rmontanana/BayesNet
rmontanana/BayesNet
1
0
Fork 0
Code Issues 2 Pull Requests Packages Projects Releases 3 Wiki Activity

Remove using namespace from Library

Browse Source
This commit is contained in:
Ricardo Montañana Gómez 2023-11-08 18:45:35 +01:00
parent 92820555da
commit f9258e43b9
Signed by: rmontanana
GPG Key ID: 46064262FD9A7ADE
96 changed files with 1316 additions and 1340 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
CMakeLists.txt
View File

@ -24,6 +24,7 @@ set(CMAKE_CXX_STANDARD_REQUIRED ON)
set(CMAKE_CXX_EXTENSIONS OFF)
set(CMAKE_EXPORT_COMPILE_COMMANDS ON)
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${TORCH_CXX_FLAGS}")
SET(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -pthread")
# Options
# -------
@ -41,11 +42,11 @@ if(Boost_FOUND)
include_directories(${Boost_INCLUDE_DIRS})
endif()
SET(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -pthread")
# CMakes modules
# --------------
set(CMAKE_MODULE_PATH ${CMAKE_CURRENT_SOURCE_DIR}/cmake/modules ${CMAKE_MODULE_PATH})
include(AddGitSubmodule)
if (CODE_COVERAGE)
enable_testing()
include(CodeCoverage)

76
lib/Files/ArffFiles.cc
View File

@ -4,11 +4,9 @@
#include <map>
#include <iostream>
using namespace std;
ArffFiles::ArffFiles() = default;
vector<string> ArffFiles::getLines() const
std::vector<std::string> ArffFiles::getLines() const
{
return lines;
}
@ -18,48 +16,48 @@ unsigned long int ArffFiles::getSize() const
return lines.size();
}
vector<pair<string, string>> ArffFiles::getAttributes() const
std::vector<std::pair<std::string, std::string>> ArffFiles::getAttributes() const
{
return attributes;
}
string ArffFiles::getClassName() const
std::string ArffFiles::getClassName() const
{
return className;
}
string ArffFiles::getClassType() const
std::string ArffFiles::getClassType() const
{
return classType;
}
vector<vector<float>>& ArffFiles::getX()
std::vector<std::vector<float>>& ArffFiles::getX()
{
return X;
}
vector<int>& ArffFiles::getY()
std::vector<int>& ArffFiles::getY()
{
return y;
}
void ArffFiles::loadCommon(string fileName)
void ArffFiles::loadCommon(std::string fileName)
{
ifstream file(fileName);
std::ifstream file(fileName);
if (!file.is_open()) {
throw invalid_argument("Unable to open file");
throw std::invalid_argument("Unable to open file");
}
string line;
string keyword;
string attribute;
string type;
string type_w;
std::string line;
std::string keyword;
std::string attribute;
std::string type;
std::string type_w;
while (getline(file, line)) {
if (line.empty() || line[0] == '%' || line == "\r" || line == " ") {
continue;
}
if (line.find("@attribute") != string::npos || line.find("@ATTRIBUTE") != string::npos) {
stringstream ss(line);
if (line.find("@attribute") != std::string::npos || line.find("@ATTRIBUTE") != std::string::npos) {
std::stringstream ss(line);
ss >> keyword >> attribute;
type = "";
while (ss >> type_w)
@ -74,35 +72,35 @@ void ArffFiles::loadCommon(string fileName)
}
file.close();
if (attributes.empty())
throw invalid_argument("No attributes found");
throw std::invalid_argument("No attributes found");
}
void ArffFiles::load(const string& fileName, bool classLast)
void ArffFiles::load(const std::string& fileName, bool classLast)
{
int labelIndex;
loadCommon(fileName);
if (classLast) {
className = get<0>(attributes.back());
classType = get<1>(attributes.back());
className = std::get<0>(attributes.back());
classType = std::get<1>(attributes.back());
attributes.pop_back();
labelIndex = static_cast<int>(attributes.size());
} else {
className = get<0>(attributes.front());
classType = get<1>(attributes.front());
className = std::get<0>(attributes.front());
classType = std::get<1>(attributes.front());
attributes.erase(attributes.begin());
labelIndex = 0;
}
generateDataset(labelIndex);
}
void ArffFiles::load(const string& fileName, const string& name)
void ArffFiles::load(const std::string& fileName, const std::string& name)
{
int labelIndex;
loadCommon(fileName);
bool found = false;
for (int i = 0; i < attributes.size(); ++i) {
if (attributes[i].first == name) {
className = get<0>(attributes[i]);
classType = get<1>(attributes[i]);
className = std::get<0>(attributes[i]);
classType = std::get<1>(attributes[i]);
attributes.erase(attributes.begin() + i);
labelIndex = i;
found = true;
@ -110,19 +108,19 @@ void ArffFiles::load(const string& fileName, const string& name)
}
}
if (!found) {
throw invalid_argument("Class name not found");
throw std::invalid_argument("Class name not found");
}
generateDataset(labelIndex);
}
void ArffFiles::generateDataset(int labelIndex)
{
X = vector<vector<float>>(attributes.size(), vector<float>(lines.size()));
auto yy = vector<string>(lines.size(), "");
auto removeLines = vector<int>(); // Lines with missing values
X = std::vector<std::vector<float>>(attributes.size(), std::vector<float>(lines.size()));
auto yy = std::vector<std::string>(lines.size(), "");
auto removeLines = std::vector<int>(); // Lines with missing values
for (size_t i = 0; i < lines.size(); i++) {
stringstream ss(lines[i]);
string value;
std::stringstream ss(lines[i]);
std::string value;
int pos = 0;
int xIndex = 0;
while (getline(ss, value, ',')) {
@ -146,21 +144,21 @@ void ArffFiles::generateDataset(int labelIndex)
y = factorize(yy);
}
string ArffFiles::trim(const string& source)
std::string ArffFiles::trim(const std::string& source)
{
string s(source);
std::string s(source);
s.erase(0, s.find_first_not_of(" '\n\r\t"));
s.erase(s.find_last_not_of(" '\n\r\t") + 1);
return s;
}
vector<int> ArffFiles::factorize(const vector<string>& labels_t)
std::vector<int> ArffFiles::factorize(const std::vector<std::string>& labels_t)
{
vector<int> yy;
std::vector<int> yy;
yy.reserve(labels_t.size());
map<string, int> labelMap;
std::map<std::string, int> labelMap;
int i = 0;
for (const string& label : labels_t) {
for (const std::string& label : labels_t) {
if (labelMap.find(label) == labelMap.end()) {
labelMap[label] = i++;
}

36
lib/Files/ArffFiles.h
View File

@ -4,31 +4,29 @@
#include <string>
#include <vector>
using namespace std;
class ArffFiles {
private:
vector<string> lines;
vector<pair<string, string>> attributes;
string className;
string classType;
vector<vector<float>> X;
vector<int> y;
std::vector<std::string> lines;
std::vector<std::pair<std::string, std::string>> attributes;
std::string className;
std::string classType;
std::vector<std::vector<float>> X;
std::vector<int> y;
void generateDataset(int);
void loadCommon(string);
void loadCommon(std::string);
public:
ArffFiles();
void load(const string&, bool = true);
void load(const string&, const string&);
vector<string> getLines() const;
void load(const std::string&, bool = true);
void load(const std::string&, const std::string&);
std::vector<std::string> getLines() const;
unsigned long int getSize() const;
string getClassName() const;
string getClassType() const;
static string trim(const string&);
vector<vector<float>>& getX();
vector<int>& getY();
vector<pair<string, string>> getAttributes() const;
static vector<int> factorize(const vector<string>& labels_t);
std::string getClassName() const;
std::string getClassType() const;
static std::string trim(const std::string&);
std::vector<std::vector<float>>& getX();
std::vector<int>& getY();
std::vector<std::pair<std::string, std::string>> getAttributes() const;
static std::vector<int> factorize(const std::vector<std::string>& labels_t);
};
#endif

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;
}

4
src/BayesNet/AODE.cc
View File

@ -9,9 +9,9 @@ namespace bayesnet {
models.push_back(std::make_unique<SPODE>(i));
}
n_models = models.size();
significanceModels = vector<double>(n_models, 1.0);
significanceModels = std::vector<double>(n_models, 1.0);
}
vector<string> AODE::graph(const string& title) const
std::vector<std::string> AODE::graph(const std::string& title) const
{
return Ensemble::graph(title);
}

2
src/BayesNet/AODE.h
View File

@ -9,7 +9,7 @@ namespace bayesnet {
public:
AODE();
virtual ~AODE() {};
vector<string> graph(const string& title = "AODE") const override;
std::vector<std::string> graph(const std::string& title = "AODE") const override;
};
}
#endif

9
src/BayesNet/AODELd.cc
View File

@ -2,16 +2,15 @@
#include "Models.h"
namespace bayesnet {
using namespace std;
AODELd::AODELd() : Ensemble(), Proposal(dataset, features, className) {}
AODELd& AODELd::fit(torch::Tensor& X_, torch::Tensor& y_, const vector<string>& features_, const string& className_, map<string, vector<int>>& states_)
AODELd& AODELd::fit(torch::Tensor& X_, torch::Tensor& y_, const std::vector<std::string>& features_, const std::string& className_, map<std::string, std::vector<int>>& states_)
{
checkInput(X_, y_);
features = features_;
className = className_;
Xf = X_;
y = y_;
// Fills vectors Xv & yv with the data from tensors X_ (discretized) & y
// Fills std::vectors Xv & yv with the data from tensors X_ (discretized) & y
states = fit_local_discretization(y);
// We have discretized the input data
// 1st we need to fit the model to build the normal TAN structure, TAN::fit initializes the base Bayesian network
@ -26,7 +25,7 @@ namespace bayesnet {
models.push_back(std::make_unique<SPODELd>(i));
}
n_models = models.size();
significanceModels = vector<double>(n_models, 1.0);
significanceModels = std::vector<double>(n_models, 1.0);
}
void AODELd::trainModel(const torch::Tensor& weights)
{
@ -34,7 +33,7 @@ namespace bayesnet {
model->fit(Xf, y, features, className, states);
}
}
vector<string> AODELd::graph(const string& name) const
std::vector<std::string> AODELd::graph(const std::string& name) const
{
return Ensemble::graph(name);
}

7
src/BayesNet/AODELd.h
View File

@ -5,17 +5,16 @@
#include "SPODELd.h"
namespace bayesnet {
using namespace std;
class AODELd : public Ensemble, public Proposal {
protected:
void trainModel(const torch::Tensor& weights) override;
void buildModel(const torch::Tensor& weights) override;
public:
AODELd();
AODELd& fit(torch::Tensor& X_, torch::Tensor& y_, const vector<string>& features_, const string& className_, map<string, vector<int>>& states_) override;
AODELd& fit(torch::Tensor& X_, torch::Tensor& y_, const std::vector<std::string>& features_, const std::string& className_, map<std::string, std::vector<int>>& states_) override;
virtual ~AODELd() = default;
vector<string> graph(const string& name = "AODELd") const override;
static inline string version() { return "0.0.1"; };
std::vector<std::string> graph(const std::string& name = "AODELd") const override;
static inline std::string version() { return "0.0.1"; };
};
}
#endif // !AODELD_H

23
src/BayesNet/BaseClassifier.h
View File

@ -4,31 +4,30 @@
#include <nlohmann/json.hpp>
#include <vector>
namespace bayesnet {
using namespace std;
enum status_t { NORMAL, WARNING, ERROR };
class BaseClassifier {
protected:
virtual void trainModel(const torch::Tensor& weights) = 0;
public:
// X is nxm vector, y is nx1 vector
virtual BaseClassifier& fit(vector<vector<int>>& X, vector<int>& y, const vector<string>& features, const string& className, map<string, vector<int>>& states) = 0;
// 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) = 0;
// X is nxm tensor, y is nx1 tensor
virtual BaseClassifier& fit(torch::Tensor& X, torch::Tensor& y, const vector<string>& features, const string& className, map<string, vector<int>>& states) = 0;
virtual BaseClassifier& fit(torch::Tensor& dataset, const vector<string>& features, const string& className, map<string, vector<int>>& states) = 0;
virtual BaseClassifier& fit(torch::Tensor& dataset, const vector<string>& features, const string& className, map<string, vector<int>>& states, const torch::Tensor& weights) = 0;
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) = 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) = 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) = 0;
virtual ~BaseClassifier() = default;
torch::Tensor virtual predict(torch::Tensor& X) = 0;
vector<int> virtual predict(vector<vector<int>>& X) = 0;
std::vector<int> virtual predict(std::vector<std::vector<int >>& X) = 0;
status_t virtual getStatus() const = 0;
float virtual score(vector<vector<int>>& X, vector<int>& y) = 0;
float virtual score(std::vector<std::vector<int>>& X, std::vector<int>& y) = 0;
float virtual score(torch::Tensor& X, torch::Tensor& y) = 0;
int virtual getNumberOfNodes()const = 0;
int virtual getNumberOfEdges()const = 0;
int virtual getNumberOfStates() const = 0;
vector<string> virtual show() const = 0;
vector<string> virtual graph(const string& title = "") const = 0;
const string inline getVersion() const { return "0.2.0"; };
vector<string> virtual topological_order() = 0;
std::vector<std::string> virtual show() const = 0;
std::vector<std::string> virtual graph(const std::string& title = "") const = 0;
const std::string inline getVersion() const { return "0.2.0"; };
std::vector<std::string> virtual topological_order() = 0;
void virtual dump_cpt()const = 0;
virtual void setHyperparameters(nlohmann::json& hyperparameters) = 0;
};

20
src/BayesNet/BayesMetrics.cc
View File

@ -2,15 +2,15 @@
#include "Mst.h"
namespace bayesnet {
//samples is n+1xm tensor used to fit the model
Metrics::Metrics(const torch::Tensor& samples, const vector<string>& features, const string& className, const int classNumStates)
Metrics::Metrics(const torch::Tensor& samples, const std::vector<std::string>& features, const std::string& className, const int classNumStates)
: samples(samples)
, features(features)
, className(className)
, classNumStates(classNumStates)
{
}
//samples is nxm vector used to fit the model
Metrics::Metrics(const vector<vector<int>>& vsamples, const vector<int>& labels, const vector<string>& features, const string& className, const int classNumStates)
//samples is nxm std::vector used to fit the model
Metrics::Metrics(const std::vector<std::vector<int>>& vsamples, const std::vector<int>& labels, const std::vector<std::string>& features, const std::string& className, const int classNumStates)
: features(features)
, className(className)
, classNumStates(classNumStates)
@ -21,7 +21,7 @@ namespace bayesnet {
}
samples.index_put_({ -1, "..." }, torch::tensor(labels, torch::kInt32));
}
vector<int> Metrics::SelectKBestWeighted(const torch::Tensor& weights, bool ascending, unsigned k)
std::vector<int> Metrics::SelectKBestWeighted(const torch::Tensor& weights, bool ascending, unsigned k)
{
// Return the K Best features
auto n = samples.size(0) - 1;
@ -56,15 +56,15 @@ namespace bayesnet {
}
return featuresKBest;
}
vector<double> Metrics::getScoresKBest() const
std::vector<double> Metrics::getScoresKBest() const
{
return scoresKBest;
}
torch::Tensor Metrics::conditionalEdge(const torch::Tensor& weights)
{
auto result = vector<double>();
auto source = vector<string>(features);
auto result = std::vector<double>();
auto source = std::vector<std::string>(features);
source.push_back(className);
auto combinations = doCombinations(source);
// Compute class prior
@ -100,7 +100,7 @@ namespace bayesnet {
return matrix;
}
// To use in Python
vector<float> Metrics::conditionalEdgeWeights(vector<float>& weights_)
std::vector<float> Metrics::conditionalEdgeWeights(std::vector<float>& weights_)
{
const torch::Tensor weights = torch::tensor(weights_);
auto matrix = conditionalEdge(weights);
@ -121,7 +121,7 @@ namespace bayesnet {
{
int numSamples = firstFeature.sizes()[0];
torch::Tensor featureCounts = secondFeature.bincount(weights);
unordered_map<int, unordered_map<int, double>> jointCounts;
std::unordered_map<int, std::unordered_map<int, double>> jointCounts;
double totalWeight = 0;
for (auto i = 0; i < numSamples; i++) {
jointCounts[secondFeature[i].item<int>()][firstFeature[i].item<int>()] += weights[i].item<double>();
@ -155,7 +155,7 @@ namespace bayesnet {
and the indices of the weights as nodes of this square matrix using
Kruskal algorithm
*/
vector<pair<int, int>> Metrics::maximumSpanningTree(const vector<string>& features, const Tensor& weights, const int root)
std::vector<std::pair<int, int>> Metrics::maximumSpanningTree(const std::vector<std::string>& features, const torch::Tensor& weights, const int root)
{
auto mst = MST(features, weights, root);
return mst.maximumSpanningTree();

38
src/BayesNet/BayesMetrics.h
View File

@ -4,23 +4,21 @@
#include <vector>
#include <string>
namespace bayesnet {
using namespace std;
using namespace torch;
class Metrics {
private:
int classNumStates = 0;
vector<double> scoresKBest;
vector<int> featuresKBest; // sorted indices of the features
double conditionalEntropy(const Tensor& firstFeature, const Tensor& secondFeature, const Tensor& weights);
std::vector<double> scoresKBest;
std::vector<int> featuresKBest; // sorted indices of the features
double conditionalEntropy(const torch::Tensor& firstFeature, const torch::Tensor& secondFeature, const torch::Tensor& weights);
protected:
Tensor samples; // n+1xm tensor used to fit the model where samples[-1] is the y vector
string className;
double entropy(const Tensor& feature, const Tensor& weights);
vector<string> features;
torch::Tensor samples; // n+1xm torch::Tensor used to fit the model where samples[-1] is the y std::vector
std::string className;
double entropy(const torch::Tensor& feature, const torch::Tensor& weights);
std::vector<std::string> features;
template <class T>
vector<pair<T, T>> doCombinations(const vector<T>& source)
std::vector<std::pair<T, T>> doCombinations(const std::vector<T>& source)
{
vector<pair<T, T>> result;
std::vector<std::pair<T, T>> result;
for (int i = 0; i < source.size(); ++i) {
T temp = source[i];
for (int j = i + 1; j < source.size(); ++j) {
@ -30,7 +28,7 @@ namespace bayesnet {
return result;
}
template <class T>
T pop_first(vector<T>& v)
T pop_first(std::vector<T>& v)
{
T temp = v[0];
v.erase(v.begin());
@ -38,14 +36,14 @@ namespace bayesnet {
}
public:
Metrics() = default;
Metrics(const torch::Tensor& samples, const vector<string>& features, const string& className, const int classNumStates);
Metrics(const vector<vector<int>>& vsamples, const vector<int>& labels, const vector<string>& features, const string& className, const int classNumStates);
vector<int> SelectKBestWeighted(const torch::Tensor& weights, bool ascending = false, unsigned k = 0);
vector<double> getScoresKBest() const;
double mutualInformation(const Tensor& firstFeature, const Tensor& secondFeature, const Tensor& weights);
vector<float> conditionalEdgeWeights(vector<float>& weights); // To use in Python
Tensor conditionalEdge(const torch::Tensor& weights);
vector<pair<int, int>> maximumSpanningTree(const vector<string>& features, const Tensor& weights, const int root);
Metrics(const torch::Tensor& samples, const std::vector<std::string>& features, const std::string& className, const int classNumStates);
Metrics(const std::vector<std::vector<int>>& vsamples, const std::vector<int>& labels, const std::vector<std::string>& features, const std::string& className, const int classNumStates);
std::vector<int> SelectKBestWeighted(const torch::Tensor& weights, bool ascending = false, unsigned k = 0);
std::vector<double> getScoresKBest() const;
double mutualInformation(const torch::Tensor& firstFeature, const torch::Tensor& secondFeature, const torch::Tensor& weights);
std::vector<float> conditionalEdgeWeights(std::vector<float>& weights); // To use in Python
torch::Tensor conditionalEdge(const torch::Tensor& weights);
std::vector<std::pair<int, int>> maximumSpanningTree(const std::vector<std::string>& features, const torch::Tensor& weights, const int root);
};
}
#endif

32
src/BayesNet/BoostAODE.cc
View File

@ -46,7 +46,7 @@ namespace bayesnet {
void BoostAODE::setHyperparameters(nlohmann::json& hyperparameters)
{
// Check if hyperparameters are valid
const vector<string> validKeys = { "repeatSparent", "maxModels", "ascending", "convergence", "threshold", "select_features" };
const std::vector<std::string> validKeys = { "repeatSparent", "maxModels", "ascending", "convergence", "threshold", "select_features" };
checkHyperparameters(validKeys, hyperparameters);
if (hyperparameters.contains("repeatSparent")) {
repeatSparent = hyperparameters["repeatSparent"];
@ -65,38 +65,38 @@ namespace bayesnet {
}
if (hyperparameters.contains("select_features")) {
auto selectedAlgorithm = hyperparameters["select_features"];
vector<string> algos = { "IWSS", "FCBF", "CFS" };
std::vector<std::string> algos = { "IWSS", "FCBF", "CFS" };
selectFeatures = true;
algorithm = selectedAlgorithm;
if (find(algos.begin(), algos.end(), selectedAlgorithm) == algos.end()) {
throw invalid_argument("Invalid selectFeatures value [IWSS, FCBF, CFS]");
if (std::find(algos.begin(), algos.end(), selectedAlgorithm) == algos.end()) {
throw std::invalid_argument("Invalid selectFeatures value [IWSS, FCBF, CFS]");
}
}
}
unordered_set<int> BoostAODE::initializeModels()
std::unordered_set<int> BoostAODE::initializeModels()
{
unordered_set<int> featuresUsed;
Tensor weights_ = torch::full({ m }, 1.0 / m, torch::kFloat64);
std::unordered_set<int> featuresUsed;
torch::Tensor weights_ = torch::full({ m }, 1.0 / m, torch::kFloat64);
int maxFeatures = 0;
if (algorithm == "CFS") {
featureSelector = new CFS(dataset, features, className, maxFeatures, states.at(className).size(), weights_);
} else if (algorithm == "IWSS") {
if (threshold < 0 || threshold >0.5) {
throw invalid_argument("Invalid threshold value for IWSS [0, 0.5]");
throw std::invalid_argument("Invalid threshold value for IWSS [0, 0.5]");
}
featureSelector = new IWSS(dataset, features, className, maxFeatures, states.at(className).size(), weights_, threshold);
} else if (algorithm == "FCBF") {
if (threshold < 1e-7 || threshold > 1) {
throw invalid_argument("Invalid threshold value [1e-7, 1]");
throw std::invalid_argument("Invalid threshold value [1e-7, 1]");
}
featureSelector = new FCBF(dataset, features, className, maxFeatures, states.at(className).size(), weights_, threshold);
}
featureSelector->fit();
auto cfsFeatures = featureSelector->getFeatures();
for (const int& feature : cfsFeatures) {
// cout << "Feature: [" << feature << "] " << feature << " " << features.at(feature) << endl;
// std::cout << "Feature: [" << feature << "] " << feature << " " << features.at(feature) << std::endl;
featuresUsed.insert(feature);
unique_ptr<Classifier> model = std::make_unique<SPODE>(feature);
std::unique_ptr<Classifier> model = std::make_unique<SPODE>(feature);
model->fit(dataset, features, className, states, weights_);
models.push_back(std::move(model));
significanceModels.push_back(1.0);
@ -107,13 +107,13 @@ namespace bayesnet {
}
void BoostAODE::trainModel(const torch::Tensor& weights)
{
unordered_set<int> featuresUsed;
std::unordered_set<int> featuresUsed;
if (selectFeatures) {
featuresUsed = initializeModels();
}
if (maxModels == 0)
maxModels = .1 * n > 10 ? .1 * n : n;
Tensor weights_ = torch::full({ m }, 1.0 / m, torch::kFloat64);
torch::Tensor weights_ = torch::full({ m }, 1.0 / m, torch::kFloat64);
bool exitCondition = false;
// Variables to control the accuracy finish condition
double priorAccuracy = 0.0;
@ -130,12 +130,12 @@ namespace bayesnet {
while (!exitCondition) {
// Step 1: Build ranking with mutual information
auto featureSelection = metrics.SelectKBestWeighted(weights_, ascending, n); // Get all the features sorted
unique_ptr<Classifier> model;
std::unique_ptr<Classifier> model;
auto feature = featureSelection[0];
if (!repeatSparent || featuresUsed.size() < featureSelection.size()) {
bool used = true;
for (const auto& feat : featureSelection) {
if (find(featuresUsed.begin(), featuresUsed.end(), feat) != featuresUsed.end()) {
if (std::find(featuresUsed.begin(), featuresUsed.end(), feat) != featuresUsed.end()) {
continue;
}
used = false;
@ -188,7 +188,7 @@ namespace bayesnet {
status = WARNING;
}
}
vector<string> BoostAODE::graph(const string& title) const
std::vector<std::string> BoostAODE::graph(const std::string& title) const
{
return Ensemble::graph(title);
}

6
src/BayesNet/BoostAODE.h
View File

@ -9,7 +9,7 @@ namespace bayesnet {
public:
BoostAODE();
virtual ~BoostAODE() {};
vector<string> graph(const string& title = "BoostAODE") const override;
std::vector<std::string> graph(const std::string& title = "BoostAODE") const override;
void setHyperparameters(nlohmann::json& hyperparameters) override;
protected:
void buildModel(const torch::Tensor& weights) override;
@ -17,14 +17,14 @@ namespace bayesnet {
private:
torch::Tensor dataset_;
torch::Tensor X_train, y_train, X_test, y_test;
unordered_set<int> initializeModels();
std::unordered_set<int> initializeModels();
// Hyperparameters
bool repeatSparent = false; // if true, a feature can be selected more than once
int maxModels = 0;
bool ascending = false; //Process KBest features ascending or descending order
bool convergence = false; //if true, stop when the model does not improve
bool selectFeatures = false; // if true, use feature selection
string algorithm = ""; // Selected feature selection algorithm
std::string algorithm = ""; // Selected feature selection algorithm
FeatureSelect* featureSelector = nullptr;
double threshold = -1;
};

10
src/BayesNet/CFS.cc
View File

@ -13,7 +13,7 @@ namespace bayesnet {
selectedScores.push_back(suLabels[feature]);
selectedFeatures.erase(selectedFeatures.begin());
while (continueCondition) {
double merit = numeric_limits<double>::lowest();
double merit = std::numeric_limits<double>::lowest();
int bestFeature = -1;
for (auto feature : featureOrder) {
selectedFeatures.push_back(feature);
@ -36,7 +36,7 @@ namespace bayesnet {
}
fitted = true;
}
bool CFS::computeContinueCondition(const vector<int>& featureOrder)
bool CFS::computeContinueCondition(const std::vector<int>& featureOrder)
{
if (selectedFeatures.size() == maxFeatures || featureOrder.size() == 0) {
return false;
@ -49,11 +49,11 @@ namespace bayesnet {
subsets show no improvement over the current best subset."
as stated in Mark A.Hall Thesis
*/
double item_ant = numeric_limits<double>::lowest();
double item_ant = std::numeric_limits<double>::lowest();
int num = 0;
vector<double> lastFive(selectedScores.end() - 5, selectedScores.end());
std::vector<double> lastFive(selectedScores.end() - 5, selectedScores.end());
for (auto item : lastFive) {
if (item_ant == numeric_limits<double>::lowest()) {
if (item_ant == std::numeric_limits<double>::lowest()) {
item_ant = item;
}
if (item > item_ant) {

7
src/BayesNet/CFS.h
View File

@ -3,19 +3,18 @@
#include <torch/torch.h>
#include <vector>
#include "FeatureSelect.h"
using namespace std;
namespace bayesnet {
class CFS : public FeatureSelect {
public:
// dataset is a n+1xm tensor of integers where dataset[-1] is the y vector
CFS(const torch::Tensor& samples, const vector<string>& features, const string& className, const int maxFeatures, const int classNumStates, const torch::Tensor& weights) :
// dataset is a n+1xm tensor of integers where dataset[-1] is the y std::vector
CFS(const torch::Tensor& samples, const std::vector<std::string>& features, const std::string& className, const int maxFeatures, const int classNumStates, const torch::Tensor& weights) :
FeatureSelect(samples, features, className, maxFeatures, classNumStates, weights)
{
}
virtual ~CFS() {};
void fit() override;
private:
bool computeContinueCondition(const vector<int>& featureOrder);
bool computeContinueCondition(const std::vector<int>& featureOrder);
};
}
#endif

64
src/BayesNet/Classifier.cc
View File

@ -2,10 +2,8 @@
#include "bayesnetUtils.h"
namespace bayesnet {
using namespace torch;
Classifier::Classifier(Network model) : model(model), m(0), n(0), metrics(Metrics()), fitted(false) {}
Classifier& Classifier::build(const vector<string>& features, const string& className, map<string, vector<int>>& states, const torch::Tensor& weights)
Classifier& Classifier::build(const std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states, const torch::Tensor& weights)
{
this->features = features;
this->className = className;
@ -21,7 +19,7 @@ namespace bayesnet {
fitted = true;
return *this;
}
void Classifier::buildDataset(Tensor& ytmp)
void Classifier::buildDataset(torch::Tensor& ytmp)
{
try {
auto yresized = torch::transpose(ytmp.view({ ytmp.size(0), 1 }), 0, 1);
@ -29,8 +27,8 @@ namespace bayesnet {
}
catch (const std::exception& e) {
std::cerr << e.what() << '\n';
cout << "X dimensions: " << dataset.sizes() << "\n";
cout << "y dimensions: " << ytmp.sizes() << "\n";
std::cout << "X dimensions: " << dataset.sizes() << "\n";
std::cout << "y dimensions: " << ytmp.sizes() << "\n";
exit(1);
}
}
@ -39,7 +37,7 @@ namespace bayesnet {
model.fit(dataset, weights, features, className, states);
}
// X is nxm where n is the number of features and m the number of samples
Classifier& Classifier::fit(torch::Tensor& X, torch::Tensor& y, const vector<string>& features, const string& className, map<string, vector<int>>& states)
Classifier& Classifier::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)
{
dataset = X;
buildDataset(y);
@ -47,24 +45,24 @@ namespace bayesnet {
return build(features, className, states, weights);
}
// X is nxm where n is the number of features and m the number of samples
Classifier& Classifier::fit(vector<vector<int>>& X, vector<int>& y, const vector<string>& features, const string& className, map<string, vector<int>>& states)
Classifier& Classifier::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)
{
dataset = torch::zeros({ static_cast<int>(X.size()), static_cast<int>(X[0].size()) }, kInt32);
dataset = torch::zeros({ static_cast<int>(X.size()), static_cast<int>(X[0].size()) }, torch::kInt32);
for (int i = 0; i < X.size(); ++i) {
dataset.index_put_({ i, "..." }, torch::tensor(X[i], kInt32));
dataset.index_put_({ i, "..." }, torch::tensor(X[i], torch::kInt32));
}
auto ytmp = torch::tensor(y, kInt32);
auto ytmp = torch::tensor(y, torch::kInt32);
buildDataset(ytmp);
const torch::Tensor weights = torch::full({ dataset.size(1) }, 1.0 / dataset.size(1), torch::kDouble);
return build(features, className, states, weights);
}
Classifier& Classifier::fit(torch::Tensor& dataset, const vector<string>& features, const string& className, map<string, vector<int>>& states)
Classifier& Classifier::fit(torch::Tensor& dataset, const std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states)
{
this->dataset = dataset;
const torch::Tensor weights = torch::full({ dataset.size(1) }, 1.0 / dataset.size(1), torch::kDouble);
return build(features, className, states, weights);
}
Classifier& Classifier::fit(torch::Tensor& dataset, const vector<string>& features, const string& className, map<string, vector<int>>& states, const torch::Tensor& weights)
Classifier& Classifier::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)
{
this->dataset = dataset;
return build(features, className, states, weights);
@ -72,57 +70,57 @@ namespace bayesnet {
void Classifier::checkFitParameters()
{
if (torch::is_floating_point(dataset)) {
throw invalid_argument("dataset (X, y) must be of type Integer");
throw std::invalid_argument("dataset (X, y) must be of type Integer");
}
if (n != features.size()) {
throw invalid_argument("Classifier: X " + to_string(n) + " and features " + to_string(features.size()) + " must have the same number of features");
throw std::invalid_argument("Classifier: X " + std::to_string(n) + " and features " + std::to_string(features.size()) + " must have the same number of features");
}
if (states.find(className) == states.end()) {
throw invalid_argument("className not found in states");
throw std::invalid_argument("className not found in states");
}
for (auto feature : features) {
if (states.find(feature) == states.end()) {
throw invalid_argument("feature [" + feature + "] not found in states");
throw std::invalid_argument("feature [" + feature + "] not found in states");
}
}
}
Tensor Classifier::predict(Tensor& X)
torch::Tensor Classifier::predict(torch::Tensor& X)
{
if (!fitted) {
throw logic_error("Classifier has not been fitted");
throw std::logic_error("Classifier has not been fitted");
}
return model.predict(X);
}
vector<int> Classifier::predict(vector<vector<int>>& X)
std::vector<int> Classifier::predict(std::vector<std::vector<int>>& X)
{
if (!fitted) {
throw logic_error("Classifier has not been fitted");
throw std::logic_error("Classifier has not been fitted");
}
auto m_ = X[0].size();
auto n_ = X.size();
vector<vector<int>> Xd(n_, vector<int>(m_, 0));
std::vector<std::vector<int>> Xd(n_, std::vector<int>(m_, 0));
for (auto i = 0; i < n_; i++) {
Xd[i] = vector<int>(X[i].begin(), X[i].end());
Xd[i] = std::vector<int>(X[i].begin(), X[i].end());
}
auto yp = model.predict(Xd);
return yp;
}
float Classifier::score(Tensor& X, Tensor& y)
float Classifier::score(torch::Tensor& X, torch::Tensor& y)
{
if (!fitted) {
throw logic_error("Classifier has not been fitted");
throw std::logic_error("Classifier has not been fitted");
}
Tensor y_pred = predict(X);
torch::Tensor y_pred = predict(X);
return (y_pred == y).sum().item<float>() / y.size(0);
}
float Classifier::score(vector<vector<int>>& X, vector<int>& y)
float Classifier::score(std::vector<std::vector<int>>& X, std::vector<int>& y)
{
if (!fitted) {
throw logic_error("Classifier has not been fitted");
throw std::logic_error("Classifier has not been fitted");
}
return model.score(X, y);
}
vector<string> Classifier::show() const
std::vector<std::string> Classifier::show() const
{
return model.show();
}
@ -147,7 +145,7 @@ namespace bayesnet {
{
return fitted ? model.getStates() : 0;
}
vector<string> Classifier::topological_order()
std::vector<std::string> Classifier::topological_order()
{
return model.topological_sort();
}
@ -155,18 +153,18 @@ namespace bayesnet {
{
model.dump_cpt();
}
void Classifier::checkHyperparameters(const vector<string>& validKeys, nlohmann::json& hyperparameters)
void Classifier::checkHyperparameters(const std::vector<std::string>& validKeys, nlohmann::json& hyperparameters)
{
for (const auto& item : hyperparameters.items()) {
if (find(validKeys.begin(), validKeys.end(), item.key()) == validKeys.end()) {
throw invalid_argument("Hyperparameter " + item.key() + " is not valid");
throw std::invalid_argument("Hyperparameter " + item.key() + " is not valid");
}
}
}
void Classifier::setHyperparameters(nlohmann::json& hyperparameters)
{
// Check if hyperparameters are valid, default is no hyperparameters
const vector<string> validKeys = { };
const std::vector<std::string> validKeys = { };
checkHyperparameters(validKeys, hyperparameters);
}
}

