Starter Kit Update

Graph-Analytics-Community-Detection-Algorithms/db_scripts/queries/Print_community.gsql

@@ -1,6 +1,18 @@
 CREATE QUERY print_community(vertex<Prescriber> input_prescriber) FOR GRAPH MyGraph SYNTAX V2 { 
-  /* Write query logic here */ 
-  //PRINT "Print_community works!";
+  /* 
+
+  Returns edges of community given prescriber
+
+  Sample input:
+  input_prescriber: pre14 | pre25
+
+  Using all Prescribers:
+  (1) Select presribers where their community id
+  	matches the input_prescriber and the 
+	prescriber they refer
+  (2) Return referral edges of the community
+
+  */ 
 
 	ListAccum<EDGE> @@edge_list;
 
@@ -17,4 +29,4 @@ CREATE QUERY print_community(vertex<Prescriber> input_prescriber) FOR GRAPH MyGr
 
 	print start;
 	print @@edge_list;
-}
+}

Graph-Analytics-Community-Detection-Algorithms/db_scripts/queries/README.gsql

@@ -0,0 +1,46 @@
+CREATE QUERY README() FOR GRAPH MyGraph {
+/*
+  IMPORANT : PLEASE INSTALL AND RUN the insert_all_referrals QUERY FIRST.
+
+	THE REFERRAL EDGE IS USED IN OTHER QUERIES.
+*/
+
+	STRING name = "Graph-Analytics-Community-Detection-Algorithms";
+	STRING graph_description = "Find communities of a specific type in your network " +
+		(Louvain Method, Connected Components, K-Core Decomposition, strongly connected components)";
+
+	STRING query_order = "1. insert_all_referrals"; 
+
+	STRING Print_community = "Returns edges of community given prescriber";
+	STRING algo_louvain = "Louvain Method with Parallelism and Refinement https://arxiv.org/pdf/1304.4453 " +
+		"The minimum label heuristics are implemented: https://doi.org/10.1016/j.parco.2015.03.003";
+	STRING algo_louvain_enhanced = "Louvain Method with Parallelism and Refinement https://arxiv.org/pdf/1304.4453 " +
+		"The minimum label heuristics are implemented: https://doi.org/10.1016/j.parco.2015.03.003";
+	STRING algo_page_rank = "Compute the pageRank score for each vertex in the GRAPH";
+	STRING conn_comp = "Identifies the Connected Components (undirected edges)";
+	STRING conn_comp_enhanced = "Identifies the Connected Components (undirected edges)";
+	STRING get_community = "Finds the vertices and interconnecting edges associated either with the given prescriber_Id, " +
+		"or if the prescriber_Id is not provided (empty string), then for the given community_Id.";
+	STRING insert_all_referrals = "Inserts and returns the total referrals across prescribers";
+	STRING insert_referrals = "Inserts and returns number of referral insertions from unvisited claims";
+	STRING kcore_decomp = "Outputs the k-core vertex membership for each value of k from k_min to k_max. ";
+	STRING kcore_max = "An implementation of Algorithm 2 in Scalable K-Core Decomposition for Static Graphs " +
+		"Using a Dynamic Graph Data Structure, Tripathy et al., IEEE Big Data 2018.";
+	STRING kcore_sub = "An implementation of Algorithm 2 in Scalable K-Core Decomposition for Static Graphs " +
+		"Using a Dynamic Graph Data Structure, Tripathy et al., IEEE Big Data 2018. ";
+	STRING scc = "Detects strongly connected components based on the following papers: " +
+		"https://www.sandia.gov/~apinar/papers/irreg00.pdf, " +
+		"https://www.sciencedirect.com/science/article/pii/S0743731505000535, " +
+		"https://stanford-ppl.github.io/website/papers/sc13-hong.pdf";
+	STRING scc_enhanced = "Detects strongly connected components based on the following papers: " +
+		"https://www.sandia.gov/~apinar/papers/irreg00.pdf, " +
+		"https://www.sciencedirect.com/science/article/pii/S0743731505000535, " +
+		"https://stanford-ppl.github.io/website/papers/sc13-hong.pdf";
+	STRING select_subgraph = "Returns edges and vertices of subgraph";
+
+	PRINT name, graph_description, query_order, Print_community, algo_louvain, algo_louvain_enhanced, algo_page_rank;
+	PRINT conn_comp, conn_comp_enhanced, get_community, insert_all_referrals, insert_referrals;
+	PRINT kcore_decomp, kcore_max, kcore_sub, scc, scc_enhanced, select_subgraph;
+
+	print "I read this!";
+}

