Fixed a small bug in PTN parsing, other stuff

1 files changed, 30 insertions, 31 deletions

diff --git a/extract.sh b/extract.sh
index a48e5ab..77c0ddc 100755
--- a/extract.sh
+++ b/extract.sh
@@ -3,48 +3,47 @@
 db_file=games_anon.db
 
 query() {
-		echo "SELECT $1 FROM games WHERE (size == $2) \
-and ((result == 'R-0') or (result == '0-R'));"
-# and (result != '1-0') and (result != '0-1') and (result != '0-0')\
-# and (result != '1/2-1/2');"
+		query="(size == $1) and (result != '1-0') and (result != '0-1') and (result != '0-0')"
+		selct=""
+		# for player in rabbitboy84 fwwwwibib archvenison Simmon AaaarghBot; do
+		for player in; do
+				selct="$selct(player_black == '$player') or (player_white == '$player') or "
+		done;
+		if [ -n "$selct" ]; then
+				query="$query and (${selct:0:-4})"
+		fi
+		echo "SELECT $2 FROM games WHERE $query;"
 }
 
 extract() {
+		size="$1"
+		things="$2"
 		if [ ! -f "data/$db_file" ]; then
 				wget "https://www.playtak.com/games_anon.db" -O "data/$db_file"
 		fi
-		for size in 5; do
-				echo Extracing games of size "$size"...
-				sqlite3 "data/$db_file" "$(query $1 $size)" | shuf > "data/playtak-$size"
-		done
+		echo Extracing games of size "$size"...
+		sqlite3 "data/$db_file" "$(query $size $things)" | shuf > "data/playtak-$size"
 }
 
 process() {
-		num_games=$1
-		echo -e "Beginning to process data\n"
-		for i in 5; do
-				echo "Size $i..."
-				./pptdb "$i" "data/playtak-$i" > "data/check-$i"
-				tail -n21 "data/check-$i"
-				echo -e "\tStripping overflows and illegal games..."
-				grep -Fvxf "data/check-$i" "data/playtak-$i" > "data/good-playtak-$i"
-				echo -e "\tChoosing $num_games from what remains ..."
-				shuf -n $num_games "data/good-playtak-$i" > "data/smalltak-$i"
-				echo -en "\tGenerating training data... "
-				./pptdb "$i" "data/smalltak-$i" generate
-				echo -e "\tWrote $(wc -l data/training-$i.csv | cut -d\  -f1) samples. Shuffling these..."
-				tail -n+2 "data/training-$i.csv" | shuf > "data/shuf-$i.csv"
-				head -n 1 "data/training-$i.csv" | cat "data/shuf-$i.csv" > "data/smalltrain-$i.csv"
-				rm "data/shuf-$i.csv"
-				mv "data/smalltrain-5.csv" "data/training-5.csv "
-				echo -e "\n\tDone! Sample training data in data/training-$i.csv"
-		done
+		size=$1
+		num_games=$2
+		./pptdb "$size" "data/playtak-$size" > "data/check-$size"
+		tail -n22 "data/check-$size"
+		echo -e "\tStripping overflows and illegal games..."
+		grep -Fvxf "data/check-$size" "data/playtak-$size" > "data/good-playtak-$size"
+		echo -e "\tChoosing $num_games from what remains ..."
+		shuf -n $num_games "data/good-playtak-$size" > "data/smalltak-$size"
+		echo -en "\tGenerating training data... "
+		./pptdb "$size" "data/smalltak-$size" generate
+		echo -e "\n\tDone! Wrote $(wc -l data/training-$size.csv | cut -d\  -f1) samples to data/training-$size.csv."
 }
 
-if [ ! -f "data/playtak-5" ]; then
-		extract notation,result
-fi
 
 make pptdb
 
-process 20000
+for size in 5 6; do
+		extract $size notation,result
+		process $size 20000
+		echo
+done