| Stage Id ▾ | Description | Submitted | Duration | Tasks: Succeeded/Total | Input | Output | Shuffle Read | Shuffle Write |
|---|---|---|---|---|---|---|---|---|
| 144 | csv at NativeMethodAccessorImpl.java:0
RDD: *(1) Project [ride_id#128, rideable_type#129, started_at#130, ended_at#131, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#136, start_lng#137, end_lat#138, end_lng#139, member_casual#140, _corrupt_record#141, regexp_extract(input_file_name(), [^/]+$, 0) AS _source_file#156]
+- FileScan csv [ride_id#128,rideable_type#129,started_at#130,ended_at#131,start_station_name#132,start_station_id#133,end_station_name#134,end_station_id#135,start_lat#136,start_lng#137,end_lat#138,end_lng#139,member_casual#140,_corrupt_record#141] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(2 paths)[s3a://rzvde-g11-durnev-pavel/raw/citibike_data/202602/202602-citibike-..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<ride_id:string,rideable_type:string,started_at:string,ended_at:string,start_station_name:s...
AdaptiveSparkPlan isFinalPlan=false
+- Project [ride_id#128, rideable_type#129, started_at#669, ended_at#670, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#675, start_lng#676, end_lat#677, end_lng#678, member_casual#140, _corrupt_record#141, _source_file#156, (isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AS _is_ride_id_not_empty#695, coalesce((ended_at#670 > started_at#669), false) AS _is_ended_after_started#696, coalesce(NOT (end_station_id#135 = start_station_id#133), false) AS _is_different_stations#697, ((((isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AND coalesce((ended_at#670 > started_at#669), false)) AND coalesce(NOT (end_station_id#135 = start_station_id#133), false)) AND isnull(_corrupt_record#141)) AS _is_valid#698]
+- Project [ride_id#128, rideable_type#129, cast(started_at#130 as timestamp) AS started_at#669, cast(ended_at#131 as timestamp) AS ended_at#670, start_station_name#132, start_station_id#133, end_s...AdaptiveSparkPlan isFinalPlan=false
+- Project [ride_id#3716, rideable_type#3717, started_at#3718, ended_at#3719, start_station_name#3720, start_station_id#3721, end_station_name#3722, end_station_id#3723, start_lat#3724, start_lng#3725, end_lat#3726, end_lng#3727, member_casual#3728, _corrupt_record#3279, _source_file#3294, _is_ride_id_not_empty#12608, _is_ended_after_started#12609, _is_different_stations#12610, _is_valid#12611, 2026-11-01 20:50:07.641085 AS _processed_dttm#14037]
+- Filter (isnotnull(_is_valid#12611) AND NOT _is_valid#12611)
+- InMemoryTableScan [_corrupt_record#3279, _is_different_stations#12610, _is_ended_after_started#12609, _is_ride_id_not_empty#12608, _is_valid#12611, _source_file#3294, end_lat#3726, end_lng#3727, end_station_id#3723, end_station_name#3722, ended_at#3719, member_casual#3728, ride_id#3716, rideable_type#3717, start_lat#3724, start_lng#3725, start_station_id#3721, start_station_name#3720, started_at#3718], [isnotnull(_is_valid#12611), NOT _is_valid#12611]
...
org.apache.spark.sql.DataFrameWriter.csv(DataFrameWriter.scala:850) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:52:12 | 3 s |
1/1
| 2.7 MiB | 7.5 MiB | ||
| 143 | isEmpty at NativeMethodAccessorImpl.java:0
RDD: *(1) Project [ride_id#128, rideable_type#129, started_at#130, ended_at#131, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#136, start_lng#137, end_lat#138, end_lng#139, member_casual#140, _corrupt_record#141, regexp_extract(input_file_name(), [^/]+$, 0) AS _source_file#156]
+- FileScan csv [ride_id#128,rideable_type#129,started_at#130,ended_at#131,start_station_name#132,start_station_id#133,end_station_name#134,end_station_id#135,start_lat#136,start_lng#137,end_lat#138,end_lng#139,member_casual#140,_corrupt_record#141] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(2 paths)[s3a://rzvde-g11-durnev-pavel/raw/citibike_data/202602/202602-citibike-..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<ride_id:string,rideable_type:string,started_at:string,ended_at:string,start_station_name:s...
AdaptiveSparkPlan isFinalPlan=false
+- Project [ride_id#128, rideable_type#129, started_at#669, ended_at#670, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#675, start_lng#676, end_lat#677, end_lng#678, member_casual#140, _corrupt_record#141, _source_file#156, (isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AS _is_ride_id_not_empty#695, coalesce((ended_at#670 > started_at#669), false) AS _is_ended_after_started#696, coalesce(NOT (end_station_id#135 = start_station_id#133), false) AS _is_different_stations#697, ((((isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AND coalesce((ended_at#670 > started_at#669), false)) AND coalesce(NOT (end_station_id#135 = start_station_id#133), false)) AND isnull(_corrupt_record#141)) AS _is_valid#698]
+- Project [ride_id#128, rideable_type#129, cast(started_at#130 as timestamp) AS started_at#669, cast(ended_at#131 as timestamp) AS ended_at#670, start_station_name#132, start_station_id#133, end_s...AdaptiveSparkPlan isFinalPlan=false
+- Project [ride_id#3716, rideable_type#3717, started_at#3718, ended_at#3719, start_station_name#3720, start_station_id#3721, end_station_name#3722, end_station_id#3723, start_lat#3724, start_lng#3725, end_lat#3726, end_lng#3727, member_casual#3728, _corrupt_record#3279, _source_file#3294, _is_ride_id_not_empty#12608, _is_ended_after_started#12609, _is_different_stations#12610, _is_valid#12611, 2026-11-01 20:50:07.641085 AS _processed_dttm#14037]
+- Filter (isnotnull(_is_valid#12611) AND NOT _is_valid#12611)
+- InMemoryTableScan [_corrupt_record#3279, _is_different_stations#12610, _is_ended_after_started#12609, _is_ride_id_not_empty#12608, _is_valid#12611, _source_file#3294, end_lat#3726, end_lng#3727, end_station_id#3723, end_station_name#3722, ended_at#3719, member_casual#3728, ride_id#3716, rideable_type#3717, start_lat#3724, start_lng#3725, start_station_id#3721, start_station_name#3720, started_at#3718], [isnotnull(_is_valid#12611), NOT _is_valid#12611]
...
org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:52:10 | 22 ms |
1/1
| 1369.3 KiB | |||
| 142 | parquet at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:792) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:51:44 | 12 s |
1/1
| 47.6 MiB | 98.2 MiB | ||
| 139 | parquet at NativeMethodAccessorImpl.java:0
RDD: AdaptiveSparkPlan isFinalPlan=false
+- Project [ride_id#3716, rideable_type#3717, started_at#3718, ended_at#3719, start_station_name#3720, start_station_id#3721, end_station_name#3722, end_station_id#3723, start_lat#3724, start_lng#3725, end_lat#3726, end_lng#3727, member_casual#3728, _source_file#3294, 2026-11-01 20:50:07.599499 AS _processed_dttm#13637, _start_station_ride_num#13639, year#13640, month#13641]
+- Window [row_number() windowspecdefinition(start_station_id#3721, _w0#13642, _w1#13643, started_at#3718 ASC NULLS FIRST, ride_id#3716 ASC NULLS FIRST, specifiedwindowframe(RowFrame, unboundedpreceding$(), currentrow$())) AS _start_station_ride_num#13639], [start_station_id#3721, _w0#13642, _w1#13643], [started_at#3718 ASC NULLS FIRST, ride_id#3716 ASC NULLS FIRST]
+- Sort [start_station_id#3721 ASC NULLS FIRST, _w0#13642 ASC NULLS FIRST, _w1#13643 ASC NULLS FIRST, started_at#3718 ASC NULLS FIRST, ride_id#3716 ASC NULLS FIRST], false, 0
+- Exchange hashpartitioning(start_station_id...
org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:792) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:51:42 | 1 s |
2/2
| 93.2 MiB | 98.2 MiB | ||
| 137 | isEmpty at NativeMethodAccessorImpl.java:0
RDD: AdaptiveSparkPlan isFinalPlan=false
+- Project [ride_id#3716, rideable_type#3717, started_at#3718, ended_at#3719, start_station_name#3720, start_station_id#3721, end_station_name#3722, end_station_id#3723, start_lat#3724, start_lng#3725, end_lat#3726, end_lng#3727, member_casual#3728, _source_file#3294, 2026-11-01 20:50:07.599499 AS _processed_dttm#13637, _start_station_ride_num#13639, year#13640, month#13641]
+- Window [row_number() windowspecdefinition(start_station_id#3721, _w0#13642, _w1#13643, started_at#3718 ASC NULLS FIRST, ride_id#3716 ASC NULLS FIRST, specifiedwindowframe(RowFrame, unboundedpreceding$(), currentrow$())) AS _start_station_ride_num#13639], [start_station_id#3721, _w0#13642, _w1#13643], [started_at#3718 ASC NULLS FIRST, ride_id#3716 ASC NULLS FIRST]
+- Sort [start_station_id#3721 ASC NULLS FIRST, _w0#13642 ASC NULLS FIRST, _w1#13643 ASC NULLS FIRST, started_at#3718 ASC NULLS FIRST, ride_id#3716 ASC NULLS FIRST], false, 0
+- Exchange hashpartitioning(start_station_id...
org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:51:42 | 21 ms |
1/1
| 46.4 MiB | |||
| 135 | count at <unknown>:0 org.apache.spark.sql.Dataset.count(Dataset.scala:3625) jdk.internal.reflect.GeneratedMethodAccessor94.invoke(Unknown Source) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:50:17 | 29 ms |
1/1
| 118.0 B | |||
| 133 | count at <unknown>:0
RDD: *(1) Project [ride_id#128, rideable_type#129, started_at#130, ended_at#131, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#136, start_lng#137, end_lat#138, end_lng#139, member_casual#140, _corrupt_record#141, regexp_extract(input_file_name(), [^/]+$, 0) AS _source_file#156]
+- FileScan csv [ride_id#128,rideable_type#129,started_at#130,ended_at#131,start_station_name#132,start_station_id#133,end_station_name#134,end_station_id#135,start_lat#136,start_lng#137,end_lat#138,end_lng#139,member_casual#140,_corrupt_record#141] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(2 paths)[s3a://rzvde-g11-durnev-pavel/raw/citibike_data/202602/202602-citibike-..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<ride_id:string,rideable_type:string,started_at:string,ended_at:string,start_station_name:s...
