Updated Centrality Queries

Graph-Analytics-Centrality-Algorithms/db_scripts/queries/README.gsql

@@ -0,0 +1,31 @@
+CREATE QUERY README() FOR GRAPH MyGraph { 
+	STRING graph_description = "Determine the entity in your network that " +
+	  "is most central to the others";
+
+	STRING query_order = "1. add_weights"; 
+
+	STRING add_weights = "Haversine formula to calculate the distances " + 
+	  "between airports by using their latitude and longitude coordinates. " +
+	  "The calculated distances are measured in miles and are added as edge " + 
+	  "weights.";
+	STRING bc_subquery = "The TigerGraph implementation is based on A " + 
+	  "Faster Algorithm for Betweenness Centrality";
+	STRING betweenness_cent = "Betweenness Centrality main query";
+	STRING cc_by_country = "Closeness Centrality main query filtered by " + 
+	  "country";
+	STRING cc_subquery = "Subquery returns closeness centrality for vertex " + 
+	  "source in graph with num_vert vertices ";
+	STRING cc = "Closeness Centrality main query";
+	STRING page_rank_by_country = "PageRank Algorithm";
+	STRING page_rank_pers = "Personalized PageRank Algorithm";
+	STRING page_rank = "PageRank Algorithm";
+	STRING shortest_ss_no_wt = "Shortest Path Algorithm without weights";
+	STRING shortest_ss_pos_wt_limits = "Shortest Path Algorithm with " + 
+	  "weights and limits";
+	STRING shortest_ss_pos_wt = "Shortest Path Algorithm with weights";
+
+	PRINT graph_description, query_order, add_weights, bc_subquery, 
+	  betweenness_cent, cc_by_country, cc_subquery, cc, page_rank_by_country, 
+	  page_rank_pers, page_rank, shortest_ss_no_wt, shortest_ss_pos_wt_limits, 
+	  shortest_ss_pos_wt;
+}

Graph-Analytics-Centrality-Algorithms/db_scripts/queries/add_weights.gsql

@@ -1,35 +1,44 @@
-CREATE QUERY add_weights(STRING e_type, BOOL overwrite=True) FOR GRAPH MyGraph SYNTAX V2 {
-/* This query uses the haversine formula to calculate the distances 
-between airports by using their latitude and longitude coordinates.
-The calculated distances are measured in miles and are added as edge weights.
+CREATE QUERY add_weights(STRING e_type, BOOL overwrite=TRUE) 
+  FOR GRAPH MyGraph SYNTAX V2 {
+/* 
+	Haversine formula to calculate the distances between airports by using
+	their latitude and longitude coordinates. The calculated distances are
+	measured in miles and are added as edge weights.
+
+	Sample inputs:
+	e_type: flight_to
+	overwrite: TRUE | FALSE
+
+	Starting with all Airport vertices, 
+	(1) Get connected Airport vertices
+	(2) Calculate the distances
 */
 
-	ListAccum<edge> @@dont_change_list;
+	ListAccum<EDGE> @@dont_change_list;
 	SumAccum<INT> @@num_changed;
-	double pi = 3.14159265359; // pi
-	double R = 3958.8; // earth's radius in miles
-
-	//to_vertex_set("CNX-3931", "Airport");
+	DOUBLE pi = 3.14159265359; // pi
+	DOUBLE R = 3958.8; // earth's radius in miles
 
 	start = {Airport.*};
 
 	heavy = SELECT t FROM start:s-(e_type:e)-Airport:t
 	    ACCUM 
-	      IF overwrite == False AND e.miles != 0 THEN
+	      IF overwrite == FALSE AND e.miles != 0 THEN
 	        @@dont_change_list += e
 	      ELSE
-	          double lat1 = s.latitude * pi / 180, // lat1 to radians
-	          double lat2 = t.latitude * pi / 180, // lat2 to radians
-	          double deltalat = (t.latitude - s.latitude) * pi / 180, // lat change in radians
-	          double deltalong = (t.longitude - s.longitude) * pi / 180, // long change in radians
-	          double a = sin(deltalat/2) * sin(deltalat/2)
-	                     + cos(lat1) * cos(lat2)
-	                     * sin(deltalong/2) * sin(deltalong/2),
-	          //double atanp1 = sqrt(a), // temp
-	          //double atanp2 = sqrt(1-a), // temp
-	          double c = 2 * atan2(sqrt(a), sqrt(1-a)),
-	          e.miles = ceil(R * c),
-	          @@num_changed += 1
+	          DOUBLE lat1 = s.latitude * pi / 180, // lat1 to radians
+	          DOUBLE lat2 = t.latitude * pi / 180, // lat2 to radians
+	          DOUBLE deltalat = (t.latitude - s.latitude) * pi / 180, /* lat 
+			    change in radians */
+	          DOUBLE deltalong = (t.longitude - s.longitude) * pi / 180, /* lon
+			    change in radians */
+	          DOUBLE a = sin(deltalat/2) * sin(deltalat/2)
+				+ cos(lat1) * cos(lat2)
+				* sin(deltalong/2) * sin(deltalong/2),
+	          DOUBLE c = 2 * atan2(sqrt(a), sqrt(1-a)),
+				e.miles = ceil(R * c),
+				@@num_changed += 1
 	      END;
-	      PRINT @@num_changed, @@dont_change_list;
+
+	PRINT @@num_changed, @@dont_change_list;
 }

