digraph G {
0 [labelType="html" label="<br><b>AdaptiveSparkPlan</b><br><br>"];
subgraph cluster1 {
isCluster="true";
label="WholeStageCodegen (2)\n \nduration: 2 ms";
2 [labelType="html" label="<b>HashAggregate</b><br><br>time in aggregation build: 2 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>7 ms (0 ms, 0 ms, 0 ms (stage 22.0: task 87))<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: 295.0 B<br>fetch wait time: 0 ms<br>remote bytes read: 472.0 B<br>merged fetch fallback count: 0<br>local blocks read: 5<br>remote merged chunks fetched: 0<br>remote blocks read: 8<br>data size total (min, med, max (stageId: taskId))<br>208.0 B (0.0 B, 16.0 B, 16.0 B (stage 22.0: task 97))<br>local merged bytes read: 0.0 B<br>number of partitions: 1<br>remote reqs duration: 8 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 22.0: task 97))"];
subgraph cluster4 {
isCluster="true";
label="WholeStageCodegen (1)\n \nduration: total (min, med, max (stageId: taskId))\n2.4 m (1.7 s, 2.6 s, 1.9 m (stage 22.0: task 98))";
5 [labelType="html" label="<b>HashAggregate</b><br><br>time in aggregation build total (min, med, max (stageId: taskId))<br>2.4 m (1.7 s, 2.6 s, 1.9 m (stage 22.0: task 98))<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: 99,666"];
}
8 [labelType="html" label="<b>Scan csv </b><br><br>number of output rows: 4,731,900<br>number of files read: 5<br>metadata time: 1 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=332]
HashAggregate(keys=[], functions=[partial_count(1)])
Project
Filter (((isnull(ride_id#171) OR (trim(ride_id#171, None) = )) OR ((isnull(cast(ended_at#174 as timestamp)) OR isnull(cast(started_at#173 as timestamp))) OR (cast(ended_at#174 as timestamp) <= cast(started_at#173 as timestamp)))) OR ((isnull(end_station_id#178) OR isnull(start_station_id#176)) OR (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: [(((isnull(ride_id#171) OR (trim(ride_id#171, None) = )) OR ((isnull(cast(ended_at#174 as timesta..., Format: CSV, Location: InMemoryFileIndex(5 paths)[s3a://rzvde-g11-terentyeva-kristina/raw/citibike_data/202510/202510-ci..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<ride_id:string,started_at:string,ended_at:string,start_station_id:string,end_station_id:st...