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

Add Dataset, Models and DotEnv

Browse Source
This commit is contained in:
Ricardo Montañana Gómez
2023-07-29 16:21:38 +02:00
parent b03e84044a
commit 85cb447283
8 changed files with 160 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files

68
src/Platform/main.cc
View File

@@ -3,33 +3,37 @@
#include "platformUtils.h"
#include "Experiment.h"
#include "Datasets.h"
#include "DotEnv.h"
#include "Models.h"
using namespace std;
const string PATH_RESULTS = "results";
const string PATH_DATASETS = "datasets";
argparse::ArgumentParser manageArguments(int argc, char** argv)
{
auto env = platform::DotEnv();
argparse::ArgumentParser program("BayesNetSample");
program.add_argument("-d", "--dataset").default_value("").help("Dataset file name");
program.add_argument("-p", "--path")
.help("folder where the data files are located, default")
.default_value(string{ PATH }
.default_value(string{ PATH_DATASETS }
);
program.add_argument("-m", "--model")
.help("Model to use {AODE, KDB, SPODE, TAN}")
.help("Model to use " + platform::Models::toString())
.action([](const std::string& value) {
static const vector<string> choices = { "AODE", "KDB", "SPODE", "TAN" };
static const vector<string> choices = platform::Models::getNames();
if (find(choices.begin(), choices.end(), value) != choices.end()) {
return value;
}
throw runtime_error("Model must be one of {AODE, KDB, SPODE, TAN}");
throw runtime_error("Model must be one of " + platform::Models::toString());
}
);
program.add_argument("--title").required().help("Experiment title");
program.add_argument("--discretize").help("Discretize input dataset").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("-f", "--folds").help("Number of folds").default_value(5).scan<'i', int>().action([](const string& value) {
program.add_argument("--title").default_value("").help("Experiment title");
program.add_argument("--discretize").help("Discretize input dataset").default_value((bool)stoi(env.get("discretize"))).implicit_value(true);
program.add_argument("--stratified").help("If Stratified KFold is to be done").default_value((bool)stoi(env.get("stratified"))).implicit_value(true);
program.add_argument("-f", "--folds").help("Number of folds").default_value(stoi(env.get("n_folds"))).scan<'i', int>().action([](const string& value) {
try {
auto k = stoi(value);
if (k < 2) {
@@ -43,9 +47,11 @@ argparse::ArgumentParser manageArguments(int argc, char** argv)
catch (...) {
throw runtime_error("Number of folds must be an integer");
}});
program.add_argument("-s", "--seed").help("Random seed").default_value(-1).scan<'i', int>();
auto seed_values = env.getSeeds();
program.add_argument("-s", "--seeds").nargs(1, 10).help("Random seeds. Set to -1 to have pseudo random").scan<'i', int>().default_value(seed_values);
bool class_last, discretize_dataset, stratified;
int n_folds, seed;
int n_folds;
vector<int> seeds;
string model_name, file_name, path, complete_file_name, title;
try {
program.parse_args(argc, argv);
@@ -55,10 +61,13 @@ argparse::ArgumentParser manageArguments(int argc, char** argv)
discretize_dataset = program.get<bool>("discretize");
stratified = program.get<bool>("stratified");
n_folds = program.get<int>("folds");
seed = program.get<int>("seed");
seeds = program.get<vector<int>>("seeds");
complete_file_name = path + file_name + ".arff";
class_last = false;//datasets[file_name];
title = program.get<string>("title");
if (title == "" && file_name == "") {
throw runtime_error("title is mandatory if dataset is not provided");
}
}
catch (const exception& err) {
cerr << err.what() << endl;
@@ -71,25 +80,30 @@ argparse::ArgumentParser manageArguments(int argc, char** argv)
int main(int argc, char** argv)
{
auto program = manageArguments(argc, argv);
bool saveResults = false;
auto file_name = program.get<string>("dataset");
auto path = program.get<string>("path");
auto model_name = program.get<string>("model");
auto discretize_dataset = program.get<bool>("discretize");
auto stratified = program.get<bool>("stratified");
auto n_folds = program.get<int>("folds");
auto seed = program.get<int>("seed");
auto seeds = program.get<vector<int>>("seeds");
vector<string> filesToProcess;
auto datasets = platform::Datasets(path, true, platform::ARFF);
auto title = program.get<string>("title");
if (file_name != "") {
if (!datasets.isDataset(file_name)) {
cerr << "Dataset " << file_name << " not found" << endl;
exit(1);
}
if (title == "") {
title = "Test " + file_name + " " + model_name + " " + to_string(n_folds) + " folds";
}
filesToProcess.push_back(file_name);
} else {
filesToProcess = platform::Datasets(path, true, platform::ARFF).getNames();
saveResults = true;
}
auto title = program.get<string>("title");
/*
* Begin Processing
@@ -97,7 +111,10 @@ int main(int argc, char** argv)
auto experiment = platform::Experiment();
experiment.setTitle(title).setLanguage("cpp").setLanguageVersion("1.0.0");
experiment.setDiscretized(discretize_dataset).setModel(model_name).setPlatform("BayesNet");
experiment.setStratified(stratified).setNFolds(n_folds).addRandomSeed(seed).setScoreName("accuracy");
experiment.setStratified(stratified).setNFolds(n_folds).setScoreName("accuracy");
for (auto seed : seeds) {
experiment.addRandomSeed(seed);
}
platform::Timer timer;
cout << "*** Starting experiment: " << title << " ***" << endl;
timer.start();
@@ -109,16 +126,19 @@ int main(int argc, char** argv)
auto samples = datasets.getNSamples(fileName);
auto className = datasets.getClassName(fileName);
cout << " (" << setw(5) << samples << "," << setw(3) << features.size() << ") " << flush;
Fold* fold;
if (stratified)
fold = new StratifiedKFold(n_folds, y, seed);
else
fold = new KFold(n_folds, samples, seed);
auto result = platform::cross_validation(fold, model_name, X, y, features, className, states);
result.setDataset(fileName);
experiment.setModelVersion(result.getModelVersion());
experiment.addResult(result);
delete fold;
for (auto seed : seeds) {
cout << "(" << seed << ") " << flush;
Fold* fold;
if (stratified)
fold = new StratifiedKFold(n_folds, y, seed);
else
fold = new KFold(n_folds, samples, seed);
auto result = platform::cross_validation(fold, model_name, X, y, features, className, states);
result.setDataset(fileName);
experiment.setModelVersion(result.getModelVersion());
experiment.addResult(result);
delete fold;
}
}
experiment.setDuration(timer.getDuration());
experiment.save(PATH_RESULTS);