AdaptiveSparkPlan isFinalPlan=false
+- Project [ride_id#128, rideable_type#129, started_at#669, ended_at#670, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#675, start_lng#676, end_lat#677, end_lng#678, member_casual#140, _corrupt_record#141, _source_file#156, (isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AS _is_ride_id_not_empty#695, coalesce((ended_at#670 > started_at#669), false) AS _is_ended_after_started#696, coalesce(NOT (end_station_id#135 = start_station_id#133), false) AS _is_different_stations#697, ((((isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AND coalesce((ended_at#670 > started_at#669), false)) AND coalesce(NOT (end_station_id#135 = start_station_id#133), false)) AND isnull(_corrupt_record#141)) AS _is_valid#698]
+- Project [ride_id#128, rideable_type#129, cast(started_at#130 as timestamp) AS started_at#669, cast(ended_at#131 as timestamp) AS ended_at#670, start_station_name#132, start_station_id#133, end_s...AdaptiveSparkPlan isFinalPlan=false
+- Project [ride_id#3716, rideable_type#3717, started_at#3718, ended_at#3719, start_station_name#3720, start_station_id#3721, end_station_name#3722, end_station_id#3723, start_lat#3724, start_lng#3725, end_lat#3726, end_lng#3727, member_casual#3728, _corrupt_record#3279, _source_file#3294, _is_ride_id_not_empty#12608, _is_ended_after_started#12609, _is_different_stations#12610, _is_valid#12611, 2026-11-01 20:50:07.641085 AS _processed_dttm#14037]
+- Filter (isnotnull(_is_valid#12611) AND NOT _is_valid#12611)
+- InMemoryTableScan [_corrupt_record#3279, _is_different_stations#12610, _is_ended_after_started#12609, _is_ride_id_not_empty#12608, _is_valid#12611, _source_file#3294, end_lat#3726, end_lng#3727, end_station_id#3723, end_station_name#3722, ended_at#3719, member_casual#3728, ride_id#3716, rideable_type#3717, start_lat#3724, start_lng#3725, start_station_id#3721, start_station_name#3720, started_at#3718], [isnotnull(_is_valid#12611), NOT _is_valid#12611]
...
org.apache.spark.sql.Dataset.count(Dataset.scala:3625) jdk.internal.reflect.GeneratedMethodAccessor94.invoke(Unknown Source) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:50:17 | 20 ms |
2/2
| 2.7 MiB | 118.0 B | ||
| 132 | count at <unknown>:0
RDD: *(1) Project [ride_id#128, rideable_type#129, started_at#130, ended_at#131, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#136, start_lng#137, end_lat#138, end_lng#139, member_casual#140, _corrupt_record#141, regexp_extract(input_file_name(), [^/]+$, 0) AS _source_file#156]
+- FileScan csv [ride_id#128,rideable_type#129,started_at#130,ended_at#131,start_station_name#132,start_station_id#133,end_station_name#134,end_station_id#135,start_lat#136,start_lng#137,end_lat#138,end_lng#139,member_casual#140,_corrupt_record#141] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(2 paths)[s3a://rzvde-g11-durnev-pavel/raw/citibike_data/202602/202602-citibike-..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<ride_id:string,rideable_type:string,started_at:string,ended_at:string,start_station_name:s...
AdaptiveSparkPlan isFinalPlan=false
+- Project [ride_id#128, rideable_type#129, started_at#669, ended_at#670, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#675, start_lng#676, end_lat#677, end_lng#678, member_casual#140, _corrupt_record#141, _source_file#156, (isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AS _is_ride_id_not_empty#695, coalesce((ended_at#670 > started_at#669), false) AS _is_ended_after_started#696, coalesce(NOT (end_station_id#135 = start_station_id#133), false) AS _is_different_stations#697, ((((isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AND coalesce((ended_at#670 > started_at#669), false)) AND coalesce(NOT (end_station_id#135 = start_station_id#133), false)) AND isnull(_corrupt_record#141)) AS _is_valid#698]
+- Project [ride_id#128, rideable_type#129, cast(started_at#130 as timestamp) AS started_at#669, cast(ended_at#131 as timestamp) AS ended_at#670, start_station_name#132, start_station_id#133, end_s...AdaptiveSparkPlan isFinalPlan=false
+- Project [ride_id#3716, rideable_type#3717, started_at#3718, ended_at#3719, start_station_name#3720, start_station_id#3721, end_station_name#3722, end_station_id#3723, start_lat#3724, start_lng#3725, end_lat#3726, end_lng#3727, member_casual#3728, _corrupt_record#3279, _source_file#3294, _is_ride_id_not_empty#12608, _is_ended_after_started#12609, _is_different_stations#12610, _is_valid#12611, 2026-11-01 20:50:07.641085 AS _processed_dttm#14037]
+- Filter (isnotnull(_is_valid#12611) AND NOT _is_valid#12611)
+- InMemoryTableScan [_corrupt_record#3279, _is_different_stations#12610, _is_ended_after_started#12609, _is_ride_id_not_empty#12608, _is_valid#12611, _source_file#3294, end_lat#3726, end_lng#3727, end_station_id#3723, end_station_name#3722, ended_at#3719, member_casual#3728, ride_id#3716, rideable_type#3717, start_lat#3724, start_lng#3725, start_station_id#3721, start_station_name#3720, started_at#3718], [isnotnull(_is_valid#12611), NOT _is_valid#12611]
...
org.apache.spark.sql.Dataset.count(Dataset.scala:3625) jdk.internal.reflect.GeneratedMethodAccessor94.invoke(Unknown Source) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:50:16 | 0.7 s |
2/2
| 104.6 MiB | |||
| 131 | count at <unknown>:0 org.apache.spark.sql.Dataset.count(Dataset.scala:3625) jdk.internal.reflect.GeneratedMethodAccessor94.invoke(Unknown Source) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:50:16 | 20 ms |
1/1
| 118.0 B | |||
| 128 | count at <unknown>:0
RDD: AdaptiveSparkPlan isFinalPlan=false
+- Project [ride_id#3716, rideable_type#3717, started_at#3718, ended_at#3719, start_station_name#3720, start_station_id#3721, end_station_name#3722, end_station_id#3723, start_lat#3724, start_lng#3725, end_lat#3726, end_lng#3727, member_casual#3728, _source_file#3294, 2026-11-01 20:50:07.599499 AS _processed_dttm#13637, _start_station_ride_num#13639, year#13640, month#13641]
+- Window [row_number() windowspecdefinition(start_station_id#3721, _w0#13642, _w1#13643, started_at#3718 ASC NULLS FIRST, ride_id#3716 ASC NULLS FIRST, specifiedwindowframe(RowFrame, unboundedpreceding$(), currentrow$())) AS _start_station_ride_num#13639], [start_station_id#3721, _w0#13642, _w1#13643], [started_at#3718 ASC NULLS FIRST, ride_id#3716 ASC NULLS FIRST]
+- Sort [start_station_id#3721 ASC NULLS FIRST, _w0#13642 ASC NULLS FIRST, _w1#13643 ASC NULLS FIRST, started_at#3718 ASC NULLS FIRST, ride_id#3716 ASC NULLS FIRST], false, 0
+- Exchange hashpartitioning(start_station_id...
org.apache.spark.sql.Dataset.count(Dataset.scala:3625) jdk.internal.reflect.GeneratedMethodAccessor94.invoke(Unknown Source) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:50:16 | 25 ms |
2/2
| 93.2 MiB | 118.0 B | ||
| 126 | count at <unknown>:0
RDD: AdaptiveSparkPlan isFinalPlan=false
+- Project [ride_id#3716, rideable_type#3717, started_at#3718, ended_at#3719, start_station_name#3720, start_station_id#3721, end_station_name#3722, end_station_id#3723, start_lat#3724, start_lng#3725, end_lat#3726, end_lng#3727, member_casual#3728, _source_file#3294, 2026-11-01 20:50:07.599499 AS _processed_dttm#13637, _start_station_ride_num#13639, year#13640, month#13641]
+- Window [row_number() windowspecdefinition(start_station_id#3721, _w0#13642, _w1#13643, started_at#3718 ASC NULLS FIRST, ride_id#3716 ASC NULLS FIRST, specifiedwindowframe(RowFrame, unboundedpreceding$(), currentrow$())) AS _start_station_ride_num#13639], [start_station_id#3721, _w0#13642, _w1#13643], [started_at#3718 ASC NULLS FIRST, ride_id#3716 ASC NULLS FIRST]
+- Sort [start_station_id#3721 ASC NULLS FIRST, _w0#13642 ASC NULLS FIRST, _w1#13643 ASC NULLS FIRST, started_at#3718 ASC NULLS FIRST, ride_id#3716 ASC NULLS FIRST], false, 0
+- Exchange hashpartitioning(start_station_id...
org.apache.spark.sql.Dataset.count(Dataset.scala:3625) jdk.internal.reflect.GeneratedMethodAccessor94.invoke(Unknown Source) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:50:09 | 7 s |
2/2
| 86.9 MiB | |||
| 124 | count at <unknown>:0
RDD: *(1) Project [ride_id#128, rideable_type#129, started_at#130, ended_at#131, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#136, start_lng#137, end_lat#138, end_lng#139, member_casual#140, _corrupt_record#141, regexp_extract(input_file_name(), [^/]+$, 0) AS _source_file#156]
+- FileScan csv [ride_id#128,rideable_type#129,started_at#130,ended_at#131,start_station_name#132,start_station_id#133,end_station_name#134,end_station_id#135,start_lat#136,start_lng#137,end_lat#138,end_lng#139,member_casual#140,_corrupt_record#141] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(2 paths)[s3a://rzvde-g11-durnev-pavel/raw/citibike_data/202602/202602-citibike-..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<ride_id:string,rideable_type:string,started_at:string,ended_at:string,start_station_name:s...
