rmontanana/mdlp
1
1
Fork 0
mirror of https://github.com/rmontanana/mdlp.git synced 2025-08-16 07:55:58 +00:00
Code Issues Packages Projects Releases Wiki Activity

Remove unneeded loop in sortIndices

Browse Source 
Add some static casts
This commit is contained in:
Ricardo Montañana Gómez
2023-03-19 19:13:37 +01:00
parent f0845c5bd1
commit cfade7a556
9 changed files with 210 additions and 146 deletions
Download Patch File Download Diff File Expand all files Collapse all files

124
tests/ArffFiles.cpp
View File

@@ -6,82 +6,88 @@
using namespace std;
ArffFiles::ArffFiles() = default;
vector<string> ArffFiles::getLines()
{
vector<string> ArffFiles::getLines() const {
return lines;
}
unsigned long int ArffFiles::getSize()
{
unsigned long int ArffFiles::getSize() const {
return lines.size();
}
vector<pair<string, string>> ArffFiles::getAttributes()
{
vector<pair<string, string>> ArffFiles::getAttributes() const {
return attributes;
}
string ArffFiles::getClassName()
{
string ArffFiles::getClassName() const {
return className;
}
string ArffFiles::getClassType()
{
string ArffFiles::getClassType() const {
return classType;
}
vector<vector<float>>& ArffFiles::getX()
{
vector<vector<float>> &ArffFiles::getX() {
return X;
}
vector<int>& ArffFiles::getY()
{
vector<int> &ArffFiles::getY() {
return y;
}
void ArffFiles::load(const string fileName, bool classLast)
{
void ArffFiles::load(const string &fileName, bool classLast) {
ifstream file(fileName);
if (file.is_open()) {
string line, keyword, attribute, type, 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);
ss >> keyword >> attribute;
type = "";
while(ss >> type_w)
type += type_w + " ";
attributes.emplace_back(attribute, type );
continue;
}
if (line[0] == '@') {
continue;
}
lines.push_back(line);
}
file.close();
if (attributes.empty())
throw invalid_argument("No attributes found");
if (classLast) {
className = get<0>(attributes.back());
classType = get<1>(attributes.back());
attributes.pop_back();
} else {
className = get<0>(attributes.front());
classType = get<1>(attributes.front());
attributes.erase(attributes.begin());
}
generateDataset(classLast);
} else
if (!file.is_open()) {
throw invalid_argument("Unable to open file");
}
string line;
string keyword;
string attribute;
string type;
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);
ss >> keyword >> attribute;
type = "";
while (ss >> type_w)
type += type_w + " ";
attributes.emplace_back(attribute, type);
continue;
}
if (line[0] == '@') {
continue;
}
lines.push_back(line);
}
file.close();
if (attributes.empty())
throw invalid_argument("No attributes found");
if (classLast) {
className = get<0>(attributes.back());
classType = get<1>(attributes.back());
attributes.pop_back();
} else {
className = get<0>(attributes.front());
classType = get<1>(attributes.front());
attributes.erase(attributes.begin());
}
generateDataset(classLast);
}
void ArffFiles::generateDataset(bool classLast)
{
void ArffFiles::generateDataset(bool classLast) {
X = vector<vector<float>>(attributes.size(), vector<float>(lines.size()));
vector<string> yy = vector<string>(lines.size(), "");
auto yy = vector<string>(lines.size(), "");
int labelIndex = classLast ? static_cast<int>(attributes.size()) : 0;
for (size_t i = 0; i < lines.size(); i++) {
stringstream ss(lines[i]);
string value;
int pos = 0, xIndex = 0;
int pos = 0;
int xIndex = 0;
while (getline(ss, value, ',')) {
if (pos++ == labelIndex) {
yy[i] = value;
@@ -92,20 +98,20 @@ void ArffFiles::generateDataset(bool classLast)
}
y = factorize(yy);
}
string ArffFiles::trim(const string& source)
{
string ArffFiles::trim(const string &source) {
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)
{
vector<int> ArffFiles::factorize(const vector<string> &labels_t) {
vector<int> yy;
yy.reserve(labels_t.size());
map<string, int> labelMap;
int i = 0;
for (const string &label : labels_t) {
for (const string &label: labels_t) {
if (labelMap.find(label) == labelMap.end()) {
labelMap[label] = i++;
}

39
tests/ArffFiles.h
View File

@@ -1,27 +1,44 @@
#ifndef ARFFFILES_H
#define ARFFFILES_H
#include <string>
#include <vector>
using namespace std;
class ArffFiles {
private:
vector<string> lines;
vector<pair<string, string>> attributes;
string className, classType;
string className;
string classType;
vector<vector<float>> X;
vector<int> y;
void generateDataset(bool);
public:
ArffFiles();
void load(string, bool = true);
vector<string> getLines();
unsigned long int getSize();
string getClassName();
string getClassType();
static string trim(const string&);
vector<vector<float>>& getX();
vector<int>& getY();
vector<pair<string, string>> getAttributes();
static vector<int> factorize(const vector<string>& labels_t);
void load(const string &, bool = true);
vector<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);
};
#endif

5
tests/CMakeLists.txt
View File

@@ -4,9 +4,10 @@ include(FetchContent)
include_directories(${GTEST_INCLUDE_DIRS})
FetchContent_Declare(
googletest
URL https://github.com/google/googletest/archive/03597a01ee50ed33e9dfd640b249b4be3799d395.zip
googletest
URL https://github.com/google/googletest/archive/03597a01ee50ed33e9dfd640b249b4be3799d395.zip
)
# For Windows: Prevent overriding the parent project's compiler/linker settings
set(gtest_force_shared_crt ON CACHE BOOL "" FORCE)