task1 - Details for Query 7

Details for Query 7

Submitted Time: 2024/12/18 02:08:14
Duration: 34 s
Succeeded Jobs: 10 11

Show the Stage ID and Task ID that corresponds to the max metric

digraph G { subgraph cluster0 { isCluster="true"; label="WholeStageCodegen (4)\n \nduration: 12 ms"; 1 [labelType="html" label="HashAggregate time in aggregation build: 12 ms number of output rows: 1"]; } 2 [labelType="html" label="Exchange shuffle records written: 20 shuffle write time total (min, med, max (stageId: taskId)) 14 ms (0 ms, 0 ms, 1 ms (stage 13.0: task 60)) records read: 20 local bytes read: 590.0 B fetch wait time: 0 ms remote bytes read: 590.0 B local blocks read: 10 remote blocks read: 10 data size total (min, med, max (stageId: taskId)) 320.0 B (16.0 B, 16.0 B, 16.0 B (stage 13.0: task 52)) shuffle bytes written total (min, med, max (stageId: taskId)) 1180.0 B (59.0 B, 59.0 B, 59.0 B (stage 13.0: task 52))"]; subgraph cluster3 { isCluster="true"; label="WholeStageCodegen (3)\n \nduration: total (min, med, max (stageId: taskId))\n1.1 m (1.1 s, 3.5 s, 4.1 s (stage 13.0: task 51))"; 4 [labelType="html" label="HashAggregate time in aggregation build total (min, med, max (stageId: taskId)) 1.1 m (1.1 s, 3.5 s, 4.0 s (stage 13.0: task 51)) number of output rows: 20"]; 5 [labelType="html" label=" Project "]; 6 [labelType="html" label="BroadcastHashJoin number of output rows: 22,400,728"]; 7 [labelType="html" label=" Project "]; 8 [labelType="html" label="BroadcastHashJoin number of output rows: 22,400,728"]; 9 [labelType="html" label=" Project "]; 10 [labelType="html" label="Filter number of output rows: 22,400,728"]; } 11 [labelType="html" label="Scan csv number of files read: 7 metadata time: 0 ms size of files read: 2.2 GiB number of output rows: 22,400,728"]; 12 [labelType="html" label="BroadcastExchange data size: 1026.1 KiB time to collect: 229 ms time to build: 8 ms time to broadcast: 4 ms"]; subgraph cluster13 { isCluster="true"; label="WholeStageCodegen (1)\n \nduration: 100 ms"; 14 [labelType="html" label=" Project "]; 15 [labelType="html" label="Filter number of output rows: 265"]; } 16 [labelType="html" label="Scan csv number of files read: 1 metadata time: 0 ms size of files read: 10.5 KiB number of output rows: 265"]; 2->1; 4->2; 5->4; 6->5; 7->6; 8->7; 9->8; 10->9; 11->10; 12->8; 14->12; 15->14; 16->15; 12->6; }

HashAggregate(keys=[], functions=[count(1)])

WholeStageCodegen (4)

Exchange SinglePartition, true, [id=#241]

HashAggregate(keys=[], functions=[partial_count(1)])

Project

BroadcastHashJoin [cast(DOLocationID#75 as int)], [LocationID#16], Inner, BuildRight

Project [DOLocationID#75]

BroadcastHashJoin [cast(PULocationID#74 as int)], [LocationID#16], Inner, BuildRight

Project [PULocationID#74, DOLocationID#75]

Filter (isnotnull(PULocationID#74) AND isnotnull(DOLocationID#75))

WholeStageCodegen (3)

FileScan csv [PULocationID#74,DOLocationID#75] Batched: false, DataFilters: [isnotnull(PULocationID#74), isnotnull(DOLocationID#75)], Format: CSV, Location: InMemoryFileIndex[s3a://data-repository-bkt/ECS765/nyc_taxi/yellow_tripdata/2023], PartitionFilters: [], PushedFilters: [IsNotNull(PULocationID), IsNotNull(DOLocationID)], ReadSchema: struct<PULocationID:string,DOLocationID:string>

BroadcastExchange HashedRelationBroadcastMode(List(cast(input[0, int, true] as bigint))), [id=#201]

Project [LocationID#16]

Filter isnotnull(LocationID#16)

WholeStageCodegen (1)

