aboutsummaryrefslogtreecommitdiff
path: root/data
diff options
context:
space:
mode:
Diffstat (limited to 'data')
-rwxr-xr-xdata/extract.sh43
1 files changed, 0 insertions, 43 deletions
diff --git a/data/extract.sh b/data/extract.sh
deleted file mode 100755
index 285be26..0000000
--- a/data/extract.sh
+++ /dev/null
@@ -1,43 +0,0 @@
-#!/bin/bash
-
-db_file=games_anon.db
-
-query() {
- echo "SELECT $1 FROM games WHERE (size == $2) \
-and (result != '1-0') and (result != '0-1') and (result != '0-0')\
-and (result != '1/2-1/2');"
-}
-
-extract() {
- for size in 5 6; do
- echo Extracing games of size "$size"...
- sqlite3 "$db_file" "$(query $1 $size)" > "playtak-$size"
- done
-}
-
-if [ ! -f "$db_file" ]; then
- wget "https://www.playtak.com/games_anon.db"
-fi
-
-extract notation,result
-
-echo Preparing pptdb
-cd ..
-if [ ! -f "pptdb" ]; then
- 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