Github user ArvindSridhar commented on a diff in the pull request:
https://github.com/apache/madlib/pull/309#discussion_r209732424
--- Diff: src/ports/postgres/modules/elastic_net/test/elastic_net.sql_in ---
@@ -839,3 +839,55 @@ SELECT elastic_net_train(
SELECT * FROM house_en;
SELECT * FROM house_en_summary;
SELECT * FROM house_en_cv;
+
+-- Test grouping on non-numeric column
+
+DROP TABLE IF EXISTS grouping_test_non_numeric;
+CREATE TABLE grouping_test_non_numeric ( id INT,
+ tax INT,
+ bedroom INT,
+ bath FLOAT,
+ price INT,
+ size INT,
+ lot INT,
+ zipcode TEXT,
+ testbool boolean);
+INSERT INTO grouping_test_non_numeric (id, tax, bedroom, bath, price,
size, lot, zipcode, testbool) VALUES
+ (1 , 590 , 2 , 1 , 50000 , 770 , 22100 , 'test', 'true'),
+ (2 , 1050 , 3 , 2 , 85000 , 1410 , 12000 , 'test2', 'true'),
+ (3 , 20 , 3 , 1 , 22500 , 1060 , 3500 , 'test', 'false'),
+ (4 , 870 , 2 , 2 , 90000 , 1300 , 17500 , 'test2',
'false');
+
+DROP TABLE IF EXISTS grouping_test_non_numeric_en1,
grouping_test_non_numeric_en1_summary;
+SELECT elastic_net_train( 'grouping_test_non_numeric', --
Source table
+ 'grouping_test_non_numeric_en1', -- Result table
+ 'price', -- Dependent variable
+ 'array[tax, bath, size]', -- Independent variable
+ 'gaussian', -- Regression family
+ 0.5, -- Alpha value
+ 0.1, -- Lambda value
+ TRUE, -- Standardize
+ 'zipcode', -- Grouping column(s)
--- End diff --
We added a check to test for column values having special characters, and
this worked fine with our patch (where we used quote_literal to quote these
values). However, when we tried special characters (namely, an apostrophe) with
the col name, we got an error and have thus commented out this test case.
---
