orhankislal commented on code in PR #582:
URL: https://github.com/apache/madlib/pull/582#discussion_r898577542


##########
src/ports/postgres/modules/utilities/in_mem_group_control.py_in:
##########
@@ -549,40 +550,43 @@ class GroupIterationController:
         self.iteration = self.iteration + 1
 
         group_param = self.group_param
-        run_sql = """
-            SELECT
-                {_grp_key} AS {col_grp_key},
-                {grouping_col},
-                {iteration} AS {col_grp_iteration},
-                ({newState}) AS {col_grp_state}
-            FROM (
-                SELECT *,
-                    array_to_string(ARRAY[{grouping_str}], ',') AS 
{col_grp_key}
-                FROM {rel_source}
-            ) AS {as_rel_source}
-            JOIN ( {select_rel_state} ) AS {rel_state}
-            {using_str}
-            JOIN ( {select_n_tuples} ) AS _rel_n_tuples
-            {using_str}
-            {groupby_str}
-            """.format(
-            newState=newState,
-            iteration=self.iteration,
-            using_str=group_param.using_str,
-            groupby_str=group_param.groupby_str,
-            _grp_key=group_param.grp_key,
-            select_rel_state=group_param.select_rel_state,
-            select_n_tuples=group_param.select_n_tuples,
-            **self.kwargs)
 
-        update_plan = plpy.prepare(run_sql,
-                                   ["text[]", group_param.grouped_state_type,
-                                    "text[]", "integer[]"])
-        res_tuples = plpy.execute(update_plan, [self.new_states.keys,
-                                                self.new_states.values,
-                                                self.grp_to_n_tuples.keys(),
-                                                self.grp_to_n_tuples.values()])
+        if self.update_plan is None:
+            run_sql = """
+                SELECT
+                    {_grp_key} AS {col_grp_key},
+                    {grouping_col},
+                    ({newState}) AS {col_grp_state}
+                FROM (
+                    SELECT *,
+                        array_to_string(ARRAY[{grouping_str}], ',') AS 
{col_grp_key}
+                    FROM {rel_source}
+                ) AS {as_rel_source}
+                JOIN ( {select_rel_state} ) AS {rel_state}
+                {using_str}
+                JOIN ( {select_n_tuples} ) AS _rel_n_tuples
+                {using_str}
+                {groupby_str}
+                """.format(
+                newState=newState,
+                iteration=self.iteration,
+                using_str=group_param.using_str,
+                groupby_str=group_param.groupby_str,
+                _grp_key=group_param.grp_key,
+                select_rel_state=group_param.select_rel_state,
+                select_n_tuples=group_param.select_n_tuples,
+                **self.kwargs)
+
+            self.update_plan = plpy.prepare(run_sql,

Review Comment:
   That is what we used to do. Now, we keep it in memory (instead of the table) 
attached to the results dictionary on line 589.



-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: dev-unsubscr...@madlib.apache.org

For queries about this service, please contact Infrastructure at:
us...@infra.apache.org

Reply via email to