Graph-Analytics-Community-Detection-Algorithms/db_scripts/queries/algo_louvain.gsql

@@ -2,13 +2,28 @@ CREATE QUERY algo_louvain(INT iter1 = 10, INT iter2 = 10, INT iter3 = 10, INT sp
         Bool sort_by_pre_ID, Bool sort_by_comm_ID) FOR GRAPH MyGraph SYNTAX V2 {
 
 /*
-* Louvain Method with Parallelism and Refinement
-* https://arxiv.org/pdf/1304.4453
-* The minimum label heuristics are implemented: https://doi.org/10.1016/j.parco.2015.03.003
-* iter: There are three phases in the algorithm -- move, merge and refine. Their max number of iterations are set by iter1, iter2, iter3 respectively.
-* split: To save memory, split number is 10 by default. When the split number is larger, the query is closer to sequential Louvain Method, which is slower. When the split number is 1, the query is parallel, but requires more memory. 
-* output_level: 0, only list number; 1, also list members
-* fComm, fDist: files to store community label and community distribution
+	Louvain Method with Parallelism and Refinement
+	https://arxiv.org/pdf/1304.4453
+	The minimum label heuristics are implemented: https://doi.org/10.1016/j.parco.2015.03.003
+
+	Inputs:
+	iter: There are three phases in the algorithm -- move, merge and refine. Their max number of iterations are set by iter1, iter2, iter3 respectively.
+	split: To save memory, split number is 10 by default. When the split number is larger, the query is closer to sequential Louvain Method, which is slower. When the split number is 1, the query is parallel, but requires more memory. 
+	output_level: 0, only list number; 1, also list members
+	fComm, fDist: files to store community label and community distribution
+
+	(1) Initialize: count edges and set a unique cluster ID for each vertex
+	(2) Phase 1 -- Move: incrementally calculates the modularity change of moving a vertex into every other community 
+	and moves the vertex to the community with the highest modularity change
+		(a) For each vertex, calculate the change in modularity FROM adding it to each of the nearby clusters
+		(b) Add vertex to cluster with highest positive change in modularity
+		(c) Repeat the above until no vertices change cluster anymore
+	(3) Phase 2 --  Merge: Coarsen the graph by aggregating the vertices which are assigned in the same community into one vertex
+		(a) Select the vertices with minimal internal id to represent the coarsened graph
+		(b) Get @cweight from totalIncident
+		(c) Calculate.num_patient incident from vertex to cluster in coarsened graph; change every interation
+	(4) Phase 3 -- Refinement: run the first phase again on each vertex to do some small adjustments for the resulting communities
+
 */
 	TYPEDEF TUPLE <INT csize, INT number> Cluster_Num;
 	TYPEDEF TUPLE <VERTEX node, INT cid, FLOAT deltaQ> V_Delta_Q;
@@ -242,7 +257,6 @@ CREATE QUERY algo_louvain(INT iter1 = 10, INT iter2 = 10, INT iter3 = 10, INT sp
 		log(debug > 0, "[redrain]#2_merge", iteration2, @@modularity2);
 	END; // outer WHILE
 
-
 # Phase 3 -- Refinement
 	iteration = 0;
 	@@modularity = 0;
@@ -317,4 +331,4 @@ CREATE QUERY algo_louvain(INT iter1 = 10, INT iter2 = 10, INT iter3 = 10, INT sp
 	END;
 	PRINT start [start.communityId];
 	PRINT "Community Detection Done";
-}
+}

