#! /bin/bash

#example: ./effort data/nasa93.csv COCII precise log/seed.log name lc
#Argument Key
#	1	Filename
#	2	Effort Multiplier Method (COC81 or COCII)
#	3	Effort Multiplier Precision (precise or rounded)
#	4	Seed Filename
#	5	Name as source:part
#	6	Learner

#Variables
Filename=$1
Iterations=30
TestSets=10

#Path=${1/%.csv/}
Path=/tmp/effort

rm -r $Path
mkdir $Path

LogFile=$Path/lc.log
#SeedFile=$Path/seed.log
SeedFile=$4
TestFile=$Path/test.tmp
TrainFile=$Path/train.tmp



#gawk 'END{print NR;}' $Path/train.tmp > $Path/trainCount.tmp

ConvertedFile=$Path/converted.csv
StatsFile=$Path/stats.tmp

#Preprocess data files
gawk -f convertCSV.awk Method=$2 Style=$3 $Filename > $ConvertedFile

rm -f $LogFile
rm -f $SeedFile

#Run the algorithm many times
for ((i=1;i<=$Iterations;i++))
do

	#Randomize Data
	rm -f $TrainFile
	rm -f $TestFile
	Seed=$RANDOM
	gawk -f randomize.awk -v Seed=$Seed -v TestSets=$TestSets -v TrainFile=$TrainFile -v TestFile=$TestFile $ConvertedFile
	
	gawk -f lc.awk Pass=1 $TrainFile Pass=2 $TestFile >> $LogFile
	echo $Seed >> $SeedFile

done

gawk -f stats.awk $LogFile > $StatsFile

#gawk -f subsetDisplay.awk $StatsFile

Train=$(gawk 'END{print NR;}' $TrainFile)
Subset=$(gawk 'BEGIN{FS=",";} NR==1{print NF-2;}' $TestFile)

gawk -f subsetDisplay.awk Name=$5 Train=$Train Test=$TestSets Method=$2 Numbers=$3 Subset=$Subset Learn=$6 /tmp/effort/stats.tmp


#Delete the temporary files
#rm -r $Path