App - Details for Query 2

Details for Query 2

Submitted Time: 2024/12/18 23:55:17
Duration: 48 s
Succeeded Jobs: 2 3 4

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

digraph G { 0 [labelType="html" label=" CollectLimit "]; subgraph cluster1 { isCluster="true"; label="WholeStageCodegen (4)\n \nduration: total (min, med, max (stageId: taskId))\n51 ms (4 ms, 9 ms, 17 ms (stage 4.0: task 23))"; 2 [labelType="html" label="HashAggregate time in aggregation build total (min, med, max (stageId: taskId)) 27 ms (0 ms, 3 ms, 12 ms (stage 4.0: task 23)) peak memory total (min, med, max (stageId: taskId)) 257.3 MiB (256.0 KiB, 64.3 MiB, 64.3 MiB (stage 6.0: task 25)) number of output rows: 12 avg hash probe bucket list iters (min, med, max (stageId: taskId)): (1, 1, 1 (stage 6.0: task 25))"]; } 3 [labelType="html" label="Exchange shuffle records written: 1,048 shuffle write time total (min, med, max (stageId: taskId)) 233 ms (7 ms, 9 ms, 29 ms (stage 3.0: task 4)) records read: 42 local bytes read total (min, med, max (stageId: taskId)) 2003.0 B (0.0 B, 469.0 B, 713.0 B (stage 6.0: task 26)) fetch wait time total (min, med, max (stageId: taskId)) 0 ms (0 ms, 0 ms, 0 ms (stage 6.0: task 25)) remote bytes read total (min, med, max (stageId: taskId)) 1421.0 B (0.0 B, 374.0 B, 534.0 B (stage 4.0: task 23)) local blocks read: 18 remote blocks read: 13 data size total (min, med, max (stageId: taskId)) 63.9 KiB (2.7 KiB, 3.1 KiB, 5.6 KiB (stage 3.0: task 21)) shuffle bytes written total (min, med, max (stageId: taskId)) 94.0 KiB (3.8 KiB, 4.6 KiB, 8.0 KiB (stage 3.0: task 21))"]; subgraph cluster4 { isCluster="true"; label="WholeStageCodegen (3)\n \nduration: total (min, med, max (stageId: taskId))\n1.5 m (1.6 s, 5.2 s, 6.6 s (stage 3.0: task 3))"; 5 [labelType="html" label="HashAggregate time in aggregation build total (min, med, max (stageId: taskId)) 1.5 m (1.6 s, 5.1 s, 6.4 s (stage 3.0: task 3)) peak memory total (min, med, max (stageId: taskId)) 5.0 MiB (256.0 KiB, 256.0 KiB, 256.0 KiB (stage 3.0: task 4)) number of output rows: 1,048"]; 6 [labelType="html" label=" Project "]; 7 [labelType="html" label="BroadcastHashJoin number of output rows: 22,400,728"]; 8 [labelType="html" label=" Project "]; 9 [labelType="html" label="BroadcastHashJoin number of output rows: 22,400,728"]; 10 [labelType="html" label=" Project "]; 11 [labelType="html" label="Filter number of output rows: 22,400,728"]; } 12 [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"]; 13 [labelType="html" label="BroadcastExchange data size: 1040.0 KiB time to collect: 411 ms time to build: 32 ms time to broadcast: 6 ms"]; subgraph cluster14 { isCluster="true"; label="WholeStageCodegen (1)\n \nduration: 212 ms"; 15 [labelType="html" label=" Project "]; 16 [labelType="html" label="Filter number of output rows: 265"]; } 17 [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->0; 3->2; 5->3; 6->5; 7->6; 8->7; 9->8; 10->9; 11->10; 12->11; 13->9; 15->13; 16->15; 17->16; 13->7; }

CollectLimit 11

HashAggregate(keys=[Travel_Month#390, Travel_Route#368], functions=[sum(cast(cast(tip_amount#26 as float) as double)), sum(cast(cast(passenger_count#18 as int) as bigint))])

WholeStageCodegen (4)

Exchange hashpartitioning(Travel_Month#390, Travel_Route#368, 200), true, [id=#147]

HashAggregate(keys=[Travel_Month#390, Travel_Route#368], functions=[partial_sum(cast(cast(tip_amount#26 as float) as double)), partial_sum(cast(cast(passenger_count#18 as int) as bigint))])

