[FIX] Graph generation ok, totally in ORM, sqlalchemy.

analysis/cooccurrences.py

@@ -53,11 +53,11 @@ def cooc(corpus=None
 
     NodeNgramX = aliased(NodeNgram)
     NodeNgramY = aliased(NodeNgram)
+    cooc_score = func.sqrt(func.sum(NodeNgramX.weight) * func.sum(NodeNgramY.weight)).label('cooc_score')
 
     doc_id = cache.NodeType['Document'].id
 
-    cooc_query = (session.query(NodeNgramX.ngram_id, NodeNgramY.ngram_id, 
-                    func.sqrt(func.sum(NodeNgramX.weight) * func.sum(NodeNgramY.weight)))
+    cooc_query = (session.query(NodeNgramX.ngram_id, NodeNgramY.ngram_id, cooc_score)
              .join(Node, Node.id == NodeNgramX.node_id)
              .join(NodeNgramY, NodeNgramY.node_id == Node.id)
              .filter(Node.parent_id==corpus.id, Node.type_id==doc_id)
@@ -109,11 +109,12 @@ def cooc(corpus=None
 # Cooc is symetric, take only the main cooccurrences and cut at the limit
     cooc_query = (cooc_query
              .filter(NodeNgramX.ngram_id < NodeNgramY.ngram_id)
-
+             .having(cooc_score > 1)
+             
              .group_by(NodeNgramX.ngram_id, NodeNgramY.ngram_id)
-             .order_by(desc(func.count()))
+             .order_by(desc('cooc_score'))
 
-             #.limit(limit)
+             #.limit(50)
              )
 
     matrix = WeightedMatrix(cooc_query)

analysis/functions.py

@@ -229,10 +229,10 @@ def get_cooc(request=None, corpus=None, cooc_id=None, type='node_link', size=siz
     #print(n)
     #print(m)
 
-    nodes_included = 333 #int(round(size/20,0))
+    nodes_included = 100 #int(round(size/20,0))
     #nodes_excluded = int(round(size/10,0))
 
-    nodes_specific = 333 #int(round(size/10,0))
+    nodes_specific = 50 #int(round(size/10,0))
     #nodes_generic = int(round(size/10,0))
 
     # TODO user the included score for the node size
@@ -267,6 +267,8 @@ def get_cooc(request=None, corpus=None, cooc_id=None, type='node_link', size=siz
         G.remove_nodes_from(nodes_to_remove)
         uG = G.to_undirected()
         partition = best_partition(uG)
+
+        print("Density of the graph:", nx.density(G))
     except:
         print("-" * 30)
         PrintException()