task1 - Details for Query 8

Details for Query 8

Submitted Time: 2024/12/18 01:18:41
Duration: 0.5 s
Succeeded Jobs: 12 13 14

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 (3)"; 2 [labelType="html" label=" Project "]; 3 [labelType="html" label="BroadcastHashJoin number of output rows: 11"]; 4 [labelType="html" label=" Project "]; 5 [labelType="html" label="BroadcastHashJoin number of output rows: 11"]; 6 [labelType="html" label=" Project "]; 7 [labelType="html" label="Filter number of output rows: 11"]; } 8 [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: 11"]; 9 [labelType="html" label="BroadcastExchange data size: 1026.1 KiB time to collect: 165 ms time to build: 6 ms time to broadcast: 3 ms"]; subgraph cluster10 { isCluster="true"; label="WholeStageCodegen (1)\n \nduration: 56 ms"; 11 [labelType="html" label=" Project "]; 12 [labelType="html" label="Filter number of output rows: 265"]; } 13 [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"]; 14 [labelType="html" label="BroadcastExchange data size: 1026.1 KiB time to collect: 158 ms time to build: 9 ms time to broadcast: 4 ms"]; subgraph cluster15 { isCluster="true"; label="WholeStageCodegen (2)\n \nduration: 47 ms"; 16 [labelType="html" label=" Project "]; 17 [labelType="html" label="Filter number of output rows: 265"]; } 18 [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; 4->3; 5->4; 6->5; 7->6; 8->7; 9->5; 11->9; 12->11; 13->12; 14->3; 16->14; 17->16; 18->17; }

CollectLimit 11

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#656, cast(month(cast(gettimestamp(tpep_pickup_datetime#70, yyyy-MM-dd HH:mm:ss, Some(GMT)) as date)) as string) AS Month#657]

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

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, Borough#17 AS Pickup_Borough#264, Zone#18 AS Pickup_Zone#285, service_zone#19 AS Pickup_service_zone#306]

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

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]

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

WholeStageCodegen (3)

FileScan csv [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] 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<tpep_pickup_datetime:string,tpep_dropoff_datetime:string,passenger_count:string,trip_dista...

BroadcastExchange HashedRelationBroadcastMode(List(cast(input[0, int, true] as bigint))), [id=#302]

Project [LocationID#16, Borough#17, Zone#18, service_zone#19]

Filter isnotnull(LocationID#16)

WholeStageCodegen (1)

FileScan csv [LocationID#16,Borough#17,Zone#18,service_zone#19] 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,Borough:string,Zone:string,service_zone:string>

BroadcastExchange HashedRelationBroadcastMode(List(cast(input[0, int, true] as bigint))), [id=#310]

Project [LocationID#16, Borough#17 AS Dropoff_Borough#438, Zone#18 AS Dropoff_Zone#443, service_zone#19 AS Dropoff_service_zone#448]

Filter isnotnull(LocationID#16)

WholeStageCodegen (2)