34
src/BayesNet/Classifier.h
View File

@ -4,46 +4,44 @@
#include "BaseClassifier.h"
#include "Network.h"
#include "BayesMetrics.h"
using namespace std;
using namespace torch;
namespace bayesnet {
class Classifier : public BaseClassifier {
private:
Classifier& build(const vector<string>& features, const string& className, map<string, vector<int>>& states, const torch::Tensor& weights);
Classifier& build(const std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states, const torch::Tensor& weights);
protected:
bool fitted;
int m, n; // m: number of samples, n: number of features
Network model;
Metrics metrics;
vector<string> features;
string className;
map<string, vector<int>> states;
Tensor dataset; // (n+1)xm tensor
std::vector<std::string> features;
std::string className;
std::map<std::string, std::vector<int>> states;
torch::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;
void checkHyperparameters(const vector<string>& validKeys, nlohmann::json& hyperparameters);
void checkHyperparameters(const std::vector<std::string>& validKeys, nlohmann::json& hyperparameters);
void buildDataset(torch::Tensor& y);
public:
Classifier(Network model);
virtual ~Classifier() = default;
Classifier& fit(vector<vector<int>>& X, vector<int>& y, const vector<string>& features, const string& className, map<string, vector<int>>& states) override;
Classifier& fit(torch::Tensor& X, torch::Tensor& y, const vector<string>& features, const string& className, map<string, vector<int>>& states) override;
Classifier& fit(torch::Tensor& dataset, const vector<string>& features, const string& className, map<string, vector<int>>& states) override;
Classifier& fit(torch::Tensor& dataset, const vector<string>& features, const string& className, map<string, vector<int>>& states, const torch::Tensor& weights) override;
Classifier& 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) override;
Classifier& 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) override;
Classifier& fit(torch::Tensor& dataset, const std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states) override;
Classifier& 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) override;
void addNodes();
int getNumberOfNodes() const override;
int getNumberOfEdges() const override;
int getNumberOfStates() const override;
Tensor predict(Tensor& X) override;
torch::Tensor predict(torch::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;
vector<string> show() const override;
vector<string> topological_order() override;
std::vector<int> predict(std::vector<std::vector<int>>& X) override;
float score(torch::Tensor& X, torch::Tensor& y) override;
float score(std::vector<std::vector<int>>& X, std::vector<int>& y) override;
std::vector<std::string> show() const override;
std::vector<std::string> topological_order() override;
void dump_cpt() const override;
void setHyperparameters(nlohmann::json& hyperparameters) override;
};

53
src/BayesNet/Ensemble.cc
View File

@ -1,7 +1,6 @@
#include "Ensemble.h"
namespace bayesnet {
using namespace torch;
Ensemble::Ensemble() : Classifier(Network()), n_models(0) {}
@ -9,20 +8,20 @@ namespace bayesnet {
{
n_models = models.size();
for (auto i = 0; i < n_models; ++i) {
// fit with vectors
// fit with std::vectors
models[i]->fit(dataset, features, className, states);
}
}
vector<int> Ensemble::voting(Tensor& y_pred)
std::vector<int> Ensemble::voting(torch::Tensor& y_pred)
{
auto y_pred_ = y_pred.accessor<int, 2>();
vector<int> y_pred_final;
std::vector<int> y_pred_final;
int numClasses = states.at(className).size();
// y_pred is m x n_models with the prediction of every model for each sample
for (int i = 0; i < y_pred.size(0); ++i) {
// votes store in each index (value of class) the significance added by each model
// i.e. votes[0] contains how much value has the value 0 of class. That value is generated by the models predictions
vector<double> votes(numClasses, 0.0);
std::vector<double> votes(numClasses, 0.0);
for (int j = 0; j < n_models; ++j) {
votes[y_pred_[i][j]] += significanceModels.at(j);
}
@ -32,18 +31,18 @@ namespace bayesnet {
}
return y_pred_final;
}
Tensor Ensemble::predict(Tensor& X)
torch::Tensor Ensemble::predict(torch::Tensor& X)
{
if (!fitted) {
throw logic_error("Ensemble has not been fitted");
throw std::logic_error("Ensemble has not been fitted");
}
Tensor y_pred = torch::zeros({ X.size(1), n_models }, kInt32);
auto threads{ vector<thread>() };
mutex mtx;
torch::Tensor y_pred = torch::zeros({ X.size(1), n_models }, torch::kInt32);
auto threads{ std::vector<std::thread>() };
std::mutex mtx;
for (auto i = 0; i < n_models; ++i) {
threads.push_back(thread([&, i]() {
threads.push_back(std::thread([&, i]() {
auto ypredict = models[i]->predict(X);
lock_guard<mutex> lock(mtx);
std::lock_guard<std::mutex> lock(mtx);
y_pred.index_put_({ "...", i }, ypredict);
}));
}
@ -52,27 +51,27 @@ namespace bayesnet {
}
return torch::tensor(voting(y_pred));
}
vector<int> Ensemble::predict(vector<vector<int>>& X)
std::vector<int> Ensemble::predict(std::vector<std::vector<int>>& X)
{
if (!fitted) {
throw logic_error("Ensemble has not been fitted");
throw std::logic_error("Ensemble has not been fitted");
}
long m_ = X[0].size();
long n_ = X.size();
vector<vector<int>> Xd(n_, vector<int>(m_, 0));
std::vector<std::vector<int>> Xd(n_, std::vector<int>(m_, 0));
for (auto i = 0; i < n_; i++) {
Xd[i] = vector<int>(X[i].begin(), X[i].end());
Xd[i] = std::vector<int>(X[i].begin(), X[i].end());
}
Tensor y_pred = torch::zeros({ m_, n_models }, kInt32);
torch::Tensor y_pred = torch::zeros({ m_, n_models }, torch::kInt32);
for (auto i = 0; i < n_models; ++i) {
y_pred.index_put_({ "...", i }, torch::tensor(models[i]->predict(Xd), kInt32));
y_pred.index_put_({ "...", i }, torch::tensor(models[i]->predict(Xd), torch::kInt32));
}
return voting(y_pred);
}
float Ensemble::score(Tensor& X, Tensor& y)
float Ensemble::score(torch::Tensor& X, torch::Tensor& y)
{
if (!fitted) {
throw logic_error("Ensemble has not been fitted");
throw std::logic_error("Ensemble has not been fitted");
}
auto y_pred = predict(X);
int correct = 0;
@ -83,10 +82,10 @@ namespace bayesnet {
}
return (double)correct / y_pred.size(0);
}
float Ensemble::score(vector<vector<int>>& X, vector<int>& y)
float Ensemble::score(std::vector<std::vector<int>>& X, std::vector<int>& y)
{
if (!fitted) {
throw logic_error("Ensemble has not been fitted");
throw std::logic_error("Ensemble has not been fitted");
}
auto y_pred = predict(X);
int correct = 0;
@ -97,20 +96,20 @@ namespace bayesnet {
}
return (double)correct / y_pred.size();
}
vector<string> Ensemble::show() const
std::vector<std::string> Ensemble::show() const
{
auto result = vector<string>();
auto result = std::vector<std::string>();
for (auto i = 0; i < n_models; ++i) {
auto res = models[i]->show();
result.insert(result.end(), res.begin(), res.end());
}
return result;
}
vector<string> Ensemble::graph(const string& title) const
std::vector<std::string> Ensemble::graph(const std::string& title) const
{
auto result = vector<string>();
auto result = std::vector<std::string>();
for (auto i = 0; i < n_models; ++i) {
auto res = models[i]->graph(title + "_" + to_string(i));
auto res = models[i]->graph(title + "_" + std::to_string(i));
result.insert(result.end(), res.begin(), res.end());
}
return result;

26
src/BayesNet/Ensemble.h
View File

@ -4,34 +4,32 @@
#include "Classifier.h"
#include "BayesMetrics.h"
#include "bayesnetUtils.h"
using namespace std;
using namespace torch;
namespace bayesnet {
class Ensemble : public Classifier {
private:
Ensemble& build(vector<string>& features, string className, map<string, vector<int>>& states);
Ensemble& build(std::vector<std::string>& features, std::string className, std::map<std::string, std::vector<int>>& states);
protected:
unsigned n_models;
vector<unique_ptr<Classifier>> models;
vector<double> significanceModels;
std::vector<std::unique_ptr<Classifier>> models;
std::vector<double> significanceModels;
void trainModel(const torch::Tensor& weights) override;
vector<int> voting(Tensor& y_pred);
std::vector<int> voting(torch::Tensor& y_pred);
public:
Ensemble();
virtual ~Ensemble() = default;
Tensor predict(Tensor& X) override;
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;
torch::Tensor predict(torch::Tensor& X) override;
std::vector<int> predict(std::vector<std::vector<int>>& X) override;
float score(torch::Tensor& X, torch::Tensor& y) override;
float score(std::vector<std::vector<int>>& X, std::vector<int>& y) override;
int getNumberOfNodes() const override;
int getNumberOfEdges() const override;
int getNumberOfStates() const override;
vector<string> show() const override;
vector<string> graph(const string& title) const override;
vector<string> topological_order() override
std::vector<std::string> show() const override;
std::vector<std::string> graph(const std::string& title) const override;
std::vector<std::string> topological_order() override
{
return vector<string>();
return std::vector<std::string>();
}
void dump_cpt() const override
{

2
src/BayesNet/FCBF.cc
View File

@ -2,7 +2,7 @@
#include "FCBF.h"
namespace bayesnet {
FCBF::FCBF(const torch::Tensor& samples, const vector<string>& features, const string& className, const int maxFeatures, const int classNumStates, const torch::Tensor& weights, const double threshold) :
FCBF::FCBF(const torch::Tensor& samples, const std::vector<std::string>& features, const std::string& className, const int maxFeatures, const int classNumStates, const torch::Tensor& weights, const double threshold) :
FeatureSelect(samples, features, className, maxFeatures, classNumStates, weights), threshold(threshold)
{
if (threshold < 1e-7) {

5
src/BayesNet/FCBF.h
View File

@ -3,12 +3,11 @@
#include <torch/torch.h>
#include <vector>
#include "FeatureSelect.h"
using namespace std;
namespace bayesnet {
class FCBF : public FeatureSelect {
public:
// dataset is a n+1xm tensor of integers where dataset[-1] is the y vector
FCBF(const torch::Tensor& samples, const vector<string>& features, const string& className, const int maxFeatures, const int classNumStates, const torch::Tensor& weights, const double threshold);
// dataset is a n+1xm tensor of integers where dataset[-1] is the y std::vector
FCBF(const torch::Tensor& samples, const std::vector<std::string>& features, const std::string& className, const int maxFeatures, const int classNumStates, const torch::Tensor& weights, const double threshold);
virtual ~FCBF() {};
void fit() override;
private:

12
src/BayesNet/FeatureSelect.cc
View File

@ -2,7 +2,7 @@
#include <limits>
#include "bayesnetUtils.h"
namespace bayesnet {
FeatureSelect::FeatureSelect(const torch::Tensor& samples, const vector<string>& features, const string& className, const int maxFeatures, const int classNumStates, const torch::Tensor& weights) :
FeatureSelect::FeatureSelect(const torch::Tensor& samples, const std::vector<std::string>& features, const std::string& className, const int maxFeatures, const int classNumStates, const torch::Tensor& weights) :
Metrics(samples, features, className, classNumStates), maxFeatures(maxFeatures == 0 ? samples.size(0) - 1 : maxFeatures), weights(weights)
{
@ -42,7 +42,7 @@ namespace bayesnet {
try {
return suFeatures.at({ firstFeature, secondFeature });
}
catch (const out_of_range& e) {
catch (const std::out_of_range& e) {
double result = symmetricalUncertainty(firstFeature, secondFeature);
suFeatures[{firstFeature, secondFeature}] = result;
return result;
@ -62,17 +62,17 @@ namespace bayesnet {
}
return rcf / sqrt(n + (n * n - n) * rff);
}
vector<int> FeatureSelect::getFeatures() const
std::vector<int> FeatureSelect::getFeatures() const
{
if (!fitted) {
throw runtime_error("FeatureSelect not fitted");
throw std::runtime_error("FeatureSelect not fitted");
}
return selectedFeatures;
}
vector<double> FeatureSelect::getScores() const
std::vector<double> FeatureSelect::getScores() const
{
if (!fitted) {
throw runtime_error("FeatureSelect not fitted");
throw std::runtime_error("FeatureSelect not fitted");
}
return selectedScores;
}

17
src/BayesNet/FeatureSelect.h
View File

@ -3,16 +3,15 @@
#include <torch/torch.h>
#include <vector>
#include "BayesMetrics.h"
using namespace std;
namespace bayesnet {
class FeatureSelect : public Metrics {
public:
// dataset is a n+1xm tensor of integers where dataset[-1] is the y vector
FeatureSelect(const torch::Tensor& samples, const vector<string>& features, const string& className, const int maxFeatures, const int classNumStates, const torch::Tensor& weights);
// dataset is a n+1xm tensor of integers where dataset[-1] is the y std::vector
FeatureSelect(const torch::Tensor& samples, const std::vector<std::string>& features, const std::string& className, const int maxFeatures, const int classNumStates, const torch::Tensor& weights);
virtual ~FeatureSelect() {};
virtual void fit() = 0;
vector<int> getFeatures() const;
vector<double> getScores() const;
std::vector<int> getFeatures() const;
std::vector<double> getScores() const;
protected:
void initialize();
void computeSuLabels();
@ -21,10 +20,10 @@ namespace bayesnet {
double computeMeritCFS();
const torch::Tensor& weights;
int maxFeatures;
vector<int> selectedFeatures;
vector<double> selectedScores;
vector<double> suLabels;
map<pair<int, int>, double> suFeatures;
std::vector<int> selectedFeatures;
std::vector<double> selectedScores;
std::vector<double> suLabels;
std::map<std::pair<int, int>, double> suFeatures;
bool fitted = false;
};
}

2
src/BayesNet/IWSS.cc
View File

@ -2,7 +2,7 @@
#include <limits>
#include "bayesnetUtils.h"
namespace bayesnet {
IWSS::IWSS(const torch::Tensor& samples, const vector<string>& features, const string& className, const int maxFeatures, const int classNumStates, const torch::Tensor& weights, const double threshold) :
IWSS::IWSS(const torch::Tensor& samples, const std::vector<std::string>& features, const std::string& className, const int maxFeatures, const int classNumStates, const torch::Tensor& weights, const double threshold) :
FeatureSelect(samples, features, className, maxFeatures, classNumStates, weights), threshold(threshold)
{
if (threshold < 0 || threshold > .5) {

5
src/BayesNet/IWSS.h
View File

@ -3,12 +3,11 @@
#include <torch/torch.h>
#include <vector>
#include "FeatureSelect.h"
using namespace std;
namespace bayesnet {
class IWSS : public FeatureSelect {
public:
// dataset is a n+1xm tensor of integers where dataset[-1] is the y vector
IWSS(const torch::Tensor& samples, const vector<string>& features, const string& className, const int maxFeatures, const int classNumStates, const torch::Tensor& weights, const double threshold);
// dataset is a n+1xm tensor of integers where dataset[-1] is the y std::vector
IWSS(const torch::Tensor& samples, const std::vector<std::string>& features, const std::string& className, const int maxFeatures, const int classNumStates, const torch::Tensor& weights, const double threshold);
virtual ~IWSS() {};
void fit() override;
private:

24
src/BayesNet/KDB.cc
View File

@ -1,13 +1,11 @@
#include "KDB.h"
namespace bayesnet {
using namespace torch;
KDB::KDB(int k, float theta) : Classifier(Network()), k(k), theta(theta) {}
void KDB::setHyperparameters(nlohmann::json& hyperparameters)
{
// Check if hyperparameters are valid
const vector<string> validKeys = { "k", "theta" };
const std::vector<std::string> validKeys = { "k", "theta" };
checkHyperparameters(validKeys, hyperparameters);
if (hyperparameters.contains("k")) {
k = hyperparameters["k"];
@ -40,16 +38,16 @@ namespace bayesnet {
// 1. For each feature Xi, compute mutual information, I(X;C),
// where C is the class.
addNodes();
const Tensor& y = dataset.index({ -1, "..." });
vector<double> mi;
const torch::Tensor& y = dataset.index({ -1, "..." });
std::vector<double> mi;
for (auto i = 0; i < features.size(); i++) {
Tensor firstFeature = dataset.index({ i, "..." });
torch::Tensor firstFeature = dataset.index({ i, "..." });
mi.push_back(metrics.mutualInformation(firstFeature, y, weights));
}
// 2. Compute class conditional mutual information I(Xi;XjIC), f or each
auto conditionalEdgeWeights = metrics.conditionalEdge(weights);
// 3. Let the used variable list, S, be empty.
vector<int> S;
std::vector<int> S;
// 4. Let the DAG network being constructed, BN, begin with a single
// class node, C.
// 5. Repeat until S includes all domain features
@ -67,9 +65,9 @@ namespace bayesnet {
S.push_back(idx);
}
}
void KDB::add_m_edges(int idx, vector<int>& S, Tensor& weights)
void KDB::add_m_edges(int idx, std::vector<int>& S, torch::Tensor& weights)
{
auto n_edges = min(k, static_cast<int>(S.size()));
auto n_edges = std::min(k, static_cast<int>(S.size()));
auto cond_w = clone(weights);
bool exit_cond = k == 0;
int num = 0;
@ -81,7 +79,7 @@ namespace bayesnet {
model.addEdge(features[max_minfo], features[idx]);
num++;
}
catch (const invalid_argument& e) {
catch (const std::invalid_argument& e) {
// Loops are not allowed
}
}
@ -91,11 +89,11 @@ namespace bayesnet {
exit_cond = num == n_edges || candidates.size(0) == 0;
}
}
vector<string> KDB::graph(const string& title) const
std::vector<std::string> KDB::graph(const std::string& title) const
{
string header{ title };
std::string header{ title };
if (title == "KDB") {
header += " (k=" + to_string(k) + ", theta=" + to_string(theta) + ")";
header += " (k=" + std::to_string(k) + ", theta=" + std::to_string(theta) + ")";
}
return model.graph(header);
}

6
src/BayesNet/KDB.h
View File

@ -4,20 +4,18 @@
#include "Classifier.h"
#include "bayesnetUtils.h"
namespace bayesnet {
using namespace std;
using namespace torch;
class KDB : public Classifier {
private:
int k;
float theta;
void add_m_edges(int idx, vector<int>& S, Tensor& weights);
void add_m_edges(int idx, std::vector<int>& S, torch::Tensor& weights);
protected:
void buildModel(const torch::Tensor& weights) override;
public:
explicit KDB(int k, float theta = 0.03);
virtual ~KDB() {};
void setHyperparameters(nlohmann::json& hyperparameters) override;
vector<string> graph(const string& name = "KDB") const override;
std::vector<std::string> graph(const std::string& name = "KDB") const override;
};
}
#endif

9
src/BayesNet/KDBLd.cc
View File

@ -1,16 +1,15 @@
#include "KDBLd.h"
namespace bayesnet {
using namespace std;
KDBLd::KDBLd(int k) : KDB(k), Proposal(dataset, features, className) {}
KDBLd& KDBLd::fit(torch::Tensor& X_, torch::Tensor& y_, const vector<string>& features_, const string& className_, map<string, vector<int>>& states_)
KDBLd& KDBLd::fit(torch::Tensor& X_, torch::Tensor& y_, const std::vector<std::string>& features_, const std::string& className_, map<std::string, std::vector<int>>& states_)
{
checkInput(X_, y_);
features = features_;
className = className_;
Xf = X_;
y = y_;
// Fills vectors Xv & yv with the data from tensors X_ (discretized) & y
// Fills std::vectors Xv & yv with the data from tensors X_ (discretized) & y
states = fit_local_discretization(y);
// We have discretized the input data
// 1st we need to fit the model to build the normal KDB structure, KDB::fit initializes the base Bayesian network
@ -18,12 +17,12 @@ namespace bayesnet {
states = localDiscretizationProposal(states, model);
return *this;
}
Tensor KDBLd::predict(Tensor& X)
torch::Tensor KDBLd::predict(torch::Tensor& X)
{
auto Xt = prepareX(X);
return KDB::predict(Xt);
}
vector<string> KDBLd::graph(const string& name) const
std::vector<std::string> KDBLd::graph(const std::string& name) const
{
return KDB::graph(name);
}

9
src/BayesNet/KDBLd.h
View File

@ -4,16 +4,15 @@
#include "Proposal.h"
namespace bayesnet {
using namespace std;
class KDBLd : public KDB, public Proposal {
private:
public:
explicit KDBLd(int k);
virtual ~KDBLd() = default;
KDBLd& fit(torch::Tensor& X, torch::Tensor& y, const vector<string>& features, const string& className, map<string, vector<int>>& states) override;
vector<string> graph(const string& name = "KDB") const override;
Tensor predict(Tensor& X) override;
static inline string version() { return "0.0.1"; };
KDBLd& fit(torch::Tensor& X, torch::Tensor& y, const std::vector<std::string>& features, const std::string& className, map<std::string, std::vector<int>>& states) override;
std::vector<std::string> graph(const std::string& name = "KDB") const override;
torch::Tensor predict(torch::Tensor& X) override;
static inline std::string version() { return "0.0.1"; };
};
}
#endif // !KDBLD_H

27
src/BayesNet/Mst.cc
View File

@ -7,8 +7,7 @@
*/
namespace bayesnet {
using namespace std;
Graph::Graph(int V) : V(V), parent(vector<int>(V))
Graph::Graph(int V) : V(V), parent(std::vector<int>(V))
{
for (int i = 0; i < V; i++)
parent[i] = i;
@ -41,35 +40,35 @@ namespace bayesnet {
uSt = find_set(G[i].second.first);
vEd = find_set(G[i].second.second);
if (uSt != vEd) {
T.push_back(G[i]); // add to mst vector
T.push_back(G[i]); // add to mst std::vector
union_set(uSt, vEd);
}
}
}
void Graph::display_mst()
{
cout << "Edge :" << " Weight" << endl;
std::cout << "Edge :" << " Weight" << std::endl;
for (int i = 0; i < T.size(); i++) {
cout << T[i].second.first << " - " << T[i].second.second << " : "
std::cout << T[i].second.first << " - " << T[i].second.second << " : "
<< T[i].first;
cout << endl;
std::cout << std::endl;
}
}
void insertElement(list<int>& variables, int variable)
void insertElement(std::list<int>& variables, int variable)
{
if (find(variables.begin(), variables.end(), variable) == variables.end()) {
if (std::find(variables.begin(), variables.end(), variable) == variables.end()) {
variables.push_front(variable);
}
}
vector<pair<int, int>> reorder(vector<pair<float, pair<int, int>>> T, int root_original)
std::vector<std::pair<int, int>> reorder(std::vector<std::pair<float, std::pair<int, int>>> T, int root_original)
{
// Create the edges of a DAG from the MST
// replacing unordered_set with list because unordered_set cannot guarantee the order of the elements inserted
auto result = vector<pair<int, int>>();
auto visited = vector<int>();
auto nextVariables = list<int>();
auto result = std::vector<std::pair<int, int>>();
auto visited = std::vector<int>();
auto nextVariables = std::list<int>();
nextVariables.push_front(root_original);
while (nextVariables.size() > 0) {
int root = nextVariables.front();
@ -104,8 +103,8 @@ namespace bayesnet {
return result;
}
MST::MST(const vector<string>& features, const Tensor& weights, const int root) : features(features), weights(weights), root(root) {}
vector<pair<int, int>> MST::maximumSpanningTree()
MST::MST(const std::vector<std::string>& features, const torch::Tensor& weights, const int root) : features(features), weights(weights), root(root) {}
std::vector<std::pair<int, int>> MST::maximumSpanningTree()
{
auto num_features = features.size();
Graph g(num_features);

18
src/BayesNet/Mst.h
View File

@ -4,24 +4,22 @@
#include <vector>
#include <string>
namespace bayesnet {
using namespace std;
using namespace torch;
class MST {
private:
Tensor weights;
vector<string> features;
torch::Tensor weights;
std::vector<std::string> features;
int root = 0;
public:
MST() = default;
MST(const vector<string>& features, const Tensor& weights, const int root);
vector<pair<int, int>> maximumSpanningTree();
MST(const std::vector<std::string>& features, const torch::Tensor& weights, const int root);
std::vector<std::pair<int, int>> maximumSpanningTree();
};
class Graph {
private:
int V; // number of nodes in graph
vector <pair<float, pair<int, int>>> G; // vector for graph
vector <pair<float, pair<int, int>>> T; // vector for mst
vector<int> parent;
std::vector <std::pair<float, std::pair<int, int>>> G; // std::vector for graph
std::vector <std::pair<float, std::pair<int, int>>> T; // std::vector for mst
std::vector<int> parent;
public:
explicit Graph(int V);
void addEdge(int u, int v, float wt);
@ -29,7 +27,7 @@ namespace bayesnet {
void union_set(int u, int v);
void kruskal_algorithm();
void display_mst();
vector <pair<float, pair<int, int>>> get_mst() { return T; }
std::vector <std::pair<float, std::pair<int, int>>> get_mst() { return T; }
};
}
#endif