Project [passenger_count#18, tip_amount#26, concat_ws( to , Start_Borough#132, Borough#65) AS Travel_Route#368, month(cast(tpep_pickup_datetime#16 as date)) AS Travel_Month#390]

BroadcastHashJoin [DOLocationID#21], [LocationID#64], Inner, BuildRight

Project [tpep_pickup_datetime#16, passenger_count#18, DOLocationID#21, tip_amount#26, Borough#65 AS Start_Borough#132]

BroadcastHashJoin [PULocationID#20], [LocationID#64], Inner, BuildRight

Project [tpep_pickup_datetime#16, passenger_count#18, PULocationID#20, DOLocationID#21, tip_amount#26]

Filter (isnotnull(PULocationID#20) AND isnotnull(DOLocationID#21))

WholeStageCodegen (3)

FileScan csv [tpep_pickup_datetime#16,passenger_count#18,PULocationID#20,DOLocationID#21,tip_amount#26] Batched: false, DataFilters: [isnotnull(PULocationID#20), isnotnull(DOLocationID#21)], Format: CSV, Location: InMemoryFileIndex[s3a://data-repository-bkt/ECS765/nyc_taxi/yellow_tripdata/2023], PartitionFilters: [], PushedFilters: [IsNotNull(PULocationID), IsNotNull(DOLocationID)], ReadSchema: struct<tpep_pickup_datetime:string,passenger_count:string,PULocationID:string,DOLocationID:string...

BroadcastExchange HashedRelationBroadcastMode(List(input[0, string, true])), [id=#106]

Project [LocationID#64, Borough#65]

Filter isnotnull(LocationID#64)

WholeStageCodegen (1)

FileScan csv [LocationID#64,Borough#65] Batched: false, DataFilters: [isnotnull(LocationID#64)], Format: CSV, Location: InMemoryFileIndex[s3a://data-repository-bkt/ECS765/nyc_taxi/taxi_zone_lookup.csv], PartitionFilters: [], PushedFilters: [IsNotNull(LocationID)], ReadSchema: struct<LocationID:string,Borough:string>

