digraph G { subgraph clusterstage_9 { label="Stage 9"; subgraph cluster65 { label="AQEShuffleRead"; 25 [labelType="html" label="ShuffledRowRDD [25] [Unordered]<br>count at NativeMethodAccessorImpl.java:0"]; } subgraph cluster62 { label="WholeStageCodegen (2)"; 26 [labelType="html" label="MapPartitionsRDD [26] [Unordered]<br>count at NativeMethodAccessorImpl.java:0"]; } subgraph cluster61 { label="Window"; 27 [labelType="html" label="MapPartitionsRDD [27] [Unordered]<br>count at NativeMethodAccessorImpl.java:0"]; } subgraph cluster58 { label="WholeStageCodegen (3)"; 28 [labelType="html" label="MapPartitionsRDD [28] [Unordered]<br>count at NativeMethodAccessorImpl.java:0"]; } subgraph cluster66 { label="mapPartitionsInternal"; 29 [labelType="html" label="MapPartitionsRDD [29] [Unordered]<br>count at NativeMethodAccessorImpl.java:0"]; } subgraph cluster67 { label="mapPartitionsInternal"; 30 [labelType="html" label="AdaptiveSparkPlan isFinalPlan=false\n+- Filter (isnotnull(is_ride_id_valid#474) AND ((is_ride_id_valid#474 AND is_duration_valid#475) AND is_station_valid#476))\n +- Window [row_number() windowspecdefinition(start_station_id#31, started_at#28 ASC NULLS FIRST, specifiedwindowframe(RowFrame, unboundedpreceding$(), currentrow$())) AS _start_station_ride_num#536], [start_station_id#31], [started_at#28 ASC NULLS FIRST]\n +- Sort [start_station_id#31 ASC NULLS FIRST, started_at#28 ASC NULLS FIRST], false, 0\n +- Exchange hashpartitioning(start_station_id#31, 200), ENSURE_REQUIREMENTS, [plan_id=68]\n +- Project [ride_id#26, rideable_type#27, started_at#28, ended_at#29, start_station_name#30, start_station_id#31, end_station_name#32, end_station_id#33, start_lat#34, start_lng#35, end_lat#36, end_lng#37, member_casual#38, is_ride_id_valid#474, is_duration_valid#475, is_station_valid#476, _source_file#493, 2026-08-18 07:26:21.132535 AS _processed_dttm#494, year(cast(started_at#28 as date)) AS ye... [30] [Cached] [Unordered]<br>count at NativeMethodAccessorImpl.java:0"]; } } 25->26; 26->27; 27->28; 28->29; 29->30; }