From ec604df6d1b32016fdb890d8c1f9d0df7e1fd2c1 Mon Sep 17 00:00:00 2001
From: "Steinar H. Gunderson" <sgunderson@bigfoot.com>
Date: Wed, 29 Aug 2012 23:35:22 +0200
Subject: [PATCH] Store all player IDs as ints instead of strings. Less
 flexibility, but chops off ~100MB RAM usage.

---
 bayeswf.cpp | 39 +++++++++++++++++++++------------------
 1 file changed, 21 insertions(+), 18 deletions(-)

diff --git a/bayeswf.cpp b/bayeswf.cpp
index 7ae502d..bf92cc8 100644
--- a/bayeswf.cpp
+++ b/bayeswf.cpp
@@ -33,11 +33,11 @@ float prior_sigma;
 // Data waiting for insertion into the database.
 
 struct RatingDBTuple {
-	string player;
+	int player;
 	float mu, mu_stddev;
 };
 struct CovarianceDBTuple {
-	string player1, player2;
+	int player1, player2;
 	float covariance;
 };
 vector<RatingDBTuple> rating_db_tuples; 
@@ -65,7 +65,7 @@ struct match {
 map<int, vector<match> > matches_for_player;
 vector<match> all_matches;
 
-void dump_scores(const vector<string> &players, const float *mu, const float *mu_stddev, int num_players)
+void dump_scores(const vector<int> &players, const float *mu, const float *mu_stddev, int num_players)
 {
 #if USE_DB
 	for (int i = 0; i < num_players; ++i) {
@@ -74,7 +74,7 @@ void dump_scores(const vector<string> &players, const float *mu, const float *mu
 	}
 #else
 	for (int i = 0; i < num_players; ++i) {
-		printf("%f %f %s\n", mu[i], mu_stddev[i], players[i].c_str());
+		printf("%f %f %d\n", mu[i], mu_stddev[i], players[i]);
 	}
 #endif
 }
@@ -243,7 +243,7 @@ void construct_hessian(const float *mu, int num_players)
 
 // Compute uncertainty (stddev) of mu estimates, which is sqrt((H^-1)_ii),
 // where H is the Hessian (see construct_hessian()).
-void compute_mu_uncertainty(const float *mu, const vector<string> &players)
+void compute_mu_uncertainty(const float *mu, const vector<int> &players)
 {
 	// FIXME: Use pseudoinverse if applicable.
 	Matrix<float, Dynamic, Dynamic> ih = hessian.inverse();
@@ -305,8 +305,8 @@ void process_file(const char *filename)
 		exit(1);
 	}
 
-	vector<string> players;
-	map<string, int> player_map;
+	vector<int> players;
+	map<int, int> player_map;
 
 	for (int i = 0; i < num_players; ++i) {
 		char buf[256];
@@ -315,17 +315,17 @@ void process_file(const char *filename)
 			exit(1);
 		}
 
-		players.push_back(buf);
-		player_map[buf] = i;
+		players.push_back(atoi(buf));
+		player_map[atoi(buf)] = i;
 	}
 
 	int num_matches = 0;
 	for ( ;; ) {
-		char pl1[256], pl2[256];
+		int pl1, pl2;
 		int score1, score2;
 		float weight;
 
-		if (fscanf(fp, "%s %s %d %d %f", pl1, pl2, &score1, &score2, &weight) != 5) {
+		if (fscanf(fp, "%d %d %d %d %f", &pl1, &pl2, &score1, &score2, &weight) != 5) {
 			//fprintf(stderr, "Read %d matches.\n", num_matches);
 			break;
 		}
@@ -333,11 +333,11 @@ void process_file(const char *filename)
 		++num_matches;
 
 		if (player_map.count(pl1) == 0) {
-			fprintf(stderr, "Unknown player '%s'\n", pl1);
+			fprintf(stderr, "Unknown player '%d'\n", pl1);
 			exit(1);
 		}
 		if (player_map.count(pl2) == 0) {
-			fprintf(stderr, "Unknown player '%s'\n", pl2);
+			fprintf(stderr, "Unknown player '%d'\n", pl2);
 			exit(1);
 		}
 
@@ -429,12 +429,13 @@ int main(int argc, char **argv)
 		txn.exec("TRUNCATE ratings");
 		pqxx::tablewriter writer(txn, "ratings");
 		for (unsigned i = 0; i < rating_db_tuples.size(); ++i) {
-			char mu_str[128], mu_stddev_str[128];
+			char player_str[128], mu_str[128], mu_stddev_str[128];
+			snprintf(player_str, 128, "%d", rating_db_tuples[i].player);
 			snprintf(mu_str, 128, "%f", rating_db_tuples[i].mu);
 			snprintf(mu_stddev_str, 128, "%f", rating_db_tuples[i].mu_stddev);
 
 			vector<string> tuple;
-			tuple.push_back(rating_db_tuples[i].player);
+			tuple.push_back(player_str);
 			tuple.push_back(mu_str);
 			tuple.push_back(mu_stddev_str);
 			writer.push_back(tuple);
@@ -447,12 +448,14 @@ int main(int argc, char **argv)
 		txn.exec("CREATE TABLE new_covariance ( player1 smallint NOT NULL, player2 smallint NOT NULL, cov float NOT NULL )");
 		pqxx::tablewriter writer(txn, "new_covariance");
 		for (unsigned i = 0; i < covariance_db_tuples.size(); ++i) {
-			char cov_str[128];
+			char player1_str[128], player2_str[128], cov_str[128];
+			snprintf(player1_str, 128, "%d", covariance_db_tuples[i].player1);
+			snprintf(player2_str, 128, "%d", covariance_db_tuples[i].player2);
 			snprintf(cov_str, 128, "%f", covariance_db_tuples[i].covariance);
 
 			vector<string> tuple;
-			tuple.push_back(covariance_db_tuples[i].player1);
-			tuple.push_back(covariance_db_tuples[i].player2);
+			tuple.push_back(player1_str);
+			tuple.push_back(player2_str);
 			tuple.push_back(cov_str);
 			writer.push_back(tuple);
 		}
-- 
2.39.5