Removed submodules
This commit is contained in:
6
.gitmodules
vendored
6
.gitmodules
vendored
@@ -1,6 +0,0 @@
|
||||
[submodule "tests/lib/Catch2"]
|
||||
path = tests/lib/Catch2
|
||||
url = https://github.com/catchorg/Catch2.git
|
||||
[submodule "tests/lib/mdlp"]
|
||||
path = tests/lib/mdlp
|
||||
url = https://github.com/rmontanana/mdlp
|
33
conanfile.py
Normal file
33
conanfile.py
Normal file
@@ -0,0 +1,33 @@
|
||||
import re
|
||||
from conan import ConanFile
|
||||
from conan.tools.files import copy
|
||||
|
||||
|
||||
class FoldingConan(ConanFile):
|
||||
name = "folding"
|
||||
version = "X.X.X"
|
||||
description = "K-Fold and stratified K-Fold header-only library"
|
||||
url = "https://github.com/rmontanana/folding"
|
||||
license = "MIT"
|
||||
homepage = "https://github.com/rmontanana/ArffFiles"
|
||||
topics = ("kfold", "stratified folding")
|
||||
no_copy_source = True
|
||||
exports_sources = "folding.hpp"
|
||||
package_type = "header-library"
|
||||
|
||||
def init(self):
|
||||
# Read the CMakeLists.txt file to get the version
|
||||
with open("folding.hpp", "r") as f:
|
||||
content = f.read()
|
||||
match = re.search(
|
||||
r'const std::string FOLDING_VERSION = "([^"]+)";', content
|
||||
)
|
||||
if match:
|
||||
self.version = match.group(1)
|
||||
|
||||
def package(self):
|
||||
copy(self, "*.hpp", self.source_folder, self.package_folder)
|
||||
|
||||
def package_info(self):
|
||||
self.cpp_info.bindirs = []
|
||||
self.cpp_info.libdirs = []
|
Submodule tests/lib/Catch2 deleted from 8039e3ea1e
@@ -1,174 +0,0 @@
|
||||
// ***************************************************************
|
||||
// SPDX-FileCopyrightText: Copyright 2024 Ricardo Montañana Gómez
|
||||
// SPDX-FileType: SOURCE
|
||||
// SPDX-License-Identifier: MIT
|
||||
// ***************************************************************
|
||||
|
||||
#include "ArffFiles.h"
|
||||
#include <fstream>
|
||||
#include <sstream>
|
||||
#include <map>
|
||||
#include <iostream>
|
||||
|
||||
ArffFiles::ArffFiles() = default;
|
||||
|
||||
std::vector<std::string> ArffFiles::getLines() const
|
||||
{
|
||||
return lines;
|
||||
}
|
||||
|
||||
unsigned long int ArffFiles::getSize() const
|
||||
{
|
||||
return lines.size();
|
||||
}
|
||||
|
||||
std::vector<std::pair<std::string, std::string>> ArffFiles::getAttributes() const
|
||||
{
|
||||
return attributes;
|
||||
}
|
||||
|
||||
std::string ArffFiles::getClassName() const
|
||||
{
|
||||
return className;
|
||||
}
|
||||
|
||||
std::string ArffFiles::getClassType() const
|
||||
{
|
||||
return classType;
|
||||
}
|
||||
|
||||
std::vector<std::vector<float>>& ArffFiles::getX()
|
||||
{
|
||||
return X;
|
||||
}
|
||||
|
||||
std::vector<int>& ArffFiles::getY()
|
||||
{
|
||||
return y;
|
||||
}
|
||||
|
||||
void ArffFiles::loadCommon(std::string fileName)
|
||||
{
|
||||
std::ifstream file(fileName);
|
||||
if (!file.is_open()) {
|
||||
throw std::invalid_argument("Unable to open file");
|
||||
}
|
||||
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") != std::string::npos || line.find("@ATTRIBUTE") != std::string::npos) {
|
||||
std::stringstream ss(line);
|
||||
ss >> keyword >> attribute;
|
||||
type = "";
|
||||
while (ss >> type_w)
|
||||
type += type_w + " ";
|
||||
attributes.emplace_back(trim(attribute), trim(type));
|
||||
continue;
|
||||
}
|
||||
