a sample_1 200
a.b sample_2 10
a sample_3 10

a sample_1 10
a sample_3 67

a sample_1 1
a.b sample_2 10
a sample_4 20

a sample_1 200 10 1 211
a.b sample_2 10 0 10 20
a sample_3 10 67 0 77
a sample_4 0 0 20 20

#! /bin/bash
clear
FILENAME=<result>
BASEPATH=<base_path>
mkdir processed/slice
cat $BASEPATH/dataset/* | cut -d' ' -f1,2 > $BASEPATH/processed/aggr
sort -u -k2 $BASEPATH/processed/aggr > $BASEPATH/processed/sorted
split -d -l 1000000 processed/sorted processed/slice/slice-
echo $(date "+START PROCESSING DATE: %d/%m/%y - TIME: %H:%M:%S")
for filename in processed/slice/*; do
  awk -v filename="$filename" -f algorithm.awk dataset/* >> processed/$FILENAME
done
echo $(date "+END PROCESSING DATE: %d/%m/%y - TIME: %H:%M:%S")
rm $BASEPATH/processed/aggr
rm $BASEPATH/processed/sorted
rm -rf $BASEPATH/processed/slice

BEGIN{
while(getline < filename){
 key=$1" "$2;
 sources[key];
 for(i=1;i<11;i++){
   keys[key"-"i] = "0";
 }
}
close(filename);
}
{
if(FNR==1){
 ARGIND++;
}
key=$1" "$2;
keys[key"-"ARGIND] = $3
}END{
for (s in sources) {
 sum = 0
 printf "%s", s
 for (j=1;j<11;j++) {
   printf "%s%s", OFS, keys[s"-"j]
   sum += keys[s"-"j]
 }
print " "sum
}
}