Graph-Analytics-Centrality-Algorithms/db_scripts/queries/bc_subquery.gsql

@@ -1,5 +1,8 @@
-CREATE QUERY bc_subquery (VERTEX source, INT max_hops) FOR GRAPH MyGraph RETURNS(MapAccum<vertex, float>) SYNTAX V2 {
-/* The TigerGraph implementation is based on A Faster Algorithm for Betweenness Centrality by Ulrik Brandes, Journal of Mathematical Sociology 25(2):163-177, (2001). According to the algorithm, sigma is the number of shortest paths from source; delta is the pair dependency from source; and dist is the shortest distance from source. The subquery returns a map of (s.id->s.@delta)
+CREATE QUERY bc_subquery (VERTEX source, INT max_hops) FOR GRAPH MyGraph RETURNS(MapAccum<VERTEX, FLOAT>) SYNTAX V2 {
+/* The TigerGraph implementation is based on A Faster Algorithm for Betweenness Centrality 
+by Ulrik Brandes, Journal of Mathematical Sociology 25(2):163-177, (2001). According to the algorithm, 
+sigma is the number of shortest paths from source; delta is the pair dependency from source; 
+and dist is the shortest distance from source. The subquery returns a map of (s.id->s.@delta)
 */
   SumAccum<float> @sigma;              
 	SumAccum<float> @delta;              

Graph-Analytics-Centrality-Algorithms/db_scripts/queries/betweenness_cent.gsql

@@ -1,22 +1,23 @@
-CREATE QUERY betweenness_cent (INT max_hops, INT maxItems, STRING country) FOR GRAPH MyGraph SYNTAX V2 {
-# Betweenness Centrality main query
+CREATE QUERY betweenness_cent (INT max_hops, INT maxItems, STRING country) 
+  FOR GRAPH MyGraph SYNTAX V2 {
+	// Betweenness Centrality main query
 
-	MapAccum<VERTEX,SumAccum<float>> @@BC;
-	SumAccum<float> @cent;
+	MapAccum<VERTEX,SumAccum<FLOAT>> @@BC;
+	SumAccum<FLOAT> @cent;
 
-        start = {ANY};
-	      IF country != "" THEN
-	        start = SELECT v FROM start:v
-	          WHERE v.country == country;
-	      END;
-	
-        start = SELECT s FROM start:s
-                ACCUM @@BC += bc_subquery(s, max_hops);
-	
-        # Write scores to local accumulators of vertices.
-	      start = SELECT s FROM start:s
-	            POST-ACCUM s.@cent += @@BC.get(s)
-	            ORDER BY s.@cent DESC
-	            LIMIT maxItems;
-        PRINT start[start.name, start.@cent];
+	start = {ANY};
+	IF country != "" THEN
+		start = SELECT v FROM start:v
+			WHERE v.country == country; // filter by country if given
+	END;
+
+	start = SELECT s FROM start:s
+			ACCUM @@BC += bc_subquery(s, max_hops); // run betweenness subquery
+
+	// Write scores to local accumulators of vertices.
+	start = SELECT s FROM start:s
+		POST-ACCUM s.@cent += @@BC.get(s)
+		ORDER BY s.@cent DESC
+		LIMIT maxItems;
+	PRINT start[start.name, start.@cent];
 }

Graph-Analytics-Centrality-Algorithms/db_scripts/queries/cc.gsql

@@ -1,5 +1,5 @@
 CREATE QUERY cc (BOOL display, INT output_limit, INT max_hops) FOR GRAPH MyGraph SYNTAX V2 {
-# Closeness Centrality main query
+        # Closeness Centrality main query
 
         TYPEDEF TUPLE<VERTEX Vertex_ID, FLOAT score> Vertex_Score;
         HeapAccum<Vertex_Score>(output_limit, score DESC) @@top_scores;

Graph-Analytics-Centrality-Algorithms/db_scripts/queries/cc_by_country.gsql

@@ -1,13 +1,12 @@
 CREATE QUERY cc_by_country (BOOL display, INT output_limit, INT maxHops, STRING country) FOR GRAPH MyGraph SYNTAX V2 {
-# Closeness Centrality main query
+# Closeness Centrality main query filtered by country
 
         TYPEDEF TUPLE<VERTEX Vertex_ID, STRING name, FLOAT score> Vertex_Score;
         HeapAccum<Vertex_Score>(output_limit, score DESC) @@top_scores;
         SumAccum<float> @score;
         SetAccum<EDGE> @@edge_set;                   # list of all edges, if display is needed
 
         INT num_vert;
-        #INT maxHops = 10;      # measure distance for vertices up to 10 hops away
 
         start = {Airport.*};
         IF country != "" THEN

Graph-Analytics-Centrality-Algorithms/db_scripts/queries/shortest_ss_no_wt.gsql

@@ -1,5 +1,7 @@
 CREATE QUERY shortest_ss_no_wt(VERTEX source, BOOL display) FOR GRAPH MyGraph SYNTAX V2 { 
- /* This query is Single-source_set Shortest Path without weights on edges. It calculates the shortest distance from the given vertex source_set to all other connected vertices, and shows one shortest path between them.   
+ /* This query is Single-source_set Shortest Path without weights on edges. 
+ It calculates the shortest distance from the given vertex source_set to all other connected vertices, 
+ and shows one shortest path between them.   
 The JSON version also show visualization of the network. 
 The attribute version only store the distance into attribute, not the path.
 */