| Stage Id ▾ | Description | Submitted | Duration | Tasks: Succeeded/Total | Input | Output | Shuffle Read | Shuffle Write |
|---|---|---|---|---|---|---|---|---|
| 17 | first at /tmp/ipykernel_480/4147188698.py:131 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) | 2026/11/06 11:04:42 | 43 ms |
1/1
| 187.0 B |
| Stage Id ▾ | Description | Submitted | Duration | Tasks: Succeeded/Total | Input | Output | Shuffle Read | Shuffle Write |
|---|---|---|---|---|---|---|---|---|
| 16 | first at /tmp/ipykernel_480/4147188698.py:131
RDD: AdaptiveSparkPlan isFinalPlan=false
+- Project [ride_id#56, rideable_type#57, started_at#93, ended_at#94, start_station_name#60, start_station_id#124, end_station_name#62, end_station_id#155, start_lat#88, start_lng#89, end_lat#90, end_lng#91, member_casual#68, _start_station_id_fixed#109, _end_station_id_fixed#139, _ride_id_ok#171, _duration_ok#172, _station_id_ok#173, _source_file#174, 2026-11-06 11:04:13.790835 AS _processed_dttm#175, year#176, month#177, _start_station_ride_num#179]
+- Window [row_number() windowspecdefinition(start_station_id#124, _w0#180, _w1#181, started_at#93 ASC NULLS FIRST, ride_id#56 ASC NULLS FIRST, specifiedwindowframe(RowFrame, unboundedpreceding$(), currentrow$())) AS _start_station_ride_num#179], [start_station_id#124, _w0#180, _w1#181], [started_at#93 ASC NULLS FIRST, ride_id#56 ASC NULLS FIRST]
+- Sort [start_station_id#124 ASC NULLS FIRST, _w0#180 ASC NULLS FIRST, _w1#181 ASC NULLS FIRST, started_at#93 ASC NULLS FIRST, ride_id#56 ASC NULLS FIRST], false, 0
...
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) | Unknown | Unknown |
0/3
| ||||
| 15 | 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) | Unknown | Unknown |
0/3
|