AdaptiveSparkPlan isFinalPlan=false
+- Project [ride_id#128, rideable_type#129, started_at#669, ended_at#670, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#675, start_lng#676, end_lat#677, end_lng#678, member_casual#140, _corrupt_record#141, _source_file#156, (isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AS _is_ride_id_not_empty#695, coalesce((ended_at#670 > started_at#669), false) AS _is_ended_after_started#696, coalesce(NOT (end_station_id#135 = start_station_id#133), false) AS _is_different_stations#697, ((((isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AND coalesce((ended_at#670 > started_at#669), false)) AND coalesce(NOT (end_station_id#135 = start_station_id#133), false)) AND isnull(_corrupt_record#141)) AS _is_valid#698]
+- Project [ride_id#128, rideable_type#129, cast(started_at#130 as timestamp) AS started_at#669, cast(ended_at#131 as timestamp) AS ended_at#670, start_station_name#132, start_station_id#133, end_s...
org.apache.spark.sql.Dataset.count(Dataset.scala:3625) jdk.internal.reflect.GeneratedMethodAccessor94.invoke(Unknown Source) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:50:07 | 2 s |
2/2
| 104.6 MiB | 86.9 MiB | ||
| 123 | first at /tmp/ipykernel_920/1525886086.py:6 org.apache.spark.sql.Dataset.collectToPython(Dataset.scala:4157) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:49:34 | 30 ms |
1/1
| 124.0 B | |||
| 121 | first at /tmp/ipykernel_920/1525886086.py:6
RDD: *(1) Project [ride_id#128, rideable_type#129, started_at#130, ended_at#131, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#136, start_lng#137, end_lat#138, end_lng#139, member_casual#140, _corrupt_record#141, regexp_extract(input_file_name(), [^/]+$, 0) AS _source_file#156]
+- FileScan csv [ride_id#128,rideable_type#129,started_at#130,ended_at#131,start_station_name#132,start_station_id#133,end_station_name#134,end_station_id#135,start_lat#136,start_lng#137,end_lat#138,end_lng#139,member_casual#140,_corrupt_record#141] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(2 paths)[s3a://rzvde-g11-durnev-pavel/raw/citibike_data/202602/202602-citibike-..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<ride_id:string,rideable_type:string,started_at:string,ended_at:string,start_station_name:s...
AdaptiveSparkPlan isFinalPlan=false
+- Project [ride_id#128, rideable_type#129, started_at#669, ended_at#670, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#675, start_lng#676, end_lat#677, end_lng#678, member_casual#140, _corrupt_record#141, _source_file#156, (isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AS _is_ride_id_not_empty#695, coalesce((ended_at#670 > started_at#669), false) AS _is_ended_after_started#696, coalesce(NOT (end_station_id#135 = start_station_id#133), false) AS _is_different_stations#697, ((((isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AND coalesce((ended_at#670 > started_at#669), false)) AND coalesce(NOT (end_station_id#135 = start_station_id#133), false)) AND isnull(_corrupt_record#141)) AS _is_valid#698]
+- Project [ride_id#128, rideable_type#129, cast(started_at#130 as timestamp) AS started_at#669, cast(ended_at#131 as timestamp) AS ended_at#670, start_station_name#132, start_station_id#133, end_s...
org.apache.spark.sql.Dataset.collectToPython(Dataset.scala:4157) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:49:33 | 0.4 s |
2/2
| 104.6 MiB | 124.0 B | ||
| 120 | count at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.Dataset.count(Dataset.scala:3625) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:49:02 | 19 ms |
1/1
| 118.0 B | |||
| 118 | count at NativeMethodAccessorImpl.java:0
RDD: *(1) Project [ride_id#128, rideable_type#129, started_at#130, ended_at#131, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#136, start_lng#137, end_lat#138, end_lng#139, member_casual#140, _corrupt_record#141, regexp_extract(input_file_name(), [^/]+$, 0) AS _source_file#156]
+- FileScan csv [ride_id#128,rideable_type#129,started_at#130,ended_at#131,start_station_name#132,start_station_id#133,end_station_name#134,end_station_id#135,start_lat#136,start_lng#137,end_lat#138,end_lng#139,member_casual#140,_corrupt_record#141] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(2 paths)[s3a://rzvde-g11-durnev-pavel/raw/citibike_data/202602/202602-citibike-..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<ride_id:string,rideable_type:string,started_at:string,ended_at:string,start_station_name:s...
AdaptiveSparkPlan isFinalPlan=false
+- Project [ride_id#128, rideable_type#129, started_at#669, ended_at#670, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#675, start_lng#676, end_lat#677, end_lng#678, member_casual#140, _corrupt_record#141, _source_file#156, (isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AS _is_ride_id_not_empty#695, coalesce((ended_at#670 > started_at#669), false) AS _is_ended_after_started#696, coalesce(NOT (end_station_id#135 = start_station_id#133), false) AS _is_different_stations#697, ((((isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AND coalesce((ended_at#670 > started_at#669), false)) AND coalesce(NOT (end_station_id#135 = start_station_id#133), false)) AND isnull(_corrupt_record#141)) AS _is_valid#698]
+- Project [ride_id#128, rideable_type#129, cast(started_at#130 as timestamp) AS started_at#669, cast(ended_at#131 as timestamp) AS ended_at#670, start_station_name#132, start_station_id#133, end_s...
org.apache.spark.sql.Dataset.count(Dataset.scala:3625) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:49:02 | 23 ms |
2/2
| 104.6 MiB | 118.0 B | ||
| 117 | collect at /tmp/ipykernel_920/2164963154.py:21 org.apache.spark.sql.Dataset.collectToPython(Dataset.scala:4157) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:48:35 | 44 ms |
1/1
| 211.0 B | |||
| 114 | collect at /tmp/ipykernel_920/2164963154.py:21 org.apache.spark.sql.Dataset.collectToPython(Dataset.scala:4157) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:48:35 | 31 ms |
1/1
| 318.0 B | 211.0 B | ||
| 112 | collect at /tmp/ipykernel_920/2164963154.py:21 org.apache.spark.sql.Dataset.collectToPython(Dataset.scala:4157) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:48:35 | 55 ms |
1/1
| 318.0 B | |||
| 110 | collect at /tmp/ipykernel_920/2164963154.py:21
RDD: *(1) Project [ride_id#128, rideable_type#129, started_at#130, ended_at#131, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#136, start_lng#137, end_lat#138, end_lng#139, member_casual#140, _corrupt_record#141, regexp_extract(input_file_name(), [^/]+$, 0) AS _source_file#156]
+- FileScan csv [ride_id#128,rideable_type#129,started_at#130,ended_at#131,start_station_name#132,start_station_id#133,end_station_name#134,end_station_id#135,start_lat#136,start_lng#137,end_lat#138,end_lng#139,member_casual#140,_corrupt_record#141] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(2 paths)[s3a://rzvde-g11-durnev-pavel/raw/citibike_data/202602/202602-citibike-..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<ride_id:string,rideable_type:string,started_at:string,ended_at:string,start_station_name:s...
org.apache.spark.sql.Dataset.collectToPython(Dataset.scala:4157) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:48:35 | 0.2 s |
2/2
| 126.2 MiB | 318.0 B | ||
| 109 | count at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.Dataset.count(Dataset.scala:3625) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:48:35 | 25 ms |
1/1
| 118.0 B | |||
| 107 | count at NativeMethodAccessorImpl.java:0
RDD: *(1) Project [ride_id#128, rideable_type#129, started_at#130, ended_at#131, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#136, start_lng#137, end_lat#138, end_lng#139, member_casual#140, _corrupt_record#141, regexp_extract(input_file_name(), [^/]+$, 0) AS _source_file#156]
+- FileScan csv [ride_id#128,rideable_type#129,started_at#130,ended_at#131,start_station_name#132,start_station_id#133,end_station_name#134,end_station_id#135,start_lat#136,start_lng#137,end_lat#138,end_lng#139,member_casual#140,_corrupt_record#141] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(2 paths)[s3a://rzvde-g11-durnev-pavel/raw/citibike_data/202602/202602-citibike-..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<ride_id:string,rideable_type:string,started_at:string,ended_at:string,start_station_name:s...
org.apache.spark.sql.Dataset.count(Dataset.scala:3625) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:48:35 | 28 ms |
2/2
| 126.2 MiB | 118.0 B | ||
| 106 | isEmpty at NativeMethodAccessorImpl.java:0
RDD: *(1) Project [ride_id#128, rideable_type#129, started_at#130, ended_at#131, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#136, start_lng#137, end_lat#138, end_lng#139, member_casual#140, _corrupt_record#141, regexp_extract(input_file_name(), [^/]+$, 0) AS _source_file#156]
+- FileScan csv [ride_id#128,rideable_type#129,started_at#130,ended_at#131,start_station_name#132,start_station_id#133,end_station_name#134,end_station_id#135,start_lat#136,start_lng#137,end_lat#138,end_lng#139,member_casual#140,_corrupt_record#141] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(2 paths)[s3a://rzvde-g11-durnev-pavel/raw/citibike_data/202602/202602-citibike-..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<ride_id:string,rideable_type:string,started_at:string,ended_at:string,start_station_name:s...
