case class GpuAggregateInPandasExec(gpuGroupingExpressions: Seq[NamedExpression], udfExpressions: Seq[GpuPythonFunction], pyOutAttributes: Seq[Attribute], resultExpressions: Seq[NamedExpression], child: SparkPlan)(cpuGroupingExpressions: Seq[NamedExpression]) extends SparkPlan with ShimUnaryExecNode with GpuPythonExecBase with Product with Serializable

Physical node for aggregation with group aggregate Pandas UDF.

This plan works by sending the necessary (projected) input grouped data as Arrow record batches to the Python worker, the Python worker invokes the UDF and sends the results to the executor. Finally the executor evaluates any post-aggregation expressions and join the result with the grouped key.

This node aims at accelerating the data transfer between JVM and Python for GPU pipeline, and scheduling GPU resources for its Python processes.

Linear Supertypes
GpuPythonExecBase, GpuExec, ShimUnaryExecNode, UnaryExecNode, SparkPlan, Serializable, Serializable, Logging, QueryPlan[SparkPlan], SQLConfHelper, TreeNode[SparkPlan], Product, Equals, AnyRef, Any
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. GpuAggregateInPandasExec
  2. GpuPythonExecBase
  3. GpuExec
  4. ShimUnaryExecNode
  5. UnaryExecNode
  6. SparkPlan
  7. Serializable
  8. Serializable
  9. Logging
  10. QueryPlan
  11. SQLConfHelper
  12. TreeNode
  13. Product
  14. Equals
  15. AnyRef
  16. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new GpuAggregateInPandasExec(gpuGroupingExpressions: Seq[NamedExpression], udfExpressions: Seq[GpuPythonFunction], pyOutAttributes: Seq[Attribute], resultExpressions: Seq[NamedExpression], child: SparkPlan)(cpuGroupingExpressions: Seq[NamedExpression])

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. lazy val additionalMetrics: Map[String, GpuMetric]
    Definition Classes
    GpuExec
  5. lazy val allAttributes: AttributeSeq
    Definition Classes
    QueryPlan
  6. lazy val allMetrics: Map[String, GpuMetric]
    Definition Classes
    GpuPythonExecBase → GpuExec
  7. def apply(number: Int): TreeNode[_]
    Definition Classes
    TreeNode
  8. def argString(maxFields: Int): String
    Definition Classes
    TreeNode
  9. def asCode: String
    Definition Classes
    TreeNode
  10. final def asInstanceOf[T0]: T0
    Definition Classes
    Any
  11. final lazy val canonicalized: SparkPlan
    Definition Classes
    QueryPlan
    Annotations
    @transient()
  12. val child: SparkPlan
    Definition Classes
    GpuAggregateInPandasExec → UnaryExecNode
  13. final def children: Seq[SparkPlan]
    Definition Classes
    UnaryExecNode → TreeNode
  14. def childrenCoalesceGoal: Seq[CoalesceGoal]

    A goal to coalesce batches as the input to this operation.

    A goal to coalesce batches as the input to this operation. In some cases an operation will only work if all of the data is in a single batch. In other cases it may be much faster if it is in a single batch, but can tolerate multiple batches. This provides a way to express those desires.

    Definition Classes
    GpuAggregateInPandasExec → GpuExec
  15. def cleanupResources(): Unit
    Attributes
    protected[sql]
    Definition Classes
    SparkPlan
  16. def clone(): SparkPlan
    Definition Classes
    TreeNode → AnyRef
  17. def coalesceAfter: Boolean

    If true is returned batches after this will be coalesced.

    If true is returned batches after this will be coalesced. This should really be used in cases where it is known that the size of a batch may shrink a lot.

