Github user orhankislal commented on a diff in the pull request:
https://github.com/apache/madlib/pull/184#discussion_r144114755
--- Diff: src/ports/postgres/modules/knn/test/knn.sql_in ---
@@ -55,15 +71,23 @@ copy knn_test_data (id, "DATA") from stdin delimiter
'|';
6|{50,45}
\.
drop table if exists madlib_knn_result_classification;
-select
knn('"KNN_TRAIN_DATA"','"DATA"','label','knn_test_data','"DATA"','id','madlib_knn_result_classification','c',3);
+select
knn('knn_train_data','data','id','label','knn_test_data','data','id','madlib_knn_result_classification',3,False);
select assert(array_agg(prediction order by id)='{1,1,0,1,0,0}', 'Wrong
output in classification with k=3') from madlib_knn_result_classification;
+drop table if exists madlib_knn_result_classification;
+select
knn('knn_train_data','data','id','label','knn_test_data','data','id','madlib_knn_result_classification',3,True);
+select assert((k_nearest_neighbours )='{1,2,3}', 'Wrong output in
classification with k=3') from madlib_knn_result_classification where id = 1;
--- End diff --
This assertion might fail on gpdb since the order of the nearest neighbors
might change. I would suggest using a query like `select
unnest(k_nearest_neighbours) = ANY('{1,2,3}'::int[]) from
madlib_knn_result_classification where id = 1;`
---
