digraph G {
0 [id="node0" labelType="html" label="<br><b>AdaptiveSparkPlan</b><br><br>" tooltip="AdaptiveSparkPlan isFinalPlan=true"];
subgraph cluster1 {
isCluster="true";
id="cluster1";
label="WholeStageCodegen (2)\n \nduration: 20 ms";
tooltip="WholeStageCodegen (2)";
2 [id="node2" labelType="html" label="<b>HashAggregate</b><br><br>spill size: 0.0 B<br>time in aggregation build: 3 ms<br>peak memory: 64.2 MiB<br>number of output rows: 11<br>number of sort fallback tasks: 0<br>avg hash probes per key: 1" tooltip="HashAggregate(keys=[passenger_count#5929L], functions=[])"];
}
3 [id="node3" labelType="html" label="<b>AQEShuffleRead</b><br><br>number of partitions: 1<br>number of empty partitions: 189<br>partition data size: 1200.0 B<br>number of coalesced partitions: 1" tooltip="AQEShuffleRead coalesced"];
4 [id="node4" labelType="html" label="<b>Exchange</b><br><br>shuffle records written: 20<br>remote merged reqs duration: 0 ms<br>remote merged blocks fetched: 0<br>records read: 20<br>local bytes read: 587.0 B<br>merged fetch fallback count: 0<br>local blocks read: 10<br>remote merged chunks fetched: 0<br>remote blocks read: 10<br>data size total (min, med, max (stageId: taskId))<br>320.0 B (160.0 B, 160.0 B, 160.0 B (stage 105.0: task 661))<br>local merged bytes read: 0.0 B<br>local merged chunks fetched: 0<br>shuffle write time total (min, med, max (stageId: taskId))<br>23 ms (7 ms, 15 ms, 15 ms (stage 105.0: task 661))<br>remote merged bytes read: 0.0 B<br>local merged blocks fetched: 0<br>corrupt merged block chunks: 0<br>fetch wait time: 0 ms<br>remote bytes read: 585.0 B<br>number of partitions: 200<br>remote reqs duration: 4 ms<br>remote bytes read to disk: 0.0 B<br>shuffle bytes written total (min, med, max (stageId: taskId))<br>1172.0 B (585.0 B, 587.0 B, 587.0 B (stage 105.0: task 661))" tooltip="Exchange hashpartitioning(passenger_count#5929L, 200), ENSURE_REQUIREMENTS, [plan_id=1296]"];
subgraph cluster5 {
isCluster="true";
id="cluster5";
label="WholeStageCodegen (1)\n \nduration: total (min, med, max (stageId: taskId))\n1.2 s (455 ms, 714 ms, 714 ms (stage 105.0: task 662))";
tooltip="WholeStageCodegen (1)";
6 [id="node6" labelType="html" label="<b>HashAggregate</b><br><br>spill size: 0.0 B<br>time in aggregation build total (min, med, max (stageId: taskId))<br>1.1 s (418 ms, 659 ms, 659 ms (stage 105.0: task 662))<br>peak memory total (min, med, max (stageId: taskId))<br>64.5 MiB (256.0 KiB, 64.2 MiB, 64.2 MiB (stage 105.0: task 662))<br>number of output rows: 20<br>number of sort fallback tasks: 0<br>avg hash probes per key: 1" tooltip="HashAggregate(keys=[passenger_count#5929L], functions=[])"];
7 [id="node7" labelType="html" label="<b>ColumnarToRow</b><br><br>number of output rows: 4,322,960<br>number of input batches: 1,056" tooltip="ColumnarToRow"];
}
8 [id="node8" labelType="html" label="<b>Scan parquet </b><br><br>number of files read: 1<br>scan time total (min, med, max (stageId: taskId))<br>141 ms (58 ms, 83 ms, 83 ms (stage 105.0: task 661))<br>metadata time: 0 ms<br>size of files read: 70.1 MiB<br>number of output rows: 4,322,960" tooltip="FileScan parquet [passenger_count#5929L] Batched: true, DataFilters: [], Format: Parquet, Location: InMemoryFileIndex(1 paths)[file:/home/jovyan/data/yellow-taxi/yellow_tripdata_2025-06.parquet], PartitionFilters: [], PushedFilters: [], ReadSchema: struct<passenger_count:bigint>"];
2->0;
3->2;
4->3;
6->4;
7->6;
8->7;
}
== Physical Plan ==
AdaptiveSparkPlan (13)
+- == Final Plan ==
ResultQueryStage (8), Statistics(sizeInBytes=8.0 EiB)
+- * HashAggregate (7)
+- AQEShuffleRead (6)
+- ShuffleQueryStage (5), Statistics(sizeInBytes=320.0 B, rowCount=20)
+- Exchange (4)
+- * HashAggregate (3)
+- * ColumnarToRow (2)
+- Scan parquet (1)
+- == Initial Plan ==
CollectLimit (12)
+- HashAggregate (11)
+- Exchange (10)
+- HashAggregate (9)
+- Scan parquet (1)
(1) Scan parquet
Output [1]: [passenger_count#5929L]
Batched: true
Location: InMemoryFileIndex [file:/home/jovyan/data/yellow-taxi/yellow_tripdata_2025-06.parquet]
ReadSchema: struct<passenger_count:bigint>
(2) ColumnarToRow [codegen id : 1]
Input [1]: [passenger_count#5929L]
(3) HashAggregate [codegen id : 1]
Input [1]: [passenger_count#5929L]
Keys [1]: [passenger_count#5929L]
Functions: []
Aggregate Attributes: []
Results [1]: [passenger_count#5929L]
(4) Exchange
Input [1]: [passenger_count#5929L]
Arguments: hashpartitioning(passenger_count#5929L, 200), ENSURE_REQUIREMENTS, [plan_id=1296]
(5) ShuffleQueryStage
Output [1]: [passenger_count#5929L]
Arguments: 0
(6) AQEShuffleRead
Input [1]: [passenger_count#5929L]
Arguments: coalesced
(7) HashAggregate [codegen id : 2]
Input [1]: [passenger_count#5929L]
Keys [1]: [passenger_count#5929L]
Functions: []
Aggregate Attributes: []
Results [1]: [passenger_count#5929L]
(8) ResultQueryStage
Output [1]: [passenger_count#5929L]
Arguments: 1
(9) HashAggregate
Input [1]: [passenger_count#5929L]
Keys [1]: [passenger_count#5929L]
Functions: []
Aggregate Attributes: []
Results [1]: [passenger_count#5929L]
(10) Exchange
Input [1]: [passenger_count#5929L]
Arguments: hashpartitioning(passenger_count#5929L, 200), ENSURE_REQUIREMENTS, [plan_id=1281]
(11) HashAggregate
Input [1]: [passenger_count#5929L]
Keys [1]: [passenger_count#5929L]
Functions: []
Aggregate Attributes: []
Results [1]: [passenger_count#5929L]
(12) CollectLimit
Input [1]: [passenger_count#5929L]
Arguments: 1000
(13) AdaptiveSparkPlan
Output [1]: [passenger_count#5929L]
Arguments: isFinalPlan=true