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

4
bayesnet/BaseClassifier.h
View File

@@ -14,13 +14,13 @@ namespace bayesnet {
enum status_t { NORMAL, WARNING, ERROR };
class BaseClassifier {
public:
virtual ~BaseClassifier() = default;
// X is nxm std::vector, y is nx1 std::vector
virtual BaseClassifier& fit(std::vector<std::vector<int>>& X, std::vector<int>& y, const std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states, const Smoothing_t smoothing) = 0;
// X is nxm tensor, y is nx1 tensor
virtual BaseClassifier& fit(torch::Tensor& X, torch::Tensor& y, const std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states, const Smoothing_t smoothing) = 0;
virtual BaseClassifier& fit(torch::Tensor& dataset, const std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states, const Smoothing_t smoothing) = 0;
virtual BaseClassifier& fit(torch::Tensor& dataset, const std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states, const torch::Tensor& weights, const Smoothing_t smoothing) = 0;
virtual ~BaseClassifier() = default;
torch::Tensor virtual predict(torch::Tensor& X) = 0;
std::vector<int> virtual predict(std::vector<std::vector<int >>& X) = 0;
torch::Tensor virtual predict_proba(torch::Tensor& X) = 0;
@@ -43,5 +43,7 @@ namespace bayesnet {
protected:
virtual void trainModel(const torch::Tensor& weights, const Smoothing_t smoothing) = 0;
std::vector<std::string> validHyperparameters;
std::vector<std::string> notes; // Used to store messages occurred during the fit process
status_t status = NORMAL;
};
}

1
bayesnet/CMakeLists.txt
View File

@@ -1,4 +1,5 @@
include_directories(
${BayesNet_SOURCE_DIR}/lib/log
${BayesNet_SOURCE_DIR}/lib/mdlp/src
${BayesNet_SOURCE_DIR}/lib/folding
${BayesNet_SOURCE_DIR}/lib/json/include

2
bayesnet/classifiers/Classifier.h
View File

@@ -46,8 +46,6 @@ namespace bayesnet {
std::string className;
std::map<std::string, std::vector<int>> states;
torch::Tensor dataset; // (n+1)xm tensor
status_t status = NORMAL;
std::vector<std::string> notes; // Used to store messages occurred during the fit process
void checkFitParameters();
virtual void buildModel(const torch::Tensor& weights) = 0;
void trainModel(const torch::Tensor& weights, const Smoothing_t smoothing) override;

1
bayesnet/ensembles/Boost.cc
View File

@@ -138,6 +138,7 @@ namespace bayesnet {
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

6
bayesnet/ensembles/Boost.h
View File

@@ -27,7 +27,7 @@ namespace bayesnet {
class Boost : public Ensemble {
public:
explicit Boost(bool predict_voting = false);
virtual ~Boost() = default;
virtual ~Boost() override = default;
void setHyperparameters(const nlohmann::json& hyperparameters_) override;
protected:
std::vector<int> featureSelection(torch::Tensor& weights_);
@@ -38,11 +38,11 @@ namespace bayesnet {
// Hyperparameters
bool bisection = true; // if true, use bisection stratety to add k models at once to the ensemble
int maxTolerance = 3;
std::string order_algorithm; // order to process the KBest features asc, desc, rand
std::string order_algorithm = Orders.DESC; // order to process the KBest features asc, desc, rand
bool convergence = true; //if true, stop when the model does not improve
bool convergence_best = false; // wether to keep the best accuracy to the moment or the last accuracy as prior accuracy
bool selectFeatures = false; // if true, use feature selection
std::string select_features_algorithm = Orders.DESC; // Selected feature selection algorithm
std::string select_features_algorithm; // Selected feature selection algorithm
FeatureSelect* featureSelector = nullptr;
double threshold = -1;
bool block_update = false; // if true, use block update algorithm, only meaningful if bisection is true

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()) {

8
bayesnet/network/Network.h
View File

@@ -10,14 +10,10 @@
#include <vector>
#include "bayesnet/config.h"
#include "Node.h"
#include "Smoothing.h"
namespace bayesnet {
enum class Smoothing_t {
NONE = -1,
ORIGINAL = 0,
LAPLACE,
CESTNIK
};
class Network {
public:
Network();

15
bayesnet/network/Smoothing.h Normal file
View File

@@ -0,0 +1,15 @@
// ***************************************************************
// SPDX-FileCopyrightText: Copyright 2024 Ricardo Montañana Gómez
// SPDX-FileType: SOURCE
// SPDX-License-Identifier: MIT
// ***************************************************************
#ifndef SMOOTHING_H
#define SMOOTHING_H
enum class Smoothing_t {
NONE = -1,
ORIGINAL = 0,
LAPLACE,
CESTNIK
};
#endif // SMOOTHING_H