Elastic_net: Fix grouping without normalization bug JIRA: MADLIB-1146
Selecting grouping columns into the output table was not working when data was NOT scaled, but grouping was used. This commit fixes it. Closes #172 Project: http://git-wip-us.apache.org/repos/asf/incubator-madlib/repo Commit: http://git-wip-us.apache.org/repos/asf/incubator-madlib/commit/2c6045fe Tree: http://git-wip-us.apache.org/repos/asf/incubator-madlib/tree/2c6045fe Diff: http://git-wip-us.apache.org/repos/asf/incubator-madlib/diff/2c6045fe Branch: refs/heads/master Commit: 2c6045fe1340dad892d4faffec78c5c672dbf854 Parents: 2308bef Author: Nandish Jayaram <njaya...@apache.org> Authored: Fri Aug 18 10:10:58 2017 -0700 Committer: Rahul Iyer <ri...@apache.org> Committed: Fri Aug 18 20:52:36 2017 -0700 ---------------------------------------------------------------------- .../modules/elastic_net/elastic_net_generate_result.py_in | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/incubator-madlib/blob/2c6045fe/src/ports/postgres/modules/elastic_net/elastic_net_generate_result.py_in ---------------------------------------------------------------------- diff --git a/src/ports/postgres/modules/elastic_net/elastic_net_generate_result.py_in b/src/ports/postgres/modules/elastic_net/elastic_net_generate_result.py_in index 7a87ef6..1dbd664 100644 --- a/src/ports/postgres/modules/elastic_net/elastic_net_generate_result.py_in +++ b/src/ports/postgres/modules/elastic_net/elastic_net_generate_result.py_in @@ -41,10 +41,9 @@ def _elastic_net_generate_result(optimizer, iteration_run, **args): grouping_cols_list = split_quoted_delimited_str(grouping_column) select_grp = ','.join(['n_tuples_including_nulls_subq.'+str(grp) for grp in grouping_cols_list]) + ',' + select_grouping_info = ','.join([grp_col+"\t"+cols_types[grp_col] + for grp_col in grouping_cols_list]) + "," if data_scaled: - select_grouping_info = ','.join([ - grp_col.strip()+"\t"+cols_types[grp_col.strip()] - for grp_col in grouping_column.split(',')]) + "," x_grp_cols = ' AND '.join([ 'n_tuples_including_nulls_subq.{0}={1}.{2}'.format(grp, args["x_mean_table"], grp) for grp in grouping_cols_list])