109 lines
2.8 KiB
Java
109 lines
2.8 KiB
Java
package de.wwwu.awolf.presenter.evaluation.measures;
|
|
|
|
import de.wwwu.awolf.model.Line;
|
|
import de.wwwu.awolf.presenter.util.FastElementSelector;
|
|
import java.util.ArrayList;
|
|
import java.util.Set;
|
|
|
|
/**
|
|
* Implementierung verschiedener Algorithmen zur Berechnung von Ausgleichsgeraden.
|
|
*
|
|
* @Author: Armin Wolf
|
|
* @Email: a_wolf28@uni-muenster.de
|
|
* @Date: 07.09.2017.
|
|
*/
|
|
public class ScaledErrorBasedMeasure {
|
|
|
|
|
|
private ArrayList<Double> sampsonError;
|
|
private ArrayList<Double> naivSampsonError;
|
|
private ArrayList<Double> scaledError;
|
|
|
|
/**
|
|
* Konstruktor
|
|
*
|
|
* @param lines Liste der Geraden
|
|
* @param m Steigung
|
|
* @param b y-Achsenabschnitt
|
|
* @param naivSlope naive Steigung
|
|
* @param naivInterception naiver y-Achsenabschnitt
|
|
*/
|
|
public ScaledErrorBasedMeasure(final Set<Line> lines, Double m, Double b, Double naivSlope,
|
|
Double naivInterception) {
|
|
|
|
this.sampsonError = new ArrayList<>();
|
|
this.naivSampsonError = new ArrayList<>();
|
|
this.scaledError = new ArrayList<>();
|
|
|
|
//Sampson-Fehler der naiven Mehtode
|
|
for (Line line : lines) {
|
|
Double e =
|
|
Math.pow(naivSlope * line.getM() - line.getB() + naivInterception, 2) / (
|
|
Math.pow(naivSlope, 2) + 1);
|
|
naivSampsonError.add(e);
|
|
}
|
|
|
|
//Sampson-Fehler der fortgeschrittenen Methode
|
|
for (Line line : lines) {
|
|
Double e = Math.pow(m * line.getM() - line.getB() + b, 2) / (Math.pow(m, 2) + 1);
|
|
sampsonError.add(e);
|
|
}
|
|
|
|
//skalierungs-Fehler
|
|
for (int i = 0; i < sampsonError.size(); i++) {
|
|
scaledError.add(sampsonError.get(i) / naivSampsonError.get(i));
|
|
}
|
|
}
|
|
|
|
/* Skalierungs Abhängige Approximationsgüten */
|
|
//unterschiedliche Alg.- auf einem Datensatz
|
|
|
|
/**
|
|
* Mean Square Error
|
|
*
|
|
* @return Ergebnis
|
|
*/
|
|
public Double mse() {
|
|
double error = 0;
|
|
for (Double d : scaledError) {
|
|
error += Math.pow(d, 2);
|
|
}
|
|
error /= scaledError.size();
|
|
return error;
|
|
}
|
|
|
|
/**
|
|
* Root Mean Square Error
|
|
*
|
|
* @return Ergebnis
|
|
*/
|
|
public Double rmse() {
|
|
return Math.sqrt(mse());
|
|
}
|
|
|
|
/**
|
|
* Mean Absolute Error:
|
|
*
|
|
* @return Ergebnis
|
|
*/
|
|
public Double mae() {
|
|
double error = 0;
|
|
for (Double d : scaledError) {
|
|
error += Math.abs(d);
|
|
}
|
|
error /= scaledError.size();
|
|
return error;
|
|
}
|
|
|
|
/**
|
|
* Median Absolute Error
|
|
*
|
|
* @return Ergebnis
|
|
*/
|
|
public Double mdae() {
|
|
return FastElementSelector
|
|
.randomizedSelect(scaledError, scaledError.size() * 0.5);
|
|
}
|
|
|
|
}
|