162
src/BayesNet/Network.cc
View File

@ -3,18 +3,18 @@
#include "Network.h"
#include "bayesnetUtils.h"
namespace bayesnet {
Network::Network() : features(vector<string>()), className(""), classNumStates(0), fitted(false), laplaceSmoothing(0) {}
Network::Network(float maxT) : features(vector<string>()), className(""), classNumStates(0), maxThreads(maxT), fitted(false), laplaceSmoothing(0) {}
Network::Network() : features(std::vector<std::string>()), className(""), classNumStates(0), fitted(false), laplaceSmoothing(0) {}
Network::Network(float maxT) : features(std::vector<std::string>()), className(""), classNumStates(0), maxThreads(maxT), fitted(false), laplaceSmoothing(0) {}
Network::Network(Network& other) : laplaceSmoothing(other.laplaceSmoothing), features(other.features), className(other.className), classNumStates(other.getClassNumStates()), maxThreads(other.
getmaxThreads()), fitted(other.fitted)
{
for (const auto& pair : other.nodes) {
nodes[pair.first] = std::make_unique<Node>(*pair.second);
for (const auto& node : other.nodes) {
nodes[node.first] = std::make_unique<Node>(*node.second);
}
}
void Network::initialize()
{
features = vector<string>();
features = std::vector<std::string>();
className = "";
classNumStates = 0;
fitted = false;
@ -29,10 +29,10 @@ namespace bayesnet {
{
return samples;
}
void Network::addNode(const string& name)
void Network::addNode(const std::string& name)
{
if (name == "") {
throw invalid_argument("Node name cannot be empty");
throw std::invalid_argument("Node name cannot be empty");
}
if (nodes.find(name) != nodes.end()) {
return;
@ -42,7 +42,7 @@ namespace bayesnet {
}
nodes[name] = std::make_unique<Node>(name);
}
vector<string> Network::getFeatures() const
std::vector<std::string> Network::getFeatures() const
{
return features;
}
@ -58,11 +58,11 @@ namespace bayesnet {
}
return result;
}
string Network::getClassName() const
std::string Network::getClassName() const
{
return className;
}
bool Network::isCyclic(const string& nodeId, unordered_set<string>& visited, unordered_set<string>& recStack)
bool Network::isCyclic(const std::string& nodeId, std::unordered_set<std::string>& visited, std::unordered_set<std::string>& recStack)
{
if (visited.find(nodeId) == visited.end()) // if node hasn't been visited yet
{
@ -78,78 +78,78 @@ namespace bayesnet {
recStack.erase(nodeId); // remove node from recursion stack before function ends
return false;
}
void Network::addEdge(const string& parent, const string& child)
void Network::addEdge(const std::string& parent, const std::string& child)
{
if (nodes.find(parent) == nodes.end()) {
throw invalid_argument("Parent node " + parent + " does not exist");
throw std::invalid_argument("Parent node " + parent + " does not exist");
}
if (nodes.find(child) == nodes.end()) {
throw invalid_argument("Child node " + child + " does not exist");
throw std::invalid_argument("Child node " + child + " does not exist");
}
// Temporarily add edge to check for cycles
nodes[parent]->addChild(nodes[child].get());
nodes[child]->addParent(nodes[parent].get());
unordered_set<string> visited;
unordered_set<string> recStack;
std::unordered_set<std::string> visited;
std::unordered_set<std::string> recStack;
if (isCyclic(nodes[child]->getName(), visited, recStack)) // if adding this edge forms a cycle
{
// remove problematic edge
nodes[parent]->removeChild(nodes[child].get());
nodes[child]->removeParent(nodes[parent].get());
throw invalid_argument("Adding this edge forms a cycle in the graph.");
throw std::invalid_argument("Adding this edge forms a cycle in the graph.");
}
}
map<string, std::unique_ptr<Node>>& Network::getNodes()
std::map<std::string, std::unique_ptr<Node>>& Network::getNodes()
{
return nodes;
}
void Network::checkFitData(int n_samples, int n_features, int n_samples_y, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states, const torch::Tensor& weights)
void Network::checkFitData(int n_samples, int n_features, int n_samples_y, const std::vector<std::string>& featureNames, const std::string& className, const std::map<std::string, std::vector<int>>& states, const torch::Tensor& weights)
{
if (weights.size(0) != n_samples) {
throw invalid_argument("Weights (" + to_string(weights.size(0)) + ") must have the same number of elements as samples (" + to_string(n_samples) + ") in Network::fit");
throw std::invalid_argument("Weights (" + std::to_string(weights.size(0)) + ") must have the same number of elements as samples (" + std::to_string(n_samples) + ") in Network::fit");
}
if (n_samples != n_samples_y) {
throw invalid_argument("X and y must have the same number of samples in Network::fit (" + to_string(n_samples) + " != " + to_string(n_samples_y) + ")");
throw std::invalid_argument("X and y must have the same number of samples in Network::fit (" + std::to_string(n_samples) + " != " + std::to_string(n_samples_y) + ")");
}
if (n_features != featureNames.size()) {
throw invalid_argument("X and features must have the same number of features in Network::fit (" + to_string(n_features) + " != " + to_string(featureNames.size()) + ")");
throw std::invalid_argument("X and features must have the same number of features in Network::fit (" + std::to_string(n_features) + " != " + std::to_string(featureNames.size()) + ")");
}
if (n_features != features.size() - 1) {
throw invalid_argument("X and local features must have the same number of features in Network::fit (" + to_string(n_features) + " != " + to_string(features.size() - 1) + ")");
throw std::invalid_argument("X and local features must have the same number of features in Network::fit (" + std::to_string(n_features) + " != " + std::to_string(features.size() - 1) + ")");
}
if (find(features.begin(), features.end(), className) == features.end()) {
throw invalid_argument("className not found in Network::features");
throw std::invalid_argument("className not found in Network::features");
}
for (auto& feature : featureNames) {
if (find(features.begin(), features.end(), feature) == features.end()) {
throw invalid_argument("Feature " + feature + " not found in Network::features");
throw std::invalid_argument("Feature " + feature + " not found in Network::features");
}
if (states.find(feature) == states.end()) {
throw invalid_argument("Feature " + feature + " not found in states");
throw std::invalid_argument("Feature " + feature + " not found in states");
}
}
}
void Network::setStates(const map<string, vector<int>>& states)
void Network::setStates(const std::map<std::string, std::vector<int>>& states)
{
// Set states to every Node in the network
for_each(features.begin(), features.end(), [this, &states](const string& feature) {
for_each(features.begin(), features.end(), [this, &states](const std::string& feature) {
nodes.at(feature)->setNumStates(states.at(feature).size());
});
classNumStates = nodes.at(className)->getNumStates();
}
// X comes in nxm, where n is the number of features and m the number of samples
void Network::fit(const torch::Tensor& X, const torch::Tensor& y, const torch::Tensor& weights, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states)
void Network::fit(const torch::Tensor& X, const torch::Tensor& y, const torch::Tensor& weights, const std::vector<std::string>& featureNames, const std::string& className, const std::map<std::string, std::vector<int>>& states)
{
checkFitData(X.size(1), X.size(0), y.size(0), featureNames, className, states, weights);
this->className = className;
Tensor ytmp = torch::transpose(y.view({ y.size(0), 1 }), 0, 1);
torch::Tensor ytmp = torch::transpose(y.view({ y.size(0), 1 }), 0, 1);
samples = torch::cat({ X , ytmp }, 0);
for (int i = 0; i < featureNames.size(); ++i) {
auto row_feature = X.index({ i, "..." });
}
completeFit(states, weights);
}
void Network::fit(const torch::Tensor& samples, const torch::Tensor& weights, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states)
void Network::fit(const torch::Tensor& samples, const torch::Tensor& weights, const std::vector<std::string>& featureNames, const std::string& className, const std::map<std::string, std::vector<int>>& states)
{
checkFitData(samples.size(1), samples.size(0) - 1, samples.size(1), featureNames, className, states, weights);
this->className = className;
@ -157,7 +157,7 @@ namespace bayesnet {
completeFit(states, weights);
}
// input_data comes in nxm, where n is the number of features and m the number of samples
void Network::fit(const vector<vector<int>>& input_data, const vector<int>& labels, const vector<double>& weights_, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states)
void Network::fit(const std::vector<std::vector<int>>& input_data, const std::vector<int>& labels, const std::vector<double>& weights_, const std::vector<std::string>& featureNames, const std::string& className, const std::map<std::string, std::vector<int>>& states)
{
const torch::Tensor weights = torch::tensor(weights_, torch::kFloat64);
checkFitData(input_data[0].size(), input_data.size(), labels.size(), featureNames, className, states, weights);
@ -170,11 +170,11 @@ namespace bayesnet {
samples.index_put_({ -1, "..." }, torch::tensor(labels, torch::kInt32));
completeFit(states, weights);
}
void Network::completeFit(const map<string, vector<int>>& states, const torch::Tensor& weights)
void Network::completeFit(const std::map<std::string, std::vector<int>>& states, const torch::Tensor& weights)
{
setStates(states);
laplaceSmoothing = 1.0 / samples.size(1); // To use in CPT computation
vector<thread> threads;
std::vector<std::thread> threads;
for (auto& node : nodes) {
threads.emplace_back([this, &node, &weights]() {
node.second->computeCPT(samples, features, laplaceSmoothing, weights);
@ -188,12 +188,12 @@ namespace bayesnet {
torch::Tensor Network::predict_tensor(const torch::Tensor& samples, const bool proba)
{
if (!fitted) {
throw logic_error("You must call fit() before calling predict()");
throw std::logic_error("You must call fit() before calling predict()");
}
torch::Tensor result;
result = torch::zeros({ samples.size(1), classNumStates }, torch::kFloat64);
for (int i = 0; i < samples.size(1); ++i) {
const Tensor sample = samples.index({ "...", i });
const torch::Tensor sample = samples.index({ "...", i });
auto psample = predict_sample(sample);
auto temp = torch::tensor(psample, torch::kFloat64);
// result.index_put_({ i, "..." }, torch::tensor(predict_sample(sample), torch::kFloat64));
@ -204,32 +204,32 @@ namespace bayesnet {
return result.argmax(1);
}
// Return mxn tensor of probabilities
Tensor Network::predict_proba(const Tensor& samples)
torch::Tensor Network::predict_proba(const torch::Tensor& samples)
{
return predict_tensor(samples, true);
}
// Return mxn tensor of probabilities
Tensor Network::predict(const Tensor& samples)
torch::Tensor Network::predict(const torch::Tensor& samples)
{
return predict_tensor(samples, false);
}
// Return mx1 vector of predictions
// tsamples is nxm vector of samples
vector<int> Network::predict(const vector<vector<int>>& tsamples)
// Return mx1 std::vector of predictions
// tsamples is nxm std::vector of samples
std::vector<int> Network::predict(const std::vector<std::vector<int>>& tsamples)
{
if (!fitted) {
throw logic_error("You must call fit() before calling predict()");
throw std::logic_error("You must call fit() before calling predict()");
}
vector<int> predictions;
vector<int> sample;
std::vector<int> predictions;
std::vector<int> sample;
for (int row = 0; row < tsamples[0].size(); ++row) {
sample.clear();
for (int col = 0; col < tsamples.size(); ++col) {
sample.push_back(tsamples[col][row]);
}
vector<double> classProbabilities = predict_sample(sample);
std::vector<double> classProbabilities = predict_sample(sample);
// Find the class with the maximum posterior probability
auto maxElem = max_element(classProbabilities.begin(), classProbabilities.end());
int predictedClass = distance(classProbabilities.begin(), maxElem);
@ -237,14 +237,14 @@ namespace bayesnet {
}
return predictions;
}
// Return mxn vector of probabilities
vector<vector<double>> Network::predict_proba(const vector<vector<int>>& tsamples)
// Return mxn std::vector of probabilities
std::vector<std::vector<double>> Network::predict_proba(const std::vector<std::vector<int>>& tsamples)
{
if (!fitted) {
throw logic_error("You must call fit() before calling predict_proba()");
throw std::logic_error("You must call fit() before calling predict_proba()");
}
vector<vector<double>> predictions;
vector<int> sample;
std::vector<std::vector<double>> predictions;
std::vector<int> sample;
for (int row = 0; row < tsamples[0].size(); ++row) {
sample.clear();
for (int col = 0; col < tsamples.size(); ++col) {
@ -254,9 +254,9 @@ namespace bayesnet {
}
return predictions;
}
double Network::score(const vector<vector<int>>& tsamples, const vector<int>& labels)
double Network::score(const std::vector<std::vector<int>>& tsamples, const std::vector<int>& labels)
{
vector<int> y_pred = predict(tsamples);
std::vector<int> y_pred = predict(tsamples);
int correct = 0;
for (int i = 0; i < y_pred.size(); ++i) {
if (y_pred[i] == labels[i]) {
@ -265,35 +265,35 @@ namespace bayesnet {
}
return (double)correct / y_pred.size();
}
// Return 1xn vector of probabilities
vector<double> Network::predict_sample(const vector<int>& sample)
// Return 1xn std::vector of probabilities
std::vector<double> Network::predict_sample(const std::vector<int>& sample)
{
// Ensure the sample size is equal to the number of features
if (sample.size() != features.size() - 1) {
throw invalid_argument("Sample size (" + to_string(sample.size()) +
") does not match the number of features (" + to_string(features.size() - 1) + ")");
throw std::invalid_argument("Sample size (" + std::to_string(sample.size()) +
") does not match the number of features (" + std::to_string(features.size() - 1) + ")");
}
map<string, int> evidence;
std::map<std::string, int> evidence;
for (int i = 0; i < sample.size(); ++i) {
evidence[features[i]] = sample[i];
}
return exactInference(evidence);
}
// Return 1xn vector of probabilities
vector<double> Network::predict_sample(const Tensor& sample)
// Return 1xn std::vector of probabilities
std::vector<double> Network::predict_sample(const torch::Tensor& sample)
{
// Ensure the sample size is equal to the number of features
if (sample.size(0) != features.size() - 1) {
throw invalid_argument("Sample size (" + to_string(sample.size(0)) +
") does not match the number of features (" + to_string(features.size() - 1) + ")");
throw std::invalid_argument("Sample size (" + std::to_string(sample.size(0)) +
") does not match the number of features (" + std::to_string(features.size() - 1) + ")");
}
map<string, int> evidence;
std::map<std::string, int> evidence;
for (int i = 0; i < sample.size(0); ++i) {
evidence[features[i]] = sample[i].item<int>();
}
return exactInference(evidence);
}
double Network::computeFactor(map<string, int>& completeEvidence)
double Network::computeFactor(std::map<std::string, int>& completeEvidence)
{
double result = 1.0;
for (auto& node : getNodes()) {
@ -301,17 +301,17 @@ namespace bayesnet {
}
return result;
}
vector<double> Network::exactInference(map<string, int>& evidence)
std::vector<double> Network::exactInference(std::map<std::string, int>& evidence)
{
vector<double> result(classNumStates, 0.0);
vector<thread> threads;
mutex mtx;
std::vector<double> result(classNumStates, 0.0);
std::vector<std::thread> threads;
std::mutex mtx;
for (int i = 0; i < classNumStates; ++i) {
threads.emplace_back([this, &result, &evidence, i, &mtx]() {
auto completeEvidence = map<string, int>(evidence);
auto completeEvidence = std::map<std::string, int>(evidence);
completeEvidence[getClassName()] = i;
double factor = computeFactor(completeEvidence);
lock_guard<mutex> lock(mtx);
std::lock_guard<std::mutex> lock(mtx);
result[i] = factor;
});
}
@ -323,12 +323,12 @@ namespace bayesnet {
transform(result.begin(), result.end(), result.begin(), [sum](const double& value) { return value / sum; });
return result;
}
vector<string> Network::show() const
std::vector<std::string> Network::show() const
{
vector<string> result;
std::vector<std::string> result;
// Draw the network
for (auto& node : nodes) {
string line = node.first + " -> ";
std::string line = node.first + " -> ";
for (auto child : node.second->getChildren()) {
line += child->getName() + ", ";
}
@ -336,12 +336,12 @@ namespace bayesnet {
}
return result;
}
vector<string> Network::graph(const string& title) const
std::vector<std::string> Network::graph(const std::string& title) const
{
auto output = vector<string>();
auto output = std::vector<std::string>();
auto prefix = "digraph BayesNet {\nlabel=<BayesNet ";
auto suffix = ">\nfontsize=30\nfontcolor=blue\nlabelloc=t\nlayout=circo\n";
string header = prefix + title + suffix;
std::string header = prefix + title + suffix;
output.push_back(header);
for (auto& node : nodes) {
auto result = node.second->graph(className);
@ -350,9 +350,9 @@ namespace bayesnet {
output.push_back("}\n");
return output;
}
vector<pair<string, string>> Network::getEdges() const
std::vector<std::pair<std::string, std::string>> Network::getEdges() const
{
auto edges = vector<pair<string, string>>();
auto edges = std::vector<std::pair<std::string, std::string>>();
for (const auto& node : nodes) {
auto head = node.first;
for (const auto& child : node.second->getChildren()) {
@ -366,7 +366,7 @@ namespace bayesnet {
{
return getEdges().size();
}
vector<string> Network::topological_sort()
std::vector<std::string> Network::topological_sort()
{
/* Check if al the fathers of every node are before the node */
auto result = features;
@ -393,10 +393,10 @@ namespace bayesnet {
ending = false;
}
} else {
throw logic_error("Error in topological sort because of node " + feature + " is not in result");
throw std::logic_error("Error in topological sort because of node " + feature + " is not in result");
}
} else {
throw logic_error("Error in topological sort because of node father " + fatherName + " is not in result");
throw std::logic_error("Error in topological sort because of node father " + fatherName + " is not in result");
}
}
}
@ -406,8 +406,8 @@ namespace bayesnet {
void Network::dump_cpt() const
{
for (auto& node : nodes) {
cout << "* " << node.first << ": (" << node.second->getNumStates() << ") : " << node.second->getCPT().sizes() << endl;
cout << node.second->getCPT() << endl;
std::cout << "* " << node.first << ": (" << node.second->getNumStates() << ") : " << node.second->getCPT().sizes() << std::endl;
std::cout << node.second->getCPT() << std::endl;
}
}
}

52
src/BayesNet/Network.h
View File

@ -7,22 +7,22 @@
namespace bayesnet {
class Network {
private:
map<string, unique_ptr<Node>> nodes;
std::map<std::string, std::unique_ptr<Node>> nodes;
bool fitted;
float maxThreads = 0.95;
int classNumStates;
vector<string> features; // Including classname
string className;
std::vector<std::string> features; // Including classname
std::string className;
double laplaceSmoothing;
torch::Tensor samples; // nxm tensor used to fit the model
bool isCyclic(const std::string&, std::unordered_set<std::string>&, std::unordered_set<std::string>&);
vector<double> predict_sample(const vector<int>&);
vector<double> predict_sample(const torch::Tensor&);
vector<double> exactInference(map<string, int>&);
double computeFactor(map<string, int>&);
void completeFit(const map<string, vector<int>>& states, const torch::Tensor& weights);
void checkFitData(int n_features, int n_samples, int n_samples_y, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states, const torch::Tensor& weights);
void setStates(const map<string, vector<int>>&);
std::vector<double> predict_sample(const std::vector<int>&);
std::vector<double> predict_sample(const torch::Tensor&);
std::vector<double> exactInference(std::map<std::string, int>&);
double computeFactor(std::map<std::string, int>&);
void completeFit(const std::map<std::string, std::vector<int>>& states, const torch::Tensor& weights);
void checkFitData(int n_features, int n_samples, int n_samples_y, const std::vector<std::string>& featureNames, const std::string& className, const std::map<std::string, std::vector<int>>& states, const torch::Tensor& weights);
void setStates(const std::map<std::string, std::vector<int>>&);
public:
Network();
explicit Network(float);
@ -30,33 +30,33 @@ namespace bayesnet {
~Network() = default;
torch::Tensor& getSamples();
float getmaxThreads();
void addNode(const string&);
void addEdge(const string&, const string&);
map<string, std::unique_ptr<Node>>& getNodes();
vector<string> getFeatures() const;
void addNode(const std::string&);
void addEdge(const std::string&, const std::string&);
std::map<std::string, std::unique_ptr<Node>>& getNodes();
std::vector<std::string> getFeatures() const;
int getStates() const;
vector<pair<string, string>> getEdges() const;
std::vector<std::pair<std::string, std::string>> getEdges() const;
int getNumEdges() const;
int getClassNumStates() const;
string getClassName() const;
std::string getClassName() const;
/*
Notice: Nodes have to be inserted in the same order as they are in the dataset, i.e., first node is first column and so on.
*/
void fit(const vector<vector<int>>& input_data, const vector<int>& labels, const vector<double>& weights, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states);
void fit(const torch::Tensor& X, const torch::Tensor& y, const torch::Tensor& weights, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states);
void fit(const torch::Tensor& samples, const torch::Tensor& weights, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states);
vector<int> predict(const vector<vector<int>>&); // Return mx1 vector of predictions
void fit(const std::vector<std::vector<int>>& input_data, const std::vector<int>& labels, const std::vector<double>& weights, const std::vector<std::string>& featureNames, const std::string& className, const std::map<std::string, std::vector<int>>& states);
void fit(const torch::Tensor& X, const torch::Tensor& y, const torch::Tensor& weights, const std::vector<std::string>& featureNames, const std::string& className, const std::map<std::string, std::vector<int>>& states);
void fit(const torch::Tensor& samples, const torch::Tensor& weights, const std::vector<std::string>& featureNames, const std::string& className, const std::map<std::string, std::vector<int>>& states);
std::vector<int> predict(const std::vector<std::vector<int>>&); // Return mx1 std::vector of predictions
torch::Tensor predict(const torch::Tensor&); // Return mx1 tensor of predictions
torch::Tensor predict_tensor(const torch::Tensor& samples, const bool proba);
vector<vector<double>> predict_proba(const vector<vector<int>>&); // Return mxn vector of probabilities
std::vector<std::vector<double>> predict_proba(const std::vector<std::vector<int>>&); // Return mxn std::vector of probabilities
torch::Tensor predict_proba(const torch::Tensor&); // Return mxn tensor of probabilities
double score(const vector<vector<int>>&, const vector<int>&);
vector<string> topological_sort();
vector<string> show() const;
vector<string> graph(const string& title) const; // Returns a vector of strings representing the graph in graphviz format
double score(const std::vector<std::vector<int>>&, const std::vector<int>&);
std::vector<std::string> topological_sort();
std::vector<std::string> show() const;
std::vector<std::string> graph(const std::string& title) const; // Returns a std::vector of std::strings representing the graph in graphviz format
void initialize();
void dump_cpt() const;
inline string version() { return "0.2.0"; }
inline std::string version() { return "0.2.0"; }
};
}
#endif

32
src/BayesNet/Node.cc
View File

@ -3,7 +3,7 @@
namespace bayesnet {
Node::Node(const std::string& name)
: name(name), numStates(0), cpTable(torch::Tensor()), parents(vector<Node*>()), children(vector<Node*>())
: name(name), numStates(0), cpTable(torch::Tensor()), parents(std::vector<Node*>()), children(std::vector<Node*>())
{
}
void Node::clear()
@ -14,7 +14,7 @@ namespace bayesnet {
dimensions.clear();
numStates = 0;
}
string Node::getName() const
std::string Node::getName() const
{
return name;
}
@ -34,11 +34,11 @@ namespace bayesnet {
{
children.push_back(child);
}
vector<Node*>& Node::getParents()
std::vector<Node*>& Node::getParents()
{
return parents;
}
vector<Node*>& Node::getChildren()
std::vector<Node*>& Node::getChildren()
{
return children;
}
@ -63,28 +63,28 @@ namespace bayesnet {
*/
unsigned Node::minFill()
{
unordered_set<string> neighbors;
std::unordered_set<std::string> neighbors;
for (auto child : children) {
neighbors.emplace(child->getName());
}
for (auto parent : parents) {
neighbors.emplace(parent->getName());
}
auto source = vector<string>(neighbors.begin(), neighbors.end());
auto source = std::vector<std::string>(neighbors.begin(), neighbors.end());
return combinations(source).size();
}
vector<pair<string, string>> Node::combinations(const vector<string>& source)
std::vector<std::pair<std::string, std::string>> Node::combinations(const std::vector<std::string>& source)
{
vector<pair<string, string>> result;
std::vector<std::pair<std::string, std::string>> result;
for (int i = 0; i < source.size(); ++i) {
string temp = source[i];
std::string temp = source[i];
for (int j = i + 1; j < source.size(); ++j) {
result.push_back({ temp, source[j] });
}
}
return result;
}
void Node::computeCPT(const torch::Tensor& dataset, const vector<string>& features, const double laplaceSmoothing, const torch::Tensor& weights)
void Node::computeCPT(const torch::Tensor& dataset, const std::vector<std::string>& features, const double laplaceSmoothing, const torch::Tensor& weights)
{
dimensions.clear();
// Get dimensions of the CPT
@ -96,7 +96,7 @@ namespace bayesnet {
// Fill table with counts
auto pos = find(features.begin(), features.end(), name);
if (pos == features.end()) {
throw logic_error("Feature " + name + " not found in dataset");
throw std::logic_error("Feature " + name + " not found in dataset");
}
int name_index = pos - features.begin();
for (int n_sample = 0; n_sample < dataset.size(1); ++n_sample) {
@ -105,7 +105,7 @@ namespace bayesnet {
for (auto parent : parents) {
pos = find(features.begin(), features.end(), parent->getName());
if (pos == features.end()) {
throw logic_error("Feature parent " + parent->getName() + " not found in dataset");
throw std::logic_error("Feature parent " + parent->getName() + " not found in dataset");
}
int parent_index = pos - features.begin();
coordinates.push_back(dataset.index({ parent_index, n_sample }));
@ -116,17 +116,17 @@ namespace bayesnet {
// Normalize the counts
cpTable = cpTable / cpTable.sum(0);
}
float Node::getFactorValue(map<string, int>& evidence)
float Node::getFactorValue(std::map<std::string, int>& evidence)
{
c10::List<c10::optional<at::Tensor>> coordinates;
// following predetermined order of indices in the cpTable (see Node.h)
coordinates.push_back(at::tensor(evidence[name]));
transform(parents.begin(), parents.end(), back_inserter(coordinates), [&evidence](const auto& parent) { return at::tensor(evidence[parent->getName()]); });
transform(parents.begin(), parents.end(), std::back_inserter(coordinates), [&evidence](const auto& parent) { return at::tensor(evidence[parent->getName()]); });
return cpTable.index({ coordinates }).item<float>();
}
vector<string> Node::graph(const string& className)
std::vector<std::string> Node::graph(const std::string& className)
{
auto output = vector<string>();
auto output = std::vector<std::string>();
auto suffix = name == className ? ", fontcolor=red, fillcolor=lightblue, style=filled " : "";
output.push_back(name + " [shape=circle" + suffix + "] \n");
transform(children.begin(), children.end(), back_inserter(output), [this](const auto& child) { return name + " -> " + child->getName(); });

25
src/BayesNet/Node.h
View File

@ -5,33 +5,32 @@
#include <vector>
#include <string>
namespace bayesnet {
using namespace std;
class Node {
private:
string name;
vector<Node*> parents;
vector<Node*> children;
std::string name;
std::vector<Node*> parents;
std::vector<Node*> children;
int numStates; // number of states of the variable
torch::Tensor cpTable; // Order of indices is 0-> node variable, 1-> 1st parent, 2-> 2nd parent, ...
vector<int64_t> dimensions; // dimensions of the cpTable
vector<pair<string, string>> combinations(const vector<string>&);
std::vector<int64_t> dimensions; // dimensions of the cpTable
std::vector<std::pair<std::string, std::string>> combinations(const std::vector<std::string>&);
public:
explicit Node(const string&);
explicit Node(const std::string&);
void clear();
void addParent(Node*);
void addChild(Node*);
void removeParent(Node*);
void removeChild(Node*);
string getName() const;
vector<Node*>& getParents();
vector<Node*>& getChildren();
std::string getName() const;
std::vector<Node*>& getParents();
std::vector<Node*>& getChildren();
torch::Tensor& getCPT();
void computeCPT(const torch::Tensor& dataset, const vector<string>& features, const double laplaceSmoothing, const torch::Tensor& weights);
void computeCPT(const torch::Tensor& dataset, const std::vector<std::string>& features, const double laplaceSmoothing, const torch::Tensor& weights);
int getNumStates() const;
void setNumStates(int);
unsigned minFill();
vector<string> graph(const string& clasName); // Returns a vector of strings representing the graph in graphviz format
float getFactorValue(map<string, int>&);
std::vector<std::string> graph(const std::string& clasName); // Returns a std::vector of std::strings representing the graph in graphviz format
float getFactorValue(std::map<std::string, int>&);
};
}
#endif

36
src/BayesNet/Proposal.cc
View File

@ -2,7 +2,7 @@
#include "ArffFiles.h"
namespace bayesnet {
Proposal::Proposal(torch::Tensor& dataset_, vector<string>& features_, string& className_) : pDataset(dataset_), pFeatures(features_), pClassName(className_) {}
Proposal::Proposal(torch::Tensor& dataset_, std::vector<std::string>& features_, std::string& className_) : pDataset(dataset_), pFeatures(features_), pClassName(className_) {}
Proposal::~Proposal()
{
for (auto& [key, value] : discretizers) {
@ -18,14 +18,14 @@ namespace bayesnet {
throw std::invalid_argument("y must be an integer tensor");
}
}
map<string, vector<int>> Proposal::localDiscretizationProposal(const map<string, vector<int>>& oldStates, Network& model)
map<std::string, std::vector<int>> Proposal::localDiscretizationProposal(const map<std::string, std::vector<int>>& oldStates, Network& model)
{
// order of local discretization is important. no good 0, 1, 2...
// although we rediscretize features after the local discretization of every feature
auto order = model.topological_sort();
auto& nodes = model.getNodes();
map<string, vector<int>> states = oldStates;
vector<int> indicesToReDiscretize;
map<std::string, std::vector<int>> states = oldStates;
std::vector<int> indicesToReDiscretize;
bool upgrade = false; // Flag to check if we need to upgrade the model
for (auto feature : order) {
auto nodeParents = nodes[feature]->getParents();
@ -33,16 +33,16 @@ namespace bayesnet {
upgrade = true;
int index = find(pFeatures.begin(), pFeatures.end(), feature) - pFeatures.begin();
indicesToReDiscretize.push_back(index); // We need to re-discretize this feature
vector<string> parents;
std::vector<std::string> parents;
transform(nodeParents.begin(), nodeParents.end(), back_inserter(parents), [](const auto& p) { return p->getName(); });
// Remove class as parent as it will be added later
parents.erase(remove(parents.begin(), parents.end(), pClassName), parents.end());
// Get the indices of the parents
vector<int> indices;
std::vector<int> indices;
indices.push_back(-1); // Add class index
transform(parents.begin(), parents.end(), back_inserter(indices), [&](const auto& p) {return find(pFeatures.begin(), pFeatures.end(), p) - pFeatures.begin(); });
// Now we fit the discretizer of the feature, conditioned on its parents and the class i.e. discretizer.fit(X[index], X[indices] + y)
vector<string> yJoinParents(Xf.size(1));
std::vector<std::string> yJoinParents(Xf.size(1));
for (auto idx : indices) {
for (int i = 0; i < Xf.size(1); ++i) {
yJoinParents[i] += to_string(pDataset.index({ idx, i }).item<int>());
@ -51,16 +51,16 @@ namespace bayesnet {
auto arff = ArffFiles();
auto yxv = arff.factorize(yJoinParents);
auto xvf_ptr = Xf.index({ index }).data_ptr<float>();
auto xvf = vector<mdlp::precision_t>(xvf_ptr, xvf_ptr + Xf.size(1));
auto xvf = std::vector<mdlp::precision_t>(xvf_ptr, xvf_ptr + Xf.size(1));
discretizers[feature]->fit(xvf, yxv);
}
if (upgrade) {
// Discretize again X (only the affected indices) with the new fitted discretizers
for (auto index : indicesToReDiscretize) {
auto Xt_ptr = Xf.index({ index }).data_ptr<float>();
auto Xt = vector<float>(Xt_ptr, Xt_ptr + Xf.size(1));
auto Xt = std::vector<float>(Xt_ptr, Xt_ptr + Xf.size(1));
pDataset.index_put_({ index, "..." }, torch::tensor(discretizers[pFeatures[index]]->transform(Xt)));
auto xStates = vector<int>(discretizers[pFeatures[index]]->getCutPoints().size() + 1);
auto xStates = std::vector<int>(discretizers[pFeatures[index]]->getCutPoints().size() + 1);
iota(xStates.begin(), xStates.end(), 0);
//Update new states of the feature/node
states[pFeatures[index]] = xStates;
@ -70,28 +70,28 @@ namespace bayesnet {
}
return states;
}
map<string, vector<int>> Proposal::fit_local_discretization(const torch::Tensor& y)
map<std::string, std::vector<int>> Proposal::fit_local_discretization(const torch::Tensor& y)
{
// Discretize the continuous input data and build pDataset (Classifier::dataset)
int m = Xf.size(1);
int n = Xf.size(0);
map<string, vector<int>> states;
pDataset = torch::zeros({ n + 1, m }, kInt32);
auto yv = vector<int>(y.data_ptr<int>(), y.data_ptr<int>() + y.size(0));
map<std::string, std::vector<int>> states;
pDataset = torch::zeros({ n + 1, m }, torch::kInt32);
auto yv = std::vector<int>(y.data_ptr<int>(), y.data_ptr<int>() + y.size(0));
// discretize input data by feature(row)
for (auto i = 0; i < pFeatures.size(); ++i) {
auto* discretizer = new mdlp::CPPFImdlp();
auto Xt_ptr = Xf.index({ i }).data_ptr<float>();
auto Xt = vector<float>(Xt_ptr, Xt_ptr + Xf.size(1));
auto Xt = std::vector<float>(Xt_ptr, Xt_ptr + Xf.size(1));
discretizer->fit(Xt, yv);
pDataset.index_put_({ i, "..." }, torch::tensor(discretizer->transform(Xt)));
auto xStates = vector<int>(discretizer->getCutPoints().size() + 1);
auto xStates = std::vector<int>(discretizer->getCutPoints().size() + 1);
iota(xStates.begin(), xStates.end(), 0);
states[pFeatures[i]] = xStates;
discretizers[pFeatures[i]] = discretizer;
}
int n_classes = torch::max(y).item<int>() + 1;
auto yStates = vector<int>(n_classes);
auto yStates = std::vector<int>(n_classes);
iota(yStates.begin(), yStates.end(), 0);
states[pClassName] = yStates;
pDataset.index_put_({ n, "..." }, y);
@ -101,7 +101,7 @@ namespace bayesnet {
{
auto Xtd = torch::zeros_like(X, torch::kInt32);
for (int i = 0; i < X.size(0); ++i) {
auto Xt = vector<float>(X[i].data_ptr<float>(), X[i].data_ptr<float>() + X.size(1));
auto Xt = std::vector<float>(X[i].data_ptr<float>(), X[i].data_ptr<float>() + X.size(1));
auto Xd = discretizers[pFeatures[i]]->transform(Xt);
Xtd.index_put_({ i }, torch::tensor(Xd, torch::kInt32));
}

12
src/BayesNet/Proposal.h
View File

@ -10,20 +10,20 @@
namespace bayesnet {
class Proposal {
public:
Proposal(torch::Tensor& pDataset, vector<string>& features_, string& className_);
Proposal(torch::Tensor& pDataset, std::vector<std::string>& features_, std::string& className_);
virtual ~Proposal();
protected:
void checkInput(const torch::Tensor& X, const torch::Tensor& y);
torch::Tensor prepareX(torch::Tensor& X);
map<string, vector<int>> localDiscretizationProposal(const map<string, vector<int>>& states, Network& model);
map<string, vector<int>> fit_local_discretization(const torch::Tensor& y);
map<std::string, std::vector<int>> localDiscretizationProposal(const map<std::string, std::vector<int>>& states, Network& model);
map<std::string, std::vector<int>> fit_local_discretization(const torch::Tensor& y);
torch::Tensor Xf; // X continuous nxm tensor
torch::Tensor y; // y discrete nx1 tensor
map<string, mdlp::CPPFImdlp*> discretizers;
map<std::string, mdlp::CPPFImdlp*> discretizers;
private:
torch::Tensor& pDataset; // (n+1)xm tensor
vector<string>& pFeatures;
string& pClassName;
std::vector<std::string>& pFeatures;
std::string& pClassName;
};
}

2
src/BayesNet/SPODE.cc
View File

@ -17,7 +17,7 @@ namespace bayesnet {
}
}
}
vector<string> SPODE::graph(const string& name) const
std::vector<std::string> SPODE::graph(const std::string& name) const
{
return model.graph(name);
}

2
src/BayesNet/SPODE.h
View File

@ -11,7 +11,7 @@ namespace bayesnet {
public:
explicit SPODE(int root);
virtual ~SPODE() {};
vector<string> graph(const string& name = "SPODE") const override;
std::vector<std::string> graph(const std::string& name = "SPODE") const override;
};
}
#endif