Details

== Parsed Logical Plan ==
GlobalLimit 11
+- LocalLimit 11
   +- Project [cast(Travel_Month#390 as string) AS Travel_Month#459, cast(Travel_Route#368 as string) AS Travel_Route#460, cast(Total_Tips#436 as string) AS Total_Tips#461, cast(Total_Passengers#438L as string) AS Total_Passengers#462, cast(Avg_Tip_Per_Passenger#443 as string) AS Avg_Tip_Per_Passenger#463]
      +- Project [Travel_Month#390, Travel_Route#368, Total_Tips#436, Total_Passengers#438L, Avg_Tip_Per_Passenger#443]
         +- Project [Travel_Month#390, Travel_Route#368, Total_Tips#436, Total_Passengers#438L, round((Total_Tips#436 / cast(Total_Passengers#438L as double)), 2) AS Avg_Tip_Per_Passenger#443]
            +- Aggregate [Travel_Month#390, Travel_Route#368], [Travel_Month#390, Travel_Route#368, sum(cast(cast(tip_amount#26 as float) as double)) AS Total_Tips#436, sum(cast(cast(passenger_count#18 as int) as bigint)) AS Total_Passengers#438L]
               +- Project [tpep_pickup_datetime#16, tpep_dropoff_datetime#17, passenger_count#18, trip_distance#19, payment_type#22, fare_amount#23, extra#24, mta_tax#25, tip_amount#26, tolls_amount#27, total_amount#28, congestion_surcharge#29, airport_fee#30, taxi_type#31, Start_Borough#132, Start_Zone#153, Start_ServiceZone#174, End_Borough#279, End_Zone#302, End_ServiceZone#325, Travel_Route#368, month(cast(tpep_pickup_datetime#16 as date)) AS Travel_Month#390]
                  +- Project [tpep_pickup_datetime#16, tpep_dropoff_datetime#17, passenger_count#18, trip_distance#19, payment_type#22, fare_amount#23, extra#24, mta_tax#25, tip_amount#26, tolls_amount#27, total_amount#28, congestion_surcharge#29, airport_fee#30, taxi_type#31, Start_Borough#132, Start_Zone#153, Start_ServiceZone#174, End_Borough#279, End_Zone#302, End_ServiceZone#325, concat_ws( to , Start_Borough#132, End_Borough#279) AS Travel_Route#368]
                     +- Project [tpep_pickup_datetime#16, tpep_dropoff_datetime#17, passenger_count#18, trip_distance#19, payment_type#22, fare_amount#23, extra#24, mta_tax#25, tip_amount#26, tolls_amount#27, total_amount#28, congestion_surcharge#29, airport_fee#30, taxi_type#31, Start_Borough#132, Start_Zone#153, Start_ServiceZone#174, End_Borough#279, End_Zone#302, End_ServiceZone#325]
                        +- Project [tpep_pickup_datetime#16, tpep_dropoff_datetime#17, passenger_count#18, trip_distance#19, DOLocationID#21, payment_type#22, fare_amount#23, extra#24, mta_tax#25, tip_amount#26, tolls_amount#27, total_amount#28, congestion_surcharge#29, airport_fee#30, taxi_type#31, Start_Borough#132, Start_Zone#153, Start_ServiceZone#174, LocationID#64, End_Borough#279, End_Zone#302, service_zone#67 AS End_ServiceZone#325]
                           +- Project [tpep_pickup_datetime#16, tpep_dropoff_datetime#17, passenger_count#18, trip_distance#19, DOLocationID#21, payment_type#22, fare_amount#23, extra#24, mta_tax#25, tip_amount#26, tolls_amount#27, total_amount#28, congestion_surcharge#29, airport_fee#30, taxi_type#31, Start_Borough#132, Start_Zone#153, Start_ServiceZone#174, LocationID#64, End_Borough#279, Zone#66 AS End_Zone#302, service_zone#67]
                              +- Project [tpep_pickup_datetime#16, tpep_dropoff_datetime#17, passenger_count#18, trip_distance#19, DOLocationID#21, payment_type#22, fare_amount#23, extra#24, mta_tax#25, tip_amount#26, tolls_amount#27, total_amount#28, congestion_surcharge#29, airport_fee#30, taxi_type#31, Start_Borough#132, Start_Zone#153, Start_ServiceZone#174, LocationID#64, Borough#65 AS End_Borough#279, Zone#66, service_zone#67]
                                 +- Join Inner, (DOLocationID#21 = LocationID#64)
                                    :- SubqueryAlias pickup_join
                                    :  +- Project [tpep_pickup_datetime#16, tpep_dropoff_datetime#17, passenger_count#18, trip_distance#19, DOLocationID#21, payment_type#22, fare_amount#23, extra#24, mta_tax#25, tip_amount#26, tolls_amount#27, total_amount#28, congestion_surcharge#29, airport_fee#30, taxi_type#31, Start_Borough#132, Start_Zone#153, Start_ServiceZone#174]
                                    :     +- Project [tpep_pickup_datetime#16, tpep_dropoff_datetime#17, passenger_count#18, trip_distance#19, PULocationID#20, DOLocationID#21, payment_type#22, fare_amount#23, extra#24, mta_tax#25, tip_amount#26, tolls_amount#27, total_amount#28, congestion_surcharge#29, airport_fee#30, taxi_type#31, LocationID#64, Start_Borough#132, Start_Zone#153, service_zone#67 AS Start_ServiceZone#174]
                                    :        +- Project [tpep_pickup_datetime#16, tpep_dropoff_datetime#17, passenger_count#18, trip_distance#19, PULocationID#20, DOLocationID#21, payment_type#22, fare_amount#23, extra#24, mta_tax#25, tip_amount#26, tolls_amount#27, total_amount#28, congestion_surcharge#29, airport_fee#30, taxi_type#31, LocationID#64, Start_Borough#132, Zone#66 AS Start_Zone#153, service_zone#67]
                                    :           +- Project [tpep_pickup_datetime#16, tpep_dropoff_datetime#17, passenger_count#18, trip_distance#19, PULocationID#20, DOLocationID#21, payment_type#22, fare_amount#23, extra#24, mta_tax#25, tip_amount#26, tolls_amount#27, total_amount#28, congestion_surcharge#29, airport_fee#30, taxi_type#31, LocationID#64, Borough#65 AS Start_Borough#132, Zone#66, service_zone#67]
                                    :              +- Join Inner, (PULocationID#20 = LocationID#64)
                                    :                 :- SubqueryAlias trips
                                    :                 :  +- Relation[tpep_pickup_datetime#16,tpep_dropoff_datetime#17,passenger_count#18,trip_distance#19,PULocationID#20,DOLocationID#21,payment_type#22,fare_amount#23,extra#24,mta_tax#25,tip_amount#26,tolls_amount#27,total_amount#28,congestion_surcharge#29,airport_fee#30,taxi_type#31] csv
                                    :                 +- SubqueryAlias pickup
                                    :                    +- Relation[LocationID#64,Borough#65,Zone#66,service_zone#67] csv
                                    +- SubqueryAlias dropoff
                                       +- Relation[LocationID#64,Borough#65,Zone#66,service_zone#67] csv

