summaryrefslogtreecommitdiff
path: root/extract.sh
diff options
context:
space:
mode:
authortslil <tslil@posteo.de>2021-01-12 17:01:29 -0500
committertslil <tslil@posteo.de>2026-08-28 19:37:41 +0100
commit91640db661fdcc04960d1f048ac60c2c4b2c5319 (patch)
treef983f0448f510401ee407a39d2fa12531f1cc32d /extract.sh
parent3d1e8f16ac53aad322f2c681f5f3c25918c58602 (diff)
Auto-generating weights
Diffstat (limited to 'extract.sh')
-rwxr-xr-xextract.sh30
1 files changed, 16 insertions, 14 deletions
diff --git a/extract.sh b/extract.sh
index 7fc66a6..a359c61 100755
--- a/extract.sh
+++ b/extract.sh
@@ -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 "$selct" ]; then
@@ -37,25 +37,27 @@ process() {
echo -en "Done.\n\tGenerating training data... "
./pptdb "$size" "data/smalltak-$size" generate
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"
+ # 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"
echo -en "Done.\n\tCompressing data... "
- if [ -f "data/training-$size.csv.gz" ]; then
- rm "data/training-$size.csv.gz"
+ # if [ -f "data/training-$size.csv.gz" ]; then
+ # rm "data/training-$size.csv.gz"
+ # fi
+ # gzip "data/training-$size.csv"
+ # echo "Done, available in data/training-$size.csv.gz"
+ if [ -f "data/validation-$size.csv.gz" ]; then
+ rm "data/validation-$size.csv.gz"
fi
- gzip "data/training-$size.csv"
- echo "Done, available in data/training-$size.csv.gz"
- # mv "data/training-$size.csv" "data/validation-$size.csv"
- # gzip "data/validation-$size.csv"
- # echo "Done, available in data/validation-$size.csv.gz"
+ mv "data/training-$size.csv" "data/validation-$size.csv"
+ gzip "data/validation-$size.csv"
+ echo "Done, available in data/validation-$size.csv.gz"
}
-
make pptdb
for size in 5 6; do
echo
extract $size notation,result
- process $size 300000
+ process $size 50000
done