Graph-Analytics-Community-Detection-Algorithms/db_scripts/queries/algo_louvain_enhanced.gsql

@@ -4,13 +4,27 @@ CREATE QUERY algo_louvain_enhanced(STRING vertex_type, STRING edge_type,
   FOR GRAPH MyGraph SYNTAX V2 {
 
 /*
-* Louvain Method with Parallelism and Refinement
-* https://arxiv.org/pdf/1304.4453
-* The minimum label heuristics are implemented: https://doi.org/10.1016/j.parco.2015.03.003
-* iter: There are three phases in the algorithm -- move, merge and refine. Their max number of iterations are set by iter1, iter2, iter3 respectively.
-* split: To save memory, split number is 10 by default. When the split number is larger, the query is closer to sequential Louvain Method, which is slower. When the split number is 1, the query is parallel, but requires more memory. 
-* output_level: 0, only list number; 1, also list members
-* fComm, fDist: files to store community label and community distribution
+  Louvain Method with Parallelism and Refinement
+  https://arxiv.org/pdf/1304.4453
+  The minimum label heuristics are implemented: https://doi.org/10.1016/j.parco.2015.03.003
+
+  Inputs:
+  iter: There are three phases in the algorithm -- move, merge and refine. Their max number of iterations are set by iter1, iter2, iter3 respectively.
+  split: To save memory, split number is 10 by default. When the split number is larger, the query is closer to sequential Louvain Method, which is slower. When the split number is 1, the query is parallel, but requires more memory. 
+  output_level: 0, only list number; 1, also list members
+  fComm, fDist: files to store community label and community distribution
+
+
+	(1) Initialize: count edges and set a unique cluster ID for each vertex
+	(2) Phase 1 -- Move: incrementally calculates the modularity change of moving a vertex into every other community 
+	and moves the vertex to the community with the highest modularity change
+		(a) For each vertex, calculate the change in modularity FROM adding it to each of the nearby clusters
+		(b) Add vertex to cluster with highest positive change in modularity
+		(c) Repeat the above until no vertices change cluster anymore
+	(3) Phase 2 --  Merge: Coarsen the graph by aggregating the vertices which are assigned in the same community into one vertex
+	(4) Phase 3 -- Refinement: run the first phase again on each vertex to do some small adjustments for the resulting communities
+
+
 */
   TYPEDEF TUPLE <INT csize, INT number> Cluster_Num;
   TYPEDEF TUPLE <VERTEX node, INT cid, FLOAT delta_Q> V_Delta_Q;
@@ -317,4 +331,4 @@ CREATE QUERY algo_louvain_enhanced(STRING vertex_type, STRING edge_type,
   END;
   PRINT start [start.@cid];
   PRINT "Community Detection Done";
-}
+}

Graph-Analytics-Community-Detection-Algorithms/db_scripts/queries/algo_page_rank.gsql

@@ -1,12 +1,18 @@
 CREATE QUERY algo_page_rank(FLOAT max_change = 0.001, INT max_iter = 25, 
         FLOAT damping = 0.85, INT output_limit) FOR GRAPH MyGraph SYNTAX V2 { 
 
-	# Compute the pageRank score for each vertex in the GRAPH
-# In each iteration, compute a score for each vertex:
-#   score = (1-damping) + damping*sum(received scores FROM its neighbors).
-# The pageRank algorithm stops when either of the following is true:
-#  a) it reaches max_iter iterations;
-#  b) the max score change for any vertex compared to the last iteration <= max_change.
+/*
+	Compute the pageRank score for each vertex in the GRAPH
+
+	No inputs
+
+	From all Prescribers:
+	(1) In each iteration, compute a score for each vertex:
+	   score = (1-damping) + damping*sum(received scores FROM its neighbors).
+	(2) The pageRank algorithm stops when either of the following is true:
+		a) it reaches max_iter iterations;
+		b) the max score change for any vertex compared to the last iteration <= max_change.
+*/
 
