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

Add Python Classifiers

Browse Source 
Add STree, Odte, SVC & RandomForest Classifiers
Remove using namespace ... in project
This commit is contained in:
Ricardo Montañana Gómez
2023-11-17 11:11:05 +01:00
parent 64f5a7f14a e8d2c9fc0b
commit 28f3d87e32
116 changed files with 1981 additions and 1359 deletions
Download Patch File Download Diff File Expand all files Collapse all files

102
sample/sample.cc
View File

@@ -1,6 +1,6 @@
#include <iostream>
#include <torch/torch.h>
#include <string>
#include <std::string>
#include <map>
#include <argparse/argparse.hpp>
#include <nlohmann/json.hpp>
@@ -12,14 +12,12 @@
#include "modelRegister.h"
#include <fstream>
using namespace std;
const std::string PATH = "../../data/";
const string PATH = "../../data/";
pair<vector<mdlp::labels_t>, map<string, int>> discretize(vector<mdlp::samples_t>& X, mdlp::labels_t& y, vector<string> features)
pair<std::vector<mdlp::labels_t>, map<std::string, int>> discretize(std::vector<mdlp::samples_t>& X, mdlp::labels_t& y, std::vector<std::string> features)
{
vector<mdlp::labels_t>Xd;
map<string, int> maxes;
std::vector<mdlp::labels_t>Xd;
map<std::string, int> maxes;
auto fimdlp = mdlp::CPPFImdlp();
for (int i = 0; i < X.size(); i++) {
@@ -31,7 +29,7 @@ pair<vector<mdlp::labels_t>, map<string, int>> discretize(vector<mdlp::samples_t
return { Xd, maxes };
}
bool file_exists(const std::string& name)
bool file_exists(const std::std::std::string& name)
{
if (FILE* file = fopen(name.c_str(), "r")) {
fclose(file);
@@ -40,12 +38,12 @@ bool file_exists(const std::string& name)
return false;
}
}
pair<vector<vector<int>>, vector<int>> extract_indices(vector<int> indices, vector<vector<int>> X, vector<int> y)
pair<std::vector<std::vector<int>>, std::vector<int>> extract_indices(std::vector<int> indices, std::vector<std::vector<int>> X, std::vector<int> y)
{
vector<vector<int>> Xr; // nxm
vector<int> yr;
std::vector<std::vector<int>> Xr; // nxm
std::vector<int> yr;
for (int col = 0; col < X.size(); ++col) {
Xr.push_back(vector<int>());
Xr.push_back(std::vector<int>());
}
for (auto index : indices) {
for (int col = 0; col < X.size(); ++col) {
@@ -58,7 +56,7 @@ pair<vector<vector<int>>, vector<int>> extract_indices(vector<int> indices, vect
int main(int argc, char** argv)
{
map<string, bool> datasets = {
map<std::string, bool> datasets = {
{"diabetes", true},
{"ecoli", true},
{"glass", true},
@@ -68,13 +66,13 @@ int main(int argc, char** argv)
{"liver-disorders", true},
{"mfeat-factors", true},
};
auto valid_datasets = vector<string>();
auto valid_datasets = std::vector<std::string>();
transform(datasets.begin(), datasets.end(), back_inserter(valid_datasets),
[](const pair<string, bool>& pair) { return pair.first; });
[](const pair<std::string, bool>& pair) { return pair.first; });
argparse::ArgumentParser program("BayesNetSample");
program.add_argument("-d", "--dataset")
.help("Dataset file name")
.action([valid_datasets](const std::string& value) {
.action([valid_datasets](const std::std::std::string& value) {
if (find(valid_datasets.begin(), valid_datasets.end(), value) != valid_datasets.end()) {
return value;
}
@@ -83,23 +81,23 @@ int main(int argc, char** argv)
);
program.add_argument("-p", "--path")
.help(" folder where the data files are located, default")
.default_value(string{ PATH }
.default_value(std::string{ PATH }
);
program.add_argument("-m", "--model")
.help("Model to use " + platform::Models::instance()->toString())
.action([](const std::string& value) {
static const vector<string> choices = platform::Models::instance()->getNames();
.help("Model to use " + platform::Models::instance()->tostd::string())
.action([](const std::std::std::string& value) {
static const std::vector<std::string> choices = platform::Models::instance()->getNames();
if (find(choices.begin(), choices.end(), value) != choices.end()) {
return value;
}
throw runtime_error("Model must be one of " + platform::Models::instance()->toString());
throw runtime_error("Model must be one of " + platform::Models::instance()->tostd::string());
}
);
program.add_argument("--discretize").help("Discretize input dataset").default_value(false).implicit_value(true);
program.add_argument("--dumpcpt").help("Dump CPT Tables").default_value(false).implicit_value(true);
program.add_argument("--stratified").help("If Stratified KFold is to be done").default_value(false).implicit_value(true);
program.add_argument("--tensors").help("Use tensors to store samples").default_value(false).implicit_value(true);
program.add_argument("-f", "--folds").help("Number of folds").default_value(5).scan<'i', int>().action([](const string& value) {
program.add_argument("-f", "--folds").help("Number of folds").default_value(5).scan<'i', int>().action([](const std::std::string& value) {
try {
auto k = stoi(value);
if (k < 2) {
@@ -115,13 +113,13 @@ int main(int argc, char** argv)
}});
program.add_argument("-s", "--seed").help("Random seed").default_value(-1).scan<'i', int>();
bool class_last, stratified, tensors, dump_cpt;
string model_name, file_name, path, complete_file_name;
std::string model_name, file_name, path, complete_file_name;