if (line[0] == '@') {
|
||||
continue;
|
||||
}
|
||||
lines.push_back(line);
|
||||
}
|
||||
file.close();
|
||||
if (attributes.empty())
|
||||
throw std::invalid_argument("No attributes found");
|
||||
}
|
||||
|
||||
void ArffFiles::load(const std::string& fileName, bool classLast)
|
||||
{
|
||||
int labelIndex;
|
||||
loadCommon(fileName);
|
||||
if (classLast) {
|
||||
className = std::get<0>(attributes.back());
|
||||
classType = std::get<1>(attributes.back());
|
||||
attributes.pop_back();
|
||||
labelIndex = static_cast<int>(attributes.size());
|
||||
} else {
|
||||
className = std::get<0>(attributes.front());
|
||||
classType = std::get<1>(attributes.front());
|
||||
attributes.erase(attributes.begin());
|
||||
labelIndex = 0;
|
||||
}
|
||||
generateDataset(labelIndex);
|
||||
}
|
||||
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 = std::get<0>(attributes[i]);
|
||||
classType = std::get<1>(attributes[i]);
|
||||
attributes.erase(attributes.begin() + i);
|
||||
labelIndex = i;
|
||||
found = true;
|
||||
break;
|
||||
}
|
||||
}
|
||||
if (!found) {
|
||||
throw std::invalid_argument("Class name not found");
|
||||
}
|
||||
generateDataset(labelIndex);
|
||||
}
|
||||
|
||||
void ArffFiles::generateDataset(int labelIndex)
|
||||
{
|
||||
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++) {
|
||||
std::stringstream ss(lines[i]);
|
||||
std::string value;
|
||||
int pos = 0;
|
||||
int xIndex = 0;
|
||||
while (getline(ss, value, ',')) {
|
||||
if (pos++ == labelIndex) {
|
||||
yy[i] = value;
|
||||
} else {
|
||||
if (value == "?") {
|
||||
X[xIndex++][i] = -1;
|
||||
removeLines.push_back(i);
|
||||
} else
|
||||
X[xIndex++][i] = stof(value);
|
||||
}
|
||||
}
|
||||
}
|
||||
for (auto i : removeLines) {
|
||||
yy.erase(yy.begin() + i);
|
||||
for (auto& x : X) {
|
||||
x.erase(x.begin() + i);
|
||||
}
|
||||
}
|
||||
y = factorize(yy);
|
||||
}
|
||||
|
||||
std::string ArffFiles::trim(const std::string& 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;
|
||||
}
|
||||
|
||||
std::vector<int> ArffFiles::factorize(const std::vector<std::string>& labels_t)
|
||||
{
|
||||
std::vector<int> yy;
|
||||
yy.reserve(labels_t.size());
|
||||
std::map<std::string, int> labelMap;
|
||||
int i = 0;
|
||||
for (const std::string& label : labels_t) {
|
||||
if (labelMap.find(label) == labelMap.end()) {
|
||||
labelMap[label] = i++;
|
||||
}
|
||||
yy.push_back(labelMap[label]);
|
||||
}
|
||||
return yy;
|
||||
}
|
@@ -1,38 +0,0 @@
|
||||
// ***************************************************************
|
||||
// SPDX-FileCopyrightText: Copyright 2024 Ricardo Montañana Gómez
|
||||
// SPDX-FileType: SOURCE
|
||||
// SPDX-License-Identifier: MIT
|
||||
// ***************************************************************
|
||||
|
||||
#ifndef ARFFFILES_H
|
||||
#define ARFFFILES_H
|
||||
|
||||
#include <string>
|
||||
#include <vector>
|
||||
|
||||
class ArffFiles {
|
||||
public:
|
||||
ArffFiles();
|
||||
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;
|
||||
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);
|
||||
private:
|
||||
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(std::string);
|
||||
};
|
||||
|
||||
#endif
|
@@ -1 +0,0 @@
|
||||
add_library(ArffFiles ArffFiles.cc)
|
Submodule tests/lib/mdlp deleted from 236d1b2f8b
Reference in New Issue
Block a user