org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:48:35 | 30 ms |
1/1
| 65.2 MiB | |||
| 105 | count at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.Dataset.count(Dataset.scala:3625) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:44:24 | 23 ms |
1/1
| 118.0 B | |||
| 103 | count at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.Dataset.count(Dataset.scala:3625) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:44:23 | 0.8 s |
2/2
| 7.5 MiB | 118.0 B | ||
| 102 | csv at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.DataFrameReader.csv(DataFrameReader.scala:538) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:44:22 | 0.3 s |
1/1
| 7.6 KiB | |||
| 101 | count at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.Dataset.count(Dataset.scala:3625) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:44:22 | 21 ms |
1/1
| 115.0 B | |||
| 99 | count at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.Dataset.count(Dataset.scala:3625) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:44:21 | 0.6 s |
2/2
| 7.4 KiB | 115.0 B | ||
| 98 | parquet at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.DataFrameReader.parquet(DataFrameReader.scala:563) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:44:21 | 0.3 s |
1/1
| ||||
| 97 | csv at NativeMethodAccessorImpl.java:0
RDD: *(1) Project [ride_id#128, rideable_type#129, started_at#130, ended_at#131, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#136, start_lng#137, end_lat#138, end_lng#139, member_casual#140, _corrupt_record#141, regexp_extract(input_file_name(), [^/]+$, 0) AS _source_file#156]
+- FileScan csv [ride_id#128,rideable_type#129,started_at#130,ended_at#131,start_station_name#132,start_station_id#133,end_station_name#134,end_station_id#135,start_lat#136,start_lng#137,end_lat#138,end_lng#139,member_casual#140,_corrupt_record#141] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(2 paths)[s3a://rzvde-g11-durnev-pavel/raw/citibike_data/202602/202602-citibike-..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<ride_id:string,rideable_type:string,started_at:string,ended_at:string,start_station_name:s...
AdaptiveSparkPlan isFinalPlan=false
+- Project [ride_id#128, rideable_type#129, started_at#669, ended_at#670, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#675, start_lng#676, end_lat#677, end_lng#678, member_casual#140, _corrupt_record#141, _source_file#156, (isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AS _is_ride_id_not_empty#695, coalesce((ended_at#670 > started_at#669), false) AS _is_ended_after_started#696, coalesce(NOT (end_station_id#135 = start_station_id#133), false) AS _is_different_stations#697, ((((isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AND coalesce((ended_at#670 > started_at#669), false)) AND coalesce(NOT (end_station_id#135 = start_station_id#133), false)) AND isnull(_corrupt_record#141)) AS _is_valid#698]
+- Project [ride_id#128, rideable_type#129, cast(started_at#130 as timestamp) AS started_at#669, cast(ended_at#131 as timestamp) AS ended_at#670, start_station_name#132, start_station_id#133, end_s...
org.apache.spark.sql.DataFrameWriter.csv(DataFrameWriter.scala:850) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:44:07 | 4 s |
1/1
| 104.6 MiB | 7.5 MiB | ||
| 96 | parquet at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:792) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:42:51 | 12 s |
1/1
| 47.6 MiB | 98.2 MiB | ||
| 93 | parquet at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:792) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:42:47 | 3 s |
2/2
| 86.9 MiB | 98.2 MiB | ||
| 91 | parquet at NativeMethodAccessorImpl.java:0
RDD: *(1) Project [ride_id#128, rideable_type#129, started_at#130, ended_at#131, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#136, start_lng#137, end_lat#138, end_lng#139, member_casual#140, _corrupt_record#141, regexp_extract(input_file_name(), [^/]+$, 0) AS _source_file#156]
+- FileScan csv [ride_id#128,rideable_type#129,started_at#130,ended_at#131,start_station_name#132,start_station_id#133,end_station_name#134,end_station_id#135,start_lat#136,start_lng#137,end_lat#138,end_lng#139,member_casual#140,_corrupt_record#141] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(2 paths)[s3a://rzvde-g11-durnev-pavel/raw/citibike_data/202602/202602-citibike-..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<ride_id:string,rideable_type:string,started_at:string,ended_at:string,start_station_name:s...
AdaptiveSparkPlan isFinalPlan=false
+- Project [ride_id#128, rideable_type#129, started_at#669, ended_at#670, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#675, start_lng#676, end_lat#677, end_lng#678, member_casual#140, _corrupt_record#141, _source_file#156, (isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AS _is_ride_id_not_empty#695, coalesce((ended_at#670 > started_at#669), false) AS _is_ended_after_started#696, coalesce(NOT (end_station_id#135 = start_station_id#133), false) AS _is_different_stations#697, ((((isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AND coalesce((ended_at#670 > started_at#669), false)) AND coalesce(NOT (end_station_id#135 = start_station_id#133), false)) AND isnull(_corrupt_record#141)) AS _is_valid#698]
+- Project [ride_id#128, rideable_type#129, cast(started_at#130 as timestamp) AS started_at#669, cast(ended_at#131 as timestamp) AS ended_at#670, start_station_name#132, start_station_id#133, end_s...
org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:792) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:42:45 | 2 s |
2/2
| 104.6 MiB | 86.9 MiB | ||
| 90 | count at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.Dataset.count(Dataset.scala:3625) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:42:41 | 22 ms |
1/1
| 118.0 B | |||
| 88 | count at NativeMethodAccessorImpl.java:0
RDD: *(1) Project [ride_id#128, rideable_type#129, started_at#130, ended_at#131, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#136, start_lng#137, end_lat#138, end_lng#139, member_casual#140, _corrupt_record#141, regexp_extract(input_file_name(), [^/]+$, 0) AS _source_file#156]
+- FileScan csv [ride_id#128,rideable_type#129,started_at#130,ended_at#131,start_station_name#132,start_station_id#133,end_station_name#134,end_station_id#135,start_lat#136,start_lng#137,end_lat#138,end_lng#139,member_casual#140,_corrupt_record#141] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(2 paths)[s3a://rzvde-g11-durnev-pavel/raw/citibike_data/202602/202602-citibike-..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<ride_id:string,rideable_type:string,started_at:string,ended_at:string,start_station_name:s...
AdaptiveSparkPlan isFinalPlan=false
+- Project [ride_id#128, rideable_type#129, started_at#669, ended_at#670, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#675, start_lng#676, end_lat#677, end_lng#678, member_casual#140, _corrupt_record#141, _source_file#156, (isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AS _is_ride_id_not_empty#695, coalesce((ended_at#670 > started_at#669), false) AS _is_ended_after_started#696, coalesce(NOT (end_station_id#135 = start_station_id#133), false) AS _is_different_stations#697, ((((isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AND coalesce((ended_at#670 > started_at#669), false)) AND coalesce(NOT (end_station_id#135 = start_station_id#133), false)) AND isnull(_corrupt_record#141)) AS _is_valid#698]
+- Project [ride_id#128, rideable_type#129, cast(started_at#130 as timestamp) AS started_at#669, cast(ended_at#131 as timestamp) AS ended_at#670, start_station_name#132, start_station_id#133, end_s...
org.apache.spark.sql.Dataset.count(Dataset.scala:3625) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:42:41 | 40 ms |
2/2
| 104.6 MiB | 118.0 B | ||
| 87 | count at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.Dataset.count(Dataset.scala:3625) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:42:41 | 27 ms |
1/1
| 118.0 B | |||
| 85 | count at NativeMethodAccessorImpl.java:0
RDD: *(1) Project [ride_id#128, rideable_type#129, started_at#130, ended_at#131, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#136, start_lng#137, end_lat#138, end_lng#139, member_casual#140, _corrupt_record#141, regexp_extract(input_file_name(), [^/]+$, 0) AS _source_file#156]
+- FileScan csv [ride_id#128,rideable_type#129,started_at#130,ended_at#131,start_station_name#132,start_station_id#133,end_station_name#134,end_station_id#135,start_lat#136,start_lng#137,end_lat#138,end_lng#139,member_casual#140,_corrupt_record#141] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(2 paths)[s3a://rzvde-g11-durnev-pavel/raw/citibike_data/202602/202602-citibike-..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<ride_id:string,rideable_type:string,started_at:string,ended_at:string,start_station_name:s...
AdaptiveSparkPlan isFinalPlan=false
+- Project [ride_id#128, rideable_type#129, started_at#669, ended_at#670, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#675, start_lng#676, end_lat#677, end_lng#678, member_casual#140, _corrupt_record#141, _source_file#156, (isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AS _is_ride_id_not_empty#695, coalesce((ended_at#670 > started_at#669), false) AS _is_ended_after_started#696, coalesce(NOT (end_station_id#135 = start_station_id#133), false) AS _is_different_stations#697, ((((isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AND coalesce((ended_at#670 > started_at#669), false)) AND coalesce(NOT (end_station_id#135 = start_station_id#133), false)) AND isnull(_corrupt_record#141)) AS _is_valid#698]
+- Project [ride_id#128, rideable_type#129, cast(started_at#130 as timestamp) AS started_at#669, cast(ended_at#131 as timestamp) AS ended_at#670, start_station_name#132, start_station_id#133, end_s...
org.apache.spark.sql.Dataset.count(Dataset.scala:3625) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:42:41 | 44 ms |
2/2
| 104.6 MiB | 118.0 B | ||
| 84 | count at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.Dataset.count(Dataset.scala:3625) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:42:41 | 23 ms |
1/1
| 118.0 B | |||
| 82 | count at NativeMethodAccessorImpl.java:0
RDD: *(1) Project [ride_id#128, rideable_type#129, started_at#130, ended_at#131, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#136, start_lng#137, end_lat#138, end_lng#139, member_casual#140, _corrupt_record#141, regexp_extract(input_file_name(), [^/]+$, 0) AS _source_file#156]
+- FileScan csv [ride_id#128,rideable_type#129,started_at#130,ended_at#131,start_station_name#132,start_station_id#133,end_station_name#134,end_station_id#135,start_lat#136,start_lng#137,end_lat#138,end_lng#139,member_casual#140,_corrupt_record#141] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(2 paths)[s3a://rzvde-g11-durnev-pavel/raw/citibike_data/202602/202602-citibike-..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<ride_id:string,rideable_type:string,started_at:string,ended_at:string,start_station_name:s...
