digraph G {
0 [labelType="html" label="<br><b>AdaptiveSparkPlan</b><br><br>"];
subgraph cluster1 {
isCluster="true";
label="WholeStageCodegen (2)\n \nduration: 4 ms";
2 [labelType="html" label="<b>HashAggregate</b><br><br>spill size: 0.0 B<br>time in aggregation build: 1 ms<br>peak memory: 32.2 MiB<br>number of output rows: 2<br>number of sort fallback tasks: 0<br>avg hash probes per key: 1"];
}
3 [labelType="html" label="<b>AQEShuffleRead</b><br><br>number of partitions: 1<br>partition data size: 504.0 B<br>number of coalesced partitions: 1"];
4 [labelType="html" label="<b>Exchange</b><br><br>shuffle records written: 6<br>local merged chunks fetched: 0<br>shuffle write time total (min, med, max (stageId: taskId))<br>14 ms (0 ms, 0 ms, 5 ms (stage 101.0: task 294))<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: 6<br>local bytes read: 483.0 B<br>fetch wait time: 0 ms<br>remote bytes read: 0.0 B<br>merged fetch fallback count: 0<br>local blocks read: 3<br>remote merged chunks fetched: 0<br>remote blocks read: 0<br>data size total (min, med, max (stageId: taskId))<br>240.0 B (0.0 B, 0.0 B, 80.0 B (stage 101.0: task 292))<br>local merged bytes read: 0.0 B<br>number of partitions: 200<br>remote reqs duration: 0 ms<br>remote bytes read to disk: 0.0 B<br>shuffle bytes written total (min, med, max (stageId: taskId))<br>483.0 B (0.0 B, 0.0 B, 162.0 B (stage 101.0: task 298))"];
subgraph cluster5 {
isCluster="true";
label="WholeStageCodegen (1)\n \nduration: total (min, med, max (stageId: taskId))\n19.6 s (0 ms, 2.2 s, 4.3 s (stage 101.0: task 293))";
6 [labelType="html" label="<b>HashAggregate</b><br><br>spill size total (min, med, max (stageId: taskId))<br>0.0 B (0.0 B, 0.0 B, 0.0 B (stage 101.0: task 292))<br>time in aggregation build total (min, med, max (stageId: taskId))<br>19.5 s (0 ms, 2.2 s, 4.3 s (stage 101.0: task 293))<br>peak memory total (min, med, max (stageId: taskId))<br>2.0 MiB (0.0 B, 256.0 KiB, 256.0 KiB (stage 101.0: task 292))<br>number of output rows: 6<br>number of sort fallback tasks: 0<br>avg hash probes per key: 0"];
7 [labelType="html" label="<br><b>Project</b><br><br>"];
8 [labelType="html" label="<b>Filter</b><br><br>number of output rows: 19,713"];
}
9 [labelType="html" label="<b>Scan csv </b><br><br>number of output rows: 19,713<br>number of files read: 5<br>metadata time total (min, med, max (stageId: taskId))<br>0 ms (0 ms, 0 ms, 0 ms (stage 101.0: task 292))<br>size of files read total (min, med, max (stageId: taskId))<br>928.8 MiB (0.0 B, 0.0 B, 928.8 MiB (driver))"];
2->0;
3->2;
4->3;
6->4;
7->6;
8->7;
9->8;
}
10
AdaptiveSparkPlan isFinalPlan=true
HashAggregate(keys=[rideable_type#18], functions=[count(1)])
WholeStageCodegen (2)
AQEShuffleRead coalesced
Exchange hashpartitioning(rideable_type#18, 200), ENSURE_REQUIREMENTS, [plan_id=1372]
HashAggregate(keys=[rideable_type#18], functions=[partial_count(1)])
Project [rideable_type#18]
Filter isnull(end_station_name#23)
WholeStageCodegen (1)
FileScan csv [rideable_type#18,end_station_name#23] Batched: false, DataFilters: [isnull(end_station_name#23)], Format: CSV, Location: InMemoryFileIndex(5 paths)[s3a://rzvde-g9-chernyshev-miron/raw/citibike_data/202507/202507-citibi..., PartitionFilters: [], PushedFilters: [IsNull(end_station_name)], ReadSchema: struct<rideable_type:string,end_station_name:string>