13
src/BayesNet/SPODELd.cc
View File

@ -1,16 +1,15 @@
#include "SPODELd.h"
namespace bayesnet {
using namespace std;
SPODELd::SPODELd(int root) : SPODE(root), Proposal(dataset, features, className) {}
SPODELd& SPODELd::fit(torch::Tensor& X_, torch::Tensor& y_, const vector<string>& features_, const string& className_, map<string, vector<int>>& states_)
SPODELd& SPODELd::fit(torch::Tensor& X_, torch::Tensor& y_, const std::vector<std::string>& features_, const std::string& className_, map<std::string, std::vector<int>>& states_)
{
checkInput(X_, y_);
features = features_;
className = className_;
Xf = X_;
y = y_;
// Fills vectors Xv & yv with the data from tensors X_ (discretized) & y
// Fills std::vectors Xv & yv with the data from tensors X_ (discretized) & y
states = fit_local_discretization(y);
// We have discretized the input data
// 1st we need to fit the model to build the normal SPODE structure, SPODE::fit initializes the base Bayesian network
@ -18,7 +17,7 @@ namespace bayesnet {
states = localDiscretizationProposal(states, model);
return *this;
}
SPODELd& SPODELd::fit(torch::Tensor& dataset, const vector<string>& features_, const string& className_, map<string, vector<int>>& states_)
SPODELd& SPODELd::fit(torch::Tensor& dataset, const std::vector<std::string>& features_, const std::string& className_, map<std::string, std::vector<int>>& states_)
{
if (!torch::is_floating_point(dataset)) {
throw std::runtime_error("Dataset must be a floating point tensor");
@ -27,7 +26,7 @@ namespace bayesnet {
y = dataset.index({ -1, "..." }).clone();
features = features_;
className = className_;
// Fills vectors Xv & yv with the data from tensors X_ (discretized) & y
// Fills std::vectors Xv & yv with the data from tensors X_ (discretized) & y
states = fit_local_discretization(y);
// We have discretized the input data
// 1st we need to fit the model to build the normal SPODE structure, SPODE::fit initializes the base Bayesian network
@ -36,12 +35,12 @@ namespace bayesnet {
return *this;
}
Tensor SPODELd::predict(Tensor& X)
torch::Tensor SPODELd::predict(torch::Tensor& X)
{
auto Xt = prepareX(X);
return SPODE::predict(Xt);
}
vector<string> SPODELd::graph(const string& name) const
std::vector<std::string> SPODELd::graph(const std::string& name) const
{
return SPODE::graph(name);
}

11
src/BayesNet/SPODELd.h
View File

@ -4,16 +4,15 @@
#include "Proposal.h"
namespace bayesnet {
using namespace std;
class SPODELd : public SPODE, public Proposal {
public:
explicit SPODELd(int root);
virtual ~SPODELd() = default;
SPODELd& fit(torch::Tensor& X, torch::Tensor& y, const vector<string>& features, const string& className, map<string, vector<int>>& states) override;
SPODELd& fit(torch::Tensor& dataset, const vector<string>& features, const string& className, map<string, vector<int>>& states) override;
vector<string> graph(const string& name = "SPODE") const override;
Tensor predict(Tensor& X) override;
static inline string version() { return "0.0.1"; };
SPODELd& fit(torch::Tensor& X, torch::Tensor& y, const std::vector<std::string>& features, const std::string& className, map<std::string, std::vector<int>>& states) override;
SPODELd& fit(torch::Tensor& dataset, const std::vector<std::string>& features, const std::string& className, map<std::string, std::vector<int>>& states) override;
std::vector<std::string> graph(const std::string& name = "SPODE") const override;
torch::Tensor predict(torch::Tensor& X) override;
static inline std::string version() { return "0.0.1"; };
};
}
#endif // !SPODELD_H

10
src/BayesNet/TAN.cc
View File

@ -1,8 +1,6 @@
#include "TAN.h"
namespace bayesnet {
using namespace torch;
TAN::TAN() : Classifier(Network()) {}
void TAN::buildModel(const torch::Tensor& weights)
@ -11,10 +9,10 @@ namespace bayesnet {
addNodes();
// 1. Compute mutual information between each feature and the class and set the root node
// as the highest mutual information with the class
auto mi = vector <pair<int, float >>();
Tensor class_dataset = dataset.index({ -1, "..." });
auto mi = std::vector <std::pair<int, float >>();
torch::Tensor class_dataset = dataset.index({ -1, "..." });
for (int i = 0; i < static_cast<int>(features.size()); ++i) {
Tensor feature_dataset = dataset.index({ i, "..." });
torch::Tensor feature_dataset = dataset.index({ i, "..." });
auto mi_value = metrics.mutualInformation(class_dataset, feature_dataset, weights);
mi.push_back({ i, mi_value });
}
@ -34,7 +32,7 @@ namespace bayesnet {
model.addEdge(className, feature);
}
}
vector<string> TAN::graph(const string& title) const
std::vector<std::string> TAN::graph(const std::string& title) const
{
return model.graph(title);
}

3
src/BayesNet/TAN.h
View File

@ -2,7 +2,6 @@
#define TAN_H
#include "Classifier.h"
namespace bayesnet {
using namespace std;
class TAN : public Classifier {
private:
protected:
@ -10,7 +9,7 @@ namespace bayesnet {
public:
TAN();
virtual ~TAN() {};
vector<string> graph(const string& name = "TAN") const override;
std::vector<std::string> graph(const std::string& name = "TAN") const override;
};
}
#endif

9
src/BayesNet/TANLd.cc
View File

@ -1,16 +1,15 @@
#include "TANLd.h"
namespace bayesnet {
using namespace std;
TANLd::TANLd() : TAN(), Proposal(dataset, features, className) {}
TANLd& TANLd::fit(torch::Tensor& X_, torch::Tensor& y_, const vector<string>& features_, const string& className_, map<string, vector<int>>& states_)
TANLd& TANLd::fit(torch::Tensor& X_, torch::Tensor& y_, const std::vector<std::string>& features_, const std::string& className_, map<std::string, std::vector<int>>& states_)
{
checkInput(X_, y_);
features = features_;
className = className_;
Xf = X_;
y = y_;
// Fills vectors Xv & yv with the data from tensors X_ (discretized) & y
// Fills std::vectors Xv & yv with the data from tensors X_ (discretized) & y
states = fit_local_discretization(y);
// We have discretized the input data
// 1st we need to fit the model to build the normal TAN structure, TAN::fit initializes the base Bayesian network
@ -19,12 +18,12 @@ namespace bayesnet {
return *this;
}
Tensor TANLd::predict(Tensor& X)
torch::Tensor TANLd::predict(torch::Tensor& X)
{
auto Xt = prepareX(X);
return TAN::predict(Xt);
}
vector<string> TANLd::graph(const string& name) const
std::vector<std::string> TANLd::graph(const std::string& name) const
{
return TAN::graph(name);
}

9
src/BayesNet/TANLd.h
View File

@ -4,16 +4,15 @@
#include "Proposal.h"
namespace bayesnet {
using namespace std;
class TANLd : public TAN, public Proposal {
private:
public:
TANLd();
virtual ~TANLd() = default;
TANLd& fit(torch::Tensor& X, torch::Tensor& y, const vector<string>& features, const string& className, map<string, vector<int>>& states) override;
vector<string> graph(const string& name = "TAN") const override;
Tensor predict(Tensor& X) override;
static inline string version() { return "0.0.1"; };
TANLd& fit(torch::Tensor& X, torch::Tensor& y, const std::vector<std::string>& features, const std::string& className, map<std::string, std::vector<int>>& states) override;
std::vector<std::string> graph(const std::string& name = "TAN") const override;
torch::Tensor predict(torch::Tensor& X) override;
static inline std::string version() { return "0.0.1"; };
};
}
#endif // !TANLD_H

14
src/BayesNet/bayesnetUtils.cc
View File

@ -1,25 +1,23 @@
#include "bayesnetUtils.h"
namespace bayesnet {
using namespace std;
using namespace torch;
// Return the indices in descending order
vector<int> argsort(vector<double>& nums)
std::vector<int> argsort(std::vector<double>& nums)
{
int n = nums.size();
vector<int> indices(n);
std::vector<int> indices(n);
iota(indices.begin(), indices.end(), 0);
sort(indices.begin(), indices.end(), [&nums](int i, int j) {return nums[i] > nums[j];});
return indices;
}
vector<vector<int>> tensorToVector(Tensor& tensor)
std::vector<std::vector<int>> tensorToVector(torch::Tensor& tensor)
{
// convert mxn tensor to nxm vector
vector<vector<int>> result;
// convert mxn tensor to nxm std::vector
std::vector<std::vector<int>> result;
// Iterate over cols
for (int i = 0; i < tensor.size(1); ++i) {
auto col_tensor = tensor.index({ "...", i });
auto col = vector<int>(col_tensor.data_ptr<int>(), col_tensor.data_ptr<int>() + tensor.size(0));
auto col = std::vector<int>(col_tensor.data_ptr<int>(), col_tensor.data_ptr<int>() + tensor.size(0));
result.push_back(col);
}
return result;

6
src/BayesNet/bayesnetUtils.h
View File

@ -3,9 +3,7 @@
#include <torch/torch.h>
#include <vector>
namespace bayesnet {
using namespace std;
using namespace torch;
vector<int> argsort(vector<double>& nums);
vector<vector<int>> tensorToVector(Tensor& tensor);
std::vector<int> argsort(std::vector<double>& nums);
std::vector<std::vector<int>> tensorToVector(torch::Tensor& tensor);
}
#endif //BAYESNET_UTILS_H

181
src/Platform/BestResults.cc
View File

@ -13,26 +13,25 @@
namespace fs = std::filesystem;
// function ftime_to_string, Code taken from
// function ftime_to_std::string, Code taken from
// https://stackoverflow.com/a/58237530/1389271
template <typename TP>
std::string ftime_to_string(TP tp)
{
using namespace std::chrono;
auto sctp = time_point_cast<system_clock::duration>(tp - TP::clock::now()
+ system_clock::now());
auto tt = system_clock::to_time_t(sctp);
auto sctp = std::chrono::time_point_cast<std::chrono::system_clock::duration>(tp - TP::clock::now()
+ std::chrono::system_clock::now());
auto tt = std::chrono::system_clock::to_time_t(sctp);
std::tm* gmt = std::gmtime(&tt);
std::stringstream buffer;
buffer << std::put_time(gmt, "%Y-%m-%d %H:%M");
return buffer.str();
}
namespace platform {
string BestResults::build()
std::string BestResults::build()
{
auto files = loadResultFiles();
if (files.size() == 0) {
cerr << Colors::MAGENTA() << "No result files were found!" << Colors::RESET() << endl;
std::cerr << Colors::MAGENTA() << "No result files were found!" << Colors::RESET() << std::endl;
exit(1);
}
json bests;
@ -42,7 +41,7 @@ namespace platform {
for (auto const& item : data.at("results")) {
bool update = false;
// Check if results file contains only one dataset
auto datasetName = item.at("dataset").get<string>();
auto datasetName = item.at("dataset").get<std::string>();
if (bests.contains(datasetName)) {
if (item.at("score").get<double>() > bests[datasetName].at(0).get<double>()) {
update = true;
@ -55,39 +54,39 @@ namespace platform {
}
}
}
string bestFileName = path + bestResultFile();
std::string bestFileName = path + bestResultFile();
if (FILE* fileTest = fopen(bestFileName.c_str(), "r")) {
fclose(fileTest);
cout << Colors::MAGENTA() << "File " << bestFileName << " already exists and it shall be overwritten." << Colors::RESET() << endl;
std::cout << Colors::MAGENTA() << "File " << bestFileName << " already exists and it shall be overwritten." << Colors::RESET() << std::endl;
}
ofstream file(bestFileName);
std::ofstream file(bestFileName);
file << bests;
file.close();
return bestFileName;
}
string BestResults::bestResultFile()
std::string BestResults::bestResultFile()
{
return "best_results_" + score + "_" + model + ".json";
}
pair<string, string> getModelScore(string name)
std::pair<std::string, std::string> getModelScore(std::string name)
{
// results_accuracy_BoostAODE_MacBookpro16_2023-09-06_12:27:00_1.json
int i = 0;
auto pos = name.find("_");
auto pos2 = name.find("_", pos + 1);
string score = name.substr(pos + 1, pos2 - pos - 1);
std::string score = name.substr(pos + 1, pos2 - pos - 1);
pos = name.find("_", pos2 + 1);
string model = name.substr(pos2 + 1, pos - pos2 - 1);
std::string model = name.substr(pos2 + 1, pos - pos2 - 1);
return { model, score };
}
vector<string> BestResults::loadResultFiles()
std::vector<std::string> BestResults::loadResultFiles()
{
vector<string> files;
std::vector<std::string> files;
using std::filesystem::directory_iterator;
string fileModel, fileScore;
std::string fileModel, fileScore;
for (const auto& file : directory_iterator(path)) {
auto fileName = file.path().filename().string();
if (fileName.find(".json") != string::npos && fileName.find("results_") == 0) {
if (fileName.find(".json") != std::string::npos && fileName.find("results_") == 0) {
tie(fileModel, fileScore) = getModelScore(fileName);
if (score == fileScore && (model == fileModel || model == "any")) {
files.push_back(fileName);
@ -96,37 +95,37 @@ namespace platform {
}
return files;
}
json BestResults::loadFile(const string& fileName)
json BestResults::loadFile(const std::string& fileName)
{
ifstream resultData(fileName);
std::ifstream resultData(fileName);
if (resultData.is_open()) {
json data = json::parse(resultData);
return data;
}
throw invalid_argument("Unable to open result file. [" + fileName + "]");
throw std::invalid_argument("Unable to open result file. [" + fileName + "]");
}
vector<string> BestResults::getModels()
std::vector<std::string> BestResults::getModels()
{
set<string> models;
vector<string> result;
std::set<std::string> models;
std::vector<std::string> result;
auto files = loadResultFiles();
if (files.size() == 0) {
cerr << Colors::MAGENTA() << "No result files were found!" << Colors::RESET() << endl;
std::cerr << Colors::MAGENTA() << "No result files were found!" << Colors::RESET() << std::endl;
exit(1);
}
string fileModel, fileScore;
std::string fileModel, fileScore;
for (const auto& file : files) {
// extract the model from the file name
tie(fileModel, fileScore) = getModelScore(file);
// add the model to the vector of models
// add the model to the std::vector of models
models.insert(fileModel);
}
result = vector<string>(models.begin(), models.end());
result = std::vector<std::string>(models.begin(), models.end());
return result;
}
vector<string> BestResults::getDatasets(json table)
std::vector<std::string> BestResults::getDatasets(json table)
{
vector<string> datasets;
std::vector<std::string> datasets;
for (const auto& dataset : table.items()) {
datasets.push_back(dataset.key());
}
@ -136,7 +135,7 @@ namespace platform {
{
auto models = getModels();
for (const auto& model : models) {
cout << "Building best results for model: " << model << endl;
std::cout << "Building best results for model: " << model << std::endl;
this->model = model;
build();
}
@ -144,62 +143,62 @@ namespace platform {
}
void BestResults::listFile()
{
string bestFileName = path + bestResultFile();
std::string bestFileName = path + bestResultFile();
if (FILE* fileTest = fopen(bestFileName.c_str(), "r")) {
fclose(fileTest);
} else {
cerr << Colors::MAGENTA() << "File " << bestFileName << " doesn't exist." << Colors::RESET() << endl;
std::cerr << Colors::MAGENTA() << "File " << bestFileName << " doesn't exist." << Colors::RESET() << std::endl;
exit(1);
}
auto temp = ConfigLocale();
auto date = ftime_to_string(filesystem::last_write_time(bestFileName));
auto date = ftime_to_string(std::filesystem::last_write_time(bestFileName));
auto data = loadFile(bestFileName);
auto datasets = getDatasets(data);
int maxDatasetName = (*max_element(datasets.begin(), datasets.end(), [](const string& a, const string& b) { return a.size() < b.size(); })).size();
int maxDatasetName = (*max_element(datasets.begin(), datasets.end(), [](const std::string& a, const std::string& b) { return a.size() < b.size(); })).size();
int maxFileName = 0;
int maxHyper = 15;
for (auto const& item : data.items()) {
maxHyper = max(maxHyper, (int)item.value().at(1).dump().size());
maxFileName = max(maxFileName, (int)item.value().at(2).get<string>().size());
maxHyper = std::max(maxHyper, (int)item.value().at(1).dump().size());
maxFileName = std::max(maxFileName, (int)item.value().at(2).get<std::string>().size());
}
stringstream oss;
oss << Colors::GREEN() << "Best results for " << model << " as of " << date << endl;
cout << oss.str();
cout << string(oss.str().size() - 8, '-') << endl;
cout << Colors::GREEN() << " # " << setw(maxDatasetName + 1) << left << "Dataset" << "Score " << setw(maxFileName) << "File" << " Hyperparameters" << endl;
cout << "=== " << string(maxDatasetName, '=') << " =========== " << string(maxFileName, '=') << " " << string(maxHyper, '=') << endl;
std::stringstream oss;
oss << Colors::GREEN() << "Best results for " << model << " as of " << date << std::endl;
std::cout << oss.str();
std::cout << std::string(oss.str().size() - 8, '-') << std::endl;
std::cout << Colors::GREEN() << " # " << std::setw(maxDatasetName + 1) << std::left << "Dataset" << "Score " << std::setw(maxFileName) << "File" << " Hyperparameters" << std::endl;
std::cout << "=== " << std::string(maxDatasetName, '=') << " =========== " << std::string(maxFileName, '=') << " " << std::string(maxHyper, '=') << std::endl;
auto i = 0;
bool odd = true;
double total = 0;
for (auto const& item : data.items()) {
auto color = odd ? Colors::BLUE() : Colors::CYAN();
double value = item.value().at(0).get<double>();
cout << color << setw(3) << fixed << right << i++ << " ";
cout << setw(maxDatasetName) << left << item.key() << " ";
cout << setw(11) << setprecision(9) << fixed << value << " ";
cout << setw(maxFileName) << item.value().at(2).get<string>() << " ";
cout << item.value().at(1) << " ";
cout << endl;
std::cout << color << std::setw(3) << std::fixed << std::right << i++ << " ";
std::cout << std::setw(maxDatasetName) << std::left << item.key() << " ";
std::cout << std::setw(11) << std::setprecision(9) << std::fixed << value << " ";
std::cout << std::setw(maxFileName) << item.value().at(2).get<std::string>() << " ";
std::cout << item.value().at(1) << " ";
std::cout << std::endl;
total += value;
odd = !odd;
}
cout << Colors::GREEN() << "=== " << string(maxDatasetName, '=') << " ===========" << endl;
cout << setw(5 + maxDatasetName) << "Total.................. " << setw(11) << setprecision(8) << fixed << total << endl;
std::cout << Colors::GREEN() << "=== " << std::string(maxDatasetName, '=') << " ===========" << std::endl;
std::cout << std::setw(5 + maxDatasetName) << "Total.................. " << std::setw(11) << std::setprecision(8) << std::fixed << total << std::endl;
}
json BestResults::buildTableResults(vector<string> models)
json BestResults::buildTableResults(std::vector<std::string> models)
{
json table;
auto maxDate = filesystem::file_time_type::max();
auto maxDate = std::filesystem::file_time_type::max();
for (const auto& model : models) {
this->model = model;
string bestFileName = path + bestResultFile();
std::string bestFileName = path + bestResultFile();
if (FILE* fileTest = fopen(bestFileName.c_str(), "r")) {
fclose(fileTest);
} else {
cerr << Colors::MAGENTA() << "File " << bestFileName << " doesn't exist." << Colors::RESET() << endl;
std::cerr << Colors::MAGENTA() << "File " << bestFileName << " doesn't exist." << Colors::RESET() << std::endl;
exit(1);
}
auto dateWrite = filesystem::last_write_time(bestFileName);
auto dateWrite = std::filesystem::last_write_time(bestFileName);
if (dateWrite < maxDate) {
maxDate = dateWrite;
}
@ -209,25 +208,25 @@ namespace platform {
table["dateTable"] = ftime_to_string(maxDate);
return table;
}
void BestResults::printTableResults(vector<string> models, json table)
void BestResults::printTableResults(std::vector<std::string> models, json table)
{
stringstream oss;
oss << Colors::GREEN() << "Best results for " << score << " as of " << table.at("dateTable").get<string>() << endl;
cout << oss.str();
cout << string(oss.str().size() - 8, '-') << endl;
cout << Colors::GREEN() << " # " << setw(maxDatasetName + 1) << left << string("Dataset");
std::stringstream oss;
oss << Colors::GREEN() << "Best results for " << score << " as of " << table.at("dateTable").get<std::string>() << std::endl;
std::cout << oss.str();
std::cout << std::string(oss.str().size() - 8, '-') << std::endl;
std::cout << Colors::GREEN() << " # " << std::setw(maxDatasetName + 1) << std::left << std::string("Dataset");
for (const auto& model : models) {
cout << setw(maxModelName) << left << model << " ";
std::cout << std::setw(maxModelName) << std::left << model << " ";
}
cout << endl;
cout << "=== " << string(maxDatasetName, '=') << " ";
std::cout << std::endl;
std::cout << "=== " << std::string(maxDatasetName, '=') << " ";
for (const auto& model : models) {
cout << string(maxModelName, '=') << " ";
std::cout << std::string(maxModelName, '=') << " ";
}
cout << endl;
std::cout << std::endl;
auto i = 0;
bool odd = true;
map<string, double> totals;
std::map<std::string, double> totals;
int nDatasets = table.begin().value().size();
for (const auto& model : models) {
totals[model] = 0.0;
@ -235,8 +234,8 @@ namespace platform {
auto datasets = getDatasets(table.begin().value());
for (auto const& dataset : datasets) {
auto color = odd ? Colors::BLUE() : Colors::CYAN();
cout << color << setw(3) << fixed << right << i++ << " ";
cout << setw(maxDatasetName) << left << dataset << " ";
std::cout << color << std::setw(3) << std::fixed << std::right << i++ << " ";
std::cout << std::setw(maxDatasetName) << std::left << dataset << " ";
double maxValue = 0;
// Find out the max value for this dataset
for (const auto& model : models) {
@ -247,23 +246,23 @@ namespace platform {
}
// Print the row with red colors on max values
for (const auto& model : models) {
string efectiveColor = color;
std::string efectiveColor = color;
double value = table[model].at(dataset).at(0).get<double>();
if (value == maxValue) {
efectiveColor = Colors::RED();
}
totals[model] += value;
cout << efectiveColor << setw(maxModelName) << setprecision(maxModelName - 2) << fixed << value << " ";
std::cout << efectiveColor << std::setw(maxModelName) << std::setprecision(maxModelName - 2) << std::fixed << value << " ";
}
cout << endl;
std::cout << std::endl;
odd = !odd;
}
cout << Colors::GREEN() << "=== " << string(maxDatasetName, '=') << " ";
std::cout << Colors::GREEN() << "=== " << std::string(maxDatasetName, '=') << " ";
for (const auto& model : models) {
cout << string(maxModelName, '=') << " ";
std::cout << std::string(maxModelName, '=') << " ";
}
cout << endl;
cout << Colors::GREEN() << setw(5 + maxDatasetName) << " Totals...................";
std::cout << std::endl;
std::cout << Colors::GREEN() << std::setw(5 + maxDatasetName) << " Totals...................";
double max = 0.0;
for (const auto& total : totals) {
if (total.second > max) {
@ -271,13 +270,13 @@ namespace platform {
}
}
for (const auto& model : models) {
string efectiveColor = Colors::GREEN();
std::string efectiveColor = Colors::GREEN();
if (totals[model] == max) {
efectiveColor = Colors::RED();
}
cout << efectiveColor << right << setw(maxModelName) << setprecision(maxModelName - 4) << fixed << totals[model] << " ";
std::cout << efectiveColor << std::right << std::setw(maxModelName) << std::setprecision(maxModelName - 4) << std::fixed << totals[model] << " ";
}
cout << endl;
std::cout << std::endl;
}
void BestResults::reportSingle(bool excel)
{
@ -286,7 +285,7 @@ namespace platform {
auto models = getModels();
// Build the table of results
json table = buildTableResults(models);
vector<string> datasets = getDatasets(table.begin().value());
std::vector<std::string> datasets = getDatasets(table.begin().value());
BestResultsExcel excel(score, datasets);
excel.reportSingle(model, path + bestResultFile());
messageExcelFile(excel.getFileName());
@ -297,15 +296,15 @@ namespace platform {
auto models = getModels();
// Build the table of results
json table = buildTableResults(models);
vector<string> datasets = getDatasets(table.begin().value());
maxModelName = (*max_element(models.begin(), models.end(), [](const string& a, const string& b) { return a.size() < b.size(); })).size();
maxModelName = max(12, maxModelName);
maxDatasetName = (*max_element(datasets.begin(), datasets.end(), [](const string& a, const string& b) { return a.size() < b.size(); })).size();
maxDatasetName = max(25, maxDatasetName);
std::vector<std::string> datasets = getDatasets(table.begin().value());
maxModelName = (*max_element(models.begin(), models.end(), [](const std::string& a, const std::string& b) { return a.size() < b.size(); })).size();
maxModelName = std::max(12, maxModelName);
maxDatasetName = (*max_element(datasets.begin(), datasets.end(), [](const std::string& a, const std::string& b) { return a.size() < b.size(); })).size();
maxDatasetName = std::max(25, maxDatasetName);
// Print the table of results
printTableResults(models, table);
// Compute the Friedman test
map<string, map<string, float>> ranksModels;
std::map<std::string, std::map<std::string, float>> ranksModels;
if (friedman) {
Statistics stats(models, datasets, table, significance);
auto result = stats.friedmanTest();
@ -319,7 +318,7 @@ namespace platform {
int idx = -1;
double min = 2000;
// Find out the control model
auto totals = vector<double>(models.size(), 0.0);
auto totals = std::vector<double>(models.size(), 0.0);
for (const auto& dataset : datasets) {
for (int i = 0; i < models.size(); ++i) {
totals[i] += ranksModels[dataset][models[i]];
@ -337,8 +336,8 @@ namespace platform {
messageExcelFile(excel.getFileName());
}
}
void BestResults::messageExcelFile(const string& fileName)
void BestResults::messageExcelFile(const std::string& fileName)
{
cout << Colors::YELLOW() << "** Excel file generated: " << fileName << Colors::RESET() << endl;
std::cout << Colors::YELLOW() << "** Excel file generated: " << fileName << Colors::RESET() << std::endl;
}
}

27
src/Platform/BestResults.h
View File

@ -2,32 +2,31 @@
#define BESTRESULTS_H
#include <string>
#include <nlohmann/json.hpp>
using namespace std;
using json = nlohmann::json;
namespace platform {
class BestResults {
public:
explicit BestResults(const string& path, const string& score, const string& model, bool friedman, double significance = 0.05)
explicit BestResults(const std::string& path, const std::string& score, const std::string& model, bool friedman, double significance = 0.05)
: path(path), score(score), model(model), friedman(friedman), significance(significance)
{
}
string build();
std::string build();
void reportSingle(bool excel);
void reportAll(bool excel);
void buildAll();
private:
vector<string> getModels();
vector<string> getDatasets(json table);
vector<string> loadResultFiles();
void messageExcelFile(const string& fileName);
json buildTableResults(vector<string> models);
void printTableResults(vector<string> models, json table);
string bestResultFile();
json loadFile(const string& fileName);
std::vector<std::string> getModels();
std::vector<std::string> getDatasets(json table);
std::vector<std::string> loadResultFiles();
void messageExcelFile(const std::string& fileName);
json buildTableResults(std::vector<std::string> models);
void printTableResults(std::vector<std::string> models, json table);
std::string bestResultFile();
json loadFile(const std::string& fileName);
void listFile();
string path;
string score;
string model;
std::string path;
std::string score;
std::string model;
bool friedman;
double significance;
int maxModelName = 0;

70
src/Platform/BestResultsExcel.cc
View File

@ -7,20 +7,20 @@
#include "ReportExcel.h"
namespace platform {
json loadResultData(const string& fileName)
json loadResultData(const std::string& fileName)
{
json data;
ifstream resultData(fileName);
std::ifstream resultData(fileName);
if (resultData.is_open()) {
data = json::parse(resultData);
} else {
throw invalid_argument("Unable to open result file. [" + fileName + "]");
throw std::invalid_argument("Unable to open result file. [" + fileName + "]");
}
return data;
}
string getColumnName(int colNum)
std::string getColumnName(int colNum)
{
string columnName = "";
std::string columnName = "";
if (colNum == 0)
return "A";
while (colNum > 0) {
@ -30,15 +30,15 @@ namespace platform {
}
return columnName;
}
BestResultsExcel::BestResultsExcel(const string& score, const vector<string>& datasets) : score(score), datasets(datasets)
BestResultsExcel::BestResultsExcel(const std::string& score, const std::vector<std::string>& datasets) : score(score), datasets(datasets)
{
workbook = workbook_new((Paths::excel() + fileName).c_str());
setProperties("Best Results");
int maxDatasetName = (*max_element(datasets.begin(), datasets.end(), [](const string& a, const string& b) { return a.size() < b.size(); })).size();
datasetNameSize = max(datasetNameSize, maxDatasetName);
int maxDatasetName = (*max_element(datasets.begin(), datasets.end(), [](const std::string& a, const std::string& b) { return a.size() < b.size(); })).size();
datasetNameSize = std::max(datasetNameSize, maxDatasetName);
createFormats();
}
void BestResultsExcel::reportAll(const vector<string>& models, const json& table, const map<string, map<string, float>>& ranks, bool friedman, double significance)
void BestResultsExcel::reportAll(const std::vector<std::string>& models, const json& table, const std::map<std::string, std::map<std::string, float>>& ranks, bool friedman, double significance)
{
this->table = table;
this->models = models;
@ -46,23 +46,23 @@ namespace platform {
this->friedman = friedman;
this->significance = significance;
worksheet = workbook_add_worksheet(workbook, "Best Results");
int maxModelName = (*max_element(models.begin(), models.end(), [](const string& a, const string& b) { return a.size() < b.size(); })).size();
modelNameSize = max(modelNameSize, maxModelName);
int maxModelName = (*std::max_element(models.begin(), models.end(), [](const std::string& a, const std::string& b) { return a.size() < b.size(); })).size();
modelNameSize = std::max(modelNameSize, maxModelName);
formatColumns();
build();
}
void BestResultsExcel::reportSingle(const string& model, const string& fileName)
void BestResultsExcel::reportSingle(const std::string& model, const std::string& fileName)
{
worksheet = workbook_add_worksheet(workbook, "Report");
if (FILE* fileTest = fopen(fileName.c_str(), "r")) {
fclose(fileTest);
} else {
cerr << "File " << fileName << " doesn't exist." << endl;
std::cerr << "File " << fileName << " doesn't exist." << std::endl;
exit(1);
}
json data = loadResultData(fileName);
string title = "Best results for " + model;
std::string title = "Best results for " + model;
worksheet_merge_range(worksheet, 0, 0, 0, 4, title.c_str(), styles["headerFirst"]);
// Body header
row = 3;
@ -73,30 +73,30 @@ namespace platform {
writeString(row, 3, "File", "bodyHeader");
writeString(row, 4, "Hyperparameters", "bodyHeader");
auto i = 0;
string hyperparameters;
std::string hyperparameters;
int hypSize = 22;
map<string, string> files; // map of files imported and their tabs
std::map<std::string, std::string> files; // map of files imported and their tabs
for (auto const& item : data.items()) {
row++;
writeInt(row, 0, i++, "ints");
writeString(row, 1, item.key().c_str(), "text");
writeDouble(row, 2, item.value().at(0).get<double>(), "result");
auto fileName = item.value().at(2).get<string>();
string hyperlink = "";
auto fileName = item.value().at(2).get<std::string>();
std::string hyperlink = "";
try {
hyperlink = files.at(fileName);
}
catch (const out_of_range& oor) {
auto tabName = "table_" + to_string(i);
catch (const std::out_of_range& oor) {
auto tabName = "table_" + std::to_string(i);
auto worksheetNew = workbook_add_worksheet(workbook, tabName.c_str());
json data = loadResultData(Paths::results() + fileName);
auto report = ReportExcel(data, false, workbook, worksheetNew);
report.show();
hyperlink = "#table_" + to_string(i);
hyperlink = "#table_" + std::to_string(i);
files[fileName] = hyperlink;
}
hyperlink += "!H" + to_string(i + 6);
string fileNameText = "=HYPERLINK(\"" + hyperlink + "\",\"" + fileName + "\")";
hyperlink += "!H" + std::to_string(i + 6);
std::string fileNameText = "=HYPERLINK(\"" + hyperlink + "\",\"" + fileName + "\")";
worksheet_write_formula(worksheet, row, 3, fileNameText.c_str(), efectiveStyle("text"));
hyperparameters = item.value().at(1).dump();
if (hyperparameters.size() > hypSize) {
@ -107,13 +107,13 @@ namespace platform {
row++;
// Set Totals
writeString(row, 1, "Total", "bodyHeader");
stringstream oss;
std::stringstream oss;
auto colName = getColumnName(2);
oss << "=sum(" << colName << "5:" << colName << row << ")";
worksheet_write_formula(worksheet, row, 2, oss.str().c_str(), styles["bodyHeader_odd"]);
// Set format
worksheet_freeze_panes(worksheet, 4, 2);
vector<int> columns_sizes = { 5, datasetNameSize, modelNameSize, 66, hypSize + 1 };
std::vector<int> columns_sizes = { 5, datasetNameSize, modelNameSize, 66, hypSize + 1 };
for (int i = 0; i < columns_sizes.size(); ++i) {
worksheet_set_column(worksheet, i, i, columns_sizes.at(i), NULL);
}
@ -125,7 +125,7 @@ namespace platform {
void BestResultsExcel::formatColumns()
{
worksheet_freeze_panes(worksheet, 4, 2);
vector<int> columns_sizes = { 5, datasetNameSize };
std::vector<int> columns_sizes = { 5, datasetNameSize };
for (int i = 0; i < models.size(); ++i) {
columns_sizes.push_back(modelNameSize);
}
@ -133,7 +133,7 @@ namespace platform {
worksheet_set_column(worksheet, i, i, columns_sizes.at(i), NULL);
}
}
void BestResultsExcel::addConditionalFormat(string formula)
void BestResultsExcel::addConditionalFormat(std::string formula)
{
// Add conditional format for max/min values in scores/ranks sheets
lxw_format* custom_format = workbook_add_format(workbook);
@ -142,8 +142,8 @@ namespace platform {
// Create a conditional format object. A static object would also work.
lxw_conditional_format* conditional_format = (lxw_conditional_format*)calloc(1, sizeof(lxw_conditional_format));
conditional_format->type = LXW_CONDITIONAL_TYPE_FORMULA;
string col = getColumnName(models.size() + 1);
stringstream oss;
std::string col = getColumnName(models.size() + 1);
std::stringstream oss;
oss << "=C5=" << formula << "($C5:$" << col << "5)";
auto formulaValue = oss.str();
conditional_format->value_string = formulaValue.c_str();
@ -170,14 +170,14 @@ namespace platform {
doFriedman();
}
}
string BestResultsExcel::getFileName()
std::string BestResultsExcel::getFileName()
{
return Paths::excel() + fileName;
}
void BestResultsExcel::header(bool ranks)
{
row = 0;
string message = ranks ? "Ranks for score " + score : "Best results for " + score;
std::string message = ranks ? "Ranks for score " + score : "Best results for " + score;
worksheet_merge_range(worksheet, 0, 0, 0, 1 + models.size(), message.c_str(), styles["headerFirst"]);
// Body header
row = 3;
@ -210,7 +210,7 @@ namespace platform {
writeString(row, 1, "Total", "bodyHeader");
int col = 1;
for (const auto& model : models) {
stringstream oss;
std::stringstream oss;
auto colName = getColumnName(col + 1);
oss << "=SUM(" << colName << "5:" << colName << row << ")";
worksheet_write_formula(worksheet, row, ++col, oss.str().c_str(), styles["bodyHeader_odd"]);
@ -221,7 +221,7 @@ namespace platform {
int col = 1;
for (const auto& model : models) {
auto colName = getColumnName(col + 1);
stringstream oss;
std::stringstream oss;
oss << "=SUM(" << colName << "5:" << colName << row - 1 << ")/" << datasets.size();
worksheet_write_formula(worksheet, row, ++col, oss.str().c_str(), styles["bodyHeader_odd"]);
}
@ -230,7 +230,7 @@ namespace platform {
void BestResultsExcel::doFriedman()
{
worksheet = workbook_add_worksheet(workbook, "Friedman");
vector<int> columns_sizes = { 5, datasetNameSize };
std::vector<int> columns_sizes = { 5, datasetNameSize };
for (int i = 0; i < models.size(); ++i) {
columns_sizes.push_back(modelNameSize);
}
@ -262,7 +262,7 @@ namespace platform {
row += 2;
worksheet_merge_range(worksheet, row, 0, row, 1 + models.size(), "Null hypothesis: H0 'There is no significant differences between the control model and the other models.'", styles["headerSmall"]);
row += 2;
string controlModel = "Control Model: " + holmResult.model;
std::string controlModel = "Control Model: " + holmResult.model;
worksheet_merge_range(worksheet, row, 1, row, 7, controlModel.c_str(), styles["bodyHeader_odd"]);
row++;
writeString(row, 1, "Model", "bodyHeader");