int nFolds, seed;
try {
program.parse_args(argc, argv);
file_name = program.get<string>("dataset");
path = program.get<string>("path");
model_name = program.get<string>("model");
file_name = program.get<std::string>("dataset");
path = program.get<std::string>("path");
model_name = program.get<std::string>("model");
complete_file_name = path + file_name + ".arff";
stratified = program.get<bool>("stratified");
tensors = program.get<bool>("tensors");
@@ -134,7 +132,7 @@ int main(int argc, char** argv)
}
}
catch (const exception& err) {
cerr << err.what() << endl;
cerr << err.what() << std::endl;
cerr << program;
exit(1);
}
@@ -145,50 +143,50 @@ int main(int argc, char** argv)
auto handler = ArffFiles();
handler.load(complete_file_name, class_last);
// Get Dataset X, y
vector<mdlp::samples_t>& X = handler.getX();
std::vector<mdlp::samples_t>& X = handler.getX();
mdlp::labels_t& y = handler.getY();
// Get className & Features
auto className = handler.getClassName();
vector<string> features;
std::vector<std::string> features;
auto attributes = handler.getAttributes();
transform(attributes.begin(), attributes.end(), back_inserter(features),
[](const pair<string, string>& item) { return item.first; });
[](const pair<std::string, std::string>& item) { return item.first; });
// Discretize Dataset
auto [Xd, maxes] = discretize(X, y, features);
maxes[className] = *max_element(y.begin(), y.end()) + 1;
map<string, vector<int>> states;
map<std::string, std::vector<int>> states;
for (auto feature : features) {
states[feature] = vector<int>(maxes[feature]);
states[feature] = std::vector<int>(maxes[feature]);
}
states[className] = vector<int>(maxes[className]);
states[className] = std::vector<int>(maxes[className]);
auto clf = platform::Models::instance()->create(model_name);
clf->fit(Xd, y, features, className, states);
if (dump_cpt) {
cout << "--- CPT Tables ---" << endl;
std::cout << "--- CPT Tables ---" << std::endl;
clf->dump_cpt();
}
auto lines = clf->show();
for (auto line : lines) {
cout << line << endl;
std::cout << line << std::endl;
}
cout << "--- Topological Order ---" << endl;
std::cout << "--- Topological Order ---" << std::endl;
auto order = clf->topological_order();
for (auto name : order) {
cout << name << ", ";
std::cout << name << ", ";
}
cout << "end." << endl;
std::cout << "end." << std::endl;
auto score = clf->score(Xd, y);
cout << "Score: " << score << endl;
std::cout << "Score: " << score << std::endl;
auto graph = clf->graph();
auto dot_file = model_name + "_" + file_name;
ofstream file(dot_file + ".dot");
file << graph;
file.close();
cout << "Graph saved in " << model_name << "_" << file_name << ".dot" << endl;
cout << "dot -Tpng -o " + dot_file + ".png " + dot_file + ".dot " << endl;
string stratified_string = stratified ? " Stratified" : "";
cout << nFolds << " Folds" << stratified_string << " Cross validation" << endl;
cout << "==========================================" << endl;
std::cout << "Graph saved in " << model_name << "_" << file_name << ".dot" << std::endl;
std::cout << "dot -Tpng -o " + dot_file + ".png " + dot_file + ".dot " << std::endl;
std::string stratified_std::string = stratified ? " Stratified" : "";
std::cout << nFolds << " Folds" << stratified_std::string << " Cross validation" << std::endl;
std::cout << "==========================================" << std::endl;
torch::Tensor Xt = torch::zeros({ static_cast<int>(Xd.size()), static_cast<int>(Xd[0].size()) }, torch::kInt32);
torch::Tensor yt = torch::tensor(y, torch::kInt32);
for (int i = 0; i < features.size(); ++i) {
@@ -202,7 +200,7 @@ int main(int argc, char** argv)
fold = new platform::KFold(nFolds, y.size(), seed);
for (auto i = 0; i < nFolds; ++i) {
auto [train, test] = fold->getFold(i);
cout << "Fold: " << i + 1 << endl;
std::cout << "Fold: " << i + 1 << std::endl;
if (tensors) {
auto ttrain = torch::tensor(train, torch::kInt64);
auto ttest = torch::tensor(test, torch::kInt64);
@@ -222,16 +220,16 @@ int main(int argc, char** argv)
score_test = clf->score(Xtest, ytest);
}
if (dump_cpt) {
cout << "--- CPT Tables ---" << endl;
std::cout << "--- CPT Tables ---" << std::endl;
clf->dump_cpt();
}
total_score_train += score_train;
total_score += score_test;
cout << "Score Train: " << score_train << endl;
cout << "Score Test : " << score_test << endl;
cout << "-------------------------------------------------------------------------------" << endl;
std::cout << "Score Train: " << score_train << std::endl;
std::cout << "Score Test : " << score_test << std::endl;
std::cout << "-------------------------------------------------------------------------------" << std::endl;
}
cout << "**********************************************************************************" << endl;
cout << "Average Score Train: " << total_score_train / nFolds << endl;
cout << "Average Score Test : " << total_score / nFolds << endl;return 0;
std::cout << "**********************************************************************************" << std::endl;
std::cout << "Average Score Train: " << total_score_train / nFolds << std::endl;
std::cout << "Average Score Test : " << total_score / nFolds << std::endl;return 0;
}