summaryrefslogtreecommitdiff
path: root/extract.sh
diff options
context:
space:
mode:
Diffstat (limited to 'extract.sh')
-rwxr-xr-xextract.sh50
1 files changed, 26 insertions, 24 deletions
diff --git a/extract.sh b/extract.sh
index 4ded1c0..60e01f9 100755
--- a/extract.sh
+++ b/extract.sh
@@ -10,38 +10,40 @@ and (result != '1/2-1/2');"
extract() {
cd data
+ if [ ! -f "$db_file" ]; then
+ wget "https://www.playtak.com/games_anon.db"
+ fi
for size in 5 6; do
echo Extracing games of size "$size"...
sqlite3 "$db_file" "$(query $1 $size)" | shuf > "playtak-$size"
done
}
-if [ ! -f "$db_file" ]; then
- wget "https://www.playtak.com/games_anon.db"
-fi
-
-extract notation,result
+process() {
+ echo -e "Beginning to process data\n"
+ for i in 5 6; do
+ echo "Size $i..."
+ ./pptdb "$i" "data/playtak-$i" > "data/check-$i"
+ tail -n21 "data/check-$i"
+ echo Stripping overflows and illegal games...
+ grep -Fvxf "data/check-$i" "data/playtak-$i" > "data/good-playtak-$i"
+ echo -n "Generating training data... "
+ ./pptdb "$i" "data/good-playtak-$i" generate
+ echo "Shuffling data..."
+ shuf "data/training-$i.csv" > "data/shuf-$i.csv"
+ mv "data/shuf-$i.csv" "data/training-$i.csv"
+ echo
+ done
+}
-echo Preparing pptdb
+# extract notation,result
if [ ! -f "pptdb" ]; then
- make pptdb
+ echo Preparing pptdb
+ make pptdb
fi
-echo -e "Beginning to process data\n"
-
-for i in 5 6; do
- echo "Size $i..."
- ./pptdb "$i" "data/playtak-$i" > "data/check-$i"
- tail -n21 "data/check-$i"
- echo Stripping overflows and illegal games...
- grep -Fvxf "data/check-$i" "data/playtak-$i" > "data/good-playtak-$i"
- echo -n "Generating training data... "
- ./pptdb "$i" "data/good-playtak-$i" generate
- echo "Shuffling data..."
- shuf "data/training-$i.csv" > "data/shuf-$i.csv"
- mv "data/shuf-$i.csv" "data/training-$i.csv"
- echo
-done
+# process
-shuf -n50000 data/good-playtak-5 > data/smalltak-5 && ./pptdb 5 data/smalltak-5 generate && \
-head -n1 data/training-5.csv > t && tail -n+2 data/training-5.csv > test.csv && shuf test.csv >> t && mv t test.csv
+make pptdb
+shuf -n10000 data/good-playtak-5 > data/smalltak-5 && ./pptdb 5 data/smalltak-5 generate && \
+head -n1 data/training-5.csv > t && tail -n+2 data/training-5.csv > data/train5.csv && shuf data/train5.csv >> t && mv t data/train5.csv