From: Steinar H. Gunderson <sgunderson@bigfoot.com>
Date: Sun, 18 Mar 2012 23:44:11 +0000 (+0100)
Subject: Compute and calculate standard deviations.
X-Git-Url: https://git.sesse.net/?p=wloh;a=commitdiff_plain;h=72a2eedd021d38d6bb0786033c6f100062363789;hp=dca2f8f927ae7bbe19e89d3d367992bf5f9ae294

Compute and calculate standard deviations.
---

diff --git a/bayeswf.cpp b/bayeswf.cpp
index 6214d28..6441801 100644
--- a/bayeswf.cpp
+++ b/bayeswf.cpp
@@ -16,6 +16,7 @@ using namespace std;
 #define DUMP_RAW 0
 
 float mu[MAX_PLAYERS];
+float mu_stddev[MAX_PLAYERS];
 float global_sigma = 70.0f;
 float prior_sigma = 70.0f;
 
@@ -40,7 +41,7 @@ struct match {
 map<int, vector<match> > matches_for_player;
 vector<match> all_matches;
 
-void dump_scores(const vector<string> &players, const float *mu, int num_players)
+void dump_scores(const vector<string> &players, const float *mu, const float *mu_stddev, int num_players)
 {
 #if 0
 	for (int i = 0; i < num_players; ++i) {
@@ -54,7 +55,7 @@ void dump_scores(const vector<string> &players, const float *mu, int num_players
 	printf("\n");
 #else
 	for (int i = 0; i < num_players; ++i) {
-		printf("%f %s\n", mu[i], players[i].c_str());
+		printf("%f %f %s\n", mu[i], mu_stddev[i], players[i].c_str());
 	}
 #endif
 }
@@ -196,7 +197,7 @@ float compute_total_logl(float *mu, int num_players)
  * Note that this does not depend on mu or the margin at all.
  */
 double hessian[MAX_PLAYERS][MAX_PLAYERS];
-void construct_hessian(const float *mu, const float *sigma, int num_players)
+void construct_hessian(const float *mu, int num_players)
 {
 	memset(hessian, 0, sizeof(hessian));
 
@@ -215,12 +216,29 @@ void construct_hessian(const float *mu, const float *sigma, int num_players)
 		hessian[p1][p1] += w / sigma_sq;
 		hessian[p2][p2] += w / sigma_sq;
 	}
+}
+
+// Compute uncertainty (stddev) of mu estimates, which is 1/sqrt(H_ii),
+// where H is the Hessian (see construct_hessian()).
+void compute_mu_uncertainty(const float *mu, int num_players)
+{
+	memset(mu_stddev, 0, sizeof(mu_stddev));
+
+	for (unsigned i = 0; i < all_matches.size(); ++i) {
+		const match &m = all_matches[i];
+
+		int p1 = m.player;
+		int p2 = m.other_player;
 
+		double sigma_sq = global_sigma * global_sigma;
+		float w = m.weight;
+
+		// Temporarily use mu_stddev to store the diagonal of the Hessian.
+		mu_stddev[p1] += w / sigma_sq;
+		mu_stddev[p2] += w / sigma_sq;
+	}
 	for (int i = 0; i < num_players; ++i) {
-		for (int j = 0; j < num_players; ++j) {
-			printf("%.12f ", hessian[i][j]);
-		}
-		printf("\n");
+		mu_stddev[i] = 1.0f / sqrt(mu_stddev[i]);
 	}
 }
 
@@ -327,7 +345,8 @@ int main(int argc, char **argv)
 #if DUMP_RAW
 	dump_raw(mu, num_players);
 #else
-	dump_scores(players, mu, num_players);
+	compute_mu_uncertainty(mu, num_players);
+	dump_scores(players, mu, mu_stddev, num_players);
 	//fprintf(stderr, "Optimal sigma: %f (two-player: %f)\n", sigma[0], sigma[0] * sqrt(2.0f));
 	printf("%f -2\n", global_sigma / sqrt(2.0f));
 	printf("%f -3\n", prior_sigma);
diff --git a/train.pl b/train.pl
index 22a2741..67b2b8d 100755
--- a/train.pl
+++ b/train.pl
@@ -56,13 +56,13 @@ while (my $ref = $q->fetchrow_hashref) {
 close DATA;
 
 $dbh->do('DELETE FROM ratings');
-my $iq = $dbh->prepare('INSERT INTO ratings ( id, rating ) VALUES (?, ?)');
+my $iq = $dbh->prepare('INSERT INTO ratings ( id, rating, rating_stddev ) VALUES (?, ?, ?)');
 
 open RATINGS, "$config::base_dir/bayeswf < $tmpnam |"
 	or die "bayeswf: $!";
 while (<RATINGS>) {
-	/(.*) (.*)/ or next;
-	$iq->execute($2, $1);
+	/(.*) (.*) (.*)/ or next;
+	$iq->execute($3, $1, $2);
 }
 
 $dbh->commit;