FileScan csv [LocationID#16] Batched: false, DataFilters: [isnotnull(LocationID#16)], Format: CSV, Location: InMemoryFileIndex[s3a://data-repository-bkt/ECS765/nyc_taxi/taxi_zone_lookup.csv], PartitionFilters: [], PushedFilters: [IsNotNull(LocationID)], ReadSchema: struct<LocationID:int>

Details

== Parsed Logical Plan ==
Aggregate [count(1) AS count#768L]
+- Project [tpep_pickup_datetime#70, tpep_dropoff_datetime#71, passenger_count#72, trip_distance#73, payment_type#76, fare_amount#630, extra#653, mta_tax#676, tip_amount#584, tolls_amount#699, total_amount#607, cast(congestion_surcharge#83 as decimal(10,2)) AS congestion_surcharge#722, airport_fee#84, taxi_type#85, Pickup_Borough#264, Pickup_Zone#285, Pickup_service_zone#306, Dropoff_Borough#438, Dropoff_Zone#443, Dropoff_service_zone#448, route#539, Month#561]
   +- Project [tpep_pickup_datetime#70, tpep_dropoff_datetime#71, passenger_count#72, trip_distance#73, payment_type#76, fare_amount#630, extra#653, mta_tax#676, tip_amount#584, cast(tolls_amount#81 as decimal(10,2)) AS tolls_amount#699, total_amount#607, congestion_surcharge#83, airport_fee#84, taxi_type#85, Pickup_Borough#264, Pickup_Zone#285, Pickup_service_zone#306, Dropoff_Borough#438, Dropoff_Zone#443, Dropoff_service_zone#448, route#539, Month#561]
      +- Project [tpep_pickup_datetime#70, tpep_dropoff_datetime#71, passenger_count#72, trip_distance#73, payment_type#76, fare_amount#630, extra#653, cast(mta_tax#79 as decimal(10,2)) AS mta_tax#676, tip_amount#584, tolls_amount#81, total_amount#607, congestion_surcharge#83, airport_fee#84, taxi_type#85, Pickup_Borough#264, Pickup_Zone#285, Pickup_service_zone#306, Dropoff_Borough#438, Dropoff_Zone#443, Dropoff_service_zone#448, route#539, Month#561]
         +- Project [tpep_pickup_datetime#70, tpep_dropoff_datetime#71, passenger_count#72, trip_distance#73, payment_type#76, fare_amount#630, cast(extra#78 as decimal(10,2)) AS extra#653, mta_tax#79, tip_amount#584, tolls_amount#81, total_amount#607, congestion_surcharge#83, airport_fee#84, taxi_type#85, Pickup_Borough#264, Pickup_Zone#285, Pickup_service_zone#306, Dropoff_Borough#438, Dropoff_Zone#443, Dropoff_service_zone#448, route#539, Month#561]
            +- Project [tpep_pickup_datetime#70, tpep_dropoff_datetime#71, passenger_count#72, trip_distance#73, payment_type#76, cast(fare_amount#77 as decimal(10,2)) AS fare_amount#630, extra#78, mta_tax#79, tip_amount#584, tolls_amount#81, total_amount#607, congestion_surcharge#83, airport_fee#84, taxi_type#85, Pickup_Borough#264, Pickup_Zone#285, Pickup_service_zone#306, Dropoff_Borough#438, Dropoff_Zone#443, Dropoff_service_zone#448, route#539, Month#561]
               +- Project [tpep_pickup_datetime#70, tpep_dropoff_datetime#71, passenger_count#72, trip_distance#73, payment_type#76, fare_amount#77, extra#78, mta_tax#79, tip_amount#584, tolls_amount#81, cast(total_amount#82 as decimal(10,2)) AS total_amount#607, congestion_surcharge#83, airport_fee#84, taxi_type#85, Pickup_Borough#264, Pickup_Zone#285, Pickup_service_zone#306, Dropoff_Borough#438, Dropoff_Zone#443, Dropoff_service_zone#448, route#539, Month#561]
                  +- Project [tpep_pickup_datetime#70, tpep_dropoff_datetime#71, passenger_count#72, trip_distance#73, payment_type#76, fare_amount#77, extra#78, mta_tax#79, cast(tip_amount#80 as decimal(10,2)) AS tip_amount#584, tolls_amount#81, total_amount#82, congestion_surcharge#83, airport_fee#84, taxi_type#85, Pickup_Borough#264, Pickup_Zone#285, Pickup_service_zone#306, Dropoff_Borough#438, Dropoff_Zone#443, Dropoff_service_zone#448, route#539, Month#561]
                     +- Project [tpep_pickup_datetime#70, tpep_dropoff_datetime#71, passenger_count#72, trip_distance#73, payment_type#76, fare_amount#77, extra#78, mta_tax#79, tip_amount#80, tolls_amount#81, total_amount#82, congestion_surcharge#83, airport_fee#84, taxi_type#85, Pickup_Borough#264, Pickup_Zone#285, Pickup_service_zone#306, Dropoff_Borough#438, Dropoff_Zone#443, Dropoff_service_zone#448, route#539, month(cast(to_timestamp('tpep_pickup_datetime, Some(yyyy-MM-dd HH:mm:ss)) as date)) AS Month#561]
