Rahul Iyer created MADLIB-1254: ---------------------------------- Summary: RF/DT: Grouping might give incorrect results if 1 group eliminates a categorical variable Key: MADLIB-1254 URL: https://issues.apache.org/jira/browse/MADLIB-1254 Project: Apache MADlib Issue Type: Bug Components: Module: Decision Tree Reporter: Rahul Iyer Fix For: v1.15
If {{forest_train}} is run with grouping enabled and if one of the groups has a categorical feature with just single level, then the categorical feature is eliminated for that group. If other groups retain that feature, then the output of impurity_var_importance is incorrect for the group in question. There could be other ramifications related to this as well. {code:java} DROP TABLE IF EXISTS dt_golf CASCADE; CREATE TABLE dt_golf ( id integer NOT NULL, "OUTLOOK" text, temperature double precision, humidity double precision, "Cont_features" double precision[], cat_features text[], windy boolean, class text ) ; INSERT INTO dt_golf (id,"OUTLOOK",temperature,humidity,"Cont_features",cat_features, windy,class) VALUES (1, 'sunny', 85, 85,ARRAY[85, 85], ARRAY['a', 'b'], false, 'Don''t Play'), (2, 'sunny', 80, 90, ARRAY[80, 90], ARRAY['a', 'b'], true, 'Don''t Play'), (3, 'overcast', 83, 78, ARRAY[83, 78], ARRAY['a', 'b'], false, 'Play'), (4, 'rain', 70, NULL, ARRAY[70, 96], ARRAY['a', 'b'], false, 'Play'), (5, 'rain', 68, 80, ARRAY[68, 80], ARRAY['a', 'b'], false, 'Play'), (6, 'rain', NULL, 70, ARRAY[65, 70], ARRAY['a', 'b'], true, 'Don''t Play'), (7, 'overcast', 64, 65, ARRAY[64, 65], ARRAY['c', 'b'], NULL , 'Play'), (8, 'sunny', 72, 95, ARRAY[72, 95], ARRAY['a', 'b'], false, 'Don''t Play'), (9, 'sunny', 69, 70, ARRAY[69, 70], ARRAY['a', 'b'], false, 'Play'), (10, 'rain', 75, 80, ARRAY[75, 80], ARRAY['a', 'b'], false, 'Play'), (11, 'sunny', 75, 70, ARRAY[75, 70], ARRAY['a', 'd'], true, 'Play'), (12, 'overcast', 72, 90, ARRAY[72, 90], ARRAY['c', 'b'], NULL, 'Play'), (13, 'overcast', 81, 75, ARRAY[81, 75], ARRAY['a', 'b'], false, 'Play'), (15, NULL, 81, 75, ARRAY[81, 75], ARRAY['a', 'b'], false, 'Play'), (16, 'overcast', NULL, 75, ARRAY[81, 75], ARRAY['a', 'd'], false, 'Play'), (14, 'rain', 71, 80, ARRAY[71, 80], ARRAY['c', 'b'], true, 'Don''t Play'); DROP TABLE IF EXISTS train_output, train_output_summary, train_output_group, train_output_poisson_count; SELECT forest_train( 'dt_golf', -- source table 'train_output', -- output model table 'id', -- id column 'temperature::double precision', -- response 'humidity, cat_features, windy, "Cont_features"', -- features NULL, -- exclude columns 'class', -- grouping 5, -- num of trees NULL, -- num of random features TRUE, -- importance 20, -- num_permutations 10, -- max depth 1, -- min split 1, -- min bucket 3, -- number of bins per continuous variable 'max_surrogates = 2 ', FALSE ); \x on SELECT * from train_output_summary; SELECT * from train_output_group; {code} Results: {code:java} SELECT * from train_output_group; -[ RECORD 1 ]-----------+----------------------------------------------------------------------------- gid | 1 class | Don't Play success | t cat_n_levels | {2,2,2} cat_levels_in_text | {c,a,True,False,c,a} oob_error | 92.5335905349795 oob_var_importance | {10.725,10.725,10.725,7.605,10.725,0} impurity_var_importance | {8.33148348160485,0,0,19.9999998625892,19.9999998625892,11.6685163809844} -[ RECORD 2 ]-----------+----------------------------------------------------------------------------- gid | 2 class | Play success | t cat_n_levels | {2,2} cat_levels_in_text | {b,d,False,True} oob_error | 43.0244073645405 oob_var_importance | {1.06581410364015e-15,1.06581410364015e-15,2.1326171875,16.019375,10.570875} impurity_var_importance | {0,0,0,37.8304000437732,38.4881698525677,23.6814277291654} {code} Note that the {{impurity_var_importance}} for {{gid=2}} has length 6 while the {{oob_var_importance}} correctly has 5. -- This message was sent by Atlassian JIRA (v7.6.3#76005)