    Definition Classes
    GpuAggregateInPandasExec → GpuExec
  18. def collect[B](pf: PartialFunction[SparkPlan, B]): Seq[B]
    Definition Classes
    TreeNode
  19. def collectFirst[B](pf: PartialFunction[SparkPlan, B]): Option[B]
    Definition Classes
    TreeNode
  20. def collectLeaves(): Seq[SparkPlan]
    Definition Classes
    TreeNode
  21. def collectWithSubqueries[B](f: PartialFunction[SparkPlan, B]): Seq[B]
    Definition Classes
    QueryPlan
  22. def commonGpuMetrics(): (GpuMetric, GpuMetric, GpuMetric, GpuMetric)

    Return the common metrics in order of NUM_INPUT_ROWS NUM_INPUT_BATCHES NUM_OUTPUT_ROWS NUM_OUTPUT_BATCHES as a tuple.

    Return the common metrics in order of NUM_INPUT_ROWS NUM_INPUT_BATCHES NUM_OUTPUT_ROWS NUM_OUTPUT_BATCHES as a tuple.

    Attributes
    protected
    Definition Classes
    GpuPythonExecBase
  23. def conf: SQLConf
    Definition Classes
    SQLConfHelper
  24. lazy val containsChild: Set[TreeNode[_]]
    Definition Classes
    TreeNode
  25. def copyTagsFrom(other: SparkPlan): Unit
    Definition Classes
    TreeNode
  26. def createAverageMetric(level: MetricsLevel, name: String): GpuMetric
    Attributes
    protected
    Definition Classes
    GpuExec
  27. def createFileCacheMetrics(): Map[String, GpuMetric]
    Attributes
    protected
    Definition Classes
    GpuExec
  28. def createMetric(level: MetricsLevel, name: String): GpuMetric
    Attributes
    protected
    Definition Classes
    GpuExec
  29. def createNanoTimingMetric(level: MetricsLevel, name: String): GpuMetric
    Attributes
    protected
    Definition Classes
    GpuExec
  30. def createSizeMetric(level: MetricsLevel, name: String): GpuMetric
    Attributes
    protected
    Definition Classes
    GpuExec
  31. def createTimingMetric(level: MetricsLevel, name: String): GpuMetric
    Attributes
    protected
    Definition Classes
    GpuExec
  32. def disableCoalesceUntilInput(): Boolean

    Returns true if there is something in the exec that cannot work when batches between multiple file partitions are combined into a single batch (coalesce).

    Returns true if there is something in the exec that cannot work when batches between multiple file partitions are combined into a single batch (coalesce).

    Definition Classes
    GpuExec
  33. def doCanonicalize(): SparkPlan

    Defines how the canonicalization should work for the current plan.

    Defines how the canonicalization should work for the current plan.

    Attributes
    protected
    Definition Classes
    GpuExec → QueryPlan
  34. final def doExecute(): RDD[InternalRow]
    Attributes
    protected
    Definition Classes
    GpuPythonExecBase → SparkPlan
  35. def doExecuteBroadcast[T](): Broadcast[T]
    Attributes
    protected[sql]
    Definition Classes
    SparkPlan
  36. final def doExecuteColumnar(): RDD[ColumnarBatch]
    Definition Classes
    GpuExec → SparkPlan
  37. def doPrepare(): Unit
    Attributes
    protected
    Definition Classes
    SparkPlan
  38. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  39. final def execute(): RDD[InternalRow]
    Definition Classes
    SparkPlan
  40. final def executeBroadcast[T](): Broadcast[T]
    Definition Classes
    SparkPlan
  41. def executeCollect(): Array[InternalRow]
    Definition Classes
    SparkPlan
  42. def executeCollectPublic(): Array[Row]
    Definition Classes
    SparkPlan
  43. final def executeColumnar(): RDD[ColumnarBatch]
    Definition Classes
    SparkPlan
  44. final def executeQuery[T](query: ⇒ T): T
    Attributes
    protected
    Definition Classes
    SparkPlan
  45. def executeTail(n: Int): Array[InternalRow]
    Definition Classes
    SparkPlan
  46. def executeTake(n: Int): Array[InternalRow]
    Definition Classes
    SparkPlan
  47. def executeToIterator(): Iterator[InternalRow]
    Definition Classes
    SparkPlan
  48. final def expressions: Seq[Expression]
    Definition Classes
    QueryPlan
  49. def fastEquals(other: TreeNode[_]): Boolean
    Definition Classes
    TreeNode
  50. def finalize(): Unit
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  51. def find(f: (SparkPlan) ⇒ Boolean): Option[SparkPlan]
    Definition Classes
    TreeNode
  52. def flatMap[A](f: (SparkPlan) ⇒ TraversableOnce[A]): Seq[A]
    Definition Classes
    TreeNode
  53. def foreach(f: (SparkPlan) ⇒ Unit): Unit
    Definition Classes
    TreeNode
  54. def foreachUp(f: (SparkPlan) ⇒ Unit): Unit
    Definition Classes
    TreeNode
  55. def formattedNodeName: String
    Attributes
    protected
    Definition Classes
    QueryPlan
  56. def generateTreeString(depth: Int, lastChildren: Seq[Boolean], append: (String) ⇒ Unit, verbose: Boolean, prefix: String, addSuffix: Boolean, maxFields: Int, printNodeId: Boolean, indent: Int): Unit
    Definition Classes
    TreeNode
  57. final def getClass(): Class[_]
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  58. def getTagValue[T](tag: TreeNodeTag[T]): Option[T]
    Definition Classes
    TreeNode
  59. def getTaskMetrics: Option[GpuTaskMetrics]
    Definition Classes
    GpuExec
  60. def gpuExpressions: Seq[Expression]

