| 3 |
FileScan csv [ride_id#0,rideable_type#1,started_at#2,ended_at#3,start_station_name#4,start_station_id#5,end_station_name#6,end_station_id#7,start_lat#8,start_lng#9,end_lat#10,end_lng#11,member_casual#12] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(6 paths)[s3a://rzvde-g10-chepusov-vladislav/raw/citibike_data/202508/202508-cit..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<ride_id:string,rideable_type:string,started_at:timestamp,ended_at:timestamp,start_station_...
|
Disk Memory Deserialized 1x Replicated
|
8 |
100.00% |
335.8 MiB |
0.0 B |
| 30 |
AdaptiveSparkPlan isFinalPlan=false
+- Filter (isnotnull(is_ride_id_valid#474) AND ((is_ride_id_valid#474 AND is_duration_valid#475) AND is_station_valid#476))
+- Window [row_number() windowspecdefinition(start_station_id#31, started_at#28 ASC NULLS FIRST, specifiedwindowframe(RowFrame, unboundedpreceding$(), currentrow$())) AS _start_station_ride_num#536], [start_station_id#31], [started_at#28 ASC NULLS FIRST]
+- Sort [start_station_id#31 ASC NULLS FIRST, started_at#28 ASC NULLS FIRST], false, 0
+- Exchange hashpartitioning(start_station_id#31, 200), ENSURE_REQUIREMENTS, [plan_id=68]
+- Project [ride_id#26, rideable_type#27, started_at#28, ended_at#29, start_station_name#30, start_station_id#31, end_station_name#32, end_station_id#33, start_lat#34, start_lng#35, end_lat#36, end_lng#37, member_casual#38, is_ride_id_valid#474, is_duration_valid#475, is_station_valid#476, _source_file#493, 2026-08-18 07:26:21.132535 AS _processed_dttm#494, year(cast(started_at#28 as date)) AS ye...
|
Disk Memory Deserialized 1x Replicated
|
6 |
100.00% |
306.3 MiB |
0.0 B |
| 49 |
AdaptiveSparkPlan isFinalPlan=false
+- Filter ((NOT is_ride_id_valid#474 OR NOT is_duration_valid#475) OR NOT is_station_valid#476)
+- Window [row_number() windowspecdefinition(start_station_id#31, started_at#28 ASC NULLS FIRST, specifiedwindowframe(RowFrame, unboundedpreceding$(), currentrow$())) AS _start_station_ride_num#536], [start_station_id#31], [started_at#28 ASC NULLS FIRST]
+- Sort [start_station_id#31 ASC NULLS FIRST, started_at#28 ASC NULLS FIRST], false, 0
+- Exchange hashpartitioning(start_station_id#31, 200), ENSURE_REQUIREMENTS, [plan_id=91]
+- Project [ride_id#26, rideable_type#27, started_at#28, ended_at#29, start_station_name#30, start_station_id#31, end_station_name#32, end_station_id#33, start_lat#34, start_lng#35, end_lat#36, end_lng#37, member_casual#38, is_ride_id_valid#474, is_duration_valid#475, is_station_valid#476, _source_file#493, 2026-08-18 07:26:21.350521 AS _processed_dttm#494, year(cast(started_at#28 as date)) AS year#513, month(cast(started_a...
|
Disk Memory Deserialized 1x Replicated
|
6 |
100.00% |
8.1 MiB |
0.0 B |