g11.durnev.pavel-CitiBike-WAP - Details for Job 74

Status: SUCCEEDED
Submitted: 2026/11/01 20:48:35
Duration: 63 ms
Associated SQL Query: 37
Completed Stages: 1
Skipped Stages: 1

Enable zooming

digraph G { subgraph clusterstage_111 { label="Stage 111 (skipped)"; subgraph cluster44 { label="Scan csv "; 21 [labelType="html" label="FileScanRDD [21] showString at NativeMethodAccessorImpl.java:0"]; 22 [labelType="html" label="MapPartitionsRDD [22] showString at NativeMethodAccessorImpl.java:0"]; } subgraph cluster41 { label="WholeStageCodegen (1)"; 23 [labelType="html" label="MapPartitionsRDD [23] showString at NativeMethodAccessorImpl.java:0"]; } subgraph cluster45 { label="mapPartitionsInternal"; 24 [labelType="html" label="MapPartitionsRDD [24] showString at NativeMethodAccessorImpl.java:0"]; } subgraph cluster46 { label="mapPartitionsInternal"; 25 [labelType="html" label="*(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]\n+- 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...\n [25] [Cached] showString at NativeMethodAccessorImpl.java:0"]; } subgraph cluster830 { label="InMemoryTableScan"; 326 [labelType="html" label="MapPartitionsRDD [326] collect at /tmp/ipykernel_920/2164963154.py:21"]; 327 [labelType="html" label="MapPartitionsRDD [327] collect at /tmp/ipykernel_920/2164963154.py:21"]; 328 [labelType="html" label="MapPartitionsRDD [328] collect at /tmp/ipykernel_920/2164963154.py:21"]; } subgraph cluster826 { label="WholeStageCodegen (1)"; 329 [labelType="html" label="MapPartitionsRDD [329] collect at /tmp/ipykernel_920/2164963154.py:21"]; } subgraph cluster825 { label="Exchange"; 330 [labelType="html" label="MapPartitionsRDD [330] collect at /tmp/ipykernel_920/2164963154.py:21"]; } } 21->22; 22->23; 23->24; 24->25; 25->326; 326->327; 327->328; 328->329; 329->330; }

digraph G { subgraph clusterstage_112 { label="Stage 112"; subgraph cluster835 { label="AQEShuffleRead"; 331 [labelType="html" label="ShuffledRowRDD [331] [Unordered] collect at /tmp/ipykernel_920/2164963154.py:21"]; } subgraph cluster832 { label="WholeStageCodegen (2)"; 332 [labelType="html" label="MapPartitionsRDD [332] [Unordered] collect at /tmp/ipykernel_920/2164963154.py:21"]; } subgraph cluster831 { label="Exchange"; 333 [labelType="html" label="MapPartitionsRDD [333] [Unordered] collect at /tmp/ipykernel_920/2164963154.py:21"]; 334 [labelType="html" label="MapPartitionsRDD [334] [Unordered] collect at /tmp/ipykernel_920/2164963154.py:21"]; 335 [labelType="html" label="MapPartitionsRDD [335] [Unordered] collect at /tmp/ipykernel_920/2164963154.py:21"]; } } 331->332; 332->333; 333->334; 334->335; }

330,331

Completed Stages (1)

Page:

Stage Id ▾	Description	Submitted	Duration	Tasks: Succeeded/Total	Input	Output	Shuffle Read	Shuffle Write
112	collect at /tmp/ipykernel_920/2164963154.py:21 +details 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

Stage Id ▾

Description

Submitted

Duration

Tasks: Succeeded/Total

Input

Output

Shuffle Read

Shuffle Write

112

collect at /tmp/ipykernel_920/2164963154.py:21 +details

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

Page:

Skipped Stages (1)

Page:

Stage Id ▾	Description	Submitted	Duration	Tasks: Succeeded/Total	Input	Output	Shuffle Read	Shuffle Write
111	collect at /tmp/ipykernel_920/2164963154.py:21 +details 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)	Unknown	Unknown	0/2

Page: