Initial commit

sample/ArffFiles.cpp

@@ -0,0 +1,117 @@
+#include "ArffFiles.h"
+
+#include <fstream>
+#include <sstream>
+#include <map>
+#include <iostream>
+
+using namespace std;
+
+ArffFiles::ArffFiles()
+{
+}
+vector<string> ArffFiles::getLines()
+{
+    return lines;
+}
+unsigned long int ArffFiles::getSize()
+{
+    return lines.size();
+}
+vector<tuple<string, string>> ArffFiles::getAttributes()
+{
+    return attributes;
+}
+string ArffFiles::getClassName()
+{
+    return className;
+}
+string ArffFiles::getClassType()
+{
+    return classType;
+}
+vector<vector<float>>& ArffFiles::getX()
+{
+    return X;
+}
+vector<int>& ArffFiles::getY()
+{
+    return y;
+}
+void ArffFiles::load(string fileName, bool classLast)
+{
+    ifstream file(fileName);
+    string keyword, attribute, type;
+    if (file.is_open()) {
+        string line;
+        while (getline(file, line)) {
+            if (line[0] == '%' || line.empty() || line == "\r" || line == " ") {
+                continue;
+            }
+            if (line.find("@attribute") != string::npos || line.find("@ATTRIBUTE") != string::npos) {
+                stringstream ss(line);
+                ss >> keyword >> attribute >> type;
+                attributes.push_back(make_tuple(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
+        throw invalid_argument("Unable to open file");
+}
+void ArffFiles::generateDataset(bool classLast)
+{
+    X = vector<vector<float>>(attributes.size(), vector<float>(lines.size()));
+    vector<string> yy = vector<string>(lines.size(), "");
+    int labelIndex = classLast ? attributes.size() : 0;
+    for (int i = 0; i < lines.size(); i++) {
+        stringstream ss(lines[i]);
+        string value;
+        int pos = 0, xIndex = 0;
+        while (getline(ss, value, ',')) {
+            if (pos++ == labelIndex) {
+                yy[i] = value;
+            } else {
+                X[xIndex++][i] = stof(value);
+            }
+        }
+    }
+    y = factorize(yy);
+}
+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> yy;
+    yy.reserve(labels_t.size());
+    map<string, int> labelMap;
+    int i = 0;
+    for (string label : labels_t) {
+        if (labelMap.find(label) == labelMap.end()) {
+            labelMap[label] = i++;
+        }
+        yy.push_back(labelMap[label]);
+    }
+    return yy;
+}

sample/ArffFiles.h

@@ -0,0 +1,28 @@
+#ifndef ARFFFILES_H
+#define ARFFFILES_H
+#include <string>
+#include <vector>
+#include <tuple>
+using namespace std;
+class ArffFiles {
+private:
+    vector<string> lines;
+    vector<tuple<string, string>> attributes;
+    string className, 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();
+    string trim(const string&);
+    vector<vector<float>>& getX();
+    vector<int>& getY();
+    vector<tuple<string, string>> getAttributes();
+    vector<int> factorize(const vector<string>& labels_t);
+};
+#endif

sample/CMakeLists.txt

@@ -0,0 +1,6 @@
+cmake_minimum_required(VERSION 3.24)
+project(main)
+
+set(CMAKE_CXX_STANDARD 17)
+
+add_executable(sample sample.cpp ArffFiles.cpp ../Metrics.cpp ../CPPFImdlp.cpp)

sample/sample.cpp

@@ -0,0 +1,54 @@
+#include "ArffFiles.h"
+#include <iostream>
+#include <vector>
+#include <iomanip>
+#include "../CPPFImdlp.h"
+
+using namespace std;
+
+int main(int argc, char** argv)
+{
+    ArffFiles file;
+    vector<string> lines;
+    string path = "../../tests/datasets/";
+    map<string, bool > datasets = {
+        {"mfeat-factors", true},
+        {"iris", true},
+        {"letter", true},
+        {"kdd_JapaneseVowels", false}
+    };
+    if (argc != 2 || datasets.find(argv[1]) == datasets.end()) {
+        cout << "Usage: " << argv[0] << " {mfeat-factors, iris, letter, kdd_JapaneseVowels}" << endl;
+        return 1;
+    }
+
+    file.load(path + argv[1] + ".arff", datasets[argv[1]]);
+    auto attributes = file.getAttributes();
+    int items = file.getSize();
+    cout << "Number of lines: " << items << endl;
+    cout << "Attributes: " << endl;
+    for (auto attribute : attributes) {
+        cout << "Name: " << get<0>(attribute) << " Type: " << get<1>(attribute) << endl;
+    }
+    cout << "Class name: " << file.getClassName() << endl;
+    cout << "Class type: " << file.getClassType() << endl;
+    cout << "Data: " << endl;
+    vector<vector<float>>& X = file.getX();
+    vector<int>& y = file.getY();
+    for (int i = 0; i < 50; i++) {
+        for (auto feature : X) {
+            cout << fixed << setprecision(1) << feature[i] << " ";
+        }
+        cout << y[i] << endl;
+    }
+    mdlp::CPPFImdlp test = mdlp::CPPFImdlp(false);
+    for (auto i = 0; i < attributes.size(); i++) {
+        cout << "Cut points for " << get<0>(attributes[i]) << endl;
+        cout << "--------------------------" << setprecision(3) << endl;
+        test.fit(X[i], y);
+        for (auto item : test.getCutPoints()) {
+            cout << item << endl;
+        }
+    }
+    return 0;
+}