significance) {
models.push_back(std::move(model));
n_models++;
significanceModels.push_back(significance);
}
void XBAODE::remove_last_model() {
models.pop_back();
significanceModels.pop_back();
n_models--;
}
std::vector<int> XBAODE::initializeModels(const Smoothing_t smoothing) {
torch::Tensor weights_ = torch::full({m}, 1.0 / m, torch::kFloat64);
std::vector<int> featuresSelected = featureSelection(weights_);

2
bayesnet/ensembles/XBAODE.h
View File

@@ -18,8 +18,6 @@ namespace bayesnet {
protected:
void trainModel(const torch::Tensor& weights, const bayesnet::Smoothing_t smoothing) override;
private:
void add_model(std::unique_ptr<Classifier> model, double significance);
void remove_last_model();
std::vector<int> initializeModels(const Smoothing_t smoothing);
std::vector<std::vector<int>> X_train_, X_test_;
std::vector<int> y_train_, y_test_;