    Return the expressions for this plan node that should be GPU expressions.

    Return the expressions for this plan node that should be GPU expressions. For most nodes this will be the same as the list of expressions, but some nodes use CPU expressions directly in some cases and will need to override this.

    Definition Classes
    GpuExec
  61. val gpuGroupingExpressions: Seq[NamedExpression]
  62. def gpuLongMetric(name: String): GpuMetric
    Definition Classes
    GpuExec
  63. def hashCode(): Int
    Definition Classes
    TreeNode → AnyRef → Any
  64. val id: Int
    Definition Classes
    SparkPlan
  65. def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  66. def initializeLogIfNecessary(isInterpreter: Boolean): Unit
    Attributes
    protected
    Definition Classes
    Logging
  67. def innerChildren: Seq[QueryPlan[_]]
    Definition Classes
    QueryPlan → TreeNode
  68. def inputSet: AttributeSet
    Definition Classes
    QueryPlan
  69. def internalDoExecuteColumnar(): RDD[ColumnarBatch]
    Definition Classes
    GpuAggregateInPandasExec → GpuExec
  70. def isCanonicalizedPlan: Boolean
    Attributes
    protected
    Definition Classes
    QueryPlan
  71. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  72. def isTraceEnabled(): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  73. def jsonFields: List[JField]
    Attributes
    protected
    Definition Classes
    TreeNode
  74. def log: Logger
    Attributes
    protected
    Definition Classes
    Logging
  75. def logDebug(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  76. def logDebug(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  77. def logError(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  78. def logError(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  79. def logInfo(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  80. def logInfo(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  81. def logName: String
    Attributes
    protected
    Definition Classes
    Logging
  82. def logTrace(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  83. def logTrace(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  84. def logWarning(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  85. def logWarning(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  86. def logicalLink: Option[LogicalPlan]
    Definition Classes
    SparkPlan
  87. def longMetric(name: String): SQLMetric
    Definition Classes
    SparkPlan
  88. def makeCopy(newArgs: Array[AnyRef]): SparkPlan
    Definition Classes
    SparkPlan → TreeNode
  89. def map[A](f: (SparkPlan) ⇒ A): Seq[A]
    Definition Classes
    TreeNode
  90. def mapChildren(f: (SparkPlan) ⇒ SparkPlan): SparkPlan
    Definition Classes
    TreeNode
  91. def mapExpressions(f: (Expression) ⇒ Expression): GpuAggregateInPandasExec.this.type
    Definition Classes
    QueryPlan
  92. def mapProductIterator[B](f: (Any) ⇒ B)(implicit arg0: ClassTag[B]): Array[B]
    Attributes
    protected
    Definition Classes
    TreeNode
  93. final lazy val metrics: Map[String, SQLMetric]
    Definition Classes
    GpuExec → SparkPlan
  94. final def missingInput: AttributeSet
    Definition Classes
    QueryPlan
  95. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  96. def nodeName: String
    Definition Classes
    TreeNode
  97. final def notify(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  98. final def notifyAll(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  99. def numberedTreeString: String
    Definition Classes
    TreeNode
  100. val origin: Origin
    Definition Classes
    TreeNode
  101. def otherCopyArgs: Seq[AnyRef]
    Definition Classes
    GpuAggregateInPandasExec → TreeNode
  102. val output: Seq[Attribute]
    Definition Classes
    GpuAggregateInPandasExec → QueryPlan
  103. val outputBatchesLevel: MetricsLevel
    Attributes
    protected
    Definition Classes
    GpuExec
  104. def outputBatching: CoalesceGoal