== Analyzed Logical Plan ==
Travel_Month: string, Travel_Route: string, Total_Tips: string, Total_Passengers: string, Avg_Tip_Per_Passenger: string
GlobalLimit 11
+- LocalLimit 11
   +- Project [cast(Travel_Month#390 as string) AS Travel_Month#459, cast(Travel_Route#368 as string) AS Travel_Route#460, cast(Total_Tips#436 as string) AS Total_Tips#461, cast(Total_Passengers#438L as string) AS Total_Passengers#462, cast(Avg_Tip_Per_Passenger#443 as string) AS Avg_Tip_Per_Passenger#463]
      +- Project [Travel_Month#390, Travel_Route#368, Total_Tips#436, Total_Passengers#438L, Avg_Tip_Per_Passenger#443]
         +- Project [Travel_Month#390, Travel_Route#368, Total_Tips#436, Total_Passengers#438L, round((Total_Tips#436 / cast(Total_Passengers#438L as double)), 2) AS Avg_Tip_Per_Passenger#443]
            +- Aggregate [Travel_Month#390, Travel_Route#368], [Travel_Month#390, Travel_Route#368, sum(cast(cast(tip_amount#26 as float) as double)) AS Total_Tips#436, sum(cast(cast(passenger_count#18 as int) as bigint)) AS Total_Passengers#438L]
               +- Project [tpep_pickup_datetime#16, tpep_dropoff_datetime#17, passenger_count#18, trip_distance#19, payment_type#22, fare_amount#23, extra#24, mta_tax#25, tip_amount#26, tolls_amount#27, total_amount#28, congestion_surcharge#29, airport_fee#30, taxi_type#31, Start_Borough#132, Start_Zone#153, Start_ServiceZone#174, End_Borough#279, End_Zone#302, End_ServiceZone#325, Travel_Route#368, month(cast(tpep_pickup_datetime#16 as date)) AS Travel_Month#390]
                  +- Project [tpep_pickup_datetime#16, tpep_dropoff_datetime#17, passenger_count#18, trip_distance#19, payment_type#22, fare_amount#23, extra#24, mta_tax#25, tip_amount#26, tolls_amount#27, total_amount#28, congestion_surcharge#29, airport_fee#30, taxi_type#31, Start_Borough#132, Start_Zone#153, Start_ServiceZone#174, End_Borough#279, End_Zone#302, End_ServiceZone#325, concat_ws( to , Start_Borough#132, End_Borough#279) AS Travel_Route#368]
                     +- Project [tpep_pickup_datetime#16, tpep_dropoff_datetime#17, passenger_count#18, trip_distance#19, payment_type#22, fare_amount#23, extra#24, mta_tax#25, tip_amount#26, tolls_amount#27, total_amount#28, congestion_surcharge#29, airport_fee#30, taxi_type#31, Start_Borough#132, Start_Zone#153, Start_ServiceZone#174, End_Borough#279, End_Zone#302, End_ServiceZone#325]
                        +- Project [tpep_pickup_datetime#16, tpep_dropoff_datetime#17, passenger_count#18, trip_distance#19, DOLocationID#21, payment_type#22, fare_amount#23, extra#24, mta_tax#25, tip_amount#26, tolls_amount#27, total_amount#28, congestion_surcharge#29, airport_fee#30, taxi_type#31, Start_Borough#132, Start_Zone#153, Start_ServiceZone#174, LocationID#64, End_Borough#279, End_Zone#302, service_zone#67 AS End_ServiceZone#325]
                           +- Project [tpep_pickup_datetime#16, tpep_dropoff_datetime#17, passenger_count#18, trip_distance#19, DOLocationID#21, payment_type#22, fare_amount#23, extra#24, mta_tax#25, tip_amount#26, tolls_amount#27, total_amount#28, congestion_surcharge#29, airport_fee#30, taxi_type#31, Start_Borough#132, Start_Zone#153, Start_ServiceZone#174, LocationID#64, End_Borough#279, Zone#66 AS End_Zone#302, service_zone#67]
                              +- Project [tpep_pickup_datetime#16, tpep_dropoff_datetime#17, passenger_count#18, trip_distance#19, DOLocationID#21, payment_type#22, fare_amount#23, extra#24, mta_tax#25, tip_amount#26, tolls_amount#27, total_amount#28, congestion_surcharge#29, airport_fee#30, taxi_type#31, Start_Borough#132, Start_Zone#153, Start_ServiceZone#174, LocationID#64, Borough#65 AS End_Borough#279, Zone#66, service_zone#67]
                                 +- Join Inner, (DOLocationID#21 = LocationID#64)
                                    :- SubqueryAlias pickup_join
                                    :  +- Project [tpep_pickup_datetime#16, tpep_dropoff_datetime#17, passenger_count#18, trip_distance#19, DOLocationID#21, payment_type#22, fare_amount#23, extra#24, mta_tax#25, tip_amount#26, tolls_amount#27, total_amount#28, congestion_surcharge#29, airport_fee#30, taxi_type#31, Start_Borough#132, Start_Zone#153, Start_ServiceZone#174]
                                    :     +- Project [tpep_pickup_datetime#16, tpep_dropoff_datetime#17, passenger_count#18, trip_distance#19, PULocationID#20, DOLocationID#21, payment_type#22, fare_amount#23, extra#24, mta_tax#25, tip_amount#26, tolls_amount#27, total_amount#28, congestion_surcharge#29, airport_fee#30, taxi_type#31, LocationID#64, Start_Borough#132, Start_Zone#153, service_zone#67 AS Start_ServiceZone#174]
                                    :        +- Project [tpep_pickup_datetime#16, tpep_dropoff_datetime#17, passenger_count#18, trip_distance#19, PULocationID#20, DOLocationID#21, payment_type#22, fare_amount#23, extra#24, mta_tax#25, tip_amount#26, tolls_amount#27, total_amount#28, congestion_surcharge#29, airport_fee#30, taxi_type#31, LocationID#64, Start_Borough#132, Zone#66 AS Start_Zone#153, service_zone#67]
                                    :           +- Project [tpep_pickup_datetime#16, tpep_dropoff_datetime#17, passenger_count#18, trip_distance#19, PULocationID#20, DOLocationID#21, payment_type#22, fare_amount#23, extra#24, mta_tax#25, tip_amount#26, tolls_amount#27, total_amount#28, congestion_surcharge#29, airport_fee#30, taxi_type#31, LocationID#64, Borough#65 AS Start_Borough#132, Zone#66, service_zone#67]
                                    :              +- Join Inner, (PULocationID#20 = LocationID#64)
                                    :                 :- SubqueryAlias trips
                                    :                 :  +- Relation[tpep_pickup_datetime#16,tpep_dropoff_datetime#17,passenger_count#18,trip_distance#19,PULocationID#20,DOLocationID#21,payment_type#22,fare_amount#23,extra#24,mta_tax#25,tip_amount#26,tolls_amount#27,total_amount#28,congestion_surcharge#29,airport_fee#30,taxi_type#31] csv
                                    :                 +- SubqueryAlias pickup
                                    :                    +- Relation[LocationID#64,Borough#65,Zone#66,service_zone#67] csv
                                    +- SubqueryAlias dropoff
                                       +- Relation[LocationID#64,Borough#65,Zone#66,service_zone#67] csv