                        +- Project [tpep_pickup_datetime#70, tpep_dropoff_datetime#71, passenger_count#72, trip_distance#73, payment_type#76, fare_amount#77, extra#78, mta_tax#79, tip_amount#80, tolls_amount#81, total_amount#82, congestion_surcharge#83, airport_fee#84, taxi_type#85, Pickup_Borough#264, Pickup_Zone#285, Pickup_service_zone#306, Dropoff_Borough#438, Dropoff_Zone#443, Dropoff_service_zone#448, concat_ws( to , Pickup_Borough#264, Dropoff_Borough#438) AS route#539]
                           +- Project [tpep_pickup_datetime#70, tpep_dropoff_datetime#71, passenger_count#72, trip_distance#73, payment_type#76, fare_amount#77, extra#78, mta_tax#79, tip_amount#80, tolls_amount#81, total_amount#82, congestion_surcharge#83, airport_fee#84, taxi_type#85, Pickup_Borough#264, Pickup_Zone#285, Pickup_service_zone#306, Dropoff_Borough#438, Dropoff_Zone#443, Dropoff_service_zone#448]
                              +- Join Inner, (cast(DOLocationID#75 as int) = LocationID#16)
                                 :- Project [tpep_pickup_datetime#70, tpep_dropoff_datetime#71, passenger_count#72, trip_distance#73, DOLocationID#75, payment_type#76, fare_amount#77, extra#78, mta_tax#79, tip_amount#80, tolls_amount#81, total_amount#82, congestion_surcharge#83, airport_fee#84, taxi_type#85, Pickup_Borough#264, Pickup_Zone#285, Pickup_service_zone#306]
                                 :  +- Project [tpep_pickup_datetime#70, tpep_dropoff_datetime#71, passenger_count#72, trip_distance#73, PULocationID#74, DOLocationID#75, payment_type#76, fare_amount#77, extra#78, mta_tax#79, tip_amount#80, tolls_amount#81, total_amount#82, congestion_surcharge#83, airport_fee#84, taxi_type#85, LocationID#16, Pickup_Borough#264, Pickup_Zone#285, service_zone#19 AS Pickup_service_zone#306]
                                 :     +- Project [tpep_pickup_datetime#70, tpep_dropoff_datetime#71, passenger_count#72, trip_distance#73, PULocationID#74, DOLocationID#75, payment_type#76, fare_amount#77, extra#78, mta_tax#79, tip_amount#80, tolls_amount#81, total_amount#82, congestion_surcharge#83, airport_fee#84, taxi_type#85, LocationID#16, Pickup_Borough#264, Zone#18 AS Pickup_Zone#285, service_zone#19]
                                 :        +- Project [tpep_pickup_datetime#70, tpep_dropoff_datetime#71, passenger_count#72, trip_distance#73, PULocationID#74, DOLocationID#75, payment_type#76, fare_amount#77, extra#78, mta_tax#79, tip_amount#80, tolls_amount#81, total_amount#82, congestion_surcharge#83, airport_fee#84, taxi_type#85, LocationID#16, Borough#17 AS Pickup_Borough#264, Zone#18, service_zone#19]
                                 :           +- Join Inner, (cast(PULocationID#74 as int) = LocationID#16)
                                 :              :- Relation[tpep_pickup_datetime#70,tpep_dropoff_datetime#71,passenger_count#72,trip_distance#73,PULocationID#74,DOLocationID#75,payment_type#76,fare_amount#77,extra#78,mta_tax#79,tip_amount#80,tolls_amount#81,total_amount#82,congestion_surcharge#83,airport_fee#84,taxi_type#85] csv
                                 :              +- Relation[LocationID#16,Borough#17,Zone#18,service_zone#19] csv
                                 +- Project [LocationID#16, Dropoff_Borough#438, Dropoff_Zone#443, service_zone#19 AS Dropoff_service_zone#448]
                                    +- Project [LocationID#16, Dropoff_Borough#438, Zone#18 AS Dropoff_Zone#443, service_zone#19]
                                       +- Project [LocationID#16, Borough#17 AS Dropoff_Borough#438, Zone#18, service_zone#19]
                                          +- Relation[LocationID#16,Borough#17,Zone#18,service_zone#19] csv