AdaptiveSparkPlan isFinalPlan=false
+- Project [ride_id#128, rideable_type#129, started_at#669, ended_at#670, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#675, start_lng#676, end_lat#677, end_lng#678, member_casual#140, _corrupt_record#141, _source_file#156, (isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AS _is_ride_id_not_empty#695, coalesce((ended_at#670 > started_at#669), false) AS _is_ended_after_started#696, coalesce(NOT (end_station_id#135 = start_station_id#133), false) AS _is_different_stations#697, ((((isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AND coalesce((ended_at#670 > started_at#669), false)) AND coalesce(NOT (end_station_id#135 = start_station_id#133), false)) AND isnull(_corrupt_record#141)) AS _is_valid#698]
+- Project [ride_id#128, rideable_type#129, cast(started_at#130 as timestamp) AS started_at#669, cast(ended_at#131 as timestamp) AS ended_at#670, start_station_name#132, start_station_id#133, end_s...
org.apache.spark.sql.Dataset.count(Dataset.scala:3625) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:42:41 | 31 ms |
2/2
| 104.6 MiB | 118.0 B | ||
| 81 | showString at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.Dataset.showString(Dataset.scala:315) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:42:15 | 2 s |
2/2
| 33.6 MiB | |||
| 79 | showString at NativeMethodAccessorImpl.java:0
RDD: *(1) Project [ride_id#128, rideable_type#129, started_at#130, ended_at#131, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#136, start_lng#137, end_lat#138, end_lng#139, member_casual#140, _corrupt_record#141, regexp_extract(input_file_name(), [^/]+$, 0) AS _source_file#156]
+- FileScan csv [ride_id#128,rideable_type#129,started_at#130,ended_at#131,start_station_name#132,start_station_id#133,end_station_name#134,end_station_id#135,start_lat#136,start_lng#137,end_lat#138,end_lng#139,member_casual#140,_corrupt_record#141] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(2 paths)[s3a://rzvde-g11-durnev-pavel/raw/citibike_data/202602/202602-citibike-..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<ride_id:string,rideable_type:string,started_at:string,ended_at:string,start_station_name:s...
AdaptiveSparkPlan isFinalPlan=false
+- Project [ride_id#128, rideable_type#129, started_at#669, ended_at#670, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#675, start_lng#676, end_lat#677, end_lng#678, member_casual#140, _corrupt_record#141, _source_file#156, (isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AS _is_ride_id_not_empty#695, coalesce((ended_at#670 > started_at#669), false) AS _is_ended_after_started#696, coalesce(NOT (end_station_id#135 = start_station_id#133), false) AS _is_different_stations#697, ((((isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AND coalesce((ended_at#670 > started_at#669), false)) AND coalesce(NOT (end_station_id#135 = start_station_id#133), false)) AND isnull(_corrupt_record#141)) AS _is_valid#698]
+- Project [ride_id#128, rideable_type#129, cast(started_at#130 as timestamp) AS started_at#669, cast(ended_at#131 as timestamp) AS ended_at#670, start_station_name#132, start_station_id#133, end_s...
org.apache.spark.sql.Dataset.showString(Dataset.scala:315) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:42:14 | 1 s |
2/2
| 104.6 MiB | 33.6 MiB | ||
| 78 | parquet at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:792) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:41:03 | 11 s |
1/1
| 47.6 MiB | 98.2 MiB | ||
| 75 | parquet at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:792) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:40:59 | 3 s |
2/2
| 86.9 MiB | 98.2 MiB | ||
| 73 | parquet at NativeMethodAccessorImpl.java:0
RDD: *(1) Project [ride_id#128, rideable_type#129, started_at#130, ended_at#131, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#136, start_lng#137, end_lat#138, end_lng#139, member_casual#140, _corrupt_record#141, regexp_extract(input_file_name(), [^/]+$, 0) AS _source_file#156]
+- FileScan csv [ride_id#128,rideable_type#129,started_at#130,ended_at#131,start_station_name#132,start_station_id#133,end_station_name#134,end_station_id#135,start_lat#136,start_lng#137,end_lat#138,end_lng#139,member_casual#140,_corrupt_record#141] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(2 paths)[s3a://rzvde-g11-durnev-pavel/raw/citibike_data/202602/202602-citibike-..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<ride_id:string,rideable_type:string,started_at:string,ended_at:string,start_station_name:s...
AdaptiveSparkPlan isFinalPlan=false
+- Project [ride_id#128, rideable_type#129, started_at#669, ended_at#670, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#675, start_lng#676, end_lat#677, end_lng#678, member_casual#140, _corrupt_record#141, _source_file#156, (isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AS _is_ride_id_not_empty#695, coalesce((ended_at#670 > started_at#669), false) AS _is_ended_after_started#696, coalesce(NOT (end_station_id#135 = start_station_id#133), false) AS _is_different_stations#697, ((((isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AND coalesce((ended_at#670 > started_at#669), false)) AND coalesce(NOT (end_station_id#135 = start_station_id#133), false)) AND isnull(_corrupt_record#141)) AS _is_valid#698]
+- Project [ride_id#128, rideable_type#129, cast(started_at#130 as timestamp) AS started_at#669, cast(ended_at#131 as timestamp) AS ended_at#670, start_station_name#132, start_station_id#133, end_s...
org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:792) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:40:57 | 2 s |
2/2
| 104.6 MiB | 86.9 MiB | ||
| 72 | parquet at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:792) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:35:45 | 11 s |
1/1
| 47.6 MiB | 98.2 MiB | ||
| 69 | parquet at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:792) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:35:40 | 4 s |
2/2
| 86.9 MiB | 98.2 MiB | ||
| 67 | parquet at NativeMethodAccessorImpl.java:0
RDD: *(1) Project [ride_id#128, rideable_type#129, started_at#130, ended_at#131, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#136, start_lng#137, end_lat#138, end_lng#139, member_casual#140, _corrupt_record#141, regexp_extract(input_file_name(), [^/]+$, 0) AS _source_file#156]
+- FileScan csv [ride_id#128,rideable_type#129,started_at#130,ended_at#131,start_station_name#132,start_station_id#133,end_station_name#134,end_station_id#135,start_lat#136,start_lng#137,end_lat#138,end_lng#139,member_casual#140,_corrupt_record#141] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(2 paths)[s3a://rzvde-g11-durnev-pavel/raw/citibike_data/202602/202602-citibike-..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<ride_id:string,rideable_type:string,started_at:string,ended_at:string,start_station_name:s...
AdaptiveSparkPlan isFinalPlan=false
+- Project [ride_id#128, rideable_type#129, started_at#669, ended_at#670, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#675, start_lng#676, end_lat#677, end_lng#678, member_casual#140, _corrupt_record#141, _source_file#156, (isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AS _is_ride_id_not_empty#695, coalesce((ended_at#670 > started_at#669), false) AS _is_ended_after_started#696, coalesce(NOT (end_station_id#135 = start_station_id#133), false) AS _is_different_stations#697, ((((isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AND coalesce((ended_at#670 > started_at#669), false)) AND coalesce(NOT (end_station_id#135 = start_station_id#133), false)) AND isnull(_corrupt_record#141)) AS _is_valid#698]
+- Project [ride_id#128, rideable_type#129, cast(started_at#130 as timestamp) AS started_at#669, cast(ended_at#131 as timestamp) AS ended_at#670, start_station_name#132, start_station_id#133, end_s...
org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:792) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:35:38 | 2 s |
2/2
| 104.6 MiB | 86.9 MiB | ||
| 66 | count at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.Dataset.count(Dataset.scala:3625) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:35:09 | 25 ms |
1/1
| 118.0 B | |||
| 64 | count at NativeMethodAccessorImpl.java:0
RDD: *(1) Project [ride_id#128, rideable_type#129, started_at#130, ended_at#131, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#136, start_lng#137, end_lat#138, end_lng#139, member_casual#140, _corrupt_record#141, regexp_extract(input_file_name(), [^/]+$, 0) AS _source_file#156]
+- FileScan csv [ride_id#128,rideable_type#129,started_at#130,ended_at#131,start_station_name#132,start_station_id#133,end_station_name#134,end_station_id#135,start_lat#136,start_lng#137,end_lat#138,end_lng#139,member_casual#140,_corrupt_record#141] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(2 paths)[s3a://rzvde-g11-durnev-pavel/raw/citibike_data/202602/202602-citibike-..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<ride_id:string,rideable_type:string,started_at:string,ended_at:string,start_station_name:s...
