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

Refactor Smoothing type to its own file

Browse Source 
Add log to boost
This commit is contained in:
Ricardo Montañana Gómez
2025-03-08 14:04:08 +01:00
parent 81fd7df7f0
commit b987dcbcc4
9 changed files with 41 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
bayesnet/ensembles/BoostAODE.cc
View File

@@ -10,6 +10,8 @@
#include <limits.h>
#include <tuple>
#include "BoostAODE.h"
#include <loguru.hpp>
#include <loguru.cpp>
namespace bayesnet {
@@ -35,9 +37,9 @@ 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)
@@ -46,14 +48,16 @@ namespace bayesnet {
torch::Tensor weights_ = torch::full({ m }, 1.0 / m, torch::kFloat64);
bool finished = false;
std::vector<int> featuresUsed;
n_models = 0;
if (selectFeatures) {
featuresUsed = initializeModels(smoothing);
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;
significanceModels.push_back(alpha_t);
}
VLOG_SCOPE_F(1, "SelectFeatures. alpha_t: %f n_models: %d", alpha_t, n_models);
if (finished) {
return;
}
@@ -83,7 +87,7 @@ 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());
@@ -120,7 +124,7 @@ 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, "finished: %d numItemsPack: %d n_models: %d featuresUsed: %zu", finished, numItemsPack, n_models, featuresUsed.size());
}
if (block_update) {
std::tie(weights_, alpha_t, finished) = update_weights_block(k, y_train, weights_);
@@ -134,10 +138,10 @@ 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;
}
@@ -149,13 +153,13 @@ 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();
@@ -163,7 +167,7 @@ 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()) {