== Analyzed Logical Plan ==
count: bigint
Aggregate [count(1) AS count#768L]
+- Project [tpep_pickup_datetime#70, tpep_dropoff_datetime#71, passenger_count#72, trip_distance#73, payment_type#76, fare_amount#630, extra#653, mta_tax#676, tip_amount#584, tolls_amount#699, total_amount#607, cast(congestion_surcharge#83 as decimal(10,2)) AS congestion_surcharge#722, airport_fee#84, taxi_type#85, Pickup_Borough#264, Pickup_Zone#285, Pickup_service_zone#306, Dropoff_Borough#438, Dropoff_Zone#443, Dropoff_service_zone#448, route#539, Month#561]
   +- Project [tpep_pickup_datetime#70, tpep_dropoff_datetime#71, passenger_count#72, trip_distance#73, payment_type#76, fare_amount#630, extra#653, mta_tax#676, tip_amount#584, cast(tolls_amount#81 as decimal(10,2)) AS tolls_amount#699, total_amount#607, congestion_surcharge#83, airport_fee#84, taxi_type#85, Pickup_Borough#264, Pickup_Zone#285, Pickup_service_zone#306, Dropoff_Borough#438, Dropoff_Zone#443, Dropoff_service_zone#448, route#539, Month#561]
      +- Project [tpep_pickup_datetime#70, tpep_dropoff_datetime#71, passenger_count#72, trip_distance#73, payment_type#76, fare_amount#630, extra#653, cast(mta_tax#79 as decimal(10,2)) AS mta_tax#676, tip_amount#584, tolls_amount#81, total_amount#607, congestion_surcharge#83, airport_fee#84, taxi_type#85, Pickup_Borough#264, Pickup_Zone#285, Pickup_service_zone#306, Dropoff_Borough#438, Dropoff_Zone#443, Dropoff_service_zone#448, route#539, Month#561]
         +- Project [tpep_pickup_datetime#70, tpep_dropoff_datetime#71, passenger_count#72, trip_distance#73, payment_type#76, fare_amount#630, cast(extra#78 as decimal(10,2)) AS extra#653, mta_tax#79, tip_amount#584, tolls_amount#81, total_amount#607, congestion_surcharge#83, airport_fee#84, taxi_type#85, Pickup_Borough#264, Pickup_Zone#285, Pickup_service_zone#306, Dropoff_Borough#438, Dropoff_Zone#443, Dropoff_service_zone#448, route#539, Month#561]
            +- Project [tpep_pickup_datetime#70, tpep_dropoff_datetime#71, passenger_count#72, trip_distance#73, payment_type#76, cast(fare_amount#77 as decimal(10,2)) AS fare_amount#630, extra#78, mta_tax#79, tip_amount#584, tolls_amount#81, total_amount#607, congestion_surcharge#83, airport_fee#84, taxi_type#85, Pickup_Borough#264, Pickup_Zone#285, Pickup_service_zone#306, Dropoff_Borough#438, Dropoff_Zone#443, Dropoff_service_zone#448, route#539, Month#561]
               +- Project [tpep_pickup_datetime#70, tpep_dropoff_datetime#71, passenger_count#72, trip_distance#73, payment_type#76, fare_amount#77, extra#78, mta_tax#79, tip_amount#584, tolls_amount#81, cast(total_amount#82 as decimal(10,2)) AS total_amount#607, congestion_surcharge#83, airport_fee#84, taxi_type#85, Pickup_Borough#264, Pickup_Zone#285, Pickup_service_zone#306, Dropoff_Borough#438, Dropoff_Zone#443, Dropoff_service_zone#448, route#539, Month#561]
                  +- Project [tpep_pickup_datetime#70, tpep_dropoff_datetime#71, passenger_count#72, trip_distance#73, payment_type#76, fare_amount#77, extra#78, mta_tax#79, cast(tip_amount#80 as decimal(10,2)) AS tip_amount#584, tolls_amount#81, total_amount#82, congestion_surcharge#83, airport_fee#84, taxi_type#85, Pickup_Borough#264, Pickup_Zone#285, Pickup_service_zone#306, Dropoff_Borough#438, Dropoff_Zone#443, Dropoff_service_zone#448, route#539, Month#561]
                     +- Project [tpep_pickup_datetime#70, tpep_dropoff_datetime#71, passenger_count#72, trip_distance#73, payment_type#76, fare_amount#77, extra#78, mta_tax#79, tip_amount#80, tolls_amount#81, total_amount#82, congestion_surcharge#83, airport_fee#84, taxi_type#85, Pickup_Borough#264, Pickup_Zone#285, Pickup_service_zone#306, Dropoff_Borough#438, Dropoff_Zone#443, Dropoff_service_zone#448, route#539, month(cast(to_timestamp('tpep_pickup_datetime, Some(yyyy-MM-dd HH:mm:ss)) as date)) AS Month#561]
