Github user iyerr3 commented on a diff in the pull request:
https://github.com/apache/madlib/pull/289#discussion_r201492311
--- Diff:
src/ports/postgres/modules/recursive_partitioning/random_forest.py_in ---
@@ -1291,38 +1300,64 @@ def _create_group_table(
schema_madlib, output_table_name, oob_error_table,
importance_table, cat_features_info_table, grp_key_to_grp_cols,
grouping_cols, tree_terminated):
- """ Ceate the group table for random forest"""
+ """ Create the group table for random forest"""
+
+ cat_var_importance_str = ''
--- End diff --
Let's please change the variable names to `oob*`. It would also help to
change the `compute_var_importance` function in decision tree to
`compute_impurity_var_importance`.
---