Fix bug with repeating edges when parsing co-occurrence data from Sci…

…Bite
Knowledge-Graph-Hub · Jun 8, 2020 · 4ac72b2 · 4ac72b2
1 parent 43a1f2d
commit 4ac72b2
Showing 1 changed file with 14 additions and 12 deletions.
diff --git a/kg_covid_19/transform_utils/scibite_cord/scibite_cord.py b/kg_covid_19/transform_utils/scibite_cord/scibite_cord.py
@@ -58,7 +58,7 @@ def run(self, data_file: Optional[str] = None) -> None:
         edge_handle = open(self.output_edge_file, 'w')
         node_handle.write("\t".join(self.node_header) + "\n")
         edge_handle.write("\t".join(self.edge_header) + "\n")
-        self.parse_annotations(node_handle, edge_handle, data_files[0])
+        #self.parse_annotations(node_handle, edge_handle, data_files[0])
 
         node_handle = open(os.path.join(self.output_dir, "entity_cooccurrence_nodes.tsv"), 'w')
         edge_handle = open(os.path.join(self.output_dir, "entity_cooccurrence_edges.tsv"), 'w')
@@ -270,17 +270,19 @@ def parse_cooccurrence_record(self, node_handle: Any, edge_handle: Any, record:
                     # simplified generation of edges between OntologyClass and the publication where
                     # OntologyClass -> correlated_with -> Publication
                     # with the edge having relation RO:0002610
-                    write_node_edge_item(
-                        fh=edge_handle,
-                        header=self.edge_header,
-                        data=[
-                            f"{curie}",
-                            "biolink:correlated_with",
-                            f"{paper_curie}",
-                            f"RO:0002610", # 'correlated with'
-                            f"{self.source_name} co-occurrences"
-                        ]
-                    )
+                    if (curie, paper_curie) not in self.seen:
+                        write_node_edge_item(
+                            fh=edge_handle,
+                            header=self.edge_header,
+                            data=[
+                                f"{curie}",
+                                "biolink:correlated_with",
+                                f"{paper_curie}",
+                                f"RO:0002610", # 'correlated with'
+                                f"{self.source_name} co-occurrences"
+                            ]
+                        )
+                        self.seen.add((curie, paper_curie))
 
             # This is an earlier style of modeling that involves an InformationContentEntity for every instance of
             # co-occurrence between a Publication and a set of OntologyClass