                        +- Project [tpep_pickup_datetime#70, tpep_dropoff_datetime#71, passenger_count#72, trip_distance#73, payment_type#76, fare_amount#77, extra#78, mta_tax#79, tip_amount#80, tolls_amount#81, total_amount#82, congestion_surcharge#83, airport_fee#84, taxi_type#85, Pickup_Borough#264, Pickup_Zone#285, Pickup_service_zone#306, Dropoff_Borough#438, Dropoff_Zone#443, Dropoff_service_zone#448, concat_ws( to , Pickup_Borough#264, Dropoff_Borough#438) AS route#539]
                           +- Project [tpep_pickup_datetime#70, tpep_dropoff_datetime#71, passenger_count#72, trip_distance#73, payment_type#76, fare_amount#77, extra#78, mta_tax#79, tip_amount#80, tolls_amount#81, total_amount#82, congestion_surcharge#83, airport_fee#84, taxi_type#85, Pickup_Borough#264, Pickup_Zone#285, Pickup_service_zone#306, Dropoff_Borough#438, Dropoff_Zone#443, Dropoff_service_zone#448]
                              +- Join Inner, (cast(DOLocationID#75 as int) = LocationID#16)
                                 :- Project [tpep_pickup_datetime#70, tpep_dropoff_datetime#71, passenger_count#72, trip_distance#73, DOLocationID#75, payment_type#76, fare_amount#77, extra#78, mta_tax#79, tip_amount#80, tolls_amount#81, total_amount#82, congestion_surcharge#83, airport_fee#84, taxi_type#85, Pickup_Borough#264, Pickup_Zone#285, Pickup_service_zone#306]
                                 :  +- Project [tpep_pickup_datetime#70, tpep_dropoff_datetime#71, passenger_count#72, trip_distance#73, PULocationID#74, DOLocationID#75, payment_type#76, fare_amount#77, extra#78, mta_tax#79, tip_amount#80, tolls_amount#81, total_amount#82, congestion_surcharge#83, airport_fee#84, taxi_type#85, LocationID#16, Pickup_Borough#264, Pickup_Zone#285, service_zone#19 AS Pickup_service_zone#306]
                                 :     +- Project [tpep_pickup_datetime#70, tpep_dropoff_datetime#71, passenger_count#72, trip_distance#73, PULocationID#74, DOLocationID#75, payment_type#76, fare_amount#77, extra#78, mta_tax#79, tip_amount#80, tolls_amount#81, total_amount#82, congestion_surcharge#83, airport_fee#84, taxi_type#85, LocationID#16, Pickup_Borough#264, Zone#18 AS Pickup_Zone#285, service_zone#19]
                                 :        +- Project [tpep_pickup_datetime#70, tpep_dropoff_datetime#71, passenger_count#72, trip_distance#73, PULocationID#74, DOLocationID#75, payment_type#76, fare_amount#77, extra#78, mta_tax#79, tip_amount#80, tolls_amount#81, total_amount#82, congestion_surcharge#83, airport_fee#84, taxi_type#85, LocationID#16, Borough#17 AS Pickup_Borough#264, Zone#18, service_zone#19]
                                 :           +- Join Inner, (cast(PULocationID#74 as int) = LocationID#16)
                                 :              :- Relation[tpep_pickup_datetime#70,tpep_dropoff_datetime#71,passenger_count#72,trip_distance#73,PULocationID#74,DOLocationID#75,payment_type#76,fare_amount#77,extra#78,mta_tax#79,tip_amount#80,tolls_amount#81,total_amount#82,congestion_surcharge#83,airport_fee#84,taxi_type#85] csv
                                 :              +- Relation[LocationID#16,Borough#17,Zone#18,service_zone#19] csv
                                 +- Project [LocationID#16, Dropoff_Borough#438, Dropoff_Zone#443, service_zone#19 AS Dropoff_service_zone#448]
                                    +- Project [LocationID#16, Dropoff_Borough#438, Zone#18 AS Dropoff_Zone#443, service_zone#19]
                                       +- Project [LocationID#16, Borough#17 AS Dropoff_Borough#438, Zone#18, service_zone#19]
                                          +- Relation[LocationID#16,Borough#17,Zone#18,service_zone#19] csv