    Lets a SparkPlan indicate what guarantees, if any, its output batch has.

    Lets a SparkPlan indicate what guarantees, if any, its output batch has. This lets us bypass GpuCoalesceBatch calls where ever possible. Returning a null indicates no guarantee at all, which is the default.

    Definition Classes
    GpuExec
  105. def outputOrdering: Seq[SortOrder]
    Definition Classes
    SparkPlan
  106. def outputPartitioning: Partitioning
    Definition Classes
    GpuAggregateInPandasExec → SparkPlan
  107. val outputRowsLevel: MetricsLevel
    Attributes
    protected
    Definition Classes
    GpuExec
  108. lazy val outputSet: AttributeSet
    Definition Classes
    QueryPlan
    Annotations
    @transient()
  109. def p(number: Int): SparkPlan
    Definition Classes
    TreeNode
  110. final def prepare(): Unit
    Definition Classes
    SparkPlan
  111. def prepareSubqueries(): Unit
    Attributes
    protected
    Definition Classes
    SparkPlan
  112. def prettyJson: String
    Definition Classes
    TreeNode
  113. def printSchema(): Unit
    Definition Classes
    QueryPlan
  114. def producedAttributes: AttributeSet
    Definition Classes
    GpuAggregateInPandasExec → QueryPlan
  115. val pyOutAttributes: Seq[Attribute]
  116. lazy val references: AttributeSet
    Definition Classes
    QueryPlan
    Annotations
    @transient()
  117. def requiredChildDistribution: Seq[Distribution]
    Definition Classes
    GpuAggregateInPandasExec → SparkPlan
  118. def requiredChildOrdering: Seq[Seq[SortOrder]]
    Definition Classes
    GpuAggregateInPandasExec → SparkPlan
  119. def resetMetrics(): Unit
    Definition Classes
    SparkPlan
  120. val resultExpressions: Seq[NamedExpression]
  121. final def sameResult(other: SparkPlan): Boolean
    Definition Classes
    QueryPlan
  122. lazy val schema: StructType
    Definition Classes
    QueryPlan
  123. def schemaString: String
    Definition Classes
    QueryPlan
  124. final def semanticHash(): Int
    Definition Classes
    QueryPlan
  125. def setLogicalLink(logicalPlan: LogicalPlan): Unit
    Definition Classes
    SparkPlan
  126. def setTagValue[T](tag: TreeNodeTag[T], value: T): Unit
    Definition Classes
    TreeNode
  127. def setTaskMetrics(gpuTaskMetrics: GpuTaskMetrics): Unit
    Definition Classes
    GpuExec
  128. def simpleString(maxFields: Int): String
    Definition Classes
    QueryPlan → TreeNode
  129. def simpleStringWithNodeId(): String
    Definition Classes
    QueryPlan → TreeNode
  130. def sparkContext: SparkContext
    Attributes
    protected
    Definition Classes
    SparkPlan
  131. def sparkSession: SparkSession
    Definition Classes
    GpuExec
  132. final val sqlContext: SQLContext
    Definition Classes
    SparkPlan
  133. def statePrefix: String
    Attributes
    protected
    Definition Classes
    QueryPlan
  134. def stringArgs: Iterator[Any]
    Attributes
    protected
    Definition Classes
    TreeNode
  135. def subqueries: Seq[SparkPlan]
    Definition Classes
    QueryPlan
  136. def subqueriesAll: Seq[SparkPlan]
    Definition Classes
    QueryPlan
  137. def supportsColumnar: Boolean
    Definition Classes