== Optimized Logical Plan ==
GlobalLimit 11
+- LocalLimit 11
   +- Aggregate [Travel_Month#390, Travel_Route#368], [cast(Travel_Month#390 as string) AS Travel_Month#459, Travel_Route#368, cast(sum(cast(cast(tip_amount#26 as float) as double)) as string) AS Total_Tips#461, cast(sum(cast(cast(passenger_count#18 as int) as bigint)) as string) AS Total_Passengers#462, cast(round((sum(cast(cast(tip_amount#26 as float) as double)) / cast(sum(cast(cast(passenger_count#18 as int) as bigint)) as double)), 2) as string) AS Avg_Tip_Per_Passenger#463]
      +- Project [passenger_count#18, tip_amount#26, concat_ws( to , Start_Borough#132, Borough#65) AS Travel_Route#368, month(cast(tpep_pickup_datetime#16 as date)) AS Travel_Month#390]
         +- Join Inner, (DOLocationID#21 = LocationID#64)
            :- Project [tpep_pickup_datetime#16, passenger_count#18, DOLocationID#21, tip_amount#26, Borough#65 AS Start_Borough#132]
            :  +- Join Inner, (PULocationID#20 = LocationID#64)
            :     :- Project [tpep_pickup_datetime#16, passenger_count#18, PULocationID#20, DOLocationID#21, tip_amount#26]
            :     :  +- Filter (isnotnull(PULocationID#20) AND isnotnull(DOLocationID#21))
            :     :     +- Relation[tpep_pickup_datetime#16,tpep_dropoff_datetime#17,passenger_count#18,trip_distance#19,PULocationID#20,DOLocationID#21,payment_type#22,fare_amount#23,extra#24,mta_tax#25,tip_amount#26,tolls_amount#27,total_amount#28,congestion_surcharge#29,airport_fee#30,taxi_type#31] csv
            :     +- Project [LocationID#64, Borough#65]
            :        +- Filter isnotnull(LocationID#64)
            :           +- Relation[LocationID#64,Borough#65,Zone#66,service_zone#67] csv
            +- Project [LocationID#64, Borough#65]
               +- Filter isnotnull(LocationID#64)
                  +- Relation[LocationID#64,Borough#65,Zone#66,service_zone#67] csv

