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

Add status to classifier and Experiment

Browse Source
This commit is contained in:
Ricardo Montañana Gómez
2023-09-05 13:39:43 +02:00
parent 64fc7bd9dd
commit 5a7c8f1818
5 changed files with 256 additions and 180 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/BayesNet/BaseClassifier.h
View File

@@ -5,6 +5,7 @@
#include <vector>
namespace bayesnet {
using namespace std;
enum status_t { NORMAL, WARNING, ERROR };
class BaseClassifier {
protected:
virtual void trainModel(const torch::Tensor& weights) = 0;
@@ -18,6 +19,7 @@ namespace bayesnet {
virtual ~BaseClassifier() = default;
torch::Tensor virtual predict(torch::Tensor& X) = 0;
vector<int> virtual predict(vector<vector<int>>& X) = 0;
status_t virtual getStatus() const = 0;
float virtual score(vector<vector<int>>& X, vector<int>& y) = 0;
float virtual score(torch::Tensor& X, torch::Tensor& y) = 0;
int virtual getNumberOfNodes()const = 0;

17
src/BayesNet/BoostAODE.cc
View File

@@ -1,6 +1,7 @@
#include "BoostAODE.h"
#include <set>
#include "BayesMetrics.h"
#include "Colors.h"
namespace bayesnet {
BoostAODE::BoostAODE() : Ensemble() {}
@@ -64,22 +65,26 @@ namespace bayesnet {
auto ypred = model->predict(X_);
// Step 3.1: Compute the classifier amout of say
auto mask_wrong = ypred != y_;
auto mask_right = ypred == y_;
auto masked_weights = weights_ * mask_wrong.to(weights_.dtype());
double wrongWeights = masked_weights.sum().item<double>();
double significance = wrongWeights == 0 ? 1 : 0.5 * log((1 - wrongWeights) / wrongWeights);
double epsilon_t = masked_weights.sum().item<double>();
double wt = (1 - epsilon_t) / epsilon_t;
double 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(significance) * weights_;
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;
// Step 3.4: Store classifier and its accuracy to weigh its future vote
models.push_back(std::move(model));
significanceModels.push_back(significance);
exitCondition = n_models == maxModels && repeatSparent;
significanceModels.push_back(alpha_t);
exitCondition = n_models == maxModels && repeatSparent || epsilon_t > 0.5;
}
if (featuresUsed.size() != features.size()) {
cout << "Warning: BoostAODE did not use all the features" << endl;
status = WARNING;
}
weights.copy_(weights_);
}

2
src/BayesNet/Classifier.h
View File

@@ -21,6 +21,7 @@ namespace bayesnet {
string className;
map<string, vector<int>> states;
Tensor dataset; // (n+1)xm tensor
status_t status = NORMAL;
void checkFitParameters();
virtual void buildModel(const torch::Tensor& weights) = 0;
void trainModel(const torch::Tensor& weights) override;
@@ -37,6 +38,7 @@ namespace bayesnet {
int getNumberOfEdges() const override;
int getNumberOfStates() const override;
Tensor predict(Tensor& X) override;
status_t getStatus() const override { return status; }
vector<int> predict(vector<vector<int>>& X) override;
float score(Tensor& X, Tensor& y) override;
float score(vector<vector<int>>& X, vector<int>& y) override;

29
src/Platform/Experiment.cc
View File

@@ -111,6 +111,26 @@ namespace platform {
}
}
string getColor(bayesnet::status_t status)
{
switch (status) {
case bayesnet::NORMAL:
return Colors::GREEN();
case bayesnet::WARNING:
return Colors::YELLOW();
case bayesnet::ERROR:
return Colors::RED();
default:
return Colors::RESET();
}
}
void showProgress(int fold, const string& color, const string& phase)
{
string prefix = phase == "a" ? "" : "\b\b\b\b";
cout << prefix << color << fold << Colors::RESET() << "(" << color << phase << Colors::RESET() << ")" << flush;
}
void Experiment::cross_validation(const string& path, const string& fileName)
{
auto datasets = platform::Datasets(path, discretized, platform::ARFF);
@@ -159,23 +179,24 @@ namespace platform {
auto y_train = y.index({ train_t });
auto X_test = X.index({ "...", test_t });
auto y_test = y.index({ test_t });
cout << nfold + 1 << "(a)" << flush;
showProgress(nfold + 1, getColor(clf->getStatus()), "a");
// Train model
clf->fit(X_train, y_train, features, className, states);
cout << "\b\bb)" << flush;
showProgress(nfold + 1, getColor(clf->getStatus()), "b");
nodes[item] = clf->getNumberOfNodes();
edges[item] = clf->getNumberOfEdges();
num_states[item] = clf->getNumberOfStates();
train_time[item] = train_timer.getDuration();
// Score train
auto accuracy_train_value = clf->score(X_train, y_train);
cout << "\b\bc)" << flush;
// Test model
showProgress(nfold + 1, getColor(clf->getStatus()), "c");
test_timer.start();
auto accuracy_test_value = clf->score(X_test, y_test);
cout << "\b\b\b, " << flush;
test_time[item] = test_timer.getDuration();
accuracy_train[item] = accuracy_train_value;
accuracy_test[item] = accuracy_test_value;
cout << "\b\b\b, " << flush;
// Store results and times in vector
result.addScoreTrain(accuracy_train_value);
result.addScoreTest(accuracy_test_value);