21
src/Platform/BestResultsExcel.h
View File

@ -5,18 +5,17 @@
#include <map>
#include <nlohmann/json.hpp>
using namespace std;
using json = nlohmann::json;
namespace platform {
class BestResultsExcel : ExcelFile {
public:
BestResultsExcel(const string& score, const vector<string>& datasets);
BestResultsExcel(const std::string& score, const std::vector<std::string>& datasets);
~BestResultsExcel();
void reportAll(const vector<string>& models, const json& table, const map<string, map<string, float>>& ranks, bool friedman, double significance);
void reportSingle(const string& model, const string& fileName);
string getFileName();
void reportAll(const std::vector<std::string>& models, const json& table, const std::map<std::string, std::map<std::string, float>>& ranks, bool friedman, double significance);
void reportSingle(const std::string& model, const std::string& fileName);
std::string getFileName();
private:
void build();
void header(bool ranks);
@ -24,13 +23,13 @@ namespace platform {
void footer(bool ranks);
void formatColumns();
void doFriedman();
void addConditionalFormat(string formula);
const string fileName = "BestResults.xlsx";
string score;
vector<string> models;
vector<string> datasets;
void addConditionalFormat(std::string formula);
const std::string fileName = "BestResults.xlsx";
std::string score;
std::vector<std::string> models;
std::vector<std::string> datasets;
json table;
map<string, map<string, float>> ranksModels;
std::map<std::string, std::map<std::string, float>> ranksModels;
bool friedman;
double significance;
int modelNameSize = 12; // Min size of the column

6
src/Platform/BestScore.h
View File

@ -7,14 +7,14 @@
namespace platform {
class BestScore {
public:
static pair<string, double> getScore(const std::string& metric)
static std::pair<std::string, double> getScore(const std::string& metric)
{
static map<pair<string, string>, pair<string, double>> data = {
static std::map<std::pair<std::string, std::string>, std::pair<std::string, double>> data = {
{{"discretiz", "accuracy"}, {"STree_default (linear-ovo)", 22.109799}},
{{"odte", "accuracy"}, {"STree_default (linear-ovo)", 22.109799}},
};
auto env = platform::DotEnv();
string experiment = env.get("experiment");
std::string experiment = env.get("experiment");
try {
return data[{experiment, metric}];
}

12
src/Platform/CLocale.h
View File

@ -2,22 +2,20 @@
#define LOCALE_H
#include <locale>
#include <iostream>
#include <sstream>
#include <string>
using namespace std;
namespace platform {
struct separation : numpunct<char> {
struct separation : std::numpunct<char> {
char do_decimal_point() const { return ','; }
char do_thousands_sep() const { return '.'; }
string do_grouping() const { return "\03"; }
std::string do_grouping() const { return "\03"; }
};
class ConfigLocale {
public:
explicit ConfigLocale()
{
locale mylocale(cout.getloc(), new separation);
locale::global(mylocale);
cout.imbue(mylocale);
std::locale mylocale(std::cout.getloc(), new separation);
std::locale::global(mylocale);
std::cout.imbue(mylocale);
}
};
}

28
src/Platform/CommandParser.cc
View File

@ -6,16 +6,16 @@
#include "Utils.h"
namespace platform {
void CommandParser::messageError(const string& message)
void CommandParser::messageError(const std::string& message)
{
cout << Colors::RED() << message << Colors::RESET() << endl;
std::cout << Colors::RED() << message << Colors::RESET() << std::endl;
}
pair<char, int> CommandParser::parse(const string& color, const vector<tuple<string, char, bool>>& options, const char defaultCommand, const int maxIndex)
std::pair<char, int> CommandParser::parse(const std::string& color, const std::vector<std::tuple<std::string, char, bool>>& options, const char defaultCommand, const int maxIndex)
{
bool finished = false;
while (!finished) {
stringstream oss;
string line;
std::stringstream oss;
std::string line;
oss << color << "Choose option (";
bool first = true;
for (auto& option : options) {
@ -24,12 +24,12 @@ namespace platform {
} else {
oss << ", ";
}
oss << get<char>(option) << "=" << get<string>(option);
oss << std::get<char>(option) << "=" << std::get<std::string>(option);
}
oss << "): ";
cout << oss.str();
getline(cin, line);
cout << Colors::RESET();
std::cout << oss.str();
getline(std::cin, line);
std::cout << Colors::RESET();
line = trim(line);
if (line.size() == 0)
continue;
@ -45,15 +45,15 @@ namespace platform {
}
bool found = false;
for (auto& option : options) {
if (line[0] == get<char>(option)) {
if (line[0] == std::get<char>(option)) {
found = true;
// it's a match
line.erase(line.begin());
line = trim(line);
if (get<bool>(option)) {
if (std::get<bool>(option)) {
// The option requires a value
if (line.size() == 0) {
messageError("Option " + get<string>(option) + " requires a value");
messageError("Option " + std::get<std::string>(option) + " requires a value");
break;
}
try {
@ -69,11 +69,11 @@ namespace platform {
}
} else {
if (line.size() > 0) {
messageError("option " + get<string>(option) + " doesn't accept values");
messageError("option " + std::get<std::string>(option) + " doesn't accept values");
break;
}
}
command = get<char>(option);
command = std::get<char>(option);
finished = true;
break;
}

5
src/Platform/CommandParser.h
View File

@ -3,17 +3,16 @@
#include <string>
#include <vector>
#include <tuple>
using namespace std;
namespace platform {
class CommandParser {
public:
CommandParser() = default;
pair<char, int> parse(const string& color, const vector<tuple<string, char, bool>>& options, const char defaultCommand, const int maxIndex);
std::pair<char, int> parse(const std::string& color, const std::vector<std::tuple<std::string, char, bool>>& options, const char defaultCommand, const int maxIndex);
char getCommand() const { return command; };
int getIndex() const { return index; };
private:
void messageError(const string& message);
void messageError(const std::string& message);
char command;
int index;
};

58
src/Platform/Dataset.cc
View File

@ -5,20 +5,20 @@ namespace platform {
Dataset::Dataset(const Dataset& dataset) : path(dataset.path), name(dataset.name), className(dataset.className), n_samples(dataset.n_samples), n_features(dataset.n_features), features(dataset.features), states(dataset.states), loaded(dataset.loaded), discretize(dataset.discretize), X(dataset.X), y(dataset.y), Xv(dataset.Xv), Xd(dataset.Xd), yv(dataset.yv), fileType(dataset.fileType)
{
}
string Dataset::getName() const
std::string Dataset::getName() const
{
return name;
}
string Dataset::getClassName() const
std::string Dataset::getClassName() const
{
return className;
}
vector<string> Dataset::getFeatures() const
std::vector<std::string> Dataset::getFeatures() const
{
if (loaded) {
return features;
} else {
throw invalid_argument("Dataset not loaded.");
throw std::invalid_argument("Dataset not loaded.");
}
}
int Dataset::getNFeatures() const
@ -26,7 +26,7 @@ namespace platform {
if (loaded) {
return n_features;
} else {
throw invalid_argument("Dataset not loaded.");
throw std::invalid_argument("Dataset not loaded.");
}
}
int Dataset::getNSamples() const
@ -34,31 +34,31 @@ namespace platform {
if (loaded) {
return n_samples;
} else {
throw invalid_argument("Dataset not loaded.");
throw std::invalid_argument("Dataset not loaded.");
}
}
map<string, vector<int>> Dataset::getStates() const
std::map<std::string, std::vector<int>> Dataset::getStates() const
{
if (loaded) {
return states;
} else {
throw invalid_argument("Dataset not loaded.");
throw std::invalid_argument("Dataset not loaded.");
}
}
pair<vector<vector<float>>&, vector<int>&> Dataset::getVectors()
pair<std::vector<std::vector<float>>&, std::vector<int>&> Dataset::getVectors()
{
if (loaded) {
return { Xv, yv };
} else {
throw invalid_argument("Dataset not loaded.");
throw std::invalid_argument("Dataset not loaded.");
}
}
pair<vector<vector<int>>&, vector<int>&> Dataset::getVectorsDiscretized()
pair<std::vector<std::vector<int>>&, std::vector<int>&> Dataset::getVectorsDiscretized()
{
if (loaded) {
return { Xd, yv };
} else {
throw invalid_argument("Dataset not loaded.");
throw std::invalid_argument("Dataset not loaded.");
}
}
pair<torch::Tensor&, torch::Tensor&> Dataset::getTensors()
@ -67,22 +67,22 @@ namespace platform {
buildTensors();
return { X, y };
} else {
throw invalid_argument("Dataset not loaded.");
throw std::invalid_argument("Dataset not loaded.");
}
}
void Dataset::load_csv()
{
ifstream file(path + "/" + name + ".csv");
if (file.is_open()) {
string line;
std::string line;
getline(file, line);
vector<string> tokens = split(line, ',');
features = vector<string>(tokens.begin(), tokens.end() - 1);
std::vector<std::string> tokens = split(line, ',');
features = std::vector<std::string>(tokens.begin(), tokens.end() - 1);
if (className == "-1") {
className = tokens.back();
}
for (auto i = 0; i < features.size(); ++i) {
Xv.push_back(vector<float>());
Xv.push_back(std::vector<float>());
}
while (getline(file, line)) {
tokens = split(line, ',');
@ -93,17 +93,17 @@ namespace platform {
}
file.close();
} else {
throw invalid_argument("Unable to open dataset file.");
throw std::invalid_argument("Unable to open dataset file.");
}
}
void Dataset::computeStates()
{
for (int i = 0; i < features.size(); ++i) {
states[features[i]] = vector<int>(*max_element(Xd[i].begin(), Xd[i].end()) + 1);
states[features[i]] = std::vector<int>(*max_element(Xd[i].begin(), Xd[i].end()) + 1);
auto item = states.at(features[i]);
iota(begin(item), end(item), 0);
}
states[className] = vector<int>(*max_element(yv.begin(), yv.end()) + 1);
states[className] = std::vector<int>(*max_element(yv.begin(), yv.end()) + 1);
iota(begin(states.at(className)), end(states.at(className)), 0);
}
void Dataset::load_arff()
@ -118,12 +118,12 @@ namespace platform {
auto attributes = arff.getAttributes();
transform(attributes.begin(), attributes.end(), back_inserter(features), [](const auto& attribute) { return attribute.first; });
}
vector<string> tokenize(string line)
std::vector<std::string> tokenize(std::string line)
{
vector<string> tokens;
std::vector<std::string> tokens;
for (auto i = 0; i < line.size(); ++i) {
if (line[i] == ' ' || line[i] == '\t' || line[i] == '\n') {
string token = line.substr(0, i);
std::string token = line.substr(0, i);
tokens.push_back(token);
line.erase(line.begin(), line.begin() + i + 1);
i = 0;
@ -140,16 +140,16 @@ namespace platform {
{
ifstream file(path + "/" + name + "_R.dat");
if (file.is_open()) {
string line;
std::string line;
getline(file, line);
line = ArffFiles::trim(line);
vector<string> tokens = tokenize(line);
std::vector<std::string> tokens = tokenize(line);
transform(tokens.begin(), tokens.end() - 1, back_inserter(features), [](const auto& attribute) { return ArffFiles::trim(attribute); });
if (className == "-1") {
className = ArffFiles::trim(tokens.back());
}
for (auto i = 0; i < features.size(); ++i) {
Xv.push_back(vector<float>());
Xv.push_back(std::vector<float>());
}
while (getline(file, line)) {
tokens = tokenize(line);
@ -162,7 +162,7 @@ namespace platform {
}
file.close();
} else {
throw invalid_argument("Unable to open dataset file.");
throw std::invalid_argument("Unable to open dataset file.");
}
}
void Dataset::load()
@ -201,9 +201,9 @@ namespace platform {
}
y = torch::tensor(yv, torch::kInt32);
}
vector<mdlp::labels_t> Dataset::discretizeDataset(vector<mdlp::samples_t>& X, mdlp::labels_t& y)
std::vector<mdlp::labels_t> Dataset::discretizeDataset(std::vector<mdlp::samples_t>& X, mdlp::labels_t& y)
{
vector<mdlp::labels_t> Xd;
std::vector<mdlp::labels_t> Xd;
auto fimdlp = mdlp::CPPFImdlp();
for (int i = 0; i < X.size(); i++) {
fimdlp.fit(X[i], y);

44
src/Platform/Dataset.h
View File

@ -7,12 +7,10 @@
#include "CPPFImdlp.h"
#include "Utils.h"
namespace platform {
using namespace std;
enum fileType_t { CSV, ARFF, RDATA };
class SourceData {
public:
SourceData(string source)
SourceData(std::string source)
{
if (source == "Surcov") {
path = "datasets/";
@ -24,10 +22,10 @@ namespace platform {
path = "data/";
fileType = RDATA;
} else {
throw invalid_argument("Unknown source.");
throw std::invalid_argument("Unknown source.");
}
}
string getPath()
std::string getPath()
{
return path;
}
@ -36,40 +34,40 @@ namespace platform {
return fileType;
}
private:
string path;
std::string path;
fileType_t fileType;
};
class Dataset {
private:
string path;
string name;
std::string path;
std::string name;
fileType_t fileType;
string className;
std::string className;
int n_samples{ 0 }, n_features{ 0 };
vector<string> features;
map<string, vector<int>> states;
std::vector<std::string> features;
std::map<std::string, std::vector<int>> states;
bool loaded;
bool discretize;
torch::Tensor X, y;
vector<vector<float>> Xv;
vector<vector<int>> Xd;
vector<int> yv;
std::vector<std::vector<float>> Xv;
std::vector<std::vector<int>> Xd;
std::vector<int> yv;
void buildTensors();
void load_csv();
void load_arff();
void load_rdata();
void computeStates();
vector<mdlp::labels_t> discretizeDataset(vector<mdlp::samples_t>& X, mdlp::labels_t& y);
std::vector<mdlp::labels_t> discretizeDataset(std::vector<mdlp::samples_t>& X, mdlp::labels_t& y);
public:
Dataset(const string& path, const string& name, const string& className, bool discretize, fileType_t fileType) : path(path), name(name), className(className), discretize(discretize), loaded(false), fileType(fileType) {};
Dataset(const std::string& path, const std::string& name, const std::string& className, bool discretize, fileType_t fileType) : path(path), name(name), className(className), discretize(discretize), loaded(false), fileType(fileType) {};
explicit Dataset(const Dataset&);
string getName() const;
string getClassName() const;
vector<string> getFeatures() const;
map<string, vector<int>> getStates() const;
pair<vector<vector<float>>&, vector<int>&> getVectors();
pair<vector<vector<int>>&, vector<int>&> getVectorsDiscretized();
pair<torch::Tensor&, torch::Tensor&> getTensors();
std::string getName() const;
std::string getClassName() const;
std::vector<string> getFeatures() const;
std::map<std::string, std::vector<int>> getStates() const;
std::pair<vector<std::vector<float>>&, std::vector<int>&> getVectors();
std::pair<vector<std::vector<int>>&, std::vector<int>&> getVectorsDiscretized();
std::pair<torch::Tensor&, torch::Tensor&> getTensors();
int getNFeatures() const;
int getNSamples() const;
void load();

52
src/Platform/Datasets.cc
View File

@ -8,14 +8,14 @@ namespace platform {
path = sd.getPath();
ifstream catalog(path + "all.txt");
if (catalog.is_open()) {
string line;
std::string line;
while (getline(catalog, line)) {
if (line.empty() || line[0] == '#') {
continue;
}
vector<string> tokens = split(line, ',');
string name = tokens[0];
string className;
std::vector<std::string> tokens = split(line, ',');
std::string name = tokens[0];
std::string className;
if (tokens.size() == 1) {
className = "-1";
} else {
@ -25,32 +25,32 @@ namespace platform {
}
catalog.close();
} else {
throw invalid_argument("Unable to open catalog file. [" + path + "all.txt" + "]");
throw std::invalid_argument("Unable to open catalog file. [" + path + "all.txt" + "]");
}
}
vector<string> Datasets::getNames()
std::vector<std::string> Datasets::getNames()
{
vector<string> result;
std::vector<std::string> result;
transform(datasets.begin(), datasets.end(), back_inserter(result), [](const auto& d) { return d.first; });
return result;
}
vector<string> Datasets::getFeatures(const string& name) const
std::vector<std::string> Datasets::getFeatures(const std::string& name) const
{
if (datasets.at(name)->isLoaded()) {
return datasets.at(name)->getFeatures();
} else {
throw invalid_argument("Dataset not loaded.");
throw std::invalid_argument("Dataset not loaded.");
}
}
map<string, vector<int>> Datasets::getStates(const string& name) const
map<std::string, std::vector<int>> Datasets::getStates(const std::string& name) const
{
if (datasets.at(name)->isLoaded()) {
return datasets.at(name)->getStates();
} else {
throw invalid_argument("Dataset not loaded.");
throw std::invalid_argument("Dataset not loaded.");
}
}
void Datasets::loadDataset(const string& name) const
void Datasets::loadDataset(const std::string& name) const
{
if (datasets.at(name)->isLoaded()) {
return;
@ -58,23 +58,23 @@ namespace platform {
datasets.at(name)->load();
}
}
string Datasets::getClassName(const string& name) const
std::string Datasets::getClassName(const std::string& name) const
{
if (datasets.at(name)->isLoaded()) {
return datasets.at(name)->getClassName();
} else {
throw invalid_argument("Dataset not loaded.");
throw std::invalid_argument("Dataset not loaded.");
}
}
int Datasets::getNSamples(const string& name) const
int Datasets::getNSamples(const std::string& name) const
{
if (datasets.at(name)->isLoaded()) {
return datasets.at(name)->getNSamples();
} else {
throw invalid_argument("Dataset not loaded.");
throw std::invalid_argument("Dataset not loaded.");
}
}
int Datasets::getNClasses(const string& name)
int Datasets::getNClasses(const std::string& name)
{
if (datasets.at(name)->isLoaded()) {
auto className = datasets.at(name)->getClassName();
@ -83,46 +83,46 @@ namespace platform {
return states.at(className).size();
}
auto [Xv, yv] = getVectors(name);
return *max_element(yv.begin(), yv.end()) + 1;
return *std::max_element(yv.begin(), yv.end()) + 1;
} else {
throw invalid_argument("Dataset not loaded.");
throw std::invalid_argument("Dataset not loaded.");
}
}
vector<int> Datasets::getClassesCounts(const string& name) const
std::vector<int> Datasets::getClassesCounts(const std::string& name) const
{
if (datasets.at(name)->isLoaded()) {
auto [Xv, yv] = datasets.at(name)->getVectors();
vector<int> counts(*max_element(yv.begin(), yv.end()) + 1);
std::vector<int> counts(*std::max_element(yv.begin(), yv.end()) + 1);
for (auto y : yv) {
counts[y]++;
}
return counts;
} else {
throw invalid_argument("Dataset not loaded.");
throw std::invalid_argument("Dataset not loaded.");
}
}
pair<vector<vector<float>>&, vector<int>&> Datasets::getVectors(const string& name)
pair<std::vector<std::vector<float>>&, std::vector<int>&> Datasets::getVectors(const std::string& name)
{
if (!datasets[name]->isLoaded()) {
datasets[name]->load();
}
return datasets[name]->getVectors();
}
pair<vector<vector<int>>&, vector<int>&> Datasets::getVectorsDiscretized(const string& name)
pair<std::vector<std::vector<int>>&, std::vector<int>&> Datasets::getVectorsDiscretized(const std::string& name)
{
if (!datasets[name]->isLoaded()) {
datasets[name]->load();
}
return datasets[name]->getVectorsDiscretized();
}
pair<torch::Tensor&, torch::Tensor&> Datasets::getTensors(const string& name)
pair<torch::Tensor&, torch::Tensor&> Datasets::getTensors(const std::string& name)
{
if (!datasets[name]->isLoaded()) {
datasets[name]->load();
}
return datasets[name]->getTensors();
}
bool Datasets::isDataset(const string& name) const
bool Datasets::isDataset(const std::string& name) const
{
return datasets.find(name) != datasets.end();
}

33
src/Platform/Datasets.h
View File

@ -2,29 +2,28 @@
#define DATASETS_H
#include "Dataset.h"
namespace platform {
using namespace std;
class Datasets {
private:
string path;
std::string path;
fileType_t fileType;
string sfileType;
map<string, unique_ptr<Dataset>> datasets;
std::string sfileType;
std::map<std::string, std::unique_ptr<Dataset>> datasets;
bool discretize;
void load(); // Loads the list of datasets
public:
explicit Datasets(bool discretize, string sfileType) : discretize(discretize), sfileType(sfileType) { load(); };
vector<string> getNames();
vector<string> getFeatures(const string& name) const;
int getNSamples(const string& name) const;
string getClassName(const string& name) const;
int getNClasses(const string& name);
vector<int> getClassesCounts(const string& name) const;
map<string, vector<int>> getStates(const string& name) const;
pair<vector<vector<float>>&, vector<int>&> getVectors(const string& name);
pair<vector<vector<int>>&, vector<int>&> getVectorsDiscretized(const string& name);
pair<torch::Tensor&, torch::Tensor&> getTensors(const string& name);
bool isDataset(const string& name) const;
void loadDataset(const string& name) const;
explicit Datasets(bool discretize, std::string sfileType) : discretize(discretize), sfileType(sfileType) { load(); };
std::vector<string> getNames();
std::vector<string> getFeatures(const std::string& name) const;
int getNSamples(const std::string& name) const;
std::string getClassName(const std::string& name) const;
int getNClasses(const std::string& name);
std::vector<int> getClassesCounts(const std::string& name) const;
std::map<std::string, std::vector<int>> getStates(const std::string& name) const;
std::pair<std::vector<std::vector<float>>&, std::vector<int>&> getVectors(const std::string& name);
std::pair<std::vector<std::vector<int>>&, std::vector<int>&> getVectorsDiscretized(const std::string& name);
std::pair<torch::Tensor&, torch::Tensor&> getTensors(const std::string& name);
bool isDataset(const std::string& name) const;
void loadDataset(const std::string& name) const;
};
};

22
src/Platform/ExcelFile.cc
View File

@ -26,7 +26,7 @@ namespace platform {
{
return workbook;
}
void ExcelFile::setProperties(string title)
void ExcelFile::setProperties(std::string title)
{
char line[title.size() + 1];
strcpy(line, title.c_str());
@ -40,34 +40,34 @@ namespace platform {
};
workbook_set_properties(workbook, &properties);
}
lxw_format* ExcelFile::efectiveStyle(const string& style)
lxw_format* ExcelFile::efectiveStyle(const std::string& style)
{
lxw_format* efectiveStyle = NULL;
if (style != "") {
string suffix = row % 2 ? "_odd" : "_even";
std::string suffix = row % 2 ? "_odd" : "_even";
try {
efectiveStyle = styles.at(style + suffix);
}
catch (const out_of_range& oor) {
catch (const std::out_of_range& oor) {
try {
efectiveStyle = styles.at(style);
}
catch (const out_of_range& oor) {
throw invalid_argument("Style " + style + " not found");
catch (const std::out_of_range& oor) {
throw std::invalid_argument("Style " + style + " not found");
}
}
}
return efectiveStyle;
}
void ExcelFile::writeString(int row, int col, const string& text, const string& style)
void ExcelFile::writeString(int row, int col, const std::string& text, const std::string& style)
{
worksheet_write_string(worksheet, row, col, text.c_str(), efectiveStyle(style));
}
void ExcelFile::writeInt(int row, int col, const int number, const string& style)
void ExcelFile::writeInt(int row, int col, const int number, const std::string& style)
{
worksheet_write_number(worksheet, row, col, number, efectiveStyle(style));
}
void ExcelFile::writeDouble(int row, int col, const double number, const string& style)
void ExcelFile::writeDouble(int row, int col, const double number, const std::string& style)
{
worksheet_write_number(worksheet, row, col, number, efectiveStyle(style));
}
@ -76,7 +76,7 @@ namespace platform {
uint32_t efectiveColor = odd ? colorEven : colorOdd;
format_set_bg_color(style, lxw_color_t(efectiveColor));
}
void ExcelFile::createStyle(const string& name, lxw_format* style, bool odd)
void ExcelFile::createStyle(const std::string& name, lxw_format* style, bool odd)
{
addColor(style, odd);
if (name == "textCentered") {
@ -116,7 +116,7 @@ namespace platform {
{
auto styleNames = { "text", "textCentered", "bodyHeader", "result", "time", "ints", "floats" };
lxw_format* style;
for (string name : styleNames) {
for (std::string name : styleNames) {
lxw_format* style = workbook_add_format(workbook);
style = workbook_add_format(workbook);
createStyle(name, style, true);

19
src/Platform/ExcelFile.h
View File

@ -5,14 +5,13 @@
#include <map>
#include "xlsxwriter.h"
using namespace std;
namespace platform {
struct separated : numpunct<char> {
struct separated : std::numpunct<char> {
char do_decimal_point() const { return ','; }
char do_thousands_sep() const { return '.'; }
string do_grouping() const { return "\03"; }
std::string do_grouping() const { return "\03"; }
};
class ExcelFile {
public:
@ -21,17 +20,17 @@ namespace platform {
ExcelFile(lxw_workbook* workbook, lxw_worksheet* worksheet);
lxw_workbook* getWorkbook();
protected:
void setProperties(string title);
void writeString(int row, int col, const string& text, const string& style = "");
void writeInt(int row, int col, const int number, const string& style = "");
void writeDouble(int row, int col, const double number, const string& style = "");
void setProperties(std::string title);
void writeString(int row, int col, const std::string& text, const std::string& style = "");
void writeInt(int row, int col, const int number, const std::string& style = "");
void writeDouble(int row, int col, const double number, const std::string& style = "");
void createFormats();
void createStyle(const string& name, lxw_format* style, bool odd);
void createStyle(const std::string& name, lxw_format* style, bool odd);
void addColor(lxw_format* style, bool odd);
lxw_format* efectiveStyle(const string& name);
lxw_format* efectiveStyle(const std::string& name);
lxw_workbook* workbook;
lxw_worksheet* worksheet;
map<string, lxw_format*> styles;
std::map<std::string, lxw_format*> styles;
int row;
int normalSize; //font size for report body
uint32_t colorTitle;

42
src/Platform/Experiment.cc
View File

@ -6,7 +6,7 @@
#include "Paths.h"
namespace platform {
using json = nlohmann::json;
string get_date()
std::string get_date()
{
time_t rawtime;
tm* timeinfo;
@ -16,7 +16,7 @@ namespace platform {
oss << std::put_time(timeinfo, "%Y-%m-%d");
return oss.str();
}
string get_time()
std::string get_time()
{
time_t rawtime;
tm* timeinfo;
@ -27,9 +27,9 @@ namespace platform {
return oss.str();
}
Experiment::Experiment() : hyperparameters(json::parse("{}")) {}
string Experiment::get_file_name()
std::string Experiment::get_file_name()
{
string result = "results_" + score_name + "_" + model + "_" + platform + "_" + get_date() + "_" + get_time() + "_" + (stratified ? "1" : "0") + ".json";
std::string result = "results_" + score_name + "_" + model + "_" + platform + "_" + get_date() + "_" + get_time() + "_" + (stratified ? "1" : "0") + ".json";
return result;
}
@ -81,7 +81,7 @@ namespace platform {
}
return result;
}
void Experiment::save(const string& path)
void Experiment::save(const std::string& path)
{
json data = build_json();
ofstream file(path + "/" + get_file_name());
@ -99,20 +99,20 @@ namespace platform {
void Experiment::show()
{
json data = build_json();
cout << data.dump(4) << endl;
std::cout << data.dump(4) << std::endl;
}
void Experiment::go(vector<string> filesToProcess, bool quiet)
void Experiment::go(std::vector<std::string> filesToProcess, bool quiet)
{
cout << "*** Starting experiment: " << title << " ***" << endl;
std::cout << "*** Starting experiment: " << title << " ***" << std::endl;
for (auto fileName : filesToProcess) {
cout << "- " << setw(20) << left << fileName << " " << right << flush;
std::cout << "- " << setw(20) << left << fileName << " " << right << flush;
cross_validation(fileName, quiet);
cout << endl;
std::cout << std::endl;
}
}
string getColor(bayesnet::status_t status)
std::string getColor(bayesnet::status_t status)
{
switch (status) {
case bayesnet::NORMAL:
@ -126,13 +126,13 @@ namespace platform {
}
}
void showProgress(int fold, const string& color, const string& phase)
void showProgress(int fold, const std::string& color, const std::string& phase)
{
string prefix = phase == "a" ? "" : "\b\b\b\b";
cout << prefix << color << fold << Colors::RESET() << "(" << color << phase << Colors::RESET() << ")" << flush;
std::string prefix = phase == "a" ? "" : "\b\b\b\b";
std::cout << prefix << color << fold << Colors::RESET() << "(" << color << phase << Colors::RESET() << ")" << flush;
}
void Experiment::cross_validation(const string& fileName, bool quiet)
void Experiment::cross_validation(const std::string& fileName, bool quiet)
{
auto datasets = platform::Datasets(discretized, Paths::datasets());
// Get dataset
@ -142,14 +142,14 @@ namespace platform {
auto samples = datasets.getNSamples(fileName);
auto className = datasets.getClassName(fileName);
if (!quiet) {
cout << " (" << setw(5) << samples << "," << setw(3) << features.size() << ") " << flush;
std::cout << " (" << setw(5) << samples << "," << setw(3) << features.size() << ") " << flush;
}
// Prepare Result
auto result = Result();
auto [values, counts] = at::_unique(y);
result.setSamples(X.size(1)).setFeatures(X.size(0)).setClasses(values.size(0));
result.setHyperparameters(hyperparameters);
// Initialize results vectors
// Initialize results std::vectors
int nResults = nfolds * static_cast<int>(randomSeeds.size());
auto accuracy_test = torch::zeros({ nResults }, torch::kFloat64);
auto accuracy_train = torch::zeros({ nResults }, torch::kFloat64);
@ -162,7 +162,7 @@ namespace platform {
int item = 0;
for (auto seed : randomSeeds) {
if (!quiet)
cout << "(" << seed << ") doing Fold: " << flush;
std::cout << "(" << seed << ") doing Fold: " << flush;
Fold* fold;
if (stratified)
fold = new StratifiedKFold(nfolds, y, seed);
@ -204,8 +204,8 @@ namespace platform {
accuracy_train[item] = accuracy_train_value;
accuracy_test[item] = accuracy_test_value;
if (!quiet)
cout << "\b\b\b, " << flush;
// Store results and times in vector
std::cout << "\b\b\b, " << flush;
// Store results and times in std::vector
result.addScoreTrain(accuracy_train_value);
result.addScoreTest(accuracy_test_value);
result.addTimeTrain(train_time[item].item<double>());
@ -214,7 +214,7 @@ namespace platform {
clf.reset();
}
if (!quiet)
cout << "end. " << flush;
std::cout << "end. " << flush;
delete fold;
}
result.setScoreTest(torch::mean(accuracy_test).item<double>()).setScoreTrain(torch::mean(accuracy_train).item<double>());