== Physical Plan ==
CollectLimit 11
+- *(4) HashAggregate(keys=[Travel_Month#390, Travel_Route#368], functions=[sum(cast(cast(tip_amount#26 as float) as double)), sum(cast(cast(passenger_count#18 as int) as bigint))], output=[Travel_Month#459, Travel_Route#368, Total_Tips#461, Total_Passengers#462, Avg_Tip_Per_Passenger#463])
   +- Exchange hashpartitioning(Travel_Month#390, Travel_Route#368, 200), true, [id=#147]
      +- *(3) HashAggregate(keys=[Travel_Month#390, Travel_Route#368], functions=[partial_sum(cast(cast(tip_amount#26 as float) as double)), partial_sum(cast(cast(passenger_count#18 as int) as bigint))], output=[Travel_Month#390, Travel_Route#368, sum#471, sum#472L])
         +- *(3) Project [passenger_count#18, tip_amount#26, concat_ws( to , Start_Borough#132, Borough#65) AS Travel_Route#368, month(cast(tpep_pickup_datetime#16 as date)) AS Travel_Month#390]
            +- *(3) BroadcastHashJoin [DOLocationID#21], [LocationID#64], Inner, BuildRight
               :- *(3) Project [tpep_pickup_datetime#16, passenger_count#18, DOLocationID#21, tip_amount#26, Borough#65 AS Start_Borough#132]
               :  +- *(3) BroadcastHashJoin [PULocationID#20], [LocationID#64], Inner, BuildRight
               :     :- *(3) Project [tpep_pickup_datetime#16, passenger_count#18, PULocationID#20, DOLocationID#21, tip_amount#26]
               :     :  +- *(3) Filter (isnotnull(PULocationID#20) AND isnotnull(DOLocationID#21))
               :     :     +- FileScan csv [tpep_pickup_datetime#16,passenger_count#18,PULocationID#20,DOLocationID#21,tip_amount#26] Batched: false, DataFilters: [isnotnull(PULocationID#20), isnotnull(DOLocationID#21)], Format: CSV, Location: InMemoryFileIndex[s3a://data-repository-bkt/ECS765/nyc_taxi/yellow_tripdata/2023], PartitionFilters: [], PushedFilters: [IsNotNull(PULocationID), IsNotNull(DOLocationID)], ReadSchema: struct<tpep_pickup_datetime:string,passenger_count:string,PULocationID:string,DOLocationID:string...
               :     +- BroadcastExchange HashedRelationBroadcastMode(List(input[0, string, true])), [id=#106]
               :        +- *(1) Project [LocationID#64, Borough#65]
               :           +- *(1) Filter isnotnull(LocationID#64)
               :              +- FileScan csv [LocationID#64,Borough#65] Batched: false, DataFilters: [isnotnull(LocationID#64)], Format: CSV, Location: InMemoryFileIndex[s3a://data-repository-bkt/ECS765/nyc_taxi/taxi_zone_lookup.csv], PartitionFilters: [], PushedFilters: [IsNotNull(LocationID)], ReadSchema: struct<LocationID:string,Borough:string>
               +- ReusedExchange [LocationID#64, Borough#65], BroadcastExchange HashedRelationBroadcastMode(List(input[0, string, true])), [id=#106]