rmontanana/PyWrap
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Refactor Classifier classes

Browse Source
This commit is contained in:
Ricardo Montañana Gómez
2023-11-12 18:35:29 +01:00
parent c7372b7fc7
commit 0059e269dd
12 changed files with 133 additions and 83 deletions
Download Patch File Download Diff File Expand all files Collapse all files

128
example/example.cc
View File

@@ -5,7 +5,9 @@
#include <vector>
#include <string>
#include <iostream>
#include "Classifier.h"
#include "STree.h"
#include "ODTE.h"
#include "SVC.h"
#include "RandomForest.h"
#include "XGBoost.h"
@@ -47,11 +49,22 @@ pair<torch::Tensor, torch::Tensor> get_train_test_indices(int size)
shuffle(indices.begin(), indices.end(), std::default_random_engine(seed));
auto train_indices = torch::zeros({ train_size }, torch::kInt32);
auto test_indices = torch::zeros({ test_size }, torch::kInt32);
int ti = 0, ei = 0;
cout << "Train indices [";
for (auto i = 0; i < train_size; ++i) {
cout << indices.at(i) << ", ";
}
cout << "]" << endl;
cout << "Test indices [";
for (auto i = train_size; i < size; ++i) {
cout << indices.at(i) << ", ";
}
cout << "]" << endl;
for (auto i = 0; i < size; ++i) {
if (i < train_size) {
train_indices[i] = indices[i];
train_indices[ti++] = indices.at(i);
} else if (i < size) {
test_indices[i - train_size] = indices[i];
test_indices[ei++] = indices.at(i);
}
}
return { train_indices, test_indices };
@@ -61,71 +74,52 @@ int main(int argc, char* argv[])
{
using json = nlohmann::json;
cout << "* Begin." << endl;
{
using namespace torch::indexing;
auto datasetName = "wine";
bool class_last = true;
auto [X, y] = loadDataset(datasetName, class_last);
// Split train/test
auto [train_indices, test_indices] = get_train_test_indices(X.size(1));
auto Xtrain = X.index({ "...", train_indices });
auto ytrain = y.index({ train_indices });
auto Xtest = X.index({ "...", test_indices });
auto ytest = y.index({ test_indices });
cout << "Dataset: " << datasetName << endl;
cout << "X: " << X.sizes() << endl;
cout << "y: " << y.sizes() << endl;
cout << "Xtrain: " << Xtrain.sizes() << endl;
cout << "ytrain: " << ytrain.sizes() << endl;
cout << "Xtest : " << Xtest.sizes() << endl;
cout << "ytest : " << ytest.sizes() << endl;
//
// STree
//
auto clf = pywrap::STree();
clf.fit(Xtrain, ytest);
double clf_score = clf.score(Xtest, ytest);
// auto stree = pywrap::STree();
// auto hyperparameters = json::parse("{\"C\": 0.7, \"max_iter\": 10000, \"kernel\": \"rbf\", \"random_state\": 17}");
// stree.setHyperparameters(hyperparameters);
// cout << "STree Version: " << clf.version() << endl;
// auto prediction = clf.predict(X);
// cout << "Prediction: " << endl << "{";
// for (int i = 0; i < prediction.size(0); ++i) {
// cout << prediction[i].item<int>() << ", ";
// }
// cout << "}" << endl;
//
// SVC
//
// auto svc = pywrap::SVC();
// cout << "SVC with hyperparameters" << endl;
// svc.fit(Xtrain, ytrain);
//
// Random Forest
//
// cout << "Building Random Forest" << endl;
// auto rf = pywrap::RandomForest();
// rf.fit(Xtrain, ytrain);
//
// XGBoost
//
// cout << "Building XGBoost" << endl;
// auto xg = pywrap::XGBoost();
// cout << "Fitting XGBoost" << endl;
// xg.fit(Xtrain, ytrain);
// double xg_score = xg.score(Xtest, ytest);
//
// Scoring
//
cout << "Scoring dataset: " << datasetName << endl;
cout << "Scores:" << endl;
cout << "STree Score ......: " << clf_score << endl;
// cout << "STree train/test .: " << clf.fit(Xtrain, ytrain).score(Xtest, ytest) << endl;
// cout << "STree hyper score : " << stree.fit(Xtrain, ytrain).score(Xtest, ytest) << endl;
// cout << "RandomForest Score: " << rf.score(Xtest, ytest) << endl;
// cout << "SVC Score ........: " << svc.score(Xtest, ytest) << endl;
// cout << "XGBoost Score ....: " << xg_score << endl;
using namespace torch::indexing;
map<string, pywrap::Classifier*> classifiers = {
{"STree", new pywrap::STree()}, {"SVC", new pywrap::SVC()},
{"RandomForest", new pywrap::RandomForest()},// {"XGBoost", new XGBoost()},
{"ODTE", new pywrap::ODTE()}
};
//
// Load dataset
//
auto datasetName = "wine";
bool class_last = false;
auto [X, y] = loadDataset(datasetName, class_last);
//
// Split train/test
//
auto [train_indices, test_indices] = get_train_test_indices(X.size(1));
auto Xtrain = X.index({ "...", train_indices });
auto ytrain = y.index({ train_indices });
auto Xtest = X.index({ "...", test_indices });
auto ytest = y.index({ test_indices });
cout << "Dataset: " << datasetName << endl;
cout << "X: " << X.sizes() << endl;
cout << "y: " << y.sizes() << endl;
cout << "Xtrain: " << Xtrain.sizes() << endl;
cout << "ytrain: " << ytrain.sizes() << endl;
cout << "Xtest : " << Xtest.sizes() << endl;
cout << "ytest : " << ytest.sizes() << endl;
//
// Train classifiers
//
for (auto& [name, clf] : classifiers) {
cout << "Training " << name << endl;
clf->fit(Xtrain, ytrain);
}
//
// Show scores
//
for (auto& [name, clf] : classifiers) {
cout << "Score " << setw(10) << name << "(Ver. " << clf->version() << "): "
<< clf->score(Xtest, ytest) << endl;
}
//
// Free classifiers
//
for (auto& [name, clf] : classifiers) {
delete clf;
}
cout << "* End." << endl;
}