AdaptiveSparkPlan isFinalPlan=false
+- Project [ride_id#128, rideable_type#129, started_at#669, ended_at#670, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#675, start_lng#676, end_lat#677, end_lng#678, member_casual#140, _corrupt_record#141, _source_file#156, (isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AS _is_ride_id_not_empty#695, coalesce((ended_at#670 > started_at#669), false) AS _is_ended_after_started#696, coalesce(NOT (end_station_id#135 = start_station_id#133), false) AS _is_different_stations#697, ((((isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AND coalesce((ended_at#670 > started_at#669), false)) AND coalesce(NOT (end_station_id#135 = start_station_id#133), false)) AND isnull(_corrupt_record#141)) AS _is_valid#698]
+- Project [ride_id#128, rideable_type#129, cast(started_at#130 as timestamp) AS started_at#669, cast(ended_at#131 as timestamp) AS ended_at#670, start_station_name#132, start_station_id#133, end_s...
org.apache.spark.sql.Dataset.count(Dataset.scala:3625) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:35:09 | 86 ms |
2/2
| 104.6 MiB | 118.0 B | ||
| 63 | count at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.Dataset.count(Dataset.scala:3625) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:35:09 | 24 ms |
1/1
| 118.0 B | |||
| 61 | count at NativeMethodAccessorImpl.java:0
RDD: *(1) Project [ride_id#128, rideable_type#129, started_at#130, ended_at#131, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#136, start_lng#137, end_lat#138, end_lng#139, member_casual#140, _corrupt_record#141, regexp_extract(input_file_name(), [^/]+$, 0) AS _source_file#156]
+- FileScan csv [ride_id#128,rideable_type#129,started_at#130,ended_at#131,start_station_name#132,start_station_id#133,end_station_name#134,end_station_id#135,start_lat#136,start_lng#137,end_lat#138,end_lng#139,member_casual#140,_corrupt_record#141] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(2 paths)[s3a://rzvde-g11-durnev-pavel/raw/citibike_data/202602/202602-citibike-..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<ride_id:string,rideable_type:string,started_at:string,ended_at:string,start_station_name:s...
AdaptiveSparkPlan isFinalPlan=false
+- Project [ride_id#128, rideable_type#129, started_at#669, ended_at#670, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#675, start_lng#676, end_lat#677, end_lng#678, member_casual#140, _corrupt_record#141, _source_file#156, (isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AS _is_ride_id_not_empty#695, coalesce((ended_at#670 > started_at#669), false) AS _is_ended_after_started#696, coalesce(NOT (end_station_id#135 = start_station_id#133), false) AS _is_different_stations#697, ((((isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AND coalesce((ended_at#670 > started_at#669), false)) AND coalesce(NOT (end_station_id#135 = start_station_id#133), false)) AND isnull(_corrupt_record#141)) AS _is_valid#698]
+- Project [ride_id#128, rideable_type#129, cast(started_at#130 as timestamp) AS started_at#669, cast(ended_at#131 as timestamp) AS ended_at#670, start_station_name#132, start_station_id#133, end_s...
org.apache.spark.sql.Dataset.count(Dataset.scala:3625) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:35:09 | 73 ms |
2/2
| 104.6 MiB | 118.0 B | ||
| 60 | count at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.Dataset.count(Dataset.scala:3625) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:35:09 | 25 ms |
1/1
| 118.0 B | |||
| 58 | count at NativeMethodAccessorImpl.java:0
RDD: *(1) Project [ride_id#128, rideable_type#129, started_at#130, ended_at#131, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#136, start_lng#137, end_lat#138, end_lng#139, member_casual#140, _corrupt_record#141, regexp_extract(input_file_name(), [^/]+$, 0) AS _source_file#156]
+- FileScan csv [ride_id#128,rideable_type#129,started_at#130,ended_at#131,start_station_name#132,start_station_id#133,end_station_name#134,end_station_id#135,start_lat#136,start_lng#137,end_lat#138,end_lng#139,member_casual#140,_corrupt_record#141] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(2 paths)[s3a://rzvde-g11-durnev-pavel/raw/citibike_data/202602/202602-citibike-..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<ride_id:string,rideable_type:string,started_at:string,ended_at:string,start_station_name:s...
AdaptiveSparkPlan isFinalPlan=false
+- Project [ride_id#128, rideable_type#129, started_at#669, ended_at#670, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#675, start_lng#676, end_lat#677, end_lng#678, member_casual#140, _corrupt_record#141, _source_file#156, (isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AS _is_ride_id_not_empty#695, coalesce((ended_at#670 > started_at#669), false) AS _is_ended_after_started#696, coalesce(NOT (end_station_id#135 = start_station_id#133), false) AS _is_different_stations#697, ((((isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AND coalesce((ended_at#670 > started_at#669), false)) AND coalesce(NOT (end_station_id#135 = start_station_id#133), false)) AND isnull(_corrupt_record#141)) AS _is_valid#698]
+- Project [ride_id#128, rideable_type#129, cast(started_at#130 as timestamp) AS started_at#669, cast(ended_at#131 as timestamp) AS ended_at#670, start_station_name#132, start_station_id#133, end_s...
org.apache.spark.sql.Dataset.count(Dataset.scala:3625) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 20:35:08 | 0.1 s |
2/2
| 104.6 MiB | 118.0 B | ||
| 57 | count at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.Dataset.count(Dataset.scala:3625) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 19:48:26 | 22 ms |
1/1
| 118.0 B | |||
| 55 | count at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.Dataset.count(Dataset.scala:3625) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 19:48:25 | 0.8 s |
2/2
| 7.5 MiB | 118.0 B | ||
| 54 | csv at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.DataFrameReader.csv(DataFrameReader.scala:538) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 19:48:25 | 0.2 s |
1/1
| 7.6 KiB | |||
| 53 | count at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.Dataset.count(Dataset.scala:3625) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 19:48:24 | 25 ms |
1/1
| 115.0 B | |||
| 51 | count at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.Dataset.count(Dataset.scala:3625) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 19:48:24 | 0.5 s |
2/2
| 7.4 KiB | 115.0 B | ||
| 50 | parquet at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.DataFrameReader.parquet(DataFrameReader.scala:563) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 19:48:23 | 0.4 s |
1/1
| ||||
| 49 | csv at NativeMethodAccessorImpl.java:0
RDD: *(1) Project [ride_id#128, rideable_type#129, started_at#130, ended_at#131, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#136, start_lng#137, end_lat#138, end_lng#139, member_casual#140, _corrupt_record#141, regexp_extract(input_file_name(), [^/]+$, 0) AS _source_file#156]
+- FileScan csv [ride_id#128,rideable_type#129,started_at#130,ended_at#131,start_station_name#132,start_station_id#133,end_station_name#134,end_station_id#135,start_lat#136,start_lng#137,end_lat#138,end_lng#139,member_casual#140,_corrupt_record#141] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(2 paths)[s3a://rzvde-g11-durnev-pavel/raw/citibike_data/202602/202602-citibike-..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<ride_id:string,rideable_type:string,started_at:string,ended_at:string,start_station_name:s...
AdaptiveSparkPlan isFinalPlan=false
+- Project [ride_id#128, rideable_type#129, started_at#669, ended_at#670, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#675, start_lng#676, end_lat#677, end_lng#678, member_casual#140, _corrupt_record#141, _source_file#156, (isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AS _is_ride_id_not_empty#695, coalesce((ended_at#670 > started_at#669), false) AS _is_ended_after_started#696, coalesce(NOT (end_station_id#135 = start_station_id#133), false) AS _is_different_stations#697, ((((isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AND coalesce((ended_at#670 > started_at#669), false)) AND coalesce(NOT (end_station_id#135 = start_station_id#133), false)) AND isnull(_corrupt_record#141)) AS _is_valid#698]
+- Project [ride_id#128, rideable_type#129, cast(started_at#130 as timestamp) AS started_at#669, cast(ended_at#131 as timestamp) AS ended_at#670, start_station_name#132, start_station_id#133, end_s...
org.apache.spark.sql.DataFrameWriter.csv(DataFrameWriter.scala:850) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 19:48:15 | 4 s |
1/1
| 104.6 MiB | 7.5 MiB | ||
| 48 | parquet at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:792) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 19:47:35 | 11 s |
1/1
| 47.6 MiB | 98.2 MiB | ||
| 45 | parquet at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:792) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 19:47:30 | 4 s |
2/2
| 86.9 MiB | 98.2 MiB | ||
| 43 | parquet at NativeMethodAccessorImpl.java:0
RDD: *(1) Project [ride_id#128, rideable_type#129, started_at#130, ended_at#131, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#136, start_lng#137, end_lat#138, end_lng#139, member_casual#140, _corrupt_record#141, regexp_extract(input_file_name(), [^/]+$, 0) AS _source_file#156]
+- FileScan csv [ride_id#128,rideable_type#129,started_at#130,ended_at#131,start_station_name#132,start_station_id#133,end_station_name#134,end_station_id#135,start_lat#136,start_lng#137,end_lat#138,end_lng#139,member_casual#140,_corrupt_record#141] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(2 paths)[s3a://rzvde-g11-durnev-pavel/raw/citibike_data/202602/202602-citibike-..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<ride_id:string,rideable_type:string,started_at:string,ended_at:string,start_station_name:s...
AdaptiveSparkPlan isFinalPlan=false
+- Project [ride_id#128, rideable_type#129, started_at#669, ended_at#670, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#675, start_lng#676, end_lat#677, end_lng#678, member_casual#140, _corrupt_record#141, _source_file#156, (isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AS _is_ride_id_not_empty#695, coalesce((ended_at#670 > started_at#669), false) AS _is_ended_after_started#696, coalesce(NOT (end_station_id#135 = start_station_id#133), false) AS _is_different_stations#697, ((((isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AND coalesce((ended_at#670 > started_at#669), false)) AND coalesce(NOT (end_station_id#135 = start_station_id#133), false)) AND isnull(_corrupt_record#141)) AS _is_valid#698]
+- Project [ride_id#128, rideable_type#129, cast(started_at#130 as timestamp) AS started_at#669, cast(ended_at#131 as timestamp) AS ended_at#670, start_station_name#132, start_station_id#133, end_s...
org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:792) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 19:47:28 | 2 s |
2/2
| 104.6 MiB | 86.9 MiB | ||
| 42 | showString at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.Dataset.showString(Dataset.scala:315) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 19:47:19 | 3 s |
2/2
| 33.6 MiB | |||
| 40 | showString at NativeMethodAccessorImpl.java:0
RDD: *(1) Project [ride_id#128, rideable_type#129, started_at#130, ended_at#131, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#136, start_lng#137, end_lat#138, end_lng#139, member_casual#140, _corrupt_record#141, regexp_extract(input_file_name(), [^/]+$, 0) AS _source_file#156]
+- FileScan csv [ride_id#128,rideable_type#129,started_at#130,ended_at#131,start_station_name#132,start_station_id#133,end_station_name#134,end_station_id#135,start_lat#136,start_lng#137,end_lat#138,end_lng#139,member_casual#140,_corrupt_record#141] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(2 paths)[s3a://rzvde-g11-durnev-pavel/raw/citibike_data/202602/202602-citibike-..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<ride_id:string,rideable_type:string,started_at:string,ended_at:string,start_station_name:s...
