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

Add selectKParis method

Browse Source
This commit is contained in:
Ricardo Montañana Gómez
2024-05-16 11:17:21 +02:00
parent 8784a24898
commit 2e3e0e0fc2
8 changed files with 224 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files

142
bayesnet/ensembles/BoostA2DE.cc
View File

@@ -19,9 +19,151 @@ namespace bayesnet {
BoostA2DE::BoostA2DE(bool predict_voting) : Boost(predict_voting)
{
}
std::vector<int> BoostA2DE::initializeModels()
{
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++) {
auto parents = { featuresSelected[i], featuresSelected[j] };
std::unique_ptr<Classifier> model = std::make_unique<SPnDE>(parents);
model->fit(dataset, features, className, states, weights_);
models.push_back(std::move(model));
significanceModels.push_back(1.0); // They will be updated later in trainModel
n_models++;
}
}
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 BoostA2DE::trainModel(const torch::Tensor& weights)
{
//
// Logging setup
//
// loguru::set_thread_name("BoostA2DE");
// 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)
// 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();
// 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 };
// while (!finished) {
// // Step 1: Build ranking with mutual information
// auto pairSelection = metrics.SelectKBestWeighted(weights_, ascending, n); // Get all the features sorted
// if (order_algorithm == Orders.RAND) {
// std::shuffle(featureSelection.begin(), featureSelection.end(), g);
// }
// // Remove used features
// featureSelection.erase(remove_if(begin(featureSelection), end(featureSelection), [&](auto x)
// { return std::find(begin(featuresUsed), end(featuresUsed), x) != end(featuresUsed);}),
// end(featureSelection)
// );
// 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 && featureSelection.size() > 0) {
// auto feature = featureSelection[0];
// featureSelection.erase(featureSelection.begin());
// std::unique_ptr<Classifier> model;
// model = std::make_unique<SPODE>(feature);
// model->fit(dataset, features, className, states, weights_);
// 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++;
// featuresUsed.push_back(feature);
// 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 || featuresUsed.size() == features.size();
// }
// 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 (featuresUsed.size() != features.size()) {
// notes.push_back("Used features in train: " + std::to_string(featuresUsed.size()) + " of " + std::to_string(features.size()));
// status = WARNING;
// }
// notes.push_back("Number of models: " + std::to_string(n_models));
}
std::vector<std::string> BoostA2DE::graph(const std::string& title) const
{

2
bayesnet/ensembles/BoostA2DE.h
View File

@@ -18,6 +18,8 @@ namespace bayesnet {
std::vector<std::string> graph(const std::string& title = "BoostA2DE") const override;
protected:
void trainModel(const torch::Tensor& weights) override;
private:
std::vector<int> initializeModels();
};
}
#endif

22
bayesnet/ensembles/BoostAODE.cc
View File

@@ -10,14 +10,12 @@
#include <limits.h>
#include <tuple>
#include "BoostAODE.h"
#include "lib/log/loguru.cpp"
namespace bayesnet {
BoostAODE::BoostAODE(bool predict_voting) : Boost(predict_voting)
{
}
std::vector<int> BoostAODE::initializeModels()
{
torch::Tensor weights_ = torch::full({ m }, 1.0 / m, torch::kFloat64);
@@ -37,9 +35,9 @@ namespace bayesnet {
//
// Logging setup
//
loguru::set_thread_name("BoostAODE");
loguru::g_stderr_verbosity = loguru::Verbosity_OFF;
loguru::add_file("boostAODE.log", loguru::Truncate, loguru::Verbosity_MAX);
// loguru::set_thread_name("BoostAODE");
// loguru::g_stderr_verbosity = loguru::Verbosity_OFF;
// loguru::add_file("boostAODE.log", loguru::Truncate, loguru::Verbosity_MAX);
// Algorithm based on the adaboost algorithm for classification
// as explained in Ensemble methods (Zhi-Hua Zhou, 2012)
@@ -85,7 +83,7 @@ namespace bayesnet {
);
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());
// VLOG_SCOPE_F(1, "counter=%d k=%d featureSelection.size: %zu", counter, k, featureSelection.size());
while (counter++ < k && featureSelection.size() > 0) {
auto feature = featureSelection[0];
featureSelection.erase(featureSelection.begin());
@@ -104,7 +102,7 @@ namespace bayesnet {
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());
// 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_);
@@ -118,10 +116,10 @@ namespace bayesnet {
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);
// 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);
// 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;
}
@@ -133,13 +131,13 @@ namespace bayesnet {
priorAccuracy = accuracy;
}
}
VLOG_SCOPE_F(1, "tolerance: %d featuresUsed.size: %zu features.size: %zu", tolerance, featuresUsed.size(), features.size());
// VLOG_SCOPE_F(1, "tolerance: %d featuresUsed.size: %zu features.size: %zu", tolerance, featuresUsed.size(), features.size());
finished = finished || tolerance > maxTolerance || featuresUsed.size() == features.size();
}
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);
// 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();
@@ -147,7 +145,7 @@ namespace bayesnet {
}
} 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);
// VLOG_SCOPE_F(4, "Convergence threshold reached & 0 models eliminated n_models=%d numItemsPack=%d", n_models, numItemsPack);
}
}
if (featuresUsed.size() != features.size()) {

1
bayesnet/ensembles/BoostAODE.h
View File

@@ -10,6 +10,7 @@
#include <vector>
#include "bayesnet/classifiers/SPODE.h"
#include "Boost.h"
namespace bayesnet {
class BoostAODE : public Boost {
public: