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

Fix metrics error in BoostAODE Convergence

Browse Source 
Update algorithm
This commit is contained in:
Ricardo Montañana Gómez
2024-03-20 23:33:02 +01:00
parent 5826702fc7
commit 6e854dfda3
6 changed files with 98 additions and 65 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
bayesnet/classifiers/Classifier.cc
View File

@@ -10,7 +10,7 @@ namespace bayesnet {
this->className = className;
this->states = states;
m = dataset.size(1);
n = dataset.size(0) - 1;
n = features.size();
checkFitParameters();
auto n_classes = states.at(className).size();
metrics = Metrics(dataset, features, className, n_classes);

35
bayesnet/ensembles/BoostAODE.cc
View File

@@ -8,7 +8,6 @@
#include "bayesnet/feature_selection/IWSS.h"
#include "BoostAODE.h"
#define LOGURU_WITH_STREAMS 1
#include "bayesnet/utils/loguru.cpp"
namespace bayesnet {
@@ -41,8 +40,8 @@ namespace bayesnet {
if (convergence) {
// Prepare train & validation sets from train data
auto fold = folding::StratifiedKFold(5, y_, 271);
dataset_ = torch::clone(dataset);
// save input dataset
dataset_ = torch::clone(dataset);
auto [train, test] = fold.getFold(0);
auto train_t = torch::tensor(train);
auto test_t = torch::tensor(test);
@@ -54,9 +53,9 @@ namespace bayesnet {
dataset = X_train;
m = X_train.size(1);
auto n_classes = states.at(className).size();
metrics = Metrics(dataset, features, className, n_classes);
// 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), "..." });
@@ -137,9 +136,9 @@ namespace bayesnet {
}
return { weights, alpha_t, terminate };
}
std::unordered_set<int> BoostAODE::initializeModels()
std::vector<int> BoostAODE::initializeModels()
{
std::unordered_set<int> featuresUsed;
std::vector<int> featuresUsed;
torch::Tensor weights_ = torch::full({ m }, 1.0 / m, torch::kFloat64);
int maxFeatures = 0;
if (select_features_algorithm == SelectFeatures.CFS) {
@@ -158,7 +157,7 @@ namespace bayesnet {
featureSelector->fit();
auto cfsFeatures = featureSelector->getFeatures();
for (const int& feature : cfsFeatures) {
featuresUsed.insert(feature);
featuresUsed.push_back(feature);
std::unique_ptr<Classifier> model = std::make_unique<SPODE>(feature);
model->fit(dataset, features, className, states, weights_);
models.push_back(std::move(model));
@@ -183,7 +182,7 @@ namespace bayesnet {
double alpha_t = 0;
torch::Tensor weights_ = torch::full({ m }, 1.0 / m, torch::kFloat64);
bool finished = false;
std::unordered_set<int> featuresUsed;
std::vector<int> featuresUsed;
if (selectFeatures) {
featuresUsed = initializeModels();
auto ypred = predict(X_train);
@@ -199,7 +198,7 @@ namespace bayesnet {
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 delta = 1.0;
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
@@ -222,9 +221,9 @@ namespace bayesnet {
);
int k = pow(2, tolerance);
int counter = 0; // The model counter of the current pack
VLOG_SCOPE_F(1, "k=%d", k);
VLOG_SCOPE_F(1, "k=%d featureSelection.size: %d", k, featureSelection.size());
while (counter++ < k && featureSelection.size() > 0) {
VLOG_SCOPE_F(2, "counter: %d numItemsPack: %d featureSelection.size: %d", counter, numItemsPack, featureSelection.size());
VLOG_SCOPE_F(2, "counter: %d numItemsPack: %d", counter, numItemsPack);
auto feature = featureSelection[0];
featureSelection.erase(featureSelection.begin());
std::unique_ptr<Classifier> model;
@@ -240,10 +239,11 @@ namespace bayesnet {
}
// Step 3.4: Store classifier and its accuracy to weigh its future vote
numItemsPack++;
featuresUsed.insert(feature);
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: %d", numItemsPack, n_models, featuresUsed.size());
}
if (convergence && !finished) {
auto y_val_predict = predict(X_test);
@@ -252,20 +252,21 @@ namespace bayesnet {
priorAccuracy = accuracy;
VLOG_SCOPE_F(3, "First accuracy: %f", priorAccuracy);
} else {
delta = accuracy - priorAccuracy;
improvement = accuracy - priorAccuracy;
}
if (delta < convergence_threshold) {
VLOG_SCOPE_F(3, "(delta<threshold) tolerance: %d numItemsPack: %d delta: %f prior: %f current: %f", tolerance, numItemsPack, delta, priorAccuracy, accuracy);
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, "*(delta>=threshold) Reset. tolerance: %d numItemsPack: %d delta: %f prior: %f current: %f", tolerance, numItemsPack, delta, 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;
}
// Keep the best accuracy until now as the prior accuracy
// priorAccuracy = std::max(accuracy, priorAccuracy);
priorAccuracy = accuracy;
priorAccuracy = std::max(accuracy, priorAccuracy);
// priorAccuracy = accuracy;
}
VLOG_SCOPE_F(1, "tolerance: %d featuresUsed.size: %d features.size: %d", tolerance, featuresUsed.size(), features.size());
finished = finished || tolerance > maxTolerance || featuresUsed.size() == features.size();
}
if (tolerance > maxTolerance) {

4
bayesnet/ensembles/BoostAODE.h
View File

@@ -15,8 +15,8 @@ namespace bayesnet {
void buildModel(const torch::Tensor& weights) override;
void trainModel(const torch::Tensor& weights) override;
private:
std::unordered_set<int> initializeModels();
torch::Tensor dataset_;
std::vector<int> initializeModels();
torch::Tensor dataset_; // Backup the original dataset
torch::Tensor X_train, y_train, X_test, y_test;
// Hyperparameters
bool bisection = false; // if true, use bisection stratety to add k models at once to the ensemble

2
bayesnet/utils/BayesMetrics.cc
View File

@@ -24,7 +24,7 @@ namespace bayesnet {
std::vector<int> Metrics::SelectKBestWeighted(const torch::Tensor& weights, bool ascending, unsigned k)
{
// Return the K Best features
auto n = samples.size(0) - 1;
auto n = features.size();
if (k == 0) {
k = n;
}