53
src/Platform/Experiment.h
View File

@ -10,34 +10,33 @@
#include "KDB.h"
#include "AODE.h"
using namespace std;
namespace platform {
using json = nlohmann::json;
class Timer {
private:
chrono::high_resolution_clock::time_point begin;
std::chrono::high_resolution_clock::time_point begin;
public:
Timer() = default;
~Timer() = default;
void start() { begin = chrono::high_resolution_clock::now(); }
void start() { begin = std::chrono::high_resolution_clock::now(); }
double getDuration()
{
chrono::high_resolution_clock::time_point end = chrono::high_resolution_clock::now();
chrono::duration<double> time_span = chrono::duration_cast<chrono::duration<double>>(end - begin);
std::chrono::high_resolution_clock::time_point end = std::chrono::high_resolution_clock::now();
std::chrono::duration<double> time_span = std::chrono::duration_cast<std::chrono::duration<double >> (end - begin);
return time_span.count();
}
};
class Result {
private:
string dataset, model_version;
std::string dataset, model_version;
json hyperparameters;
int samples{ 0 }, features{ 0 }, classes{ 0 };
double score_train{ 0 }, score_test{ 0 }, score_train_std{ 0 }, score_test_std{ 0 }, train_time{ 0 }, train_time_std{ 0 }, test_time{ 0 }, test_time_std{ 0 };
float nodes{ 0 }, leaves{ 0 }, depth{ 0 };
vector<double> scores_train, scores_test, times_train, times_test;
std::vector<double> scores_train, scores_test, times_train, times_test;
public:
Result() = default;
Result& setDataset(const string& dataset) { this->dataset = dataset; return *this; }
Result& setDataset(const std::string& dataset) { this->dataset = dataset; return *this; }
Result& setHyperparameters(const json& hyperparameters) { this->hyperparameters = hyperparameters; return *this; }
Result& setSamples(int samples) { this->samples = samples; return *this; }
Result& setFeatures(int features) { this->features = features; return *this; }
@ -59,7 +58,7 @@ namespace platform {
Result& addTimeTest(double time) { times_test.push_back(time); return *this; }
const float get_score_train() const { return score_train; }
float get_score_test() { return score_test; }
const string& getDataset() const { return dataset; }
const std::string& getDataset() const { return dataset; }
const json& getHyperparameters() const { return hyperparameters; }
const int getSamples() const { return samples; }
const int getFeatures() const { return features; }
@ -75,30 +74,30 @@ namespace platform {
const float getNodes() const { return nodes; }
const float getLeaves() const { return leaves; }
const float getDepth() const { return depth; }
const vector<double>& getScoresTrain() const { return scores_train; }
const vector<double>& getScoresTest() const { return scores_test; }
const vector<double>& getTimesTrain() const { return times_train; }
const vector<double>& getTimesTest() const { return times_test; }
const std::vector<double>& getScoresTrain() const { return scores_train; }
const std::vector<double>& getScoresTest() const { return scores_test; }
const std::vector<double>& getTimesTrain() const { return times_train; }
const std::vector<double>& getTimesTest() const { return times_test; }
};
class Experiment {
private:
string title, model, platform, score_name, model_version, language_version, language;
std::string title, model, platform, score_name, model_version, language_version, language;
bool discretized{ false }, stratified{ false };
vector<Result> results;
vector<int> randomSeeds;
std::vector<Result> results;
std::vector<int> randomSeeds;
json hyperparameters = "{}";
int nfolds{ 0 };
float duration{ 0 };
json build_json();
public:
Experiment();
Experiment& setTitle(const string& title) { this->title = title; return *this; }
Experiment& setModel(const string& model) { this->model = model; return *this; }
Experiment& setPlatform(const string& platform) { this->platform = platform; return *this; }
Experiment& setScoreName(const string& score_name) { this->score_name = score_name; return *this; }
Experiment& setModelVersion(const string& model_version) { this->model_version = model_version; return *this; }
Experiment& setLanguage(const string& language) { this->language = language; return *this; }
Experiment& setLanguageVersion(const string& language_version) { this->language_version = language_version; return *this; }
Experiment& setTitle(const std::string& title) { this->title = title; return *this; }
Experiment& setModel(const std::string& model) { this->model = model; return *this; }
Experiment& setPlatform(const std::string& platform) { this->platform = platform; return *this; }
Experiment& setScoreName(const std::string& score_name) { this->score_name = score_name; return *this; }
Experiment& setModelVersion(const std::string& model_version) { this->model_version = model_version; return *this; }
Experiment& setLanguage(const std::string& language) { this->language = language; return *this; }
Experiment& setLanguageVersion(const std::string& language_version) { this->language_version = language_version; return *this; }
Experiment& setDiscretized(bool discretized) { this->discretized = discretized; return *this; }
Experiment& setStratified(bool stratified) { this->stratified = stratified; return *this; }
Experiment& setNFolds(int nfolds) { this->nfolds = nfolds; return *this; }
@ -106,10 +105,10 @@ namespace platform {
Experiment& addRandomSeed(int randomSeed) { randomSeeds.push_back(randomSeed); return *this; }
Experiment& setDuration(float duration) { this->duration = duration; return *this; }
Experiment& setHyperparameters(const json& hyperparameters) { this->hyperparameters = hyperparameters; return *this; }
string get_file_name();
void save(const string& path);
void cross_validation(const string& fileName, bool quiet);
void go(vector<string> filesToProcess, bool quiet);
std::string get_file_name();
void save(const std::string& path);
void cross_validation(const std::string& fileName, bool quiet);
void go(std::vector<std::string> filesToProcess, bool quiet);
void show();
void report();
};

42
src/Platform/Folding.cc
View File

@ -4,23 +4,23 @@
namespace platform {
Fold::Fold(int k, int n, int seed) : k(k), n(n), seed(seed)
{
random_device rd;
random_seed = default_random_engine(seed == -1 ? rd() : seed);
srand(seed == -1 ? time(0) : seed);
std::random_device rd;
random_seed = std::default_random_engine(seed == -1 ? rd() : seed);
std::srand(seed == -1 ? time(0) : seed);
}
KFold::KFold(int k, int n, int seed) : Fold(k, n, seed), indices(vector<int>(n))
KFold::KFold(int k, int n, int seed) : Fold(k, n, seed), indices(std::vector<int>(n))
{
iota(begin(indices), end(indices), 0); // fill with 0, 1, ..., n - 1
std::iota(begin(indices), end(indices), 0); // fill with 0, 1, ..., n - 1
shuffle(indices.begin(), indices.end(), random_seed);
}
pair<vector<int>, vector<int>> KFold::getFold(int nFold)
std::pair<std::vector<int>, std::vector<int>> KFold::getFold(int nFold)
{
if (nFold >= k || nFold < 0) {
throw out_of_range("nFold (" + to_string(nFold) + ") must be less than k (" + to_string(k) + ")");
throw std::out_of_range("nFold (" + std::to_string(nFold) + ") must be less than k (" + std::to_string(k) + ")");
}
int nTest = n / k;
auto train = vector<int>();
auto test = vector<int>();
auto train = std::vector<int>();
auto test = std::vector<int>();
for (int i = 0; i < n; i++) {
if (i >= nTest * nFold && i < nTest * (nFold + 1)) {
test.push_back(indices[i]);
@ -33,10 +33,10 @@ namespace platform {
StratifiedKFold::StratifiedKFold(int k, torch::Tensor& y, int seed) : Fold(k, y.numel(), seed)
{
n = y.numel();
this->y = vector<int>(y.data_ptr<int>(), y.data_ptr<int>() + n);
this->y = std::vector<int>(y.data_ptr<int>(), y.data_ptr<int>() + n);
build();
}
StratifiedKFold::StratifiedKFold(int k, const vector<int>& y, int seed)
StratifiedKFold::StratifiedKFold(int k, const std::vector<int>& y, int seed)
: Fold(k, y.size(), seed)
{
this->y = y;
@ -45,12 +45,12 @@ namespace platform {
}
void StratifiedKFold::build()
{
stratified_indices = vector<vector<int>>(k);
stratified_indices = std::vector<std::vector<int>>(k);
int fold_size = n / k;
// Compute class counts and indices
auto class_indices = map<int, vector<int>>();
vector<int> class_counts(*max_element(y.begin(), y.end()) + 1, 0);
auto class_indices = std::map<int, std::vector<int>>();
std::vector<int> class_counts(*max_element(y.begin(), y.end()) + 1, 0);
for (auto i = 0; i < n; ++i) {
class_counts[y[i]]++;
class_indices[y[i]].push_back(i);
@ -63,8 +63,8 @@ namespace platform {
for (auto label = 0; label < class_counts.size(); ++label) {
auto num_samples_to_take = class_counts.at(label) / k;
if (num_samples_to_take == 0) {
cerr << "Warning! The number of samples in class " << label << " (" << class_counts.at(label)
<< ") is less than the number of folds (" << k << ")." << endl;
std::cerr << "Warning! The number of samples in class " << label << " (" << class_counts.at(label)
<< ") is less than the number of folds (" << k << ")." << std::endl;
faulty = true;
continue;
}
@ -74,7 +74,7 @@ namespace platform {
move(class_indices[label].begin(), it, back_inserter(stratified_indices[fold])); // ##
class_indices[label].erase(class_indices[label].begin(), it);
}
auto chosen = vector<bool>(k, false);
auto chosen = std::vector<bool>(k, false);
while (remainder_samples_to_take > 0) {
int fold = (rand() % static_cast<int>(k));
if (chosen.at(fold)) {
@ -88,13 +88,13 @@ namespace platform {
}
}
}
pair<vector<int>, vector<int>> StratifiedKFold::getFold(int nFold)
std::pair<std::vector<int>, std::vector<int>> StratifiedKFold::getFold(int nFold)
{
if (nFold >= k || nFold < 0) {
throw out_of_range("nFold (" + to_string(nFold) + ") must be less than k (" + to_string(k) + ")");
throw std::out_of_range("nFold (" + std::to_string(nFold) + ") must be less than k (" + std::to_string(k) + ")");
}
vector<int> test_indices = stratified_indices[nFold];
vector<int> train_indices;
std::vector<int> test_indices = stratified_indices[nFold];
std::vector<int> train_indices;
for (int i = 0; i < k; ++i) {
if (i == nFold) continue;
train_indices.insert(train_indices.end(), stratified_indices[i].begin(), stratified_indices[i].end());

17
src/Platform/Folding.h
View File

@ -3,37 +3,36 @@
#include <torch/torch.h>
#include <vector>
#include <random>
using namespace std;
namespace platform {
class Fold {
protected:
int k;
int n;
int seed;
default_random_engine random_seed;
std::default_random_engine random_seed;
public:
Fold(int k, int n, int seed = -1);
virtual pair<vector<int>, vector<int>> getFold(int nFold) = 0;
virtual std::pair<std::vector<int>, std::vector<int>> getFold(int nFold) = 0;
virtual ~Fold() = default;
int getNumberOfFolds() { return k; }
};
class KFold : public Fold {
private:
vector<int> indices;
std::vector<int> indices;
public:
KFold(int k, int n, int seed = -1);
pair<vector<int>, vector<int>> getFold(int nFold) override;
std::pair<std::vector<int>, std::vector<int>> getFold(int nFold) override;
};
class StratifiedKFold : public Fold {
private:
vector<int> y;
vector<vector<int>> stratified_indices;
std::vector<int> y;
std::vector<std::vector<int>> stratified_indices;
void build();
bool faulty = false; // Only true if the number of samples of any class is less than the number of folds.
public:
StratifiedKFold(int k, const vector<int>& y, int seed = -1);
StratifiedKFold(int k, const std::vector<int>& y, int seed = -1);
StratifiedKFold(int k, torch::Tensor& y, int seed = -1);
pair<vector<int>, vector<int>> getFold(int nFold) override;
std::pair<std::vector<int>, std::vector<int>> getFold(int nFold) override;
bool isFaulty() { return faulty; }
};
}

72
src/Platform/ManageResults.cc
View File

@ -10,7 +10,7 @@
namespace platform {
ManageResults::ManageResults(int numFiles, const string& model, const string& score, bool complete, bool partial, bool compare) :
ManageResults::ManageResults(int numFiles, const std::string& model, const std::string& score, bool complete, bool partial, bool compare) :
numFiles{ numFiles }, complete{ complete }, partial{ partial }, compare{ compare }, results(Results(Paths::results(), model, score, complete, partial))
{
indexList = true;
@ -23,7 +23,7 @@ namespace platform {
void ManageResults::doMenu()
{
if (results.empty()) {
cout << Colors::MAGENTA() << "No results found!" << Colors::RESET() << endl;
std::cout << Colors::MAGENTA() << "No results found!" << Colors::RESET() << std::endl;
return;
}
results.sortDate();
@ -32,68 +32,68 @@ namespace platform {
if (openExcel) {
workbook_close(workbook);
}
cout << Colors::RESET() << "Done!" << endl;
std::cout << Colors::RESET() << "Done!" << std::endl;
}
void ManageResults::list()
{
auto temp = ConfigLocale();
string suffix = numFiles != results.size() ? " of " + to_string(results.size()) : "";
stringstream oss;
std::string suffix = numFiles != results.size() ? " of " + std::to_string(results.size()) : "";
std::stringstream oss;
oss << "Results on screen: " << numFiles << suffix;
cout << Colors::GREEN() << oss.str() << endl;
cout << string(oss.str().size(), '-') << endl;
std::cout << Colors::GREEN() << oss.str() << std::endl;
std::cout << std::string(oss.str().size(), '-') << std::endl;
if (complete) {
cout << Colors::MAGENTA() << "Only listing complete results" << endl;
std::cout << Colors::MAGENTA() << "Only listing complete results" << std::endl;
}
if (partial) {
cout << Colors::MAGENTA() << "Only listing partial results" << endl;
std::cout << Colors::MAGENTA() << "Only listing partial results" << std::endl;
}
auto i = 0;
int maxModel = results.maxModelSize();
cout << Colors::GREEN() << " # Date " << setw(maxModel) << left << "Model" << " Score Name Score C/P Duration Title" << endl;
cout << "=== ========== " << string(maxModel, '=') << " =========== =========== === ========= =============================================================" << endl;
std::cout << Colors::GREEN() << " # Date " << std::setw(maxModel) << std::left << "Model" << " Score Name Score C/P Duration Title" << std::endl;
std::cout << "=== ========== " << std::string(maxModel, '=') << " =========== =========== === ========= =============================================================" << std::endl;
bool odd = true;
for (auto& result : results) {
auto color = odd ? Colors::BLUE() : Colors::CYAN();
cout << color << setw(3) << fixed << right << i++ << " ";
cout << result.to_string(maxModel) << endl;
std::cout << color << std::setw(3) << std::fixed << std::right << i++ << " ";
std::cout << result.to_string(maxModel) << std::endl;
if (i == numFiles) {
break;
}
odd = !odd;
}
}
bool ManageResults::confirmAction(const string& intent, const string& fileName) const
bool ManageResults::confirmAction(const std::string& intent, const std::string& fileName) const
{
string color;
std::string color;
if (intent == "delete") {
color = Colors::RED();
} else {
color = Colors::YELLOW();
}
string line;
std::string line;
bool finished = false;
while (!finished) {
cout << color << "Really want to " << intent << " " << fileName << "? (y/n): ";
getline(cin, line);
std::cout << color << "Really want to " << intent << " " << fileName << "? (y/n): ";
getline(std::cin, line);
finished = line.size() == 1 && (tolower(line[0]) == 'y' || tolower(line[0] == 'n'));
}
if (tolower(line[0]) == 'y') {
return true;
}
cout << "Not done!" << endl;
std::cout << "Not done!" << std::endl;
return false;
}
void ManageResults::report(const int index, const bool excelReport)
{
cout << Colors::YELLOW() << "Reporting " << results.at(index).getFilename() << endl;
std::cout << Colors::YELLOW() << "Reporting " << results.at(index).getFilename() << std::endl;
auto data = results.at(index).load();
if (excelReport) {
ReportExcel reporter(data, compare, workbook);
reporter.show();
openExcel = true;
workbook = reporter.getWorkbook();
cout << "Adding sheet to " << Paths::excel() + Paths::excelResults() << endl;
std::cout << "Adding sheet to " << Paths::excel() + Paths::excelResults() << std::endl;
} else {
ReportConsole reporter(data, compare);
reporter.show();
@ -103,20 +103,20 @@ namespace platform {
{
// Show a dataset result inside a report
auto data = results.at(index).load();
cout << Colors::YELLOW() << "Showing " << results.at(index).getFilename() << endl;
std::cout << Colors::YELLOW() << "Showing " << results.at(index).getFilename() << std::endl;
ReportConsole reporter(data, compare, idx);
reporter.show();
}
void ManageResults::sortList()
{
cout << Colors::YELLOW() << "Choose sorting field (date='d', score='s', duration='u', model='m'): ";
string line;
std::cout << Colors::YELLOW() << "Choose sorting field (date='d', score='s', duration='u', model='m'): ";
std::string line;
char option;
getline(cin, line);
getline(std::cin, line);
if (line.size() == 0)
return;
if (line.size() > 1) {
cout << "Invalid option" << endl;
std::cout << "Invalid option" << std::endl;
return;
}
option = line[0];
@ -134,7 +134,7 @@ namespace platform {
results.sortModel();
break;
default:
cout << "Invalid option" << endl;
std::cout << "Invalid option" << std::endl;
}
}
void ManageResults::menu()
@ -142,9 +142,9 @@ namespace platform {
char option;
int index, subIndex;
bool finished = false;
string filename;
std::string filename;
// tuple<Option, digit, requires value>
vector<tuple<string, char, bool>> mainOptions = {
std::vector<std::tuple<std::string, char, bool>> mainOptions = {
{"quit", 'q', false},
{"list", 'l', false},
{"delete", 'd', true},
@ -153,7 +153,7 @@ namespace platform {
{"report", 'r', true},
{"excel", 'e', true}
};
vector<tuple<string, char, bool>> listOptions = {
std::vector<std::tuple<std::string, char, bool>> listOptions = {
{"report", 'r', true},
{"list", 'l', false},
{"quit", 'q', false}
@ -161,9 +161,9 @@ namespace platform {
auto parser = CommandParser();
while (!finished) {
if (indexList) {
tie(option, index) = parser.parse(Colors::GREEN(), mainOptions, 'r', numFiles - 1);
std::tie(option, index) = parser.parse(Colors::GREEN(), mainOptions, 'r', numFiles - 1);
} else {
tie(option, subIndex) = parser.parse(Colors::MAGENTA(), listOptions, 'r', results.at(index).load()["results"].size() - 1);
std::tie(option, subIndex) = parser.parse(Colors::MAGENTA(), listOptions, 'r', results.at(index).load()["results"].size() - 1);
}
switch (option) {
case 'q':
@ -177,9 +177,9 @@ namespace platform {
filename = results.at(index).getFilename();
if (!confirmAction("delete", filename))
break;
cout << "Deleting " << filename << endl;
std::cout << "Deleting " << filename << std::endl;
results.deleteResult(index);
cout << "File: " + filename + " deleted!" << endl;
std::cout << "File: " + filename + " deleted!" << std::endl;
list();
break;
case 'h':
@ -187,9 +187,9 @@ namespace platform {
if (!confirmAction("hide", filename))
break;
filename = results.at(index).getFilename();
cout << "Hiding " << filename << endl;
std::cout << "Hiding " << filename << std::endl;
results.hideResult(index, Paths::hiddenResults());
cout << "File: " + filename + " hidden! (moved to " << Paths::hiddenResults() << ")" << endl;
std::cout << "File: " + filename + " hidden! (moved to " << Paths::hiddenResults() << ")" << std::endl;
list();
break;
case 's':

4
src/Platform/ManageResults.h
View File

@ -6,12 +6,12 @@
namespace platform {
class ManageResults {
public:
ManageResults(int numFiles, const string& model, const string& score, bool complete, bool partial, bool compare);
ManageResults(int numFiles, const std::string& model, const std::string& score, bool complete, bool partial, bool compare);
~ManageResults() = default;
void doMenu();
private:
void list();
bool confirmAction(const string& intent, const string& fileName) const;
bool confirmAction(const std::string& intent, const std::string& fileName) const;
void report(const int index, const bool excelReport);
void showIndex(const int index, const int idx);
void sortList();

18
src/Platform/Models.cc
View File

@ -1,6 +1,5 @@
#include "Models.h"
namespace platform {
using namespace std;
// Idea from: https://www.codeproject.com/Articles/567242/AplusC-2b-2bplusObjectplusFactory
Models* Models::factory = nullptr;;
Models* Models::instance()
@ -10,13 +9,13 @@ namespace platform {
factory = new Models();
return factory;
}
void Models::registerFactoryFunction(const string& name,
void Models::registerFactoryFunction(const std::string& name,
function<bayesnet::BaseClassifier* (void)> classFactoryFunction)
{
// register the class factory function
functionRegistry[name] = classFactoryFunction;
}
shared_ptr<bayesnet::BaseClassifier> Models::create(const string& name)
shared_ptr<bayesnet::BaseClassifier> Models::create(const std::string& name)
{
bayesnet::BaseClassifier* instance = nullptr;
@ -30,23 +29,22 @@ namespace platform {
else
return nullptr;
}
vector<string> Models::getNames()
std::vector<std::string> Models::getNames()
{
vector<string> names;
std::vector<std::string> names;
transform(functionRegistry.begin(), functionRegistry.end(), back_inserter(names),
[](const pair<string, function<bayesnet::BaseClassifier* (void)>>& pair) { return pair.first; });
[](const pair<std::string, function<bayesnet::BaseClassifier* (void)>>& pair) { return pair.first; });
return names;
}
string Models::toString()
std::string Models::tostring()
{
string result = "";
std::string result = "";
for (const auto& pair : functionRegistry) {
result += pair.first + ", ";
}
return "{" + result.substr(0, result.size() - 2) + "}";
}
Registrar::Registrar(const string& name, function<bayesnet::BaseClassifier* (void)> classFactoryFunction)
Registrar::Registrar(const std::string& name, function<bayesnet::BaseClassifier* (void)> classFactoryFunction)
{
// register the class factory function
Models::instance()->registerFactoryFunction(name, classFactoryFunction);

12
src/Platform/Models.h
View File

@ -14,7 +14,7 @@
namespace platform {
class Models {
private:
map<string, function<bayesnet::BaseClassifier* (void)>> functionRegistry;
map<std::string, function<bayesnet::BaseClassifier* (void)>> functionRegistry;
static Models* factory; //singleton
Models() {};
public:
@ -22,16 +22,16 @@ namespace platform {
void operator=(const Models&) = delete;
// Idea from: https://www.codeproject.com/Articles/567242/AplusC-2b-2bplusObjectplusFactory
static Models* instance();
shared_ptr<bayesnet::BaseClassifier> create(const string& name);
void registerFactoryFunction(const string& name,
shared_ptr<bayesnet::BaseClassifier> create(const std::string& name);
void registerFactoryFunction(const std::string& name,
function<bayesnet::BaseClassifier* (void)> classFactoryFunction);
vector<string> getNames();
string toString();
std::vector<string> getNames();
std::string tostring();
};
class Registrar {
public:
Registrar(const string& className, function<bayesnet::BaseClassifier* (void)> classFactoryFunction);
Registrar(const std::string& className, function<bayesnet::BaseClassifier* (void)> classFactoryFunction);
};
}
#endif

36
src/Platform/ReportBase.cc
View File

@ -7,8 +7,8 @@
namespace platform {
ReportBase::ReportBase(json data_, bool compare) : data(data_), compare(compare), margin(0.1)
{
stringstream oss;
oss << "Better than ZeroR + " << setprecision(1) << fixed << margin * 100 << "%";
std::stringstream oss;
oss << "Better than ZeroR + " << std::setprecision(1) << fixed << margin * 100 << "%";
meaning = {
{Symbols::equal_best, "Equal to best"},
{Symbols::better_best, "Better than best"},
@ -16,10 +16,10 @@ namespace platform {
{Symbols::upward_arrow, oss.str()}
};
}
string ReportBase::fromVector(const string& key)
std::string ReportBase::fromVector(const std::string& key)
{
stringstream oss;
string sep = "";
std::stringstream oss;
std::string sep = "";
oss << "[";
for (auto& item : data[key]) {
oss << sep << item.get<double>();
@ -28,13 +28,13 @@ namespace platform {
oss << "]";
return oss.str();
}
string ReportBase::fVector(const string& title, const json& data, const int width, const int precision)
std::string ReportBase::fVector(const std::string& title, const json& data, const int width, const int precision)
{
stringstream oss;
string sep = "";
std::stringstream oss;
std::string sep = "";
oss << title << "[";
for (const auto& item : data) {
oss << sep << fixed << setw(width) << setprecision(precision) << item.get<double>();
oss << sep << fixed << setw(width) << std::setprecision(precision) << item.get<double>();
sep = ", ";
}
oss << "]";
@ -45,25 +45,25 @@ namespace platform {
header();
body();
}
string ReportBase::compareResult(const string& dataset, double result)
std::string ReportBase::compareResult(const std::string& dataset, double result)
{
string status = " ";
std::string status = " ";
if (compare) {
double best = bestResult(dataset, data["model"].get<string>());
double best = bestResult(dataset, data["model"].get<std::string>());
if (result == best) {
status = Symbols::equal_best;
} else if (result > best) {
status = Symbols::better_best;
}
} else {
if (data["score_name"].get<string>() == "accuracy") {
if (data["score_name"].get<std::string>() == "accuracy") {
auto dt = Datasets(false, Paths::datasets());
dt.loadDataset(dataset);
auto numClasses = dt.getNClasses(dataset);
if (numClasses == 2) {
vector<int> distribution = dt.getClassesCounts(dataset);
std::vector<int> distribution = dt.getClassesCounts(dataset);
double nSamples = dt.getNSamples(dataset);
vector<int>::iterator maxValue = max_element(distribution.begin(), distribution.end());
std::vector<int>::iterator maxValue = max_element(distribution.begin(), distribution.end());
double mark = *maxValue / nSamples * (1 + margin);
if (mark > 1) {
mark = 0.9995;
@ -82,14 +82,14 @@ namespace platform {
}
return status;
}
double ReportBase::bestResult(const string& dataset, const string& model)
double ReportBase::bestResult(const std::string& dataset, const std::string& model)
{
double value = 0.0;
if (bestResults.size() == 0) {
// try to load the best results
string score = data["score_name"];
std::string score = data["score_name"];
replace(score.begin(), score.end(), '_', '-');
string fileName = "best_results_" + score + "_" + model + ".json";
std::string fileName = "best_results_" + score + "_" + model + ".json";
ifstream resultData(Paths::results() + "/" + fileName);
if (resultData.is_open()) {
bestResults = json::parse(resultData);

13
src/Platform/ReportBase.h
View File

@ -8,7 +8,6 @@
using json = nlohmann::json;
namespace platform {
using namespace std;
class ReportBase {
public:
@ -17,19 +16,19 @@ namespace platform {
void show();
protected:
json data;
string fromVector(const string& key);
string fVector(const string& title, const json& data, const int width, const int precision);
std::string fromVector(const std::string& key);
std::string fVector(const std::string& title, const json& data, const int width, const int precision);
bool getExistBestFile();
virtual void header() = 0;
virtual void body() = 0;
virtual void showSummary() = 0;
string compareResult(const string& dataset, double result);
map<string, int> summary;
std::string compareResult(const std::string& dataset, double result);
std::map<std::string, int> summary;
double margin;
map<string, string> meaning;
std::map<std::string, std::string> meaning;
bool compare;
private:
double bestResult(const string& dataset, const string& model);
double bestResult(const std::string& dataset, const std::string& model);
json bestResults;
bool existBestFile = true;
};

