Searching for a good representation

1 files changed, 15 insertions, 16 deletions

diff --git a/extract.sh b/extract.sh
index 1e9443d..e091a9c 100755
--- a/extract.sh
+++ b/extract.sh
@@ -21,19 +21,24 @@ extract() {
 }
 
 process() {
+		num_games=$1
 		echo -e "Beginning to process data\n"
-		for i in 5 6; do
+		for i in 5; do
 				echo "Size $i..."
 				./pptdb "$i" "data/playtak-$i" > "data/check-$i"
 				tail -n21 "data/check-$i"
-				echo Stripping overflows and illegal games...
+				echo -e "\tStripping overflows and illegal games..."
 				grep -Fvxf "data/check-$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
+				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
 }
 
@@ -41,12 +46,6 @@ if [ ! -f "data/playtak-5" ]; then
 		extract notation,result
 fi
 
-if [ ! -f "pptdb" ]; then
-		echo Preparing pptdb
-		make pptdb
-fi
-
-# process
+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
+process 5000