Details

== Parsed Logical Plan ==
GlobalLimit 11
+- LocalLimit 11
   +- Project [cast(tpep_pickup_datetime#70 as string) AS tpep_pickup_datetime#636, cast(tpep_dropoff_datetime#71 as string) AS tpep_dropoff_datetime#637, cast(passenger_count#72 as string) AS passenger_count#638, cast(trip_distance#73 as string) AS trip_distance#639, cast(payment_type#76 as string) AS payment_type#640, cast(fare_amount#77 as string) AS fare_amount#641, cast(extra#78 as string) AS extra#642, cast(mta_tax#79 as string) AS mta_tax#643, cast(tip_amount#80 as string) AS tip_amount#644, cast(tolls_amount#81 as string) AS tolls_amount#645, cast(total_amount#82 as string) AS total_amount#646, cast(congestion_surcharge#83 as string) AS congestion_surcharge#647, cast(airport_fee#84 as string) AS airport_fee#648, cast(taxi_type#85 as string) AS taxi_type#649, cast(Pickup_Borough#264 as string) AS Pickup_Borough#650, cast(Pickup_Zone#285 as string) AS Pickup_Zone#651, cast(Pickup_service_zone#306 as string) AS Pickup_service_zone#652, cast(Dropoff_Borough#438 as string) AS Dropoff_Borough#653, cast(Dropoff_Zone#443 as string) AS Dropoff_Zone#654, cast(Dropoff_service_zone#448 as string) AS Dropoff_service_zone#655, cast(route#539 as string) AS route#656, cast(Month#561 as string) AS Month#657]
      +- 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 ==
tpep_pickup_datetime: string, tpep_dropoff_datetime: string, passenger_count: string, trip_distance: string, payment_type: string, fare_amount: string, extra: string, mta_tax: string, tip_amount: string, tolls_amount: string, total_amount: string, congestion_surcharge: string, airport_fee: string, taxi_type: string, Pickup_Borough: string, Pickup_Zone: string, Pickup_service_zone: string, Dropoff_Borough: string, Dropoff_Zone: string, Dropoff_service_zone: string, route: string, Month: string
GlobalLimit 11
+- LocalLimit 11
   +- Project [cast(tpep_pickup_datetime#70 as string) AS tpep_pickup_datetime#636, cast(tpep_dropoff_datetime#71 as string) AS tpep_dropoff_datetime#637, cast(passenger_count#72 as string) AS passenger_count#638, cast(trip_distance#73 as string) AS trip_distance#639, cast(payment_type#76 as string) AS payment_type#640, cast(fare_amount#77 as string) AS fare_amount#641, cast(extra#78 as string) AS extra#642, cast(mta_tax#79 as string) AS mta_tax#643, cast(tip_amount#80 as string) AS tip_amount#644, cast(tolls_amount#81 as string) AS tolls_amount#645, cast(total_amount#82 as string) AS total_amount#646, cast(congestion_surcharge#83 as string) AS congestion_surcharge#647, cast(airport_fee#84 as string) AS airport_fee#648, cast(taxi_type#85 as string) AS taxi_type#649, cast(Pickup_Borough#264 as string) AS Pickup_Borough#650, cast(Pickup_Zone#285 as string) AS Pickup_Zone#651, cast(Pickup_service_zone#306 as string) AS Pickup_service_zone#652, cast(Dropoff_Borough#438 as string) AS Dropoff_Borough#653, cast(Dropoff_Zone#443 as string) AS Dropoff_Zone#654, cast(Dropoff_service_zone#448 as string) AS Dropoff_service_zone#655, cast(route#539 as string) AS route#656, cast(Month#561 as string) AS Month#657]
      +- 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 ==
GlobalLimit 11
+- LocalLimit 11
   +- 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#656, cast(month(cast(gettimestamp(tpep_pickup_datetime#70, yyyy-MM-dd HH:mm:ss, Some(GMT)) as date)) as string) AS Month#657]
      +- 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, Borough#17 AS Pickup_Borough#264, Zone#18 AS Pickup_Zone#285, service_zone#19 AS Pickup_service_zone#306]
         :  +- Join Inner, (cast(PULocationID#74 as int) = LocationID#16)
         :     :- 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
         :     +- Filter isnotnull(LocationID#16)
         :        +- Relation[LocationID#16,Borough#17,Zone#18,service_zone#19] csv
         +- Project [LocationID#16, Borough#17 AS Dropoff_Borough#438, Zone#18 AS Dropoff_Zone#443, service_zone#19 AS Dropoff_service_zone#448]
            +- Filter isnotnull(LocationID#16)
               +- Relation[LocationID#16,Borough#17,Zone#18,service_zone#19] csv

== Physical Plan ==
CollectLimit 11
+- *(3) 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#656, cast(month(cast(gettimestamp(tpep_pickup_datetime#70, yyyy-MM-dd HH:mm:ss, Some(GMT)) as date)) as string) AS Month#657]
   +- *(3) BroadcastHashJoin [cast(DOLocationID#75 as int)], [LocationID#16], Inner, BuildRight
      :- *(3) 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, Borough#17 AS Pickup_Borough#264, Zone#18 AS Pickup_Zone#285, service_zone#19 AS Pickup_service_zone#306]
      :  +- *(3) BroadcastHashJoin [cast(PULocationID#74 as int)], [LocationID#16], Inner, BuildRight
      :     :- *(3) 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]
      :     :  +- *(3) Filter (isnotnull(PULocationID#74) AND isnotnull(DOLocationID#75))
      :     :     +- FileScan csv [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] 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<tpep_pickup_datetime:string,tpep_dropoff_datetime:string,passenger_count:string,trip_dista...
      :     +- BroadcastExchange HashedRelationBroadcastMode(List(cast(input[0, int, true] as bigint))), [id=#302]
      :        +- *(1) Project [LocationID#16, Borough#17, Zone#18, service_zone#19]
      :           +- *(1) Filter isnotnull(LocationID#16)
      :              +- FileScan csv [LocationID#16,Borough#17,Zone#18,service_zone#19] 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,Borough:string,Zone:string,service_zone:string>
      +- BroadcastExchange HashedRelationBroadcastMode(List(cast(input[0, int, true] as bigint))), [id=#310]
         +- *(2) Project [LocationID#16, Borough#17 AS Dropoff_Borough#438, Zone#18 AS Dropoff_Zone#443, service_zone#19 AS Dropoff_service_zone#448]
            +- *(2) Filter isnotnull(LocationID#16)
               +- FileScan csv [LocationID#16,Borough#17,Zone#18,service_zone#19] 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,Borough:string,Zone:string,service_zone:string>