AdaptiveSparkPlan isFinalPlan=false
+- Project [ride_id#128, rideable_type#129, started_at#669, ended_at#670, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#675, start_lng#676, end_lat#677, end_lng#678, member_casual#140, _corrupt_record#141, _source_file#156, (isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AS _is_ride_id_not_empty#695, coalesce((ended_at#670 > started_at#669), false) AS _is_ended_after_started#696, coalesce(NOT (end_station_id#135 = start_station_id#133), false) AS _is_different_stations#697, ((((isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AND coalesce((ended_at#670 > started_at#669), false)) AND coalesce(NOT (end_station_id#135 = start_station_id#133), false)) AND isnull(_corrupt_record#141)) AS _is_valid#698]
+- Project [ride_id#128, rideable_type#129, cast(started_at#130 as timestamp) AS started_at#669, cast(ended_at#131 as timestamp) AS ended_at#670, start_station_name#132, start_station_id#133, end_s...
org.apache.spark.sql.Dataset.showString(Dataset.scala:315) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 19:47:17 | 2 s |
2/2
| 104.6 MiB | 33.6 MiB | ||
| 39 | showString at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.Dataset.showString(Dataset.scala:315) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 19:47:10 | 46 ms |
1/1
| 146.0 B | |||
| 37 | showString at NativeMethodAccessorImpl.java:0
RDD: *(1) Project [ride_id#128, rideable_type#129, started_at#130, ended_at#131, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#136, start_lng#137, end_lat#138, end_lng#139, member_casual#140, _corrupt_record#141, regexp_extract(input_file_name(), [^/]+$, 0) AS _source_file#156]
+- FileScan csv [ride_id#128,rideable_type#129,started_at#130,ended_at#131,start_station_name#132,start_station_id#133,end_station_name#134,end_station_id#135,start_lat#136,start_lng#137,end_lat#138,end_lng#139,member_casual#140,_corrupt_record#141] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(2 paths)[s3a://rzvde-g11-durnev-pavel/raw/citibike_data/202602/202602-citibike-..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<ride_id:string,rideable_type:string,started_at:string,ended_at:string,start_station_name:s...
AdaptiveSparkPlan isFinalPlan=false
+- Project [ride_id#128, rideable_type#129, started_at#669, ended_at#670, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#675, start_lng#676, end_lat#677, end_lng#678, member_casual#140, _corrupt_record#141, _source_file#156, (isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AS _is_ride_id_not_empty#695, coalesce((ended_at#670 > started_at#669), false) AS _is_ended_after_started#696, coalesce(NOT (end_station_id#135 = start_station_id#133), false) AS _is_different_stations#697, ((((isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AND coalesce((ended_at#670 > started_at#669), false)) AND coalesce(NOT (end_station_id#135 = start_station_id#133), false)) AND isnull(_corrupt_record#141)) AS _is_valid#698]
+- Project [ride_id#128, rideable_type#129, cast(started_at#130 as timestamp) AS started_at#669, cast(ended_at#131 as timestamp) AS ended_at#670, start_station_name#132, start_station_id#133, end_s...
org.apache.spark.sql.Dataset.showString(Dataset.scala:315) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 19:47:09 | 0.2 s |
2/2
| 104.6 MiB | 146.0 B | ||
| 36 | showString at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.Dataset.showString(Dataset.scala:315) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 19:42:12 | 33 ms |
1/1
| 318.0 B | |||
| 34 | showString at NativeMethodAccessorImpl.java:0
RDD: *(1) Project [ride_id#128, rideable_type#129, started_at#130, ended_at#131, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#136, start_lng#137, end_lat#138, end_lng#139, member_casual#140, _corrupt_record#141, regexp_extract(input_file_name(), [^/]+$, 0) AS _source_file#156]
+- FileScan csv [ride_id#128,rideable_type#129,started_at#130,ended_at#131,start_station_name#132,start_station_id#133,end_station_name#134,end_station_id#135,start_lat#136,start_lng#137,end_lat#138,end_lng#139,member_casual#140,_corrupt_record#141] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(2 paths)[s3a://rzvde-g11-durnev-pavel/raw/citibike_data/202602/202602-citibike-..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<ride_id:string,rideable_type:string,started_at:string,ended_at:string,start_station_name:s...
org.apache.spark.sql.Dataset.showString(Dataset.scala:315) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 19:42:11 | 0.2 s |
2/2
| 126.2 MiB | 318.0 B | ||
| 33 | showString at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.Dataset.showString(Dataset.scala:315) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 19:41:55 | 34 ms |
1/1
| 290.0 B | |||
| 31 | showString at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.Dataset.showString(Dataset.scala:315) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 19:41:53 | 1 s |
2/2
| 40.8 MiB | 290.0 B | ||
| 30 | showString at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.Dataset.showString(Dataset.scala:315) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 19:41:53 | 56 ms |
1/1
| 326.0 B | |||
| 28 | showString at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.Dataset.showString(Dataset.scala:315) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 19:41:51 | 2 s |
2/2
| 40.8 MiB | 326.0 B | ||
| 27 | count at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.Dataset.count(Dataset.scala:3625) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 19:41:51 | 28 ms |
1/1
| 118.0 B | |||
| 25 | count at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.Dataset.count(Dataset.scala:3625) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 19:41:50 | 1 s |
2/2
| 40.8 MiB | 118.0 B | ||
| 24 | showString at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.Dataset.showString(Dataset.scala:315) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 19:41:49 | 0.3 s |
1/1
| 7.5 KiB | |||
| 23 | csv at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.DataFrameReader.csv(DataFrameReader.scala:538) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 19:41:49 | 0.4 s |
1/1
| 7.5 KiB | |||
| 22 | count at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.Dataset.count(Dataset.scala:3625) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 19:31:13 | 31 ms |
1/1
| 118.0 B | |||
| 20 | count at NativeMethodAccessorImpl.java:0
RDD: *(1) Project [ride_id#128, rideable_type#129, started_at#130, ended_at#131, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#136, start_lng#137, end_lat#138, end_lng#139, member_casual#140, _corrupt_record#141, regexp_extract(input_file_name(), [^/]+$, 0) AS _source_file#156]
+- FileScan csv [ride_id#128,rideable_type#129,started_at#130,ended_at#131,start_station_name#132,start_station_id#133,end_station_name#134,end_station_id#135,start_lat#136,start_lng#137,end_lat#138,end_lng#139,member_casual#140,_corrupt_record#141] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(2 paths)[s3a://rzvde-g11-durnev-pavel/raw/citibike_data/202602/202602-citibike-..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<ride_id:string,rideable_type:string,started_at:string,ended_at:string,start_station_name:s...
AdaptiveSparkPlan isFinalPlan=false
+- Project [ride_id#128, rideable_type#129, started_at#669, ended_at#670, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#675, start_lng#676, end_lat#677, end_lng#678, member_casual#140, _corrupt_record#141, _source_file#156, (isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AS _is_ride_id_not_empty#695, coalesce((ended_at#670 > started_at#669), false) AS _is_ended_after_started#696, coalesce(NOT (end_station_id#135 = start_station_id#133), false) AS _is_different_stations#697, ((((isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AND coalesce((ended_at#670 > started_at#669), false)) AND coalesce(NOT (end_station_id#135 = start_station_id#133), false)) AND isnull(_corrupt_record#141)) AS _is_valid#698]
+- Project [ride_id#128, rideable_type#129, cast(started_at#130 as timestamp) AS started_at#669, cast(ended_at#131 as timestamp) AS ended_at#670, start_station_name#132, start_station_id#133, end_s...
org.apache.spark.sql.Dataset.count(Dataset.scala:3625) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 19:31:13 | 0.2 s |
2/2
| 104.6 MiB | 118.0 B | ||
| 19 | count at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.Dataset.count(Dataset.scala:3625) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 19:31:13 | 43 ms |
1/1
| 118.0 B | |||
| 17 | count at NativeMethodAccessorImpl.java:0
RDD: *(1) Project [ride_id#128, rideable_type#129, started_at#130, ended_at#131, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#136, start_lng#137, end_lat#138, end_lng#139, member_casual#140, _corrupt_record#141, regexp_extract(input_file_name(), [^/]+$, 0) AS _source_file#156]
+- FileScan csv [ride_id#128,rideable_type#129,started_at#130,ended_at#131,start_station_name#132,start_station_id#133,end_station_name#134,end_station_id#135,start_lat#136,start_lng#137,end_lat#138,end_lng#139,member_casual#140,_corrupt_record#141] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(2 paths)[s3a://rzvde-g11-durnev-pavel/raw/citibike_data/202602/202602-citibike-..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<ride_id:string,rideable_type:string,started_at:string,ended_at:string,start_station_name:s...
