digraph G {
0 [labelType="html" label="<br><b>AdaptiveSparkPlan</b><br><br>"];
subgraph cluster1 {
isCluster="true";
label="WholeStageCodegen (2)\n \nduration: 1 ms";
2 [labelType="html" label="<b>HashAggregate</b><br><br>time in aggregation build: 1 ms<br>number of output rows: 1"];
}
3 [labelType="html" label="<b>Exchange</b><br><br>shuffle records written: 13<br>local merged chunks fetched: 0<br>shuffle write time total (min, med, max (stageId: taskId))<br>6 ms (0 ms, 0 ms, 0 ms (stage 19.0: task 81))<br>remote merged bytes read: 0.0 B<br>local merged blocks fetched: 0<br>corrupt merged block chunks: 0<br>remote merged reqs duration: 0 ms<br>remote merged blocks fetched: 0<br>records read: 13<br>local bytes read: 236.0 B<br>fetch wait time: 0 ms<br>remote bytes read: 531.0 B<br>merged fetch fallback count: 0<br>local blocks read: 4<br>remote merged chunks fetched: 0<br>remote blocks read: 9<br>data size total (min, med, max (stageId: taskId))<br>208.0 B (0.0 B, 16.0 B, 16.0 B (stage 19.0: task 84))<br>local merged bytes read: 0.0 B<br>number of partitions: 1<br>remote reqs duration: 17 ms<br>remote bytes read to disk: 0.0 B<br>shuffle bytes written total (min, med, max (stageId: taskId))<br>767.0 B (0.0 B, 59.0 B, 59.0 B (stage 19.0: task 84))"];
subgraph cluster4 {
isCluster="true";
label="WholeStageCodegen (1)\n \nduration: total (min, med, max (stageId: taskId))\n4.2 m (1.7 s, 3.0 s, 3.6 m (stage 19.0: task 73))";
5 [labelType="html" label="<b>HashAggregate</b><br><br>time in aggregation build total (min, med, max (stageId: taskId))<br>4.2 m (1.7 s, 3.0 s, 3.6 m (stage 19.0: task 73))<br>number of output rows: 13"];
6 [labelType="html" label="<br><b>Project</b><br><br>"];
7 [labelType="html" label="<b>Filter</b><br><br>number of output rows: 4,632,234"];
}
8 [labelType="html" label="<b>Scan csv </b><br><br>number of output rows: 4,716,202<br>number of files read: 5<br>metadata time: 0 ms<br>size of files read: 881.3 MiB"];
2->0;
3->2;
5->3;
6->5;
7->6;
8->7;
}
9
AdaptiveSparkPlan isFinalPlan=true
HashAggregate(keys=[], functions=[count(1)])
WholeStageCodegen (2)
Exchange SinglePartition, ENSURE_REQUIREMENTS, [plan_id=288]
HashAggregate(keys=[], functions=[partial_count(1)])
Project
Filter (((((((((isnotnull(ended_at#174) AND isnotnull(started_at#173)) AND isnotnull(ride_id#171)) AND NOT (trim(ride_id#171, None) = )) AND isnotnull(cast(ended_at#174 as timestamp))) AND isnotnull(cast(started_at#173 as timestamp))) AND (cast(ended_at#174 as timestamp) > cast(started_at#173 as timestamp))) AND isnotnull(end_station_id#178)) AND isnotnull(start_station_id#176)) AND NOT (end_station_id#178 = start_station_id#176))
WholeStageCodegen (1)
FileScan csv [ride_id#171,started_at#173,ended_at#174,start_station_id#176,end_station_id#178] Batched: false, DataFilters: [isnotnull(ended_at#174), isnotnull(started_at#173), isnotnull(ride_id#171), NOT (trim(ride_id#17..., Format: CSV, Location: InMemoryFileIndex(5 paths)[s3a://rzvde-g11-terentyeva-kristina/raw/citibike_data/202510/202510-ci..., PartitionFilters: [], PushedFilters: [IsNotNull(ended_at), IsNotNull(started_at), IsNotNull(ride_id), IsNotNull(end_station_id), IsNot..., ReadSchema: struct<ride_id:string,started_at:string,ended_at:string,start_station_id:string,end_station_id:st...