    GpuExec → SparkPlan
  138. final def synchronized[T0](arg0: ⇒ T0): T0
    Definition Classes
    AnyRef
  139. def toJSON: String
    Definition Classes
    TreeNode
  140. def toString(): String
    Definition Classes
    TreeNode → AnyRef → Any
  141. def transform(rule: PartialFunction[SparkPlan, SparkPlan]): SparkPlan
    Definition Classes
    TreeNode
  142. def transformAllExpressions(rule: PartialFunction[Expression, Expression]): GpuAggregateInPandasExec.this.type
    Definition Classes
    QueryPlan
  143. def transformDown(rule: PartialFunction[SparkPlan, SparkPlan]): SparkPlan
    Definition Classes
    TreeNode
  144. def transformExpressions(rule: PartialFunction[Expression, Expression]): GpuAggregateInPandasExec.this.type
    Definition Classes
    QueryPlan
  145. def transformExpressionsDown(rule: PartialFunction[Expression, Expression]): GpuAggregateInPandasExec.this.type
    Definition Classes
    QueryPlan
  146. def transformExpressionsUp(rule: PartialFunction[Expression, Expression]): GpuAggregateInPandasExec.this.type
    Definition Classes
    QueryPlan
  147. def transformUp(rule: PartialFunction[SparkPlan, SparkPlan]): SparkPlan
    Definition Classes
    TreeNode
  148. def transformUpWithNewOutput(rule: PartialFunction[SparkPlan, (SparkPlan, Seq[(Attribute, Attribute)])], skipCond: (SparkPlan) ⇒ Boolean, canGetOutput: (SparkPlan) ⇒ Boolean): SparkPlan
    Definition Classes
    QueryPlan
  149. def treeString(append: (String) ⇒ Unit, verbose: Boolean, addSuffix: Boolean, maxFields: Int, printOperatorId: Boolean): Unit
    Definition Classes
    TreeNode
  150. final def treeString(verbose: Boolean, addSuffix: Boolean, maxFields: Int, printOperatorId: Boolean): String
    Definition Classes
    TreeNode
  151. final def treeString: String
    Definition Classes
    TreeNode
  152. val udfExpressions: Seq[GpuPythonFunction]
  153. def unsetTagValue[T](tag: TreeNodeTag[T]): Unit
    Definition Classes
    TreeNode
  154. def vectorTypes: Option[Seq[String]]
    Definition Classes
    SparkPlan
  155. def verboseString(maxFields: Int): String
    Definition Classes
    QueryPlan → TreeNode
  156. def verboseStringWithOperatorId(): String
    Definition Classes
    UnaryExecNode → QueryPlan
  157. def verboseStringWithSuffix(maxFields: Int): String
    Definition Classes
    TreeNode
  158. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  159. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  160. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  161. def waitForSubqueries(): Unit
    Attributes
    protected
    Definition Classes
    SparkPlan
  162. def withNewChildren(newChildren: Seq[SparkPlan]): SparkPlan
    Definition Classes
    TreeNode

Inherited from GpuPythonExecBase

Inherited from GpuExec

Inherited from ShimUnaryExecNode

Inherited from UnaryExecNode

Inherited from SparkPlan

Inherited from Serializable

Inherited from Serializable

Inherited from Logging

Inherited from QueryPlan[SparkPlan]

Inherited from SQLConfHelper

Inherited from TreeNode[SparkPlan]

Inherited from Product

Inherited from Equals

Inherited from AnyRef

Inherited from Any

Ungrouped