103
src/Platform/ReportConsole.cc
View File

@ -6,25 +6,30 @@
#include "CLocale.h"
namespace platform {
string ReportConsole::headerLine(const string& text, int utf = 0)
std::string ReportConsole::headerLine(const std::string& text, int utf = 0)
{
int n = MAXL - text.length() - 3;
n = n < 0 ? 0 : n;
return "* " + text + string(n + utf, ' ') + "*\n";
return "* " + text + std::string(n + utf, ' ') + "*\n";
}
void ReportConsole::header()
{
stringstream oss;
cout << Colors::MAGENTA() << string(MAXL, '*') << endl;
cout << headerLine("Report " + data["model"].get<string>() + " ver. " + data["version"].get<string>() + " with " + to_string(data["folds"].get<int>()) + " Folds cross validation and " + to_string(data["seeds"].size()) + " random seeds. " + data["date"].get<string>() + " " + data["time"].get<string>());
cout << headerLine(data["title"].get<string>());
cout << headerLine("Random seeds: " + fromVector("seeds") + " Stratified: " + (data["stratified"].get<bool>() ? "True" : "False"));
oss << "Execution took " << setprecision(2) << fixed << data["duration"].get<float>() << " seconds, " << data["duration"].get<float>() / 3600 << " hours, on " << data["platform"].get<string>();
cout << headerLine(oss.str());
cout << headerLine("Score is " + data["score_name"].get<string>());
cout << string(MAXL, '*') << endl;
cout << endl;
std::stringstream oss;
std::cout << Colors::MAGENTA() << std::string(MAXL, '*') << std::endl;
std::cout << headerLine(
"Report " + data["model"].get<std::string>() + " ver. " + data["version"].get<std::string>()
+ " with " + std::to_string(data["folds"].get<int>()) + " Folds cross validation and " + std::to_string(data["seeds"].size())
+ " random seeds. " + data["date"].get<std::string>() + " " + data["time"].get<std::string>()
);
std::cout << headerLine(data["title"].get<std::string>());
std::cout << headerLine("Random seeds: " + fromVector("seeds") + " Stratified: " + (data["stratified"].get<bool>() ? "True" : "False"));
oss << "Execution took " << std::setprecision(2) << std::fixed << data["duration"].get<float>()
<< " seconds, " << data["duration"].get<float>() / 3600 << " hours, on " << data["platform"].get<std::string>();
std::cout << headerLine(oss.str());
std::cout << headerLine("Score is " + data["score_name"].get<std::string>());
std::cout << std::string(MAXL, '*') << std::endl;
std::cout << std::endl;
}
void ReportConsole::body()
{
@ -32,12 +37,12 @@ namespace platform {
int maxHyper = 15;
int maxDataset = 7;
for (const auto& r : data["results"]) {
maxHyper = max(maxHyper, (int)r["hyperparameters"].dump().size());
maxDataset = max(maxDataset, (int)r["dataset"].get<string>().size());
maxHyper = std::max(maxHyper, (int)r["hyperparameters"].dump().size());
maxDataset = std::max(maxDataset, (int)r["dataset"].get<std::string>().size());
}
cout << Colors::GREEN() << " # " << setw(maxDataset) << left << "Dataset" << " Sampl. Feat. Cls Nodes Edges States Score Time Hyperparameters" << endl;
cout << "=== " << string(maxDataset, '=') << " ====== ===== === ========= ========= ========= =============== =================== " << string(maxHyper, '=') << endl;
std::cout << Colors::GREEN() << " # " << std::setw(maxDataset) << std::left << "Dataset" << " Sampl. Feat. Cls Nodes Edges States Score Time Hyperparameters" << std::endl;
std::cout << "=== " << std::string(maxDataset, '=') << " ====== ===== === ========= ========= ========= =============== =================== " << std::string(maxHyper, '=') << std::endl;
json lastResult;
double totalScore = 0.0;
bool odd = true;
@ -48,33 +53,33 @@ namespace platform {
continue;
}
auto color = odd ? Colors::CYAN() : Colors::BLUE();
cout << color;
cout << setw(3) << right << index++ << " ";
cout << setw(maxDataset) << left << r["dataset"].get<string>() << " ";
cout << setw(6) << right << r["samples"].get<int>() << " ";
cout << setw(5) << right << r["features"].get<int>() << " ";
cout << setw(3) << right << r["classes"].get<int>() << " ";
cout << setw(9) << setprecision(2) << fixed << r["nodes"].get<float>() << " ";
cout << setw(9) << setprecision(2) << fixed << r["leaves"].get<float>() << " ";
cout << setw(9) << setprecision(2) << fixed << r["depth"].get<float>() << " ";
cout << setw(8) << right << setprecision(6) << fixed << r["score"].get<double>() << "±" << setw(6) << setprecision(4) << fixed << r["score_std"].get<double>();
const string status = compareResult(r["dataset"].get<string>(), r["score"].get<double>());
cout << status;
cout << setw(12) << right << setprecision(6) << fixed << r["time"].get<double>() << "±" << setw(6) << setprecision(4) << fixed << r["time_std"].get<double>() << " ";
cout << r["hyperparameters"].dump();
cout << endl;
cout << flush;
std::cout << color;
std::cout << std::setw(3) << std::right << index++ << " ";
std::cout << std::setw(maxDataset) << std::left << r["dataset"].get<std::string>() << " ";
std::cout << std::setw(6) << std::right << r["samples"].get<int>() << " ";
std::cout << std::setw(5) << std::right << r["features"].get<int>() << " ";
std::cout << std::setw(3) << std::right << r["classes"].get<int>() << " ";
std::cout << std::setw(9) << std::setprecision(2) << std::fixed << r["nodes"].get<float>() << " ";
std::cout << std::setw(9) << std::setprecision(2) << std::fixed << r["leaves"].get<float>() << " ";
std::cout << std::setw(9) << std::setprecision(2) << std::fixed << r["depth"].get<float>() << " ";
std::cout << std::setw(8) << std::right << std::setprecision(6) << std::fixed << r["score"].get<double>() << "±" << std::setw(6) << std::setprecision(4) << std::fixed << r["score_std"].get<double>();
const std::string status = compareResult(r["dataset"].get<std::string>(), r["score"].get<double>());
std::cout << status;
std::cout << std::setw(12) << std::right << std::setprecision(6) << std::fixed << r["time"].get<double>() << "±" << std::setw(6) << std::setprecision(4) << std::fixed << r["time_std"].get<double>() << " ";
std::cout << r["hyperparameters"].dump();
std::cout << std::endl;
std::cout << std::flush;
lastResult = r;
totalScore += r["score"].get<double>();
odd = !odd;
}
if (data["results"].size() == 1 || selectedIndex != -1) {
cout << string(MAXL, '*') << endl;
cout << headerLine(fVector("Train scores: ", lastResult["scores_train"], 14, 12));
cout << headerLine(fVector("Test scores: ", lastResult["scores_test"], 14, 12));
cout << headerLine(fVector("Train times: ", lastResult["times_train"], 10, 3));
cout << headerLine(fVector("Test times: ", lastResult["times_test"], 10, 3));
cout << string(MAXL, '*') << endl;
std::cout << std::string(MAXL, '*') << std::endl;
std::cout << headerLine(fVector("Train scores: ", lastResult["scores_train"], 14, 12));
std::cout << headerLine(fVector("Test scores: ", lastResult["scores_test"], 14, 12));
std::cout << headerLine(fVector("Train times: ", lastResult["times_train"], 10, 3));
std::cout << headerLine(fVector("Test times: ", lastResult["times_test"], 10, 3));
std::cout << std::string(MAXL, '*') << std::endl;
} else {
footer(totalScore);
}
@ -82,28 +87,28 @@ namespace platform {
void ReportConsole::showSummary()
{
for (const auto& item : summary) {
stringstream oss;
oss << setw(3) << left << item.first;
oss << setw(3) << right << item.second << " ";
oss << left << meaning.at(item.first);
cout << headerLine(oss.str(), 2);
std::stringstream oss;
oss << std::setw(3) << std::left << item.first;
oss << std::setw(3) << std::right << item.second << " ";
oss << std::left << meaning.at(item.first);
std::cout << headerLine(oss.str(), 2);
}
}
void ReportConsole::footer(double totalScore)
{
cout << Colors::MAGENTA() << string(MAXL, '*') << endl;
std::cout << Colors::MAGENTA() << std::string(MAXL, '*') << std::endl;
showSummary();
auto score = data["score_name"].get<string>();
auto score = data["score_name"].get<std::string>();
auto best = BestScore::getScore(score);
if (best.first != "") {
stringstream oss;
std::stringstream oss;
oss << score << " compared to " << best.first << " .: " << totalScore / best.second;
cout << headerLine(oss.str());
std::cout << headerLine(oss.str());
}
if (!getExistBestFile() && compare) {
cout << headerLine("*** Best Results File not found. Couldn't compare any result!");
std::cout << headerLine("*** Best Results File not found. Couldn't compare any result!");
}
cout << string(MAXL, '*') << endl << Colors::RESET();
std::cout << std::string(MAXL, '*') << std::endl << Colors::RESET();
}
}

3
src/Platform/ReportConsole.h
View File

@ -5,7 +5,6 @@
#include "Colors.h"
namespace platform {
using namespace std;
const int MAXL = 133;
class ReportConsole : public ReportBase {
public:
@ -13,7 +12,7 @@ namespace platform {
virtual ~ReportConsole() = default;
private:
int selectedIndex;
string headerLine(const string& text, int utf);
std::string headerLine(const std::string& text, int utf);
void header() override;
void body() override;
void footer(double totalScore);

54
src/Platform/ReportExcel.cc
View File

@ -14,28 +14,28 @@ namespace platform {
void ReportExcel::formatColumns()
{
worksheet_freeze_panes(worksheet, 6, 1);
vector<int> columns_sizes = { 22, 10, 9, 7, 12, 12, 12, 12, 12, 3, 15, 12, 23 };
std::vector<int> columns_sizes = { 22, 10, 9, 7, 12, 12, 12, 12, 12, 3, 15, 12, 23 };
for (int i = 0; i < columns_sizes.size(); ++i) {
worksheet_set_column(worksheet, i, i, columns_sizes.at(i), NULL);
}
}
void ReportExcel::createWorksheet()
{
const string name = data["model"].get<string>();
string suffix = "";
string efectiveName;
const std::string name = data["model"].get<std::string>();
std::string suffix = "";
std::string efectiveName;
int num = 1;
// Create a sheet with the name of the model
while (true) {
efectiveName = name + suffix;
if (workbook_get_worksheet_by_name(workbook, efectiveName.c_str())) {
suffix = to_string(++num);
suffix = std::to_string(++num);
} else {
worksheet = workbook_add_worksheet(workbook, efectiveName.c_str());
break;
}
if (num > 100) {
throw invalid_argument("Couldn't create sheet " + efectiveName);
throw std::invalid_argument("Couldn't create sheet " + efectiveName);
}
}
}
@ -48,7 +48,7 @@ namespace platform {
if (worksheet == NULL) {
createWorksheet();
}
setProperties(data["title"].get<string>());
setProperties(data["title"].get<std::string>());
createFormats();
formatColumns();
}
@ -60,26 +60,26 @@ namespace platform {
void ReportExcel::header()
{
locale mylocale(cout.getloc(), new separated);
locale::global(mylocale);
cout.imbue(mylocale);
stringstream oss;
string message = data["model"].get<string>() + " ver. " + data["version"].get<string>() + " " +
data["language"].get<string>() + " ver. " + data["language_version"].get<string>() +
" with " + to_string(data["folds"].get<int>()) + " Folds cross validation and " + to_string(data["seeds"].size()) +
" random seeds. " + data["date"].get<string>() + " " + data["time"].get<string>();
std::locale mylocale(std::cout.getloc(), new separated);
std::locale::global(mylocale);
std::cout.imbue(mylocale);
std::stringstream oss;
std::string message = data["model"].get<std::string>() + " ver. " + data["version"].get<std::string>() + " " +
data["language"].get<std::string>() + " ver. " + data["language_version"].get<std::string>() +
" with " + std::to_string(data["folds"].get<int>()) + " Folds cross validation and " + std::to_string(data["seeds"].size()) +
" random seeds. " + data["date"].get<std::string>() + " " + data["time"].get<std::string>();
worksheet_merge_range(worksheet, 0, 0, 0, 12, message.c_str(), styles["headerFirst"]);
worksheet_merge_range(worksheet, 1, 0, 1, 12, data["title"].get<string>().c_str(), styles["headerRest"]);
worksheet_merge_range(worksheet, 2, 0, 3, 0, ("Score is " + data["score_name"].get<string>()).c_str(), styles["headerRest"]);
worksheet_merge_range(worksheet, 1, 0, 1, 12, data["title"].get<std::string>().c_str(), styles["headerRest"]);
worksheet_merge_range(worksheet, 2, 0, 3, 0, ("Score is " + data["score_name"].get<std::string>()).c_str(), styles["headerRest"]);
worksheet_merge_range(worksheet, 2, 1, 3, 3, "Execution time", styles["headerRest"]);
oss << setprecision(2) << fixed << data["duration"].get<float>() << " s";
oss << std::setprecision(2) << std::fixed << data["duration"].get<float>() << " s";
worksheet_merge_range(worksheet, 2, 4, 2, 5, oss.str().c_str(), styles["headerRest"]);
oss.str("");
oss.clear();
oss << setprecision(2) << fixed << data["duration"].get<float>() / 3600 << " h";
oss << std::setprecision(2) << std::fixed << data["duration"].get<float>() / 3600 << " h";
worksheet_merge_range(worksheet, 3, 4, 3, 5, oss.str().c_str(), styles["headerRest"]);
worksheet_merge_range(worksheet, 2, 6, 3, 7, "Platform", styles["headerRest"]);
worksheet_merge_range(worksheet, 2, 8, 3, 9, data["platform"].get<string>().c_str(), styles["headerRest"]);
worksheet_merge_range(worksheet, 2, 8, 3, 9, data["platform"].get<std::string>().c_str(), styles["headerRest"]);
worksheet_merge_range(worksheet, 2, 10, 2, 12, ("Random seeds: " + fromVector("seeds")).c_str(), styles["headerSmall"]);
oss.str("");
oss.clear();
@ -93,7 +93,7 @@ namespace platform {
void ReportExcel::body()
{
auto head = vector<string>(
auto head = std::vector<std::string>(
{ "Dataset", "Samples", "Features", "Classes", "Nodes", "Edges", "States", "Score", "Score Std.", "St.", "Time",
"Time Std.", "Hyperparameters" });
int col = 0;
@ -105,9 +105,9 @@ namespace platform {
int hypSize = 22;
json lastResult;
double totalScore = 0.0;
string hyperparameters;
std::string hyperparameters;
for (const auto& r : data["results"]) {
writeString(row, col, r["dataset"].get<string>(), "text");
writeString(row, col, r["dataset"].get<std::string>(), "text");
writeInt(row, col + 1, r["samples"].get<int>(), "ints");
writeInt(row, col + 2, r["features"].get<int>(), "ints");
writeInt(row, col + 3, r["classes"].get<int>(), "ints");
@ -116,7 +116,7 @@ namespace platform {
writeDouble(row, col + 6, r["depth"].get<double>(), "floats");
writeDouble(row, col + 7, r["score"].get<double>(), "result");
writeDouble(row, col + 8, r["score_std"].get<double>(), "result");
const string status = compareResult(r["dataset"].get<string>(), r["score"].get<double>());
const std::string status = compareResult(r["dataset"].get<std::string>(), r["score"].get<double>());
writeString(row, col + 9, status, "textCentered");
writeDouble(row, col + 10, r["time"].get<double>(), "time");
writeDouble(row, col + 11, r["time_std"].get<double>(), "time");
@ -133,12 +133,12 @@ namespace platform {
worksheet_set_column(worksheet, 12, 12, hypSize + 5, NULL);
// Show totals if only one dataset is present in the result
if (data["results"].size() == 1) {
for (const string& group : { "scores_train", "scores_test", "times_train", "times_test" }) {
for (const std::string& group : { "scores_train", "scores_test", "times_train", "times_test" }) {
row++;
col = 1;
writeString(row, col, group, "text");
for (double item : lastResult[group]) {
string style = group.find("scores") != string::npos ? "result" : "time";
std::string style = group.find("scores") != std::string::npos ? "result" : "time";
writeDouble(row, ++col, item, style);
}
}
@ -167,7 +167,7 @@ namespace platform {
{
showSummary();
row += 4 + summary.size();
auto score = data["score_name"].get<string>();
auto score = data["score_name"].get<std::string>();
auto best = BestScore::getScore(score);
if (best.first != "") {
worksheet_merge_range(worksheet, row, 1, row, 5, (score + " compared to " + best.first + " .:").c_str(), efectiveStyle("text"));

1
src/Platform/ReportExcel.h
View File

@ -6,7 +6,6 @@
#include "ExcelFile.h"
#include "Colors.h"
namespace platform {
using namespace std;
class ReportExcel : public ReportBase, public ExcelFile {
public:
explicit ReportExcel(json data_, bool compare, lxw_workbook* workbook, lxw_worksheet* worksheet = NULL);

24
src/Platform/Result.cc
View File

@ -8,7 +8,7 @@
#include "CLocale.h"
namespace platform {
Result::Result(const string& path, const string& filename)
Result::Result(const std::string& path, const std::string& filename)
: path(path)
, filename(filename)
{
@ -31,28 +31,28 @@ namespace platform {
json Result::load() const
{
ifstream resultData(path + "/" + filename);
std::ifstream resultData(path + "/" + filename);
if (resultData.is_open()) {
json data = json::parse(resultData);
return data;
}
throw invalid_argument("Unable to open result file. [" + path + "/" + filename + "]");
throw std::invalid_argument("Unable to open result file. [" + path + "/" + filename + "]");
}
string Result::to_string(int maxModel) const
std::string Result::to_string(int maxModel) const
{
auto tmp = ConfigLocale();
stringstream oss;
std::stringstream oss;
double durationShow = duration > 3600 ? duration / 3600 : duration > 60 ? duration / 60 : duration;
string durationUnit = duration > 3600 ? "h" : duration > 60 ? "m" : "s";
std::string durationUnit = duration > 3600 ? "h" : duration > 60 ? "m" : "s";
oss << date << " ";
oss << setw(maxModel) << left << model << " ";
oss << setw(11) << left << scoreName << " ";
oss << right << setw(11) << setprecision(7) << fixed << score << " ";
oss << std::setw(maxModel) << std::left << model << " ";
oss << std::setw(11) << std::left << scoreName << " ";
oss << std::right << std::setw(11) << std::setprecision(7) << std::fixed << score << " ";
auto completeString = isComplete() ? "C" : "P";
oss << setw(1) << " " << completeString << " ";
oss << setw(7) << setprecision(2) << fixed << durationShow << " " << durationUnit << " ";
oss << setw(50) << left << title << " ";
oss << std::setw(1) << " " << completeString << " ";
oss << std::setw(7) << std::setprecision(2) << std::fixed << durationShow << " " << durationUnit << " ";
oss << std::setw(50) << std::left << title << " ";
return oss.str();
}
}

27
src/Platform/Result.h
View File

@ -5,31 +5,30 @@
#include <string>
#include <nlohmann/json.hpp>
namespace platform {
using namespace std;
using json = nlohmann::json;
class Result {
public:
Result(const string& path, const string& filename);
Result(const std::string& path, const std::string& filename);
json load() const;
string to_string(int maxModel) const;
string getFilename() const { return filename; };
string getDate() const { return date; };
std::string to_string(int maxModel) const;
std::string getFilename() const { return filename; };
std::string getDate() const { return date; };
double getScore() const { return score; };
string getTitle() const { return title; };
std::string getTitle() const { return title; };
double getDuration() const { return duration; };
string getModel() const { return model; };
string getScoreName() const { return scoreName; };
std::string getModel() const { return model; };
std::string getScoreName() const { return scoreName; };
bool isComplete() const { return complete; };
private:
string path;
string filename;
string date;
std::string path;
std::string filename;
std::string date;
double score;
string title;
std::string title;
double duration;
string model;
string scoreName;
std::string model;
std::string scoreName;
bool complete;
};
};

6
src/Platform/Results.cc
View File

@ -2,7 +2,7 @@
#include <algorithm>
namespace platform {
Results::Results(const string& path, const string& model, const string& score, bool complete, bool partial) :
Results::Results(const std::string& path, const std::string& model, const std::string& score, bool complete, bool partial) :
path(path), model(model), scoreName(score), complete(complete), partial(partial)
{
load();
@ -17,7 +17,7 @@ namespace platform {
using std::filesystem::directory_iterator;
for (const auto& file : directory_iterator(path)) {
auto filename = file.path().filename().string();
if (filename.find(".json") != string::npos && filename.find("results_") == 0) {
if (filename.find(".json") != std::string::npos && filename.find("results_") == 0) {
auto result = Result(path, filename);
bool addResult = true;
if (model != "any" && result.getModel() != model || scoreName != "any" && scoreName != result.getScoreName() || complete && !result.isComplete() || partial && result.isComplete())
@ -27,7 +27,7 @@ namespace platform {
}
}
}
void Results::hideResult(int index, const string& pathHidden)
void Results::hideResult(int index, const std::string& pathHidden)
{
auto filename = files.at(index).getFilename();
rename((path + "/" + filename).c_str(), (pathHidden + "/" + filename).c_str());

17
src/Platform/Results.h
View File

@ -6,32 +6,31 @@
#include <nlohmann/json.hpp>
#include "Result.h"
namespace platform {
using namespace std;
using json = nlohmann::json;
class Results {
public:
Results(const string& path, const string& model, const string& score, bool complete, bool partial);
Results(const std::string& path, const std::string& model, const std::string& score, bool complete, bool partial);
void sortDate();
void sortScore();
void sortModel();
void sortDuration();
int maxModelSize() const { return maxModel; };
void hideResult(int index, const string& pathHidden);
void hideResult(int index, const std::string& pathHidden);
void deleteResult(int index);
int size() const;
bool empty() const;
vector<Result>::iterator begin() { return files.begin(); };
vector<Result>::iterator end() { return files.end(); };
std::vector<Result>::iterator begin() { return files.begin(); };
std::vector<Result>::iterator end() { return files.end(); };
Result& at(int index) { return files.at(index); };
private:
string path;
string model;
string scoreName;
std::string path;
std::string model;
std::string scoreName;
bool complete;
bool partial;
int maxModel;
vector<Result> files;
std::vector<Result> files;
void load(); // Loads the list of results
};
};

92
src/Platform/Statistics.cc
View File

@ -9,7 +9,7 @@
namespace platform {
Statistics::Statistics(const vector<string>& models, const vector<string>& datasets, const json& data, double significance, bool output) :
Statistics::Statistics(const std::vector<std::string>& models, const std::vector<std::string>& datasets, const json& data, double significance, bool output) :
models(models), datasets(datasets), data(data), significance(significance), output(output)
{
nModels = models.size();
@ -20,27 +20,27 @@ namespace platform {
void Statistics::fit()
{
if (nModels < 3 || nDatasets < 3) {
cerr << "nModels: " << nModels << endl;
cerr << "nDatasets: " << nDatasets << endl;
throw runtime_error("Can't make the Friedman test with less than 3 models and/or less than 3 datasets.");
std::cerr << "nModels: " << nModels << std::endl;
std::cerr << "nDatasets: " << nDatasets << std::endl;
throw std::runtime_error("Can't make the Friedman test with less than 3 models and/or less than 3 datasets.");
}
ranksModels.clear();
computeRanks();
// Set the control model as the one with the lowest average rank
controlIdx = distance(ranks.begin(), min_element(ranks.begin(), ranks.end(), [](const auto& l, const auto& r) { return l.second < r.second; }));
computeWTL();
maxModelName = (*max_element(models.begin(), models.end(), [](const string& a, const string& b) { return a.size() < b.size(); })).size();
maxDatasetName = (*max_element(datasets.begin(), datasets.end(), [](const string& a, const string& b) { return a.size() < b.size(); })).size();
maxModelName = (*std::max_element(models.begin(), models.end(), [](const std::string& a, const std::string& b) { return a.size() < b.size(); })).size();
maxDatasetName = (*std::max_element(datasets.begin(), datasets.end(), [](const std::string& a, const std::string& b) { return a.size() < b.size(); })).size();
fitted = true;
}
map<string, float> assignRanks(vector<pair<string, double>>& ranksOrder)
std::map<std::string, float> assignRanks(std::vector<std::pair<std::string, double>>& ranksOrder)
{
// sort the ranksOrder vector by value
sort(ranksOrder.begin(), ranksOrder.end(), [](const pair<string, double>& a, const pair<string, double>& b) {
// sort the ranksOrder std::vector by value
std::sort(ranksOrder.begin(), ranksOrder.end(), [](const std::pair<std::string, double>& a, const std::pair<std::string, double>& b) {
return a.second > b.second;
});
//Assign ranks to values and if they are the same they share the same averaged rank
map<string, float> ranks;
std::map<std::string, float> ranks;
for (int i = 0; i < ranksOrder.size(); i++) {
ranks[ranksOrder[i].first] = i + 1.0;
}
@ -63,9 +63,9 @@ namespace platform {
}
void Statistics::computeRanks()
{
map<string, float> ranksLine;
std::map<std::string, float> ranksLine;
for (const auto& dataset : datasets) {
vector<pair<string, double>> ranksOrder;
std::vector<std::pair<std::string, double>> ranksOrder;
for (const auto& model : models) {
double value = data[model].at(dataset).at(0).get<double>();
ranksOrder.push_back({ model, value });
@ -118,11 +118,11 @@ namespace platform {
if (!fitted) {
fit();
}
stringstream oss;
std::stringstream oss;
// Reference https://link.springer.com/article/10.1007/s44196-022-00083-8
// Post-hoc Holm test
// Calculate the p-value for the models paired with the control model
map<int, double> stats; // p-value of each model paired with the control model
std::map<int, double> stats; // p-value of each model paired with the control model
boost::math::normal dist(0.0, 1.0);
double diff = sqrt(nModels * (nModels + 1) / (6.0 * nDatasets));
for (int i = 0; i < nModels; i++) {
@ -135,11 +135,11 @@ namespace platform {
stats[i] = p_value;
}
// Sort the models by p-value
vector<pair<int, double>> statsOrder;
std::vector<std::pair<int, double>> statsOrder;
for (const auto& stat : stats) {
statsOrder.push_back({ stat.first, stat.second });
}
sort(statsOrder.begin(), statsOrder.end(), [](const pair<int, double>& a, const pair<int, double>& b) {
std::sort(statsOrder.begin(), statsOrder.end(), [](const std::pair<int, double>& a, const std::pair<int, double>& b) {
return a.second < b.second;
});
@ -147,29 +147,29 @@ namespace platform {
for (int i = 0; i < statsOrder.size(); ++i) {
auto item = statsOrder.at(i);
double before = i == 0 ? 0.0 : statsOrder.at(i - 1).second;
double p_value = min((double)1.0, item.second * (nModels - i));
p_value = max(before, p_value);
double p_value = std::min((double)1.0, item.second * (nModels - i));
p_value = std::max(before, p_value);
statsOrder[i] = { item.first, p_value };
}
holmResult.model = models.at(controlIdx);
auto color = friedmanResult ? Colors::CYAN() : Colors::YELLOW();
oss << color;
oss << " *************************************************************************************************************" << endl;
oss << " Post-hoc Holm test: H0: 'There is no significant differences between the control model and the other models.'" << endl;
oss << " Control model: " << models.at(controlIdx) << endl;
oss << " " << left << setw(maxModelName) << string("Model") << " p-value rank win tie loss Status" << endl;
oss << " " << string(maxModelName, '=') << " ============ ========= === === ==== =============" << endl;
oss << " *************************************************************************************************************" << std::endl;
oss << " Post-hoc Holm test: H0: 'There is no significant differences between the control model and the other models.'" << std::endl;
oss << " Control model: " << models.at(controlIdx) << std::endl;
oss << " " << std::left << std::setw(maxModelName) << std::string("Model") << " p-value rank win tie loss Status" << std::endl;
oss << " " << std::string(maxModelName, '=') << " ============ ========= === === ==== =============" << std::endl;
// sort ranks from lowest to highest
vector<pair<string, float>> ranksOrder;
std::vector<std::pair<std::string, float>> ranksOrder;
for (const auto& rank : ranks) {
ranksOrder.push_back({ rank.first, rank.second });
}
sort(ranksOrder.begin(), ranksOrder.end(), [](const pair<string, float>& a, const pair<string, float>& b) {
std::sort(ranksOrder.begin(), ranksOrder.end(), [](const std::pair<std::string, float>& a, const std::pair<std::string, float>& b) {
return a.second < b.second;
});
// Show the control model info.
oss << " " << Colors::BLUE() << left << setw(maxModelName) << ranksOrder.at(0).first << " ";
oss << setw(12) << " " << setprecision(7) << fixed << " " << ranksOrder.at(0).second << endl;
oss << " " << Colors::BLUE() << std::left << std::setw(maxModelName) << ranksOrder.at(0).first << " ";
oss << std::setw(12) << " " << std::setprecision(7) << std::fixed << " " << ranksOrder.at(0).second << std::endl;
for (const auto& item : ranksOrder) {
auto idx = distance(models.begin(), find(models.begin(), models.end(), item.first));
double pvalue = 0.0;
@ -185,15 +185,15 @@ namespace platform {
auto colorStatus = pvalue > significance ? Colors::GREEN() : Colors::MAGENTA();
auto status = pvalue > significance ? Symbols::check_mark : Symbols::cross;
auto textStatus = pvalue > significance ? " accepted H0" : " rejected H0";
oss << " " << colorStatus << left << setw(maxModelName) << item.first << " ";
oss << setprecision(6) << scientific << pvalue << setprecision(7) << fixed << " " << item.second;
oss << " " << right << setw(3) << wtl.at(idx).win << " " << setw(3) << wtl.at(idx).tie << " " << setw(4) << wtl.at(idx).loss;
oss << " " << status << textStatus << endl;
oss << " " << colorStatus << std::left << std::setw(maxModelName) << item.first << " ";
oss << std::setprecision(6) << std::scientific << pvalue << std::setprecision(7) << std::fixed << " " << item.second;
oss << " " << std::right << std::setw(3) << wtl.at(idx).win << " " << std::setw(3) << wtl.at(idx).tie << " " << std::setw(4) << wtl.at(idx).loss;
oss << " " << status << textStatus << std::endl;
}
oss << color << " *************************************************************************************************************" << endl;
oss << color << " *************************************************************************************************************" << std::endl;
oss << Colors::RESET();
if (output) {
cout << oss.str();
std::cout << oss.str();
}
}
bool Statistics::friedmanTest()
@ -201,12 +201,12 @@ namespace platform {
if (!fitted) {
fit();
}
stringstream oss;
std::stringstream oss;
// Friedman test
// Calculate the Friedman statistic
oss << Colors::BLUE() << endl;
oss << "***************************************************************************************************************" << endl;
oss << Colors::GREEN() << "Friedman test: H0: 'There is no significant differences between all the classifiers.'" << Colors::BLUE() << endl;
oss << Colors::BLUE() << std::endl;
oss << "***************************************************************************************************************" << std::endl;
oss << Colors::GREEN() << "Friedman test: H0: 'There is no significant differences between all the classifiers.'" << Colors::BLUE() << std::endl;
double degreesOfFreedom = nModels - 1.0;
double sumSquared = 0;
for (const auto& rank : ranks) {
@ -218,21 +218,21 @@ namespace platform {
boost::math::chi_squared chiSquared(degreesOfFreedom);
long double p_value = (long double)1.0 - cdf(chiSquared, friedmanQ);
double criticalValue = quantile(chiSquared, 1 - significance);
oss << "Friedman statistic: " << friedmanQ << endl;
oss << "Critical χ2 Value for df=" << fixed << (int)degreesOfFreedom
<< " and alpha=" << setprecision(2) << fixed << significance << ": " << setprecision(7) << scientific << criticalValue << std::endl;
oss << "p-value: " << scientific << p_value << " is " << (p_value < significance ? "less" : "greater") << " than " << setprecision(2) << fixed << significance << endl;
oss << "Friedman statistic: " << friedmanQ << std::endl;
oss << "Critical χ2 Value for df=" << std::fixed << (int)degreesOfFreedom
<< " and alpha=" << std::setprecision(2) << std::fixed << significance << ": " << std::setprecision(7) << std::scientific << criticalValue << std::endl;
oss << "p-value: " << std::scientific << p_value << " is " << (p_value < significance ? "less" : "greater") << " than " << std::setprecision(2) << std::fixed << significance << std::endl;
bool result;
if (p_value < significance) {
oss << Colors::GREEN() << "The null hypothesis H0 is rejected." << endl;
oss << Colors::GREEN() << "The null hypothesis H0 is rejected." << std::endl;
result = true;
} else {
oss << Colors::YELLOW() << "The null hypothesis H0 is accepted. Computed p-values will not be significant." << endl;
oss << Colors::YELLOW() << "The null hypothesis H0 is accepted. Computed p-values will not be significant." << std::endl;
result = false;
}
oss << Colors::BLUE() << "***************************************************************************************************************" << Colors::RESET() << endl;
oss << Colors::BLUE() << "***************************************************************************************************************" << Colors::RESET() << std::endl;
if (output) {
cout << oss.str();
std::cout << oss.str();
}
friedmanResult = { friedmanQ, criticalValue, p_value, result };
return result;
@ -245,7 +245,7 @@ namespace platform {
{
return holmResult;
}
map<string, map<string, float>>& Statistics::getRanks()
std::map<std::string, std::map<std::string, float>>& Statistics::getRanks()
{
return ranksModels;
}

21
src/Platform/Statistics.h
View File

@ -5,7 +5,6 @@
#include <map>
#include <nlohmann/json.hpp>
using namespace std;
using json = nlohmann::json;
namespace platform {
@ -21,30 +20,30 @@ namespace platform {
bool reject;
};
struct HolmLine {
string model;
std::string model;
long double pvalue;
double rank;
WTL wtl;
bool reject;
};
struct HolmResult {
string model;
vector<HolmLine> holmLines;
std::string model;
std::vector<HolmLine> holmLines;
};
class Statistics {
public:
Statistics(const vector<string>& models, const vector<string>& datasets, const json& data, double significance = 0.05, bool output = true);
Statistics(const std::vector<std::string>& models, const std::vector<std::string>& datasets, const json& data, double significance = 0.05, bool output = true);
bool friedmanTest();
void postHocHolmTest(bool friedmanResult);
FriedmanResult& getFriedmanResult();
HolmResult& getHolmResult();
map<string, map<string, float>>& getRanks();
std::map<std::string, std::map<std::string, float>>& getRanks();
private:
void fit();
void computeRanks();
void computeWTL();
const vector<string>& models;
const vector<string>& datasets;
const std::vector<std::string>& models;
const std::vector<std::string>& datasets;
const json& data;
double significance;
bool output;
@ -52,13 +51,13 @@ namespace platform {
int nModels = 0;
int nDatasets = 0;
int controlIdx = 0;
map<int, WTL> wtl;
map<string, float> ranks;
std::map<int, WTL> wtl;
std::map<std::string, float> ranks;
int maxModelName = 0;
int maxDatasetName = 0;
FriedmanResult friedmanResult;
HolmResult holmResult;
map<string, map<string, float>> ranksModels;
std::map<std::string, std::map<std::string, float>> ranksModels;
};
}
#endif // !STATISTICS_H

17
src/Platform/Symbols.h
View File

@ -1,18 +1,17 @@
#ifndef SYMBOLS_H
#define SYMBOLS_H
#include <string>
using namespace std;
namespace platform {
class Symbols {
public:
inline static const string check_mark{ "\u2714" };
inline static const string exclamation{ "\u2757" };
inline static const string black_star{ "\u2605" };
inline static const string cross{ "\u2717" };
inline static const string upward_arrow{ "\u27B6" };
inline static const string down_arrow{ "\u27B4" };
inline static const string equal_best{ check_mark };
inline static const string better_best{ black_star };
inline static const std::string check_mark{ "\u2714" };
inline static const std::string exclamation{ "\u2757" };
inline static const std::string black_star{ "\u2605" };
inline static const std::string cross{ "\u2717" };
inline static const std::string upward_arrow{ "\u27B6" };
inline static const std::string down_arrow{ "\u27B4" };
inline static const std::string equal_best{ check_mark };
inline static const std::string better_best{ black_star };
};
}
#endif // !SYMBOLS_H

2
src/Platform/Utils.h
View File

@ -4,7 +4,7 @@
#include <string>
#include <vector>
namespace platform {
//static vector<string> split(const string& text, char delimiter);
//static std::vector<std::string> split(const std::string& text, char delimiter);
static std::vector<std::string> split(const std::string& text, char delimiter)
{
std::vector<std::string> result;

