FK0
var =  2080.1
med =  165.72
apri0 =  0.14085

FK1
var =  3864.9
med =  217.92
apri1 =  0.16901

FK2
var =  3631.9
med =  244.64
apri2 =  0.19718

FK3
var =  3248.3
med =  325.60
apri3 =  0.16901

FK4
var =  5336.4
med =  281.82
apri4 =  0.15493

FK5
var =  4829.6
med =  326.93
apri5 =  0.16901

Für k = 1

confusionmatrix =

   4   3   0   0   3   0
   5   6   1   0   0   0
   2   2   5   2   3   0
   0   1   3   4   2   2
   3   1   1   4   1   1
   0   3   3   5   0   1

guete =  0.29577

Für k = 3
confusionmatrix =

   7   1   1   0   1   0
   6   5   1   0   0   0
   3   3   4   2   2   0
   1   2   3   5   0   1
   4   1   3   3   0   0
   1   2   3   3   1   2

guete =  0.32394

Für k = 5
confusionmatrix =

   7   0   1   0   2   0
   6   3   0   1   2   0
   4   4   6   0   0   0
   0   0   2   8   1   1
   2   2   2   4   1   0
   1   1   3   3   0   4

guete =  0.40845


SOURCE

Training = load("chickwts_training.csv")
Testing = load("chickwts_testing.csv")



function [tmp] = dist(huhn, Training) #Sortiert Training nach Spalte 2 in der der Abstand zu Huhn steht
	tmp = Training
	tmp(:,2) = abs(Training(:,2)-huhn(1,2)) #Distanzen berechnen und in tmp eintragen
	tmp = sortrows(tmp,2) #Sortiere nach Distanz zu Alphahuhn!
endfunction

function [class] = vote(k,Ranking)
	classes = [0,0,0,0,0,0]
	for in = 1:k
		ind = Ranking(in,3)+1 #Wegen Klasse 0 eines draufzählen
		classes(1,ind)=(classes(1,ind)+1)
	endfor
	[value,class] = max(classes)
	class = class-1 #Wieder abziehen wegen der 0 vorher.
endfunction

function [chicks] = classify(k,NeueHuehner,Training)
	chicks = resize(NeueHuehner,rows(NeueHuehner),(columns(NeueHuehner)+1)) #Neue Spalte anfügen
	for i = 1:rows(NeueHuehner)
		chicks(i,4) = vote(k,dist(NeueHuehner(i,:),Training)) #Voten, welcher Klasse das Huhn angehört
	endfor
endfunction

function [confusionmatrix,guete] = confusion(chicks)
	confusionmatrix = zeros(6,6) # Leere Matrix
	for i = 1:rows(chicks)
		#x = Klasse die Richtig wäre
		#y = Als was wurde es klassifiziert?
		x = chicks(i,3)+1 #Die gleiche Sache mit Klasse 0
		y = chicks(i,4)+1
		confusionmatrix(x,y) = confusionmatrix(x,y) +1
	endfor
	guete = sum(diag(confusionmatrix))/rows(chicks) #Auf der Diagonale stehen die Richtigen
endfunction


FUKL0=Training(Training(:,3)==0,:)
FUKL1=Training(Training(:,3)==1,:)
FUKL2=Training(Training(:,3)==2,:)
FUKL3=Training(Training(:,3)==3,:)
FUKL4=Training(Training(:,3)==4,:)
FUKL5=Training(Training(:,3)==5,:)

var(FUKL0(:,2))
mean((FUKL0(:,2)))
apri0=rows(FUKL0)/rows(Training)
var(FUKL1(:,2))
mean((FUKL1(:,2)))
apri1=rows(FUKL1)/rows(Training)
var(FUKL2(:,2))
mean((FUKL2(:,2)))
apri2=rows(FUKL2)/rows(Training)
var(FUKL3(:,2))
mean((FUKL3(:,2)))
apri3=rows(FUKL3)/rows(Training)
var(FUKL4(:,2))
mean((FUKL4(:,2)))
apri4=rows(FUKL4)/rows(Training)
var(FUKL5(:,2))
mean((FUKL5(:,2)))
apri5=rows(FUKL5)/rows(Training)
#Beispielabfrage:     confusion(classify(3,Testing, Training))