class GroupBy extends Serializable
Linear Supertypes
Ordering
- Alphabetic
- By Inheritance
Inherited
- GroupBy
- Serializable
- Serializable
- AnyRef
- Any
- Hide All
- Show All
Visibility
- Public
- All
Instance Constructors
- new GroupBy(aggregations: Seq[Aggregation], keyColumns: Seq[String], inputDf: DataFrame, mutationDf: DataFrame = null, skewFilter: Option[String] = None, finalize: Boolean = true)
Value Members
-
final
def
!=(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
final
def
##(): Int
- Definition Classes
- AnyRef → Any
-
final
def
==(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
- lazy val aggPartWithSchema: Seq[(AggregationPart, DataType)]
- lazy val aggregationParts: Seq[AggregationPart]
- val aggregations: Seq[Aggregation]
-
final
def
asInstanceOf[T0]: T0
- Definition Classes
- Any
-
def
clone(): AnyRef
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( ... ) @native()
- lazy val columnAggregators: Array[ColumnAggregator]
-
final
def
eq(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
-
def
equals(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
def
finalize(): Unit
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( classOf[java.lang.Throwable] )
-
final
def
getClass(): Class[_]
- Definition Classes
- AnyRef → Any
- Annotations
- @native()
-
def
hashCode(): Int
- Definition Classes
- AnyRef → Any
- Annotations
- @native()
- def hopsAggregate(minQueryTs: Long, resolution: Resolution): RDD[(KeyWithHash, OutputArrayType)]
- val inputDf: DataFrame
-
final
def
isInstanceOf[T0]: Boolean
- Definition Classes
- Any
- val keyColumns: Seq[String]
- val keySchema: StructType
- val mutationDf: DataFrame
-
final
def
ne(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
-
final
def
notify(): Unit
- Definition Classes
- AnyRef
- Annotations
- @native()
-
final
def
notifyAll(): Unit
- Definition Classes
- AnyRef
- Annotations
- @native()
- lazy val outputSchema: StructType
- lazy val postAggSchema: StructType
- val preAggSchema: StructType
-
val
selectedSchema: Array[(String, DataType)]
- Attributes
- protected
- def snapshotEntities: DataFrame
- def snapshotEntitiesBase: RDD[(Array[Any], Array[Any])]
- def snapshotEvents(partitionRange: PartitionRange): DataFrame
- def snapshotEventsBase(partitionRange: PartitionRange, resolution: Resolution = DailyResolution): RDD[(Array[Any], Array[Any])]
- implicit val sparkSession: SparkSession
-
final
def
synchronized[T0](arg0: ⇒ T0): T0
- Definition Classes
- AnyRef
-
def
temporalEntities(queriesUnfilteredDf: DataFrame, resolution: Resolution = FiveMinuteResolution): DataFrame
Support for entities with mutations.
Support for entities with mutations. Three way join between: Queries: grouped by key and dsOf[ts] Snapshot[InputDf]: Grouped by key and ds providing a FinalBatchIR to be extended. Mutations[MutationDf]: Grouped by key and dsOf[MutationTs] providing an array of updates/deletes to be done With this process the components (end of day batchIr + day's mutations + day's queries -> output)
- def temporalEvents(queriesUnfilteredDf: DataFrame, queryTimeRange: Option[TimeRange] = None, resolution: Resolution = FiveMinuteResolution): DataFrame
-
def
toDf(aggregateRdd: RDD[(Array[Any], Array[Any])], additionalFields: Seq[(String, DataType)]): DataFrame
- Attributes
- protected[spark]
-
def
toString(): String
- Definition Classes
- AnyRef → Any
-
val
tsIndex: Int
- Attributes
- protected[spark]
-
final
def
wait(): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws( ... )
-
final
def
wait(arg0: Long, arg1: Int): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws( ... )
-
final
def
wait(arg0: Long): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws( ... ) @native()
-
lazy val
windowAggregator: RowAggregator
- Attributes
- protected[spark]
- Annotations
- @transient()