         TYPEDEF TUPLE<vertex Vertex_ID, FLOAT score> Vertex_Score;
         HeapAccum<Vertex_Score>(output_limit, score DESC) @@top_scores;
@@ -34,4 +40,4 @@ CREATE QUERY algo_page_rank(FLOAT max_change = 0.001, INT max_iter = 25,
                 PRINT @@top_scores;
         END;
 
-}
+}

Graph-Analytics-Community-Detection-Algorithms/db_scripts/queries/conn_comp.gsql

@@ -1,6 +1,18 @@
 CREATE QUERY conn_comp (STRING vertex_type, STRING edge_type, STRING rev_edge_type) 
         FOR GRAPH MyGraph SYNTAX V2 {
-# This query identifies the Connected Components (undirected edges)
+ /*
+          Identifies the Connected Components (undirected edges)
+
+          Sample inputs:
+          vertex_type: claim
+          edge_type: associated
+          rev_edge_type: reverse_associated
+
+          Start from given vertex_type:
+          (1) Initialize: Label each vertex with its own internal ID
+          (2) Propagate smaller internal IDs until no more ID changes can be Done
+
+ */
 
         MinAccum<int> @cc_id = 0;       //each vertex's tentative component id
         SumAccum<int> @old_id = 0;
@@ -16,7 +28,7 @@ CREATE QUERY conn_comp (STRING vertex_type, STRING edge_type, STRING rev_edge_ty
                        x.@old_id = getvid(x)        
             ;
 
-# Propagate smaller internal IDs until no more ID changes can be DOne
+# Propagate smaller internal IDs until no more ID changes can be Done
         WHILE (start.size()>0) DO
                 start = SELECT t
                         FROM start:s -((edge_type|rev_edge_type):e)- :t
@@ -38,4 +50,4 @@ CREATE QUERY conn_comp (STRING vertex_type, STRING edge_type, STRING rev_edge_ty
                 POST-ACCUM @@comp_sizes += (s.@cc_id -> 1);
         PRINT @@comp_sizes;
         PRINT start [start.@cc_id];
-}
+}

Graph-Analytics-Community-Detection-Algorithms/db_scripts/queries/conn_comp_enhanced.gsql

@@ -1,6 +1,19 @@
 CREATE QUERY conn_comp_enhanced (SET<VERTEX> vertex_types, STRING vt2, 
         STRING edge_type, STRING rev_edge_type, INT output_level) FOR GRAPH MyGraph SYNTAX V2 {
-# This query identifies the Connected Components (undirected edges)
+/*
+	Identifies the Connected Components (undirected edges)
+
+	Sample inputs:
+	vertex_type: claim
+	vt2: N/A
+        edge_type: associated
+        rev_edge_type: reverse_associated
+	output_level: 1 
+
+        Start from given vertex_type:
+        (1) Initialize: Label each vertex with its own internal ID
+        (2) Propagate smaller internal IDs until no more ID changes can be Done
+*/
 
         MinAccum<int> @cc_id = 0;       //each vertex's tentative component id
         SumAccum<int> @old_id = 0;
@@ -16,7 +29,7 @@ CREATE QUERY conn_comp_enhanced (SET<VERTEX> vertex_types, STRING vt2,
                        x.@old_id = getvid(x)        
             ;
 
-# Propagate smaller internal IDs until no more ID changes can be DOne
+# Propagate smaller internal IDs until no more ID changes can be Done
         WHILE (start.size()>0) DO
                 start = SELECT t
                         FROM start:s -((edge_type|rev_edge_type):e)- :t
@@ -41,4 +54,4 @@ CREATE QUERY conn_comp_enhanced (SET<VERTEX> vertex_types, STRING vt2,
 	      IF output_level > 0 THEN
           PRINT start [start.@cc_id];
 	      END;
-}
+}

