Packages

c

org.apache.spark.sql.execution.python

CoGroupedArrowPythonRunner

class CoGroupedArrowPythonRunner extends BasePythonRunner[(Iterator[InternalRow], Iterator[InternalRow]), ColumnarBatch] with BasicPythonArrowOutput

Python UDF Runner for cogrouped udfs. It sends Arrow bathes from two different DataFrames, groups them in Python, and receive it back in JVM as batches of single DataFrame.

Linear Supertypes
BasicPythonArrowOutput, PythonArrowOutput[ColumnarBatch], BasePythonRunner[(Iterator[InternalRow], Iterator[InternalRow]), ColumnarBatch], Logging, AnyRef, Any
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. CoGroupedArrowPythonRunner
  2. BasicPythonArrowOutput
  3. PythonArrowOutput
  4. BasePythonRunner
  5. Logging
  6. AnyRef
  7. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new CoGroupedArrowPythonRunner(funcs: Seq[ChainedPythonFunctions], evalType: Int, argOffsets: Array[Array[Int]], leftSchema: StructType, rightSchema: StructType, timeZoneId: String, conf: Map[String, String], pythonMetrics: Map[String, SQLMetric])

Type Members

  1. class MonitorThread extends Thread
    Definition Classes
    BasePythonRunner
  2. abstract class ReaderIterator extends Iterator[OUT]
    Definition Classes
    BasePythonRunner
  3. class WriterMonitorThread extends Thread
    Definition Classes
    BasePythonRunner
  4. abstract class WriterThread extends Thread
    Definition Classes
    BasePythonRunner

Value Members

  1. final def !=(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  2. final def ##(): Int
    Definition Classes
    AnyRef → Any
  3. final def ==(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  4. val accumulator: PythonAccumulatorV2
    Attributes
    protected
    Definition Classes
    BasePythonRunner
  5. val argOffsets: Array[Array[Int]]
    Attributes
    protected
    Definition Classes
    BasePythonRunner
  6. final def asInstanceOf[T0]: T0
    Definition Classes
    Any
  7. val authSocketTimeout: Long
    Attributes
    protected
    Definition Classes
    BasePythonRunner
  8. val bufferSize: Int
    Attributes
    protected
    Definition Classes
    BasePythonRunner
  9. def clone(): AnyRef
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  10. def compute(inputIterator: Iterator[(Iterator[InternalRow], Iterator[InternalRow])], partitionIndex: Int, context: TaskContext): Iterator[ColumnarBatch]
    Definition Classes
    BasePythonRunner
  11. def deserializeColumnarBatch(batch: ColumnarBatch, schema: StructType): ColumnarBatch
    Attributes
    protected
    Definition Classes
    BasicPythonArrowOutput → PythonArrowOutput
  12. val envVars: Map[String, String]
    Attributes
    protected
    Definition Classes
    BasePythonRunner
  13. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  14. def equals(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  15. val evalType: Int
    Attributes
    protected
    Definition Classes
    BasePythonRunner
  16. def finalize(): Unit
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  17. val funcs: Seq[ChainedPythonFunctions]
    Attributes
    protected
    Definition Classes
    BasePythonRunner
  18. final def getClass(): Class[_]
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  19. def handleMetadataAfterExec(stream: DataInputStream): Unit
    Attributes
    protected
    Definition Classes
    PythonArrowOutput
  20. def hashCode(): Int
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  21. def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  22. def initializeLogIfNecessary(isInterpreter: Boolean): Unit
    Attributes
    protected
    Definition Classes
    Logging
  23. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  24. def isTraceEnabled(): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  25. def log: Logger
    Attributes
    protected
    Definition Classes
    Logging
  26. def logDebug(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  27. def logDebug(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  28. def logError(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  29. def logError(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  30. def logInfo(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  31. def logInfo(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  32. def logName: String
    Attributes
    protected
    Definition Classes
    Logging
  33. def logTrace(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  34. def logTrace(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  35. def logWarning(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  36. def logWarning(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  37. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  38. def newReaderIterator(stream: DataInputStream, writerThread: WriterThread, startTime: Long, env: SparkEnv, worker: Socket, pid: Option[Int], releasedOrClosed: AtomicBoolean, context: TaskContext): Iterator[ColumnarBatch]
    Attributes
    protected
    Definition Classes
    PythonArrowOutput
  39. def newWriterThread(env: SparkEnv, worker: Socket, inputIterator: Iterator[(Iterator[InternalRow], Iterator[InternalRow])], partitionIndex: Int, context: TaskContext): WriterThread
    Attributes
    protected
    Definition Classes
    CoGroupedArrowPythonRunner → BasePythonRunner
  40. final def notify(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  41. final def notifyAll(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  42. val pythonExec: String
    Attributes
    protected
    Definition Classes
    BasePythonRunner
  43. val pythonMetrics: Map[String, SQLMetric]
    Definition Classes
    CoGroupedArrowPythonRunner → PythonArrowOutput
  44. val pythonVer: String
    Attributes
    protected
    Definition Classes
    BasePythonRunner
  45. val simplifiedTraceback: Boolean
    Definition Classes
    CoGroupedArrowPythonRunner → BasePythonRunner
  46. final def synchronized[T0](arg0: ⇒ T0): T0
    Definition Classes
    AnyRef
  47. def toString(): String
    Definition Classes
    AnyRef → Any
  48. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  49. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  50. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()

Inherited from BasicPythonArrowOutput

Inherited from PythonArrowOutput[ColumnarBatch]

Inherited from BasePythonRunner[(Iterator[InternalRow], Iterator[InternalRow]), ColumnarBatch]

Inherited from Logging

Inherited from AnyRef

Inherited from Any

Ungrouped