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

Convert ArffFile library to header only library

Browse Source
This commit is contained in:
Ricardo Montañana Gómez 2024-05-21 10:11:33 +02:00
parent 2584e8294d
commit 22b742f068
Signed by: rmontanana
GPG Key ID: 46064262FD9A7ADE
13 changed files with 330 additions and 424 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
CMakeLists.txt
View File

@ -25,8 +25,11 @@ 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")
set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} -fprofile-arcs -ftest-coverage -fno-elide-constructors -fno-default-inline")
set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} -fprofile-arcs -ftest-coverage -fno-elide-constructors")
set(CMAKE_CXX_FLAGS_RELEASE "${CMAKE_CXX_FLAGS_RELEASE} -O3")
if (NOT ${CMAKE_SYSTEM_NAME} MATCHES "Darwin")
set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} -fno-default-inline")
endif()
# Options
# -------
@ -63,7 +66,6 @@ endif (ENABLE_CLANG_TIDY)
# include(FetchContent)
add_git_submodule("lib/json")
add_git_submodule("lib/mdlp")
add_subdirectory("lib/Files")
# Subdirectories
# --------------

2
bayesnet/classifiers/Proposal.cc
View File

@ -4,7 +4,7 @@
// SPDX-License-Identifier: MIT
// ***************************************************************
#include <ArffFiles.h>
#include <ArffFiles.hpp>
#include "Proposal.h"
namespace bayesnet {

171
lib/Files/ArffFiles.cc
View File

@ -1,171 +0,0 @@
#include "ArffFiles.h"
#include <fstream>
#include <sstream>
#include <map>
#include <iostream>
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(const 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;
// Read file
while (getline(file, line)) {
if (line.empty() || line[0] == '%' || line == "\r" || line == " ") {
// Skip comments and empty lines
continue;
}
if (line.find("@attribute") != std::string::npos || line.find("@ATTRIBUTE") != std::string::npos) {
// Read attributes
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;
}
// Read data
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
size_t numLine = 0;
for (numLine = 0; numLine < lines.size(); numLine++) {
std::stringstream ss(lines[numLine]);
std::string value;
int pos = 0;
int xIndex = 0;
while (getline(ss, value, ',')) {
if (pos++ == labelIndex) {
yy[numLine] = value;
} else {
if (value == "?") {
X[xIndex++][numLine] = -1;
removeLines.push_back(numLine);
} else
X[xIndex++][numLine] = 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;
}

33
lib/Files/ArffFiles.h
View File

@ -1,33 +0,0 @@
#ifndef ARFFFILES_H
#define ARFFFILES_H
#include <string>
#include <vector>
class ArffFiles {
public:
ArffFiles() = default;
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);
protected:
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;
int maxLines = 0;
void generateDataset(int);
void loadCommon(const std::string&);
};
#endif

161
lib/Files/ArffFiles.hpp Normal file
View File

@ -0,0 +1,161 @@
#ifndef ARFFFILES_HPP
#define ARFFFILES_HPP
#include <string>
#include <vector>
#include <fstream>
#include <sstream>
#include <map>
#include <cctype> // std::isdigit
#include <algorithm> // std::all_of
#include <iostream>
class ArffFiles {
public:
ArffFiles() = default;
void load(const std::string& fileName, bool classLast = true)
{
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 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);
};
std::vector<std::string> getLines() const { return lines; };
unsigned long int getSize() const { return lines.size(); };
std::string getClassName() const { return className; };
std::string getClassType() const { return classType; };
std::vector<std::string> getLabels() const { return labels; }
static std::string 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<std::vector<float>>& getX() { return X; };
std::vector<int>& getY() { return y; }
std::vector<std::pair<std::string, std::string>> getAttributes() const { return attributes; };
std::vector<int> factorize(const std::vector<std::string>& labels_t)
{
std::vector<int> yy;
labels.clear();
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++;
bool allDigits = std::all_of(label.begin(), label.end(), isdigit);
if (allDigits)
labels.push_back("Class " + label);
else
labels.push_back(label);
}
yy.push_back(labelMap[label]);
}
return yy;
};
private:
void 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);
};
void 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");
};
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;
std::vector<std::string> labels;
};
#endif

1
lib/Files/CMakeLists.txt
View File

@ -1 +0,0 @@
add_library(ArffFiles ArffFiles.cc)

1
lib/catch2 Submodule

@ -0,0 +1 @@
Subproject commit 029fe3b4609dd84cd939b73357f37bbb75bcf82f

3
sample/CMakeLists.txt
View File

@ -14,7 +14,6 @@ include_directories(
/usr/local/include
)
add_subdirectory(lib/Files)
add_subdirectory(lib/mdlp)
add_executable(bayesnet_sample sample.cc)
target_link_libraries(bayesnet_sample ArffFiles mdlp "${TORCH_LIBRARIES}" "${BayesNet}")
target_link_libraries(bayesnet_sample mdlp "${TORCH_LIBRARIES}" "${BayesNet}")

174
sample/lib/Files/ArffFiles.cc
View File

@ -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;
}

38
sample/lib/Files/ArffFiles.h
View File

@ -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 {
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);
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);
};
#endif

161
sample/lib/Files/ArffFiles.hpp Normal file
View File

@ -0,0 +1,161 @@
#ifndef ARFFFILES_HPP
#define ARFFFILES_HPP
#include <string>
#include <vector>
#include <fstream>
#include <sstream>
#include <map>
#include <cctype> // std::isdigit
#include <algorithm> // std::all_of
#include <iostream>
class ArffFiles {
public:
ArffFiles() = default;
void load(const std::string& fileName, bool classLast = true)
{
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 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);
};
std::vector<std::string> getLines() const { return lines; };
unsigned long int getSize() const { return lines.size(); };
std::string getClassName() const { return className; };
std::string getClassType() const { return classType; };
std::vector<std::string> getLabels() const { return labels; }
static std::string 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<std::vector<float>>& getX() { return X; };
std::vector<int>& getY() { return y; }
std::vector<std::pair<std::string, std::string>> getAttributes() const { return attributes; };
std::vector<int> factorize(const std::vector<std::string>& labels_t)
{
std::vector<int> yy;
labels.clear();
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++;
bool allDigits = std::all_of(label.begin(), label.end(), isdigit);
if (allDigits)
labels.push_back("Class " + label);
else
labels.push_back(label);
}
yy.push_back(labelMap[label]);
}
return yy;
};
private:
void 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);
};
void 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");
};
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;
std::vector<std::string> labels;
};
#endif

1
sample/lib/Files/CMakeLists.txt
View File

@ -1 +0,0 @@
add_library(ArffFiles ArffFiles.cc)

2
sample/sample.cc
View File

@ -4,7 +4,7 @@
// SPDX-License-Identifier: MIT
// ***************************************************************
#include <ArffFiles.h>
#include <ArffFiles.hpp>
#include <CPPFImdlp.h>
#include <bayesnet/ensembles/BoostAODE.h>