AdaptiveSparkPlan isFinalPlan=false
+- Project [ride_id#128, rideable_type#129, started_at#669, ended_at#670, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#675, start_lng#676, end_lat#677, end_lng#678, member_casual#140, _corrupt_record#141, _source_file#156, (isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AS _is_ride_id_not_empty#695, coalesce((ended_at#670 > started_at#669), false) AS _is_ended_after_started#696, coalesce(NOT (end_station_id#135 = start_station_id#133), false) AS _is_different_stations#697, ((((isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AND coalesce((ended_at#670 > started_at#669), false)) AND coalesce(NOT (end_station_id#135 = start_station_id#133), false)) AND isnull(_corrupt_record#141)) AS _is_valid#698]
+- Project [ride_id#128, rideable_type#129, cast(started_at#130 as timestamp) AS started_at#669, cast(ended_at#131 as timestamp) AS ended_at#670, start_station_name#132, start_station_id#133, end_s...
org.apache.spark.sql.Dataset.count(Dataset.scala:3625) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 19:31:13 | 0.2 s |
2/2
| 104.6 MiB | 118.0 B | ||
| 16 | csv at NativeMethodAccessorImpl.java:0
RDD: *(1) Project [ride_id#128, rideable_type#129, started_at#130, ended_at#131, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#136, start_lng#137, end_lat#138, end_lng#139, member_casual#140, _corrupt_record#141, regexp_extract(input_file_name(), [^/]+$, 0) AS _source_file#156]
+- FileScan csv [ride_id#128,rideable_type#129,started_at#130,ended_at#131,start_station_name#132,start_station_id#133,end_station_name#134,end_station_id#135,start_lat#136,start_lng#137,end_lat#138,end_lng#139,member_casual#140,_corrupt_record#141] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(2 paths)[s3a://rzvde-g11-durnev-pavel/raw/citibike_data/202602/202602-citibike-..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<ride_id:string,rideable_type:string,started_at:string,ended_at:string,start_station_name:s...
AdaptiveSparkPlan isFinalPlan=false
+- Project [ride_id#128, rideable_type#129, started_at#669, ended_at#670, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#675, start_lng#676, end_lat#677, end_lng#678, member_casual#140, _corrupt_record#141, _source_file#156, (isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AS _is_ride_id_not_empty#695, coalesce((ended_at#670 > started_at#669), false) AS _is_ended_after_started#696, coalesce(NOT (end_station_id#135 = start_station_id#133), false) AS _is_different_stations#697, ((((isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AND coalesce((ended_at#670 > started_at#669), false)) AND coalesce(NOT (end_station_id#135 = start_station_id#133), false)) AND isnull(_corrupt_record#141)) AS _is_valid#698]
+- Project [ride_id#128, rideable_type#129, cast(started_at#130 as timestamp) AS started_at#669, cast(ended_at#131 as timestamp) AS ended_at#670, start_station_name#132, start_station_id#133, end_s...
org.apache.spark.sql.DataFrameWriter.csv(DataFrameWriter.scala:850) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 19:31:06 | 4 s |
1/1
| 104.6 MiB | 7.5 MiB | ||
| 15 | parquet at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:792) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 19:30:40 | 16 s |
1/1
| 47.6 MiB | 98.2 MiB | ||
| 12 | parquet at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:792) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 19:30:35 | 4 s |
2/2
| 86.9 MiB | 98.2 MiB | ||
| 10 | parquet at NativeMethodAccessorImpl.java:0
RDD: *(1) Project [ride_id#128, rideable_type#129, started_at#130, ended_at#131, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#136, start_lng#137, end_lat#138, end_lng#139, member_casual#140, _corrupt_record#141, regexp_extract(input_file_name(), [^/]+$, 0) AS _source_file#156]
+- FileScan csv [ride_id#128,rideable_type#129,started_at#130,ended_at#131,start_station_name#132,start_station_id#133,end_station_name#134,end_station_id#135,start_lat#136,start_lng#137,end_lat#138,end_lng#139,member_casual#140,_corrupt_record#141] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(2 paths)[s3a://rzvde-g11-durnev-pavel/raw/citibike_data/202602/202602-citibike-..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<ride_id:string,rideable_type:string,started_at:string,ended_at:string,start_station_name:s...
AdaptiveSparkPlan isFinalPlan=false
+- Project [ride_id#128, rideable_type#129, started_at#669, ended_at#670, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#675, start_lng#676, end_lat#677, end_lng#678, member_casual#140, _corrupt_record#141, _source_file#156, (isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AS _is_ride_id_not_empty#695, coalesce((ended_at#670 > started_at#669), false) AS _is_ended_after_started#696, coalesce(NOT (end_station_id#135 = start_station_id#133), false) AS _is_different_stations#697, ((((isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AND coalesce((ended_at#670 > started_at#669), false)) AND coalesce(NOT (end_station_id#135 = start_station_id#133), false)) AND isnull(_corrupt_record#141)) AS _is_valid#698]
+- Project [ride_id#128, rideable_type#129, cast(started_at#130 as timestamp) AS started_at#669, cast(ended_at#131 as timestamp) AS ended_at#670, start_station_name#132, start_station_id#133, end_s...
org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:792) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 19:30:32 | 2 s |
2/2
| 104.6 MiB | 86.9 MiB | ||
| 9 | parquet at NativeMethodAccessorImpl.java:0
RDD: *(1) Project [ride_id#128, rideable_type#129, started_at#130, ended_at#131, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#136, start_lng#137, end_lat#138, end_lng#139, member_casual#140, _corrupt_record#141, regexp_extract(input_file_name(), [^/]+$, 0) AS _source_file#156]
+- FileScan csv [ride_id#128,rideable_type#129,started_at#130,ended_at#131,start_station_name#132,start_station_id#133,end_station_name#134,end_station_id#135,start_lat#136,start_lng#137,end_lat#138,end_lng#139,member_casual#140,_corrupt_record#141] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(2 paths)[s3a://rzvde-g11-durnev-pavel/raw/citibike_data/202602/202602-citibike-..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<ride_id:string,rideable_type:string,started_at:string,ended_at:string,start_station_name:s...
AdaptiveSparkPlan isFinalPlan=false
+- Project [ride_id#128, rideable_type#129, started_at#669, ended_at#670, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#675, start_lng#676, end_lat#677, end_lng#678, member_casual#140, _corrupt_record#141, _source_file#156, (isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AS _is_ride_id_not_empty#695, coalesce((ended_at#670 > started_at#669), false) AS _is_ended_after_started#696, coalesce(NOT (end_station_id#135 = start_station_id#133), false) AS _is_different_stations#697, ((((isnotnull(ride_id#128) AND NOT (trim(ride_id#128, None) = )) AND coalesce((ended_at#670 > started_at#669), false)) AND coalesce(NOT (end_station_id#135 = start_station_id#133), false)) AND isnull(_corrupt_record#141)) AS _is_valid#698]
+- Project [ride_id#128, rideable_type#129, cast(started_at#130 as timestamp) AS started_at#669, cast(ended_at#131 as timestamp) AS ended_at#670, start_station_name#132, start_station_id#133, end_s...
org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:792) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 19:30:25 | 7 s |
2/2
| 126.2 MiB | |||
| 8 | showString at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.Dataset.showString(Dataset.scala:315) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 19:24:30 | 0.1 s |
1/1
| 318.0 B | |||
| 6 | showString at NativeMethodAccessorImpl.java:0
RDD: *(1) Project [ride_id#128, rideable_type#129, started_at#130, ended_at#131, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#136, start_lng#137, end_lat#138, end_lng#139, member_casual#140, _corrupt_record#141, regexp_extract(input_file_name(), [^/]+$, 0) AS _source_file#156]
+- FileScan csv [ride_id#128,rideable_type#129,started_at#130,ended_at#131,start_station_name#132,start_station_id#133,end_station_name#134,end_station_id#135,start_lat#136,start_lng#137,end_lat#138,end_lng#139,member_casual#140,_corrupt_record#141] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(2 paths)[s3a://rzvde-g11-durnev-pavel/raw/citibike_data/202602/202602-citibike-..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<ride_id:string,rideable_type:string,started_at:string,ended_at:string,start_station_name:s...
org.apache.spark.sql.Dataset.showString(Dataset.scala:315) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 19:24:29 | 0.6 s |
2/2
| 126.2 MiB | 318.0 B | ||
| 5 | showString at NativeMethodAccessorImpl.java:0
RDD: *(1) Project [ride_id#128, rideable_type#129, started_at#130, ended_at#131, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#136, start_lng#137, end_lat#138, end_lng#139, member_casual#140, _corrupt_record#141, regexp_extract(input_file_name(), [^/]+$, 0) AS _source_file#156]
+- FileScan csv [ride_id#128,rideable_type#129,started_at#130,ended_at#131,start_station_name#132,start_station_id#133,end_station_name#134,end_station_id#135,start_lat#136,start_lng#137,end_lat#138,end_lng#139,member_casual#140,_corrupt_record#141] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(2 paths)[s3a://rzvde-g11-durnev-pavel/raw/citibike_data/202602/202602-citibike-..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<ride_id:string,rideable_type:string,started_at:string,ended_at:string,start_station_name:s...
org.apache.spark.sql.Dataset.showString(Dataset.scala:315) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 19:24:15 | 14 s |
2/2
| 226.6 MiB | |||
| 4 | count at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.Dataset.count(Dataset.scala:3625) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 19:24:14 | 0.2 s |
1/1
| 118.0 B | |||
| 2 | count at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.Dataset.count(Dataset.scala:3625) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 19:23:47 | 27 s |
2/2
| 40.8 MiB | 118.0 B | ||
| 1 | showString at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.Dataset.showString(Dataset.scala:315) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 19:23:46 | 0.8 s |
1/1
| 7.5 KiB | |||
| 0 | csv at NativeMethodAccessorImpl.java:0 org.apache.spark.sql.DataFrameReader.csv(DataFrameReader.scala:538) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.base/java.lang.reflect.Method.invoke(Method.java:568) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.base/java.lang.Thread.run(Thread.java:840) | 2026/11/01 19:23:42 | 3 s |
1/1
| 3.2 KiB |