== Parsed Logical Plan ==
GlobalLimit 11
+- LocalLimit 11
+- Project [cast(tpep_pickup_datetime#70 as string) AS tpep_pickup_datetime#797, cast(tpep_dropoff_datetime#71 as string) AS tpep_dropoff_datetime#798, cast(passenger_count#72 as string) AS passenger_count#799, cast(trip_distance#73 as string) AS trip_distance#800, cast(payment_type#76 as string) AS payment_type#801, cast(fare_amount#630 as string) AS fare_amount#802, cast(extra#653 as string) AS extra#803, cast(mta_tax#676 as string) AS mta_tax#804, cast(tip_amount#584 as string) AS tip_amount#805, cast(tolls_amount#699 as string) AS tolls_amount#806, cast(total_amount#607 as string) AS total_amount#807, cast(congestion_surcharge#722 as string) AS congestion_surcharge#808, cast(airport_fee#84 as string) AS airport_fee#809, cast(taxi_type#85 as string) AS taxi_type#810, cast(Pickup_Borough#264 as string) AS Pickup_Borough#811, cast(Pickup_Zone#285 as string) AS Pickup_Zone#812, cast(Pickup_service_zone#306 as string) AS Pickup_service_zone#813, cast(Dropoff_Borough#438 as string) AS Dropoff_Borough#814, cast(Dropoff_Zone#443 as string) AS Dropoff_Zone#815, cast(Dropoff_service_zone#448 as string) AS Dropoff_service_zone#816, cast(route#539 as string) AS route#817, cast(Month#561 as string) AS Month#818]
+- 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 ==
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#797, cast(tpep_dropoff_datetime#71 as string) AS tpep_dropoff_datetime#798, cast(passenger_count#72 as string) AS passenger_count#799, cast(trip_distance#73 as string) AS trip_distance#800, cast(payment_type#76 as string) AS payment_type#801, cast(fare_amount#630 as string) AS fare_amount#802, cast(extra#653 as string) AS extra#803, cast(mta_tax#676 as string) AS mta_tax#804, cast(tip_amount#584 as string) AS tip_amount#805, cast(tolls_amount#699 as string) AS tolls_amount#806, cast(total_amount#607 as string) AS total_amount#807, cast(congestion_surcharge#722 as string) AS congestion_surcharge#808, cast(airport_fee#84 as string) AS airport_fee#809, cast(taxi_type#85 as string) AS taxi_type#810, cast(Pickup_Borough#264 as string) AS Pickup_Borough#811, cast(Pickup_Zone#285 as string) AS Pickup_Zone#812, cast(Pickup_service_zone#306 as string) AS Pickup_service_zone#813, cast(Dropoff_Borough#438 as string) AS Dropoff_Borough#814, cast(Dropoff_Zone#443 as string) AS Dropoff_Zone#815, cast(Dropoff_service_zone#448 as string) AS Dropoff_service_zone#816, cast(route#539 as string) AS route#817, cast(Month#561 as string) AS Month#818]
+- 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 ==
GlobalLimit 11
+- LocalLimit 11
+- Project [tpep_pickup_datetime#70, tpep_dropoff_datetime#71, passenger_count#72, trip_distance#73, payment_type#76, cast(cast(fare_amount#77 as decimal(10,2)) as string) AS fare_amount#802, cast(cast(extra#78 as decimal(10,2)) as string) AS extra#803, cast(cast(mta_tax#79 as decimal(10,2)) as string) AS mta_tax#804, cast(cast(tip_amount#80 as decimal(10,2)) as string) AS tip_amount#805, cast(cast(tolls_amount#81 as decimal(10,2)) as string) AS tolls_amount#806, cast(cast(total_amount#82 as decimal(10,2)) as string) AS total_amount#807, cast(cast(congestion_surcharge#83 as decimal(10,2)) as string) AS congestion_surcharge#808, 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#817, cast(month(cast(gettimestamp(tpep_pickup_datetime#70, yyyy-MM-dd HH:mm:ss, Some(GMT)) as date)) as string) AS Month#818]
+- 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, cast(cast(fare_amount#77 as decimal(10,2)) as string) AS fare_amount#802, cast(cast(extra#78 as decimal(10,2)) as string) AS extra#803, cast(cast(mta_tax#79 as decimal(10,2)) as string) AS mta_tax#804, cast(cast(tip_amount#80 as decimal(10,2)) as string) AS tip_amount#805, cast(cast(tolls_amount#81 as decimal(10,2)) as string) AS tolls_amount#806, cast(cast(total_amount#82 as decimal(10,2)) as string) AS total_amount#807, cast(cast(congestion_surcharge#83 as decimal(10,2)) as string) AS congestion_surcharge#808, 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#817, cast(month(cast(gettimestamp(tpep_pickup_datetime#70, yyyy-MM-dd HH:mm:ss, Some(GMT)) as date)) as string) AS Month#818]
+- *(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>