39
src/Platform/b_best.cc
View File

@ -4,7 +4,6 @@
#include "BestResults.h"
#include "Colors.h"
using namespace std;
argparse::ArgumentParser manageArguments(int argc, char** argv)
{
@ -15,19 +14,19 @@ argparse::ArgumentParser manageArguments(int argc, char** argv)
program.add_argument("--report").help("report of best score results file").default_value(false).implicit_value(true);
program.add_argument("--friedman").help("Friedman test").default_value(false).implicit_value(true);
program.add_argument("--excel").help("Output to excel").default_value(false).implicit_value(true);
program.add_argument("--level").help("significance level").default_value(0.05).scan<'g', double>().action([](const string& value) {
program.add_argument("--level").help("significance level").default_value(0.05).scan<'g', double>().action([](const std::string& value) {
try {
auto k = stod(value);
auto k = std::stod(value);
if (k < 0.01 || k > 0.15) {
throw runtime_error("Significance level hast to be a number in [0.01, 0.15]");
throw std::runtime_error("Significance level hast to be a number in [0.01, 0.15]");
}
return k;
}
catch (const runtime_error& err) {
throw runtime_error(err.what());
catch (const std::runtime_error& err) {
throw std::runtime_error(err.what());
}
catch (...) {
throw runtime_error("Number of folds must be an decimal number");
throw std::runtime_error("Number of folds must be an decimal number");
}});
return program;
}
@ -35,35 +34,35 @@ argparse::ArgumentParser manageArguments(int argc, char** argv)
int main(int argc, char** argv)
{
auto program = manageArguments(argc, argv);
string model, score;
std::string model, score;
bool build, report, friedman, excel;
double level;
try {
program.parse_args(argc, argv);
model = program.get<string>("model");
score = program.get<string>("score");
model = program.get<std::string>("model");
score = program.get<std::string>("score");
build = program.get<bool>("build");
report = program.get<bool>("report");
friedman = program.get<bool>("friedman");
excel = program.get<bool>("excel");
level = program.get<double>("level");
if (model == "" || score == "") {
throw runtime_error("Model and score name must be supplied");
throw std::runtime_error("Model and score name must be supplied");
}
if (friedman && model != "any") {
cerr << "Friedman test can only be used with all models" << endl;
cerr << program;
std::cerr << "Friedman test can only be used with all models" << std::endl;
std::cerr << program;
exit(1);
}
if (!report && !build) {
cerr << "Either build, report or both, have to be selected to do anything!" << endl;
cerr << program;
std::cerr << "Either build, report or both, have to be selected to do anything!" << std::endl;
std::cerr << program;
exit(1);
}
}
catch (const exception& err) {
cerr << err.what() << endl;
cerr << program;
catch (const std::exception& err) {
std::cerr << err.what() << std::endl;
std::cerr << program;
exit(1);
}
// Generate report
@ -72,8 +71,8 @@ int main(int argc, char** argv)
if (model == "any") {
results.buildAll();
} else {
string fileName = results.build();
cout << Colors::GREEN() << fileName << " created!" << Colors::RESET() << endl;
std::string fileName = results.build();
std::cout << Colors::GREEN() << fileName << " created!" << Colors::RESET() << std::endl;
}
}
if (report) {

39
src/Platform/b_list.cc
View File

@ -4,54 +4,53 @@
#include "Colors.h"
#include "Datasets.h"
using namespace std;
const int BALANCE_LENGTH = 75;
struct separated : numpunct<char> {
char do_decimal_point() const { return ','; }
char do_thousands_sep() const { return '.'; }
string do_grouping() const { return "\03"; }
std::string do_grouping() const { return "\03"; }
};
void outputBalance(const string& balance)
void outputBalance(const std::string& balance)
{
auto temp = string(balance);
auto temp = std::string(balance);
while (temp.size() > BALANCE_LENGTH - 1) {
auto part = temp.substr(0, BALANCE_LENGTH);
cout << part << endl;
cout << setw(48) << " ";
std::cout << part << std::endl;
std::cout << setw(48) << " ";
temp = temp.substr(BALANCE_LENGTH);
}
cout << temp << endl;
std::cout << temp << std::endl;
}
int main(int argc, char** argv)
{
auto data = platform::Datasets(false, platform::Paths::datasets());
locale mylocale(cout.getloc(), new separated);
locale mylocale(std::cout.getloc(), new separated);
locale::global(mylocale);
cout.imbue(mylocale);
cout << Colors::GREEN() << "Dataset Sampl. Feat. Cls. Balance" << endl;
string balanceBars = string(BALANCE_LENGTH, '=');
cout << "============================== ====== ===== === " << balanceBars << endl;
std::cout.imbue(mylocale);
std::cout << Colors::GREEN() << "Dataset Sampl. Feat. Cls. Balance" << std::endl;
std::string balanceBars = std::string(BALANCE_LENGTH, '=');
std::cout << "============================== ====== ===== === " << balanceBars << std::endl;
bool odd = true;
for (const auto& dataset : data.getNames()) {
auto color = odd ? Colors::CYAN() : Colors::BLUE();
cout << color << setw(30) << left << dataset << " ";
std::cout << color << setw(30) << left << dataset << " ";
data.loadDataset(dataset);
auto nSamples = data.getNSamples(dataset);
cout << setw(6) << right << nSamples << " ";
cout << setw(5) << right << data.getFeatures(dataset).size() << " ";
cout << setw(3) << right << data.getNClasses(dataset) << " ";
stringstream oss;
string sep = "";
std::cout << setw(6) << right << nSamples << " ";
std::cout << setw(5) << right << data.getFeatures(dataset).size() << " ";
std::cout << setw(3) << right << data.getNClasses(dataset) << " ";
std::stringstream oss;
std::string sep = "";
for (auto number : data.getClassesCounts(dataset)) {
oss << sep << setprecision(2) << fixed << (float)number / nSamples * 100.0 << "% (" << number << ")";
oss << sep << std::setprecision(2) << fixed << (float)number / nSamples * 100.0 << "% (" << number << ")";
sep = " / ";
}
outputBalance(oss.str());
odd = !odd;
}
cout << Colors::RESET() << endl;
std::cout << Colors::RESET() << std::endl;
return 0;
}

37
src/Platform/b_main.cc
View File

@ -9,7 +9,6 @@
#include "Paths.h"
using namespace std;
using json = nlohmann::json;
argparse::ArgumentParser manageArguments()
@ -19,13 +18,13 @@ argparse::ArgumentParser manageArguments()
program.add_argument("-d", "--dataset").default_value("").help("Dataset file name");
program.add_argument("--hyperparameters").default_value("{}").help("Hyperparamters passed to the model in Experiment");
program.add_argument("-m", "--model")
.help("Model to use " + platform::Models::instance()->toString())
.help("Model to use " + platform::Models::instance()->tostring())
.action([](const std::string& value) {
static const vector<string> choices = platform::Models::instance()->getNames();
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 std::runtime_error("Model must be one of " + platform::Models::instance()->tostring());
}
);
program.add_argument("--title").default_value("").help("Experiment title");
@ -33,19 +32,19 @@ argparse::ArgumentParser manageArguments()
program.add_argument("--quiet").help("Don't display detailed progress").default_value(false).implicit_value(true);
program.add_argument("--save").help("Save result (always save if no dataset is supplied)").default_value(false).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) {
program.add_argument("-f", "--folds").help("Number of folds").default_value(stoi(env.get("n_folds"))).scan<'i', int>().action([](const std::string& value) {
try {
auto k = stoi(value);
if (k < 2) {
throw runtime_error("Number of folds must be greater than 1");
throw std::runtime_error("Number of folds must be greater than 1");
}
return k;
}
catch (const runtime_error& err) {
throw runtime_error(err.what());
throw std::runtime_error(err.what());
}
catch (...) {
throw runtime_error("Number of folds must be an integer");
throw std::runtime_error("Number of folds must be an integer");
}});
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);
@ -54,39 +53,39 @@ argparse::ArgumentParser manageArguments()
int main(int argc, char** argv)
{
string file_name, model_name, title;
std::string file_name, model_name, title;
json hyperparameters_json;
bool discretize_dataset, stratified, saveResults, quiet;
vector<int> seeds;
vector<string> filesToTest;
std::vector<int> seeds;
std::vector<std::string> filesToTest;
int n_folds;
auto program = manageArguments();
try {
program.parse_args(argc, argv);
file_name = program.get<string>("dataset");
model_name = program.get<string>("model");
file_name = program.get<std::string>("dataset");
model_name = program.get<std::string>("model");
discretize_dataset = program.get<bool>("discretize");
stratified = program.get<bool>("stratified");
quiet = program.get<bool>("quiet");
n_folds = program.get<int>("folds");
seeds = program.get<vector<int>>("seeds");
auto hyperparameters = program.get<string>("hyperparameters");
seeds = program.get<std::vector<int>>("seeds");
auto hyperparameters = program.get<std::string>("hyperparameters");
hyperparameters_json = json::parse(hyperparameters);
title = program.get<string>("title");
title = program.get<std::string>("title");
if (title == "" && file_name == "") {
throw runtime_error("title is mandatory if dataset is not provided");
}
saveResults = program.get<bool>("save");
}
catch (const exception& err) {
cerr << err.what() << endl;
cerr << err.what() << std::endl;
cerr << program;
exit(1);
}
auto datasets = platform::Datasets(discretize_dataset, platform::Paths::datasets());
if (file_name != "") {
if (!datasets.isDataset(file_name)) {
cerr << "Dataset " << file_name << " not found" << endl;
cerr << "Dataset " << file_name << " not found" << std::endl;
exit(1);
}
if (title == "") {
@ -118,6 +117,6 @@ int main(int argc, char** argv)
}
if (!quiet)
experiment.report();
cout << "Done!" << endl;
std::cout << "Done!" << std::endl;
return 0;
}

17
src/Platform/b_manage.cc
View File

@ -2,7 +2,6 @@
#include <argparse/argparse.hpp>
#include "ManageResults.h"
using namespace std;
argparse::ArgumentParser manageArguments(int argc, char** argv)
{
@ -17,17 +16,17 @@ argparse::ArgumentParser manageArguments(int argc, char** argv)
program.parse_args(argc, argv);
auto number = program.get<int>("number");
if (number < 0) {
throw runtime_error("Number of results must be greater than or equal to 0");
throw std::runtime_error("Number of results must be greater than or equal to 0");
}
auto model = program.get<string>("model");
auto score = program.get<string>("score");
auto model = program.get<std::string>("model");
auto score = program.get<std::string>("score");
auto complete = program.get<bool>("complete");
auto partial = program.get<bool>("partial");
auto compare = program.get<bool>("compare");
}
catch (const exception& err) {
cerr << err.what() << endl;
cerr << program;
catch (const std::exception& err) {
std::cerr << err.what() << std::endl;
std::cerr << program;
exit(1);
}
return program;
@ -37,8 +36,8 @@ int main(int argc, char** argv)
{
auto program = manageArguments(argc, argv);
int number = program.get<int>("number");
string model = program.get<string>("model");
string score = program.get<string>("score");
std::string model = program.get<std::string>("model");
std::string score = program.get<std::string>("score");
auto complete = program.get<bool>("complete");
auto partial = program.get<bool>("partial");
auto compare = program.get<bool>("compare");

9
src/PyClassifiers/CMakeLists.txt Normal file
View File

@ -0,0 +1,9 @@
include_directories(${BayesNet_SOURCE_DIR}/lib/mdlp)
include_directories(${BayesNet_SOURCE_DIR}/lib/Files)
include_directories(${BayesNet_SOURCE_DIR}/lib/json/include)
include_directories(${BayesNet_SOURCE_DIR}/src/BayesNet)
include_directories(${BayesNet_SOURCE_DIR}/src/Platform)
add_library(BayesNet bayesnetUtils.cc Network.cc Node.cc BayesMetrics.cc Classifier.cc
KDB.cc TAN.cc SPODE.cc Ensemble.cc AODE.cc TANLd.cc KDBLd.cc SPODELd.cc AODELd.cc BoostAODE.cc
Mst.cc Proposal.cc CFS.cc FCBF.cc IWSS.cc FeatureSelect.cc ${BayesNet_SOURCE_DIR}/src/Platform/Models.cc)
target_link_libraries(BayesNet mdlp "${TORCH_LIBRARIES}")

15
src/PyClassifiers/PyClf.h Normal file
View File

@ -0,0 +1,15 @@
#ifndef PYCLF_H
#define PYCLF_H
#include <string>
#include "DotEnv.h"
namespace PyClassifiers {
class PyClf {
public:
PyClf(const std::string& name);
virtual ~PyClf();
private:
std::string name;
};
} /* namespace PyClassifiers */
#endif /* PYCLF_H */

18
src/PyClassifiers/Pyclf.cc Normal file
View File

@ -0,0 +1,18 @@
#include "PyClf.h"
namespace PyClassifiers {
PyClf::PyClf(const std::std::string& name) : name(name)
{
env = platform::DotEnv();
}
PyClf::~PyClf()
{
}
} /* namespace PyClassifiers */

11
tests/TestBayesMetrics.cc
View File

@ -4,24 +4,23 @@
#include "BayesMetrics.h"
#include "TestUtils.h"
using namespace std;
TEST_CASE("Metrics Test", "[BayesNet]")
{
string file_name = GENERATE("glass", "iris", "ecoli", "diabetes");
map<string, pair<int, vector<int>>> resultsKBest = {
std::string file_name = GENERATE("glass", "iris", "ecoli", "diabetes");
map<std::string, pair<int, std::vector<int>>> resultsKBest = {
{"glass", {7, { 0, 1, 7, 6, 3, 5, 2 }}},
{"iris", {3, { 0, 3, 2 }} },
{"ecoli", {6, { 2, 4, 1, 0, 6, 5 }}},
{"diabetes", {2, { 7, 1 }}}
};
map<string, double> resultsMI = {
map<std::string, double> resultsMI = {
{"glass", 0.12805398},
{"iris", 0.3158139948},
{"ecoli", 0.0089431099},
{"diabetes", 0.0345470614}
};
map<pair<string, int>, vector<pair<int, int>>> resultsMST = {
map<pair<std::string, int>, std::vector<pair<int, int>>> resultsMST = {
{ {"glass", 0}, { {0, 6}, {0, 5}, {0, 3}, {5, 1}, {5, 8}, {5, 4}, {6, 2}, {6, 7} } },
{ {"glass", 1}, { {1, 5}, {5, 0}, {5, 8}, {5, 4}, {0, 6}, {0, 3}, {6, 2}, {6, 7} } },
{ {"iris", 0}, { {0, 1}, {0, 2}, {1, 3} } },
@ -41,7 +40,7 @@ TEST_CASE("Metrics Test", "[BayesNet]")
SECTION("Test SelectKBestWeighted")
{
vector<int> kBest = metrics.SelectKBestWeighted(raw.weights, true, resultsKBest.at(file_name).first);
std::vector<int> kBest = metrics.SelectKBestWeighted(raw.weights, true, resultsKBest.at(file_name).first);
REQUIRE(kBest.size() == resultsKBest.at(file_name).first);
REQUIRE(kBest == resultsKBest.at(file_name).second);
}

14
tests/TestBayesModels.cc
View File

@ -2,9 +2,9 @@
#include <catch2/catch_test_macros.hpp>
#include <catch2/catch_approx.hpp>
#include <catch2/generators/catch_generators.hpp>
#include <vector>
#include <std::vector>
#include <map>
#include <string>
#include <std::string>
#include "KDB.h"
#include "TAN.h"
#include "SPODE.h"
@ -18,7 +18,7 @@
TEST_CASE("Test Bayesian Classifiers score", "[BayesNet]")
{
map <pair<string, string>, float> scores = {
map <pair<std::string, std::string>, float> scores = {
// Diabetes
{{"diabetes", "AODE"}, 0.811198}, {{"diabetes", "KDB"}, 0.852865}, {{"diabetes", "SPODE"}, 0.802083}, {{"diabetes", "TAN"}, 0.821615},
{{"diabetes", "AODELd"}, 0.8138f}, {{"diabetes", "KDBLd"}, 0.80208f}, {{"diabetes", "SPODELd"}, 0.78646f}, {{"diabetes", "TANLd"}, 0.8099f}, {{"diabetes", "BoostAODE"}, 0.83984f},
@ -33,7 +33,7 @@ TEST_CASE("Test Bayesian Classifiers score", "[BayesNet]")
{{"iris", "AODELd"}, 0.973333}, {{"iris", "KDBLd"}, 0.973333}, {{"iris", "SPODELd"}, 0.96f}, {{"iris", "TANLd"}, 0.97333f}, {{"iris", "BoostAODE"}, 0.98f}
};
string file_name = GENERATE("glass", "iris", "ecoli", "diabetes");
std::string file_name = GENERATE("glass", "iris", "ecoli", "diabetes");
auto raw = RawDatasets(file_name, false);
SECTION("Test TAN classifier (" + file_name + ")")
@ -111,12 +111,12 @@ TEST_CASE("Test Bayesian Classifiers score", "[BayesNet]")
REQUIRE(score == Catch::Approx(scores[{file_name, "BoostAODE"}]).epsilon(raw.epsilon));
}
// for (auto scores : scores) {
// cout << "{{\"" << scores.first.first << "\", \"" << scores.first.second << "\"}, " << scores.second << "}, ";
// std::cout << "{{\"" << scores.first.first << "\", \"" << scores.first.second << "\"}, " << scores.second << "}, ";
// }
}
TEST_CASE("Models features", "[BayesNet]")
{
auto graph = vector<string>({ "digraph BayesNet {\nlabel=<BayesNet Test>\nfontsize=30\nfontcolor=blue\nlabelloc=t\nlayout=circo\n",
auto graph = std::vector<std::string>({ "digraph BayesNet {\nlabel=<BayesNet Test>\nfontsize=30\nfontcolor=blue\nlabelloc=t\nlayout=circo\n",
"class [shape=circle, fontcolor=red, fillcolor=lightblue, style=filled ] \n",
"class -> sepallength", "class -> sepalwidth", "class -> petallength", "class -> petalwidth", "petallength [shape=circle] \n",
"petallength -> sepallength", "petalwidth [shape=circle] \n", "sepallength [shape=circle] \n",
@ -128,7 +128,7 @@ TEST_CASE("Models features", "[BayesNet]")
clf.fit(raw.Xv, raw.yv, raw.featuresv, raw.classNamev, raw.statesv);
REQUIRE(clf.getNumberOfNodes() == 6);
REQUIRE(clf.getNumberOfEdges() == 7);
REQUIRE(clf.show() == vector<string>{"class -> sepallength, sepalwidth, petallength, petalwidth, ", "petallength -> sepallength, ", "petalwidth -> ", "sepallength -> sepalwidth, ", "sepalwidth -> petalwidth, "});
REQUIRE(clf.show() == std::vector<std::string>{"class -> sepallength, sepalwidth, petallength, petalwidth, ", "petallength -> sepallength, ", "petalwidth -> ", "sepallength -> sepalwidth, ", "sepalwidth -> petalwidth, "});
REQUIRE(clf.graph("Test") == graph);
}
TEST_CASE("Get num features & num edges", "[BayesNet]")

26
tests/TestBayesNetwork.cc
View File

@ -1,13 +1,13 @@
#include <catch2/catch_test_macros.hpp>
#include <catch2/catch_approx.hpp>
#include <catch2/generators/catch_generators.hpp>
#include <string>
#include <std::string>
#include "TestUtils.h"
#include "Network.h"
void buildModel(bayesnet::Network& net, const vector<string>& features, const string& className)
void buildModel(bayesnet::Network& net, const std::vector<std::string>& features, const std::std::string& className)
{
vector<pair<int, int>> network = { {0, 1}, {0, 2}, {1, 3} };
std::vector<pair<int, int>> network = { {0, 1}, {0, 2}, {1, 3} };
for (const auto& feature : features) {
net.addNode(feature);
}
@ -30,9 +30,9 @@ TEST_CASE("Test Bayesian Network", "[BayesNet]")
{
net.addNode("A");
net.addNode("B");
REQUIRE(net.getFeatures() == vector<string>{"A", "B"});
REQUIRE(net.getFeatures() == std::vector<std::string>{"A", "B"});
net.addNode("C");
REQUIRE(net.getFeatures() == vector<string>{"A", "B", "C"});
REQUIRE(net.getFeatures() == std::vector<std::string>{"A", "B", "C"});
}
SECTION("Test get edges")
{
@ -41,10 +41,10 @@ TEST_CASE("Test Bayesian Network", "[BayesNet]")
net.addNode("C");
net.addEdge("A", "B");
net.addEdge("B", "C");
REQUIRE(net.getEdges() == vector<pair<string, string>>{ {"A", "B"}, { "B", "C" } });
REQUIRE(net.getEdges() == std::vector<pair<std::string, std::string>>{ {"A", "B"}, { "B", "C" } });
REQUIRE(net.getNumEdges() == 2);
net.addEdge("A", "C");
REQUIRE(net.getEdges() == vector<pair<string, string>>{ {"A", "B"}, { "A", "C" }, { "B", "C" } });
REQUIRE(net.getEdges() == std::vector<pair<std::string, std::string>>{ {"A", "B"}, { "A", "C" }, { "B", "C" } });
REQUIRE(net.getNumEdges() == 3);
}
SECTION("Test getNodes")
@ -66,7 +66,7 @@ TEST_CASE("Test Bayesian Network", "[BayesNet]")
buildModel(net, raw.featuresv, raw.classNamev);
buildModel(net2, raw.featurest, raw.classNamet);
buildModel(net3, raw.featurest, raw.classNamet);
vector<pair<string, string>> edges = {
std::vector<pair<std::string, std::string>> edges = {
{"class", "sepallength"}, {"class", "sepalwidth"}, {"class", "petallength"},
{"class", "petalwidth" }, {"sepallength", "sepalwidth"}, {"sepallength", "petallength"},
{"sepalwidth", "petalwidth"}
@ -74,7 +74,7 @@ TEST_CASE("Test Bayesian Network", "[BayesNet]")
REQUIRE(net.getEdges() == edges);
REQUIRE(net2.getEdges() == edges);
REQUIRE(net3.getEdges() == edges);
vector<string> features = { "sepallength", "sepalwidth", "petallength", "petalwidth", "class" };
std::vector<std::string> features = { "sepallength", "sepalwidth", "petallength", "petalwidth", "class" };
REQUIRE(net.getFeatures() == features);
REQUIRE(net2.getFeatures() == features);
REQUIRE(net3.getFeatures() == features);
@ -84,7 +84,7 @@ TEST_CASE("Test Bayesian Network", "[BayesNet]")
// Check Nodes parents & children
for (const auto& feature : features) {
// Parents
vector<string> parents, parents2, parents3, children, children2, children3;
std::vector<std::string> parents, parents2, parents3, children, children2, children3;
auto nodeParents = nodes[feature]->getParents();
auto nodeParents2 = nodes2[feature]->getParents();
auto nodeParents3 = nodes3[feature]->getParents();
@ -173,8 +173,8 @@ TEST_CASE("Test Bayesian Network", "[BayesNet]")
// {
// auto net = bayesnet::Network();
// net.fit(raw.Xv, raw.yv, raw.weightsv, raw.featuresv, raw.classNamev, raw.statesv);
// vector<vector<int>> test = { {1, 2, 0, 1}, {0, 1, 2, 0}, {1, 1, 1, 1}, {0, 0, 0, 0}, {2, 2, 2, 2} };
// vector<int> y_test = { 0, 1, 1, 0, 2 };
// std::vector<std::vector<int>> test = { {1, 2, 0, 1}, {0, 1, 2, 0}, {1, 1, 1, 1}, {0, 0, 0, 0}, {2, 2, 2, 2} };
// std::vector<int> y_test = { 0, 1, 1, 0, 2 };
// auto y_pred = net.predict(test);
// REQUIRE(y_pred == y_test);
// }
@ -183,7 +183,7 @@ TEST_CASE("Test Bayesian Network", "[BayesNet]")
// {
// auto net = bayesnet::Network();
// net.fit(raw.Xv, raw.yv, raw.weightsv, raw.featuresv, raw.classNamev, raw.statesv);
// vector<vector<int>> test = { {1, 2, 0, 1}, {0, 1, 2, 0}, {1, 1, 1, 1}, {0, 0, 0, 0}, {2, 2, 2, 2} };
// std::vector<std::vector<int>> test = { {1, 2, 0, 1}, {0, 1, 2, 0}, {1, 1, 1, 1}, {0, 0, 0, 0}, {2, 2, 2, 2} };
// auto y_test = { 0, 1, 1, 0, 2 };
// auto y_pred = net.predict(test);
// REQUIRE(y_pred == y_test);

12
tests/TestFolding.cc
View File

@ -7,7 +7,7 @@
TEST_CASE("KFold Test", "[Platform][KFold]")
{
// Initialize a KFold object with k=5 and a seed of 19.
string file_name = GENERATE("glass", "iris", "ecoli", "diabetes");
std::string file_name = GENERATE("glass", "iris", "ecoli", "diabetes");
auto raw = RawDatasets(file_name, true);
int nFolds = 5;
platform::KFold kfold(nFolds, raw.nSamples, 19);
@ -29,7 +29,7 @@ TEST_CASE("KFold Test", "[Platform][KFold]")
}
}
map<int, int> counts(vector<int> y, vector<int> indices)
map<int, int> counts(std::vector<int> y, std::vector<int> indices)
{
map<int, int> result;
for (auto i = 0; i < indices.size(); ++i) {
@ -40,8 +40,8 @@ map<int, int> counts(vector<int> y, vector<int> indices)
TEST_CASE("StratifiedKFold Test", "[Platform][StratifiedKFold]")
{
// Initialize a StratifiedKFold object with k=3, using the y vector, and a seed of 17.
string file_name = GENERATE("glass", "iris", "ecoli", "diabetes");
// Initialize a StratifiedKFold object with k=3, using the y std::vector, and a seed of 17.
std::string file_name = GENERATE("glass", "iris", "ecoli", "diabetes");
int nFolds = GENERATE(3, 5, 10);
auto raw = RawDatasets(file_name, true);
platform::StratifiedKFold stratified_kfoldt(nFolds, raw.yt, 17);
@ -55,10 +55,10 @@ TEST_CASE("StratifiedKFold Test", "[Platform][StratifiedKFold]")
SECTION("Stratified Fold Test")
{
// Test each fold's size and contents.
auto counts = map<int, vector<int>>();
auto counts = map<int, std::vector<int>>();
// Initialize the counts per Fold
for (int i = 0; i < nFolds; ++i) {
counts[i] = vector<int>(raw.classNumStates, 0);
counts[i] = std::vector<int>(raw.classNumStates, 0);
}
// Check fold and compute counts of each fold
for (int fold = 0; fold < nFolds; ++fold) {

50
tests/TestUtils.cc
View File

@ -1,19 +1,17 @@
#include "TestUtils.h"
using namespace std;
using namespace torch;
class Paths {
public:
static string datasets()
static std::string datasets()
{
return "../../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++) {
fimdlp.fit(X[i], y);
@ -24,9 +22,9 @@ pair<vector<mdlp::labels_t>, map<string, int>> discretize(vector<mdlp::samples_t
return { Xd, maxes };
}
vector<mdlp::labels_t> discretizeDataset(vector<mdlp::samples_t>& X, mdlp::labels_t& y)
std::vector<mdlp::labels_t> discretizeDataset(std::vector<mdlp::samples_t>& X, mdlp::labels_t& y)
{
vector<mdlp::labels_t> Xd;
std::vector<mdlp::labels_t> Xd;
auto fimdlp = mdlp::CPPFImdlp();
for (int i = 0; i < X.size(); i++) {
fimdlp.fit(X[i], y);
@ -36,7 +34,7 @@ vector<mdlp::labels_t> discretizeDataset(vector<mdlp::samples_t>& X, mdlp::label
return Xd;
}
bool file_exists(const string& name)
bool file_exists(const std::std::string& name)
{
if (FILE* file = fopen(name.c_str(), "r")) {
fclose(file);
@ -46,30 +44,30 @@ bool file_exists(const string& name)
}
}
tuple<Tensor, Tensor, vector<string>, string, map<string, vector<int>>> loadDataset(const string& name, bool class_last, bool discretize_dataset)
tuple<torch::Tensor, torch::Tensor, std::vector<std::string>, std::string, map<std::string, std::vector<int>>> loadDataset(const std::std::string& name, bool class_last, bool discretize_dataset)
{
auto handler = ArffFiles();
handler.load(Paths::datasets() + static_cast<string>(name) + ".arff", class_last);
handler.load(Paths::datasets() + static_cast<std::string>(name) + ".arff", 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 auto& pair) { return pair.first; });
Tensor Xd;
auto states = map<string, vector<int>>();
torch::Tensor Xd;
auto states = map<std::string, std::vector<int>>();
if (discretize_dataset) {
auto Xr = discretizeDataset(X, y);
Xd = torch::zeros({ static_cast<int>(Xr.size()), static_cast<int>(Xr[0].size()) }, torch::kInt32);
for (int i = 0; i < features.size(); ++i) {
states[features[i]] = vector<int>(*max_element(Xr[i].begin(), Xr[i].end()) + 1);
states[features[i]] = std::vector<int>(*max_element(Xr[i].begin(), Xr[i].end()) + 1);
auto item = states.at(features[i]);
iota(begin(item), end(item), 0);
Xd.index_put_({ i, "..." }, torch::tensor(Xr[i], torch::kInt32));
}
states[className] = vector<int>(*max_element(y.begin(), y.end()) + 1);
states[className] = std::vector<int>(*max_element(y.begin(), y.end()) + 1);
iota(begin(states.at(className)), end(states.at(className)), 0);
} else {
Xd = torch::zeros({ static_cast<int>(X.size()), static_cast<int>(X[0].size()) }, torch::kFloat32);
@ -80,27 +78,27 @@ tuple<Tensor, Tensor, vector<string>, string, map<string, vector<int>>> loadData
return { Xd, torch::tensor(y, torch::kInt32), features, className, states };
}
tuple<vector<vector<int>>, vector<int>, vector<string>, string, map<string, vector<int>>> loadFile(const string& name)
tuple<std::vector<std::vector<int>>, std::vector<int>, std::vector<std::string>, std::string, map<std::string, std::vector<int>>> loadFile(const std::std::string& name)
{
auto handler = ArffFiles();
handler.load(Paths::datasets() + static_cast<string>(name) + ".arff");
handler.load(Paths::datasets() + static_cast<std::string>(name) + ".arff");
// 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 auto& pair) { return pair.first; });
// Discretize Dataset
vector<mdlp::labels_t> Xd;
map<string, int> maxes;
std::vector<mdlp::labels_t> Xd;
map<std::string, int> maxes;
tie(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]);
return { Xd, y, features, className, states };
}

29
tests/TestUtils.h
View File

@ -4,20 +4,19 @@
#include <string>
#include <vector>
#include <map>
#include <tuple>
#include <std::tuple>
#include "ArffFiles.h"
#include "CPPFImdlp.h"
using namespace std;
bool file_exists(const std::string& name);
pair<vector<mdlp::labels_t>, map<string, int>> discretize(vector<mdlp::samples_t>& X, mdlp::labels_t& y, vector<string> features);
vector<mdlp::labels_t> discretizeDataset(vector<mdlp::samples_t>& X, mdlp::labels_t& y);
tuple<vector<vector<int>>, vector<int>, vector<string>, string, map<string, vector<int>>> loadFile(const string& name);
tuple<torch::Tensor, torch::Tensor, vector<string>, string, map<string, vector<int>>> loadDataset(const string& name, bool class_last, bool discretize_dataset);
bool file_exists(const std::std::string& name);
std::pair<vector<mdlp::labels_t>, map<std::string, int>> discretize(std::vector<mdlp::samples_t>& X, mdlp::labels_t& y, std::vector<string> features);
std::vector<mdlp::labels_t> discretizeDataset(std::vector<mdlp::samples_t>& X, mdlp::labels_t& y);
std::tuple<vector<vector<int>>, std::vector<int>, std::vector<string>, std::string, map<std::string, std::vector<int>>> loadFile(const std::string& name);
std::tuple<torch::Tensor, torch::Tensor, std::vector<string>, std::string, map<std::string, std::vector<int>>> loadDataset(const std::string& name, bool class_last, bool discretize_dataset);
class RawDatasets {
public:
RawDatasets(const string& file_name, bool discretize)
RawDatasets(const std::string& file_name, bool discretize)
{
// Xt can be either discretized or not
tie(Xt, yt, featurest, classNamet, statest) = loadDataset(file_name, true, discretize);
@ -27,16 +26,16 @@ public:
dataset = torch::cat({ Xt, yresized }, 0);
nSamples = dataset.size(1);
weights = torch::full({ nSamples }, 1.0 / nSamples, torch::kDouble);
weightsv = vector<double>(nSamples, 1.0 / nSamples);
weightsv = std::vector<double>(nSamples, 1.0 / nSamples);
classNumStates = discretize ? statest.at(classNamet).size() : 0;
}
torch::Tensor Xt, yt, dataset, weights;
vector<vector<int>> Xv;
vector<double> weightsv;
vector<int> yv;
vector<string> featurest, featuresv;
map<string, vector<int>> statest, statesv;
string classNamet, classNamev;
std::vector<vector<int>> Xv;
std::vector<double> weightsv;
std::vector<int> yv;
std::vector<string> featurest, featuresv;
map<std::string, std::vector<int>> statest, statesv;
std::string classNamet, classNamev;
int nSamples, classNumStates;
double epsilon = 1e-5;
};