#!/usr/bin/gawk -f
#select the parameters that minimize RMSE between the predicted and actual values over all the data
#scale factors are shown in the left hand columns, followed by the effort multipliers followed by
#programs size (in Kloc) and finally, actual effort

BEGIN {
	Repeats = 1;
	IGNORECASE = 1;
	FS = OFS=",";
	E = 2.71828182846;
	ScaleFactors = 5;
	# set to 1 if this is a csv file and we should skip the header line
	Skip = 1; 
	Tests = Trains = 0;
	Seed = 1;
}

NR==1 {
	print "LC,STAR";
	srand(Seed);
}

{ sub(/\%.*/,""); }

/^[ \t]*$/ { next; }

FNR <= Skip { next; }

{
	for (I=ScaleFactors+1;I<=NF;I++)
		$I = $I ? log($I) : 0;
	Kloc = $(NF-1);
	Pm = $NF;
	for (I=1;I<=ScaleFactors;I++)
		$I = 0.01*($I)*Kloc;
	Eaf = 0; 
	for (I=1; I<=(NF-2); I++)
		Eaf += $I;
}

Pass==1 {
	Trains++;
	Sum1 += Kloc;
	Sum2 += Kloc*Kloc;
	Sum3 += Pm - Eaf;
	Sum4 += (Pm - Eaf) * Kloc;
}

Pass==2 {
	for(R=1;R<=Repeats;R++)
	{
		Tests++;
		if(Trains)
		{
			if (!A) A = (Sum2*Sum3 - Sum1*Sum4 ) / ( Trains*Sum2 - Sum1*Sum1 );
			if (!B) B = (Trains*Sum4 - Sum1*Sum3 ) / ( Trains*Sum2 - Sum1*Sum1 );
		}
		Got = A + Eaf + B * Kloc;
		Got = E ^ Got;
		Want = E ^ Pm;
		print Got,Want
	}
}

END {
}