digraph G { subgraph clusterstage_16 { label="Stage 16 (skipped)"; subgraph cluster0 { label="Scan csv "; 0 [labelType="html" label="FileScanRDD [0]<br>count at NativeMethodAccessorImpl.java:0"]; 1 [labelType="html" label="MapPartitionsRDD [1]<br>count at NativeMethodAccessorImpl.java:0"]; } subgraph cluster1 { label="mapPartitionsInternal"; 2 [labelType="html" label="MapPartitionsRDD [2]<br>count at NativeMethodAccessorImpl.java:0"]; } subgraph cluster2 { label="mapPartitionsInternal"; 3 [labelType="html" label="FileScan csv [ride_id#0,rideable_type#1,started_at#2,ended_at#3,start_station_name#4,start_station_id#5,end_station_name#6,end_station_id#7,start_lat#8,start_lng#9,end_lat#10,end_lng#11,member_casual#12] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(6 paths)[s3a://rzvde-g10-chepusov-vladislav/raw/citibike_data/202508/202508-cit..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<ride_id:string,rideable_type:string,started_at:timestamp,ended_at:timestamp,start_station_...\n [3] [Cached]<br>count at NativeMethodAccessorImpl.java:0"]; } subgraph cluster108 { label="InMemoryTableScan"; 39 [labelType="html" label="MapPartitionsRDD [39]<br>count at NativeMethodAccessorImpl.java:0"]; 40 [labelType="html" label="MapPartitionsRDD [40]<br>count at NativeMethodAccessorImpl.java:0"]; 41 [labelType="html" label="MapPartitionsRDD [41]<br>count at NativeMethodAccessorImpl.java:0"]; } subgraph cluster103 { label="WholeStageCodegen (1)"; 42 [labelType="html" label="MapPartitionsRDD [42]<br>count at NativeMethodAccessorImpl.java:0"]; } subgraph cluster102 { label="Exchange"; 43 [labelType="html" label="MapPartitionsRDD [43]<br>count at NativeMethodAccessorImpl.java:0"]; } } 0->1; 1->2; 2->3; 3->39; 39->40; 40->41; 41->42; 42->43; }

digraph G { subgraph clusterstage_17 { label="Stage 17"; subgraph cluster116 { label="AQEShuffleRead"; 44 [labelType="html" label="ShuffledRowRDD [44] [Unordered]<br>count at NativeMethodAccessorImpl.java:0"]; } subgraph cluster113 { label="WholeStageCodegen (2)"; 45 [labelType="html" label="MapPartitionsRDD [45] [Unordered]<br>count at NativeMethodAccessorImpl.java:0"]; } subgraph cluster112 { label="Window"; 46 [labelType="html" label="MapPartitionsRDD [46] [Unordered]<br>count at NativeMethodAccessorImpl.java:0"]; } subgraph cluster109 { label="WholeStageCodegen (3)"; 47 [labelType="html" label="MapPartitionsRDD [47] [Unordered]<br>count at NativeMethodAccessorImpl.java:0"]; } subgraph cluster117 { label="mapPartitionsInternal"; 48 [labelType="html" label="MapPartitionsRDD [48] [Unordered]<br>count at NativeMethodAccessorImpl.java:0"]; } subgraph cluster118 { label="mapPartitionsInternal"; 49 [labelType="html" label="AdaptiveSparkPlan isFinalPlan=false\n+- Filter ((NOT is_ride_id_valid#474 OR NOT is_duration_valid#475) OR NOT 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=91]\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 07:26:21.350521 AS _processed_dttm#494, year(cast(started_at#28 as date)) AS year#513, month(cast(started_a... [49] [Cached] [Unordered]<br>count at NativeMethodAccessorImpl.java:0"]; } } 44->45; 45->46; 46->47; 47->48; 48->49; }