== Optimized Logical Plan ==
Aggregate [count(1) AS count#768L]
+- Project
   +- Join Inner, (cast(DOLocationID#75 as int) = LocationID#16)
      :- Project [DOLocationID#75]
      :  +- Join Inner, (cast(PULocationID#74 as int) = LocationID#16)
      :     :- Project [PULocationID#74, DOLocationID#75]
      :     :  +- Filter (isnotnull(PULocationID#74) AND isnotnull(DOLocationID#75))
      :     :     +- Relation[tpep_pickup_datetime#70,tpep_dropoff_datetime#71,passenger_count#72,trip_distance#73,PULocationID#74,DOLocationID#75,payment_type#76,fare_amount#77,extra#78,mta_tax#79,tip_amount#80,tolls_amount#81,total_amount#82,congestion_surcharge#83,airport_fee#84,taxi_type#85] csv
      :     +- Project [LocationID#16]
      :        +- Filter isnotnull(LocationID#16)
      :           +- Relation[LocationID#16,Borough#17,Zone#18,service_zone#19] csv
      +- Project [LocationID#16]
         +- Filter isnotnull(LocationID#16)
            +- Relation[LocationID#16,Borough#17,Zone#18,service_zone#19] csv

== Physical Plan ==
*(4) HashAggregate(keys=[], functions=[count(1)], output=[count#768L])
+- Exchange SinglePartition, true, [id=#241]
   +- *(3) HashAggregate(keys=[], functions=[partial_count(1)], output=[count#771L])
      +- *(3) Project
         +- *(3) BroadcastHashJoin [cast(DOLocationID#75 as int)], [LocationID#16], Inner, BuildRight
            :- *(3) Project [DOLocationID#75]
            :  +- *(3) BroadcastHashJoin [cast(PULocationID#74 as int)], [LocationID#16], Inner, BuildRight
            :     :- *(3) Project [PULocationID#74, DOLocationID#75]
            :     :  +- *(3) Filter (isnotnull(PULocationID#74) AND isnotnull(DOLocationID#75))
            :     :     +- FileScan csv [PULocationID#74,DOLocationID#75] Batched: false, DataFilters: [isnotnull(PULocationID#74), isnotnull(DOLocationID#75)], Format: CSV, Location: InMemoryFileIndex[s3a://data-repository-bkt/ECS765/nyc_taxi/yellow_tripdata/2023], PartitionFilters: [], PushedFilters: [IsNotNull(PULocationID), IsNotNull(DOLocationID)], ReadSchema: struct<PULocationID:string,DOLocationID:string>
            :     +- BroadcastExchange HashedRelationBroadcastMode(List(cast(input[0, int, true] as bigint))), [id=#201]
            :        +- *(1) Project [LocationID#16]
            :           +- *(1) Filter isnotnull(LocationID#16)
            :              +- FileScan csv [LocationID#16] Batched: false, DataFilters: [isnotnull(LocationID#16)], Format: CSV, Location: InMemoryFileIndex[s3a://data-repository-bkt/ECS765/nyc_taxi/taxi_zone_lookup.csv], PartitionFilters: [], PushedFilters: [IsNotNull(LocationID)], ReadSchema: struct<LocationID:int>
            +- ReusedExchange [LocationID#16], BroadcastExchange HashedRelationBroadcastMode(List(cast(input[0, int, true] as bigint))), [id=#201]