Github user njayaram2 commented on a diff in the pull request:
https://github.com/apache/madlib/pull/225#discussion_r163657952
--- Diff: src/ports/postgres/modules/knn/test/knn.sql_in ---
@@ -72,43 +72,55 @@ copy knn_test_data (id, data) from stdin delimiter '|';
\.
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,False,'MADLIB_SCHEMA.squared_dist_norm2');
+select knn('knn_train_data','data','id','label','knn_test_data','data','id','madlib_knn_result_classification',3,False,'MADLIB_SCHEMA.squared_dist_norm2',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);
select assert(array_agg(x)= '{1,2,3}','Wrong output in classification with k=3') from
(select unnest(k_nearest_neighbours) as x from madlib_knn_result_classification where id =
1 order by x asc) y;
+
drop table if exists madlib_knn_result_regression;
-select knn('knn_train_data_reg','data','id','label','knn_test_data','data','id','madlib_knn_result_regression',4,False,'MADLIB_SCHEMA.squared_dist_norm2');
+select knn('knn_train_data_reg','data','id','label','knn_test_data','data','id','madlib_knn_result_regression',4,False,'MADLIB_SCHEMA.squared_dist_norm2',False);
select assert(array_agg(prediction order by id)='{1,1,0.5,1,0.25,0.25}', 'Wrong output
in regression') from madlib_knn_result_regression;
drop table if exists madlib_knn_result_regression;
select knn('knn_train_data_reg','data','id','label','knn_test_data','data','id','madlib_knn_result_regression',3,True);
select assert(array_agg(x)= '{1,2,3}' , 'Wrong output in regression with k=3') from (select
unnest(k_nearest_neighbours) as x from madlib_knn_result_regression where id = 1 order by
x asc) y;
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,False,NULL);
+select knn('knn_train_data','data','id','label','knn_test_data','data','id','madlib_knn_result_classification',3,False,NULL,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,False,'MADLIB_SCHEMA.dist_norm1');
+select knn('knn_train_data','data','id','label','knn_test_data','data','id','madlib_knn_result_classification',3,False,'MADLIB_SCHEMA.dist_norm1',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,False,'MADLIB_SCHEMA.dist_angle');
+select knn('knn_train_data','data','id','label','knn_test_data','data','id','madlib_knn_result_classification',3,False,'MADLIB_SCHEMA.dist_angle',False);
select assert(array_agg(prediction order by id)='{1,0,0,1,0,1}', '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,False,'MADLIB_SCHEMA.dist_tanimoto');
+select knn('knn_train_data','data','id','label','knn_test_data','data','id','madlib_knn_result_classification',3,False,'MADLIB_SCHEMA.dist_tanimoto',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_regression;
-select knn('knn_train_data_reg','data','id','label','knn_test_data','data','id','madlib_knn_result_regression',4,False,'MADLIB_SCHEMA.dist_norm1');
+select knn('knn_train_data_reg','data','id','label','knn_test_data','data','id','madlib_knn_result_regression',4,False,'MADLIB_SCHEMA.dist_norm1',False);
select assert(array_agg(prediction order by id)='{1,1,0.5,1,0.25,0.25}', 'Wrong output
in regression') from madlib_knn_result_regression;
drop table if exists madlib_knn_result_regression;
-select knn('knn_train_data_reg','data','id','label','knn_test_data','data','id','madlib_knn_result_regression',4,False,'MADLIB_SCHEMA.dist_angle');
+select knn('knn_train_data_reg','data','id','label','knn_test_data','data','id','madlib_knn_result_regression',4,False,'MADLIB_SCHEMA.dist_angle',False);
select assert(array_agg(prediction order by id)='{0.75,0.25,0.25,0.75,0.25,1}', 'Wrong
output in regression') from madlib_knn_result_regression;
--- End diff --
The changes to the above test cases are not necessary since the default value for the
new param added is `False` anyway. We could may be specify `False` explicitly for some test
cases, and keep the default value for others.
---
|