From 7ee86fd0ee5c6894fe8aa15b89f626220deafc63 Mon Sep 17 00:00:00 2001
From: tslil <tslil@posteo.de>
Date: Thu, 7 Jan 2021 16:34:07 -0500
Subject: Searching for a good representation

---
 extract.sh  | 31 ++++++++++++++-------------
 src/pptdb.c | 69 ++++++++++++++++++++++++++++++-------------------------------
 2 files changed, 49 insertions(+), 51 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
diff --git a/src/pptdb.c b/src/pptdb.c
index 7995219..5e49c26 100644
--- a/src/pptdb.c
+++ b/src/pptdb.c
@@ -11,37 +11,35 @@ FILE *training_fh = NULL;
 
 static void
 write_input(void) {
-	// Four numbers for capstone coords (col,row)
+	// Whose turn is it?
+	/* fprintf(training_fh,"%d,",current_colour == C_BLACK); */
 	// Two numbers for flats remaining
-	fprintf(training_fh,"%.6f,%.6f,",
-					(float)(white_count & 127)/max_flats,
-					(float)(black_count & 127)/max_flats);
-	// Two layers of board_size * board_size:
-	float t; int h; uint16_t mask;
+	/* fprintf(training_fh,"%.6f,%.6f,", */
+	/*				(float)(white_count & 127)/max_flats, */
+	/*				(float)(black_count & 127)/max_flats); */
+	// Two data points for each square
+	float t; uint16_t mask;
 	for (int k = 0; k < board_size * board_size; k++) {
+		const int h = COUNT_AT(k);
 		// stacks encoded as balanced ternary
 		t = 0;
-		h = COUNT_AT(k);
-
-		if (h>0) {
-			mask = 1<<(h-1);
-			while (h-->0) {
-				t += (colours[k] & mask) ? +1 : -1;
-				t/=3;
-				mask >>= 1;
-			}
-		}
-		fprintf(training_fh,"%.6f,",t);
-	}
-	float val;
-	for (int k = 0; k < board_size * board_size; k++) {
-		val = 0;
-		if (COUNT_AT(k)) {
-			if (STONE_AT(k) == STONE_STANDING) val = (colours[k] & 1) ? +1/3 : -1/3;
-			else if (STONE_AT(k) == STONE_CAPSTONE) val = (colours[k] & 1) ? +1.0 : -1.0;
-			else val = (colours[k] & 1) ? +2/3 : -2/3;
+		mask = 1<<(h-1);
+		for (int j = 0; j < h; j++) {
+			t += (colours[k] & mask) ? +1 : -1;
+			t /= 3;
+			mask >>=1;
 		}
-		fprintf(training_fh,"%.6f,",val);
+		// top stone in [-1, +1] ordered as |standing| < |flat| < |cap|
+		/* val = 0; */
+		/* if (COUNT_AT(k)) { */
+		/*	if (STONE_AT(k) == STONE_STANDING) val = (colours[k] & 1) ? +1/4 : -1/4; */
+		/*	else if (STONE_AT(k) == STONE_CAPSTONE) val = (colours[k] & 1) ? +1.0 : -1.0; */
+		/*	else val = (colours[k] & 1) ? +1/2 : -1/2; */
+		/* } */
+		fprintf(training_fh,"%.8f,",
+						t*2);
+						/* (h > 0) ? ((colours[k] & 2) ? +2/3 : -2/3) : 0.0, */
+						/* val */
 	}
 }
 
@@ -93,15 +91,17 @@ parse_line(const char *pt, const ssize_t read) {
 
 			if (r != ACT_OK) return r;
 
-			// Measure height of stacks exceeding 1
-			for (int k = 0; k < board_size * board_size; k++) {
-				if (COUNT_AT(k)>1) heights[COUNT_AT(k)]+=1;
+			if (generate == 0) {
+				// Measure height of stacks exceeding 1
+				for (int k = 0; k < board_size * board_size; k++) {
+					if (COUNT_AT(k)>1) heights[COUNT_AT(k)]+=1;
+				}
 			}
 		}
 		// Generate training data, not too early in the game
 		if (generate && ply > 10) {
 			write_input();
-			fprintf(training_fh,"%d\n", result);
+			fprintf(training_fh,"%d,%d\n", result, 1-result);
 		}
 		// Parse next action
 		while (idx<read && pt[idx++]!=',');
@@ -139,12 +139,11 @@ main(int argc, char **argv) {
 		training_fh = fopen(td_fn, "w");
 		if (training_fh == NULL) exit(EXIT_FAILURE);
 		// Write header
-		fputs("\"White flats\",\"Black flats\",",training_fh);
-		for (int k = 0; k < size*size; k++)
+		/* fputs("\"Player\",\"White flats\",\"Black flats\",",training_fh); */
+		for (int k = 0; k < size*size; k++) {
 			fprintf(training_fh,"\"Stack %d\",",k);
-		for (int k = 0; k < size*size; k++)
-			fprintf(training_fh,"\"Wall %d\",",k);
-		fputs("\"Outcome\"\n",training_fh);
+		}
+		fputs("\"White win\",\"Black win\"\n",training_fh);
 	} else generate=0;
 
 	while ((read = getline(&line, &len, playtak_fh)) != -1) {
-- 
cgit v1.2.3