diff options
Diffstat (limited to 'extract.sh')
| -rwxr-xr-x | extract.sh | 19 |
1 files changed, 9 insertions, 10 deletions
@@ -5,8 +5,8 @@ db_file=games_anon.db query() { query="(size == $1) and (result != '1-0') and (result != '0-1') and (result != '0-0')" selct="" - # for player in rabbitboy84 fwwwwibib archvenison Simmon AaaarghBot; do - for player in; do + for player in rabbitboy84 fwwwwibib archvenison Simmon AaaarghBot; do + # for player in; do selct="$selct(player_black == '$player') or (player_white == '$player') or " done; if [ -n "$selct" ]; then @@ -30,14 +30,13 @@ process() { num_games=$2 ./pptdb "$size" "data/playtak-$size" > "data/check-$size" tail -n22 "data/check-$size" - echo -ne "\tStripping overflows and illegal games..." + echo -ne "\tStripping overflows and illegal games... " grep -Fvxf "data/check-$size" "data/playtak-$size" > "data/good-playtak-$size" - echo -e "Done\n\tChoosing $num_games from what remains ..." + echo -en "Done.\n\tChoosing $num_games from what remains... " shuf -n $num_games "data/good-playtak-$size" > "data/smalltak-$size" - echo -en "Done\n\tGenerating training data... " + echo -en "Done.\n\tGenerating training data... " ./pptdb "$size" "data/smalltak-$size" generate - echo -e "\tDone, $(wc -l data/training-$size.csv | cut -d\ -f1) samples." - echo -en "\tShuffling... " + echo -en "\tShuffling $(wc -l data/training-$size.csv | cut -d\ -f1) samples... " head -n 1 "data/training-$size.csv" > "data/shuf-$size.csv" tail -n+2 "data/training-$size.csv" | shuf >> "data/shuf-$size.csv" mv "data/shuf-$size.csv" "data/training-$size.csv" @@ -46,14 +45,14 @@ process() { rm "data/training-$size.csv.gz" fi gzip "data/training-$size.csv" - echo -e "Done!\n\tCompressed version available in data/training-$size.csv.gz" + echo "Done, available in data/training-$size.csv.gz" } make pptdb for size in 5 6; do - extract $size notation,result - process $size 20000 echo + extract $size notation,result + process $size 30000 done |