attempt to fix observer species count accuracy for small sizes #335

inaturalist · Jul 7, 2022 · 57d4839 · 57d4839
1 parent 87d7f0d
commit 57d4839
Showing 1 changed file with 5 additions and 0 deletions.
diff --git a/lib/controllers/v1/observations_controller.js b/lib/controllers/v1/observations_controller.js
@@ -1219,6 +1219,11 @@ ObservationsController.observationsSpeciesObserverCounts = async req => {
         }
       }
     };
+    // attempting to account for inaccurate counts for queries with a small size
+    // see https://www.elastic.co/guide/en/elasticsearch/reference/current/search-aggregations-bucket-terms-aggregation.html#search-aggregations-bucket-terms-aggregation-shard-size
+    if ( ( ( aggSize * 1.5 ) + 10 ) < 50 ) {
+      countQuery.aggs.user_taxa.terms.shard_size = 50;
+    }
   }
   countQuery.per_page = 0;
   countQuery.skip_total_hits = true;