Graph-Analytics-Community-Detection-Algorithms/db_scripts/queries/get_community.gsql

@@ -1,10 +1,22 @@
 CREATE QUERY get_community(STRING prescriber_Id, INT community_Id) FOR GRAPH MyGraph SYNTAX V2 {
-  /* This query finds the vertices and interconnecting edges associated either with the given
-   * prescriber_Id, or if the prescriber_Id is not provided (empty string), then
-   * for the given community_Id.
-   * NOTE: This algorithm requires that the community_Id attribute has been set,
-   * by running the alg_louvain query,
+  /* 
+
+    Finds the vertices and interconnecting edges associated either with the given
+    prescriber_Id, or if the prescriber_Id is not provided (empty string), then
+    for the given community_Id.
+    NOTE: This algorithm requires that the community_Id attribute has been set,
+    by running the alg_louvain query,
+
+    Sample inputs:
+    prescriber_Id: pre78 | pre30
+    community_Id: 10
+
+    Start from all Prescribers:
+    (1) Select prescribers where the id equals the given prescriber_id and set comm_Id
+    (2) Get all the vertices and intercomnnecting edges with the give comm_Id
+
    */
+
   SetAccum<EDGE> @@edge_list;
   INT comm_Id;
 
@@ -20,11 +32,11 @@ CREATE QUERY get_community(STRING prescriber_Id, INT community_Id) FOR GRAPH MyG
   END;
   PRINT comm_Id;
 
-  // Get all the vertices and intercomnnecting edges with the give comm_Id
+  // Get all the vertices and intercomnnecting edges with the given comm_Id
   comm_vertices = SELECT s
     FROM start:s -(referral>:e)- :t
     WHERE s.communityId == comm_Id AND t.communityId == comm_Id
     ACCUM @@edge_list += e;
   PRINT comm_vertices[comm_vertices.Prescriber_id];
   PRINT @@edge_list;
-}
+}

Graph-Analytics-Community-Detection-Algorithms/db_scripts/queries/insert_all_referrals.gsql

@@ -1,4 +1,14 @@
 CREATE QUERY insert_all_referrals () FOR GRAPH MyGraph SYNTAX V2 { 
+
+/*
+
+	Inserts and returns the total referrals across prescribers
+
+	No inputs
+
+	From all Prescriber vertices:
+	(1) Select all prescribers, insert referrals, and count the number of referrals
+*/
 
 	SumAccum<INT> @@num_insertions;
 
@@ -8,4 +18,4 @@ CREATE QUERY insert_all_referrals () FOR GRAPH MyGraph SYNTAX V2 {
 	      ACCUM @@num_insertions += insert_referrals(s);
 
 	PRINT @@num_insertions;
-}
+}

Graph-Analytics-Community-Detection-Algorithms/db_scripts/queries/insert_referrals.gsql

@@ -1,6 +1,22 @@
 CREATE QUERY insert_referrals(VERTEX<Prescriber> input_prescriber) 
 	FOR GRAPH MyGraph RETURNS (INT) SYNTAX V2 {
 
+	/*
+
+	Inserts and returns number of referral insertions from unvisited claims
+
+	Sample input:
+	input_prescriber: pre38
+
+	Start from the input_prescriber:
+	(1) Select claims from input_prescriber and mark as visited
+	(2) Select patients from the claims and update date lists
+	(3) Select other claims from patients in (2) that are unvisited 
+	(4) Select claims from (3) and insert into referral 
+
+
+	*/
+
 	OrAccum<BOOL> @visited, @is_referred_claim;
 	ListAccum<DATETIME> @date_list;
 	SumAccum<INT> @@num_insertions;
@@ -27,4 +43,4 @@ CREATE QUERY insert_referrals(VERTEX<Prescriber> input_prescriber)
 	                        @@num_insertions += 1;
 	print start_set;
 	RETURN @@num_insertions;
-}
+}