ColumnFormatSamplingRelation

Instance Constructors

new ColumnFormatSamplingRelation(schema: StructType, baseRelation: BaseColumnFormatRelation, sqlContext: SQLContext, samplingOptions: Map[String, String], origOptions: Map[String, String], sampleTable: String, baseSchema: StructType, baseTable: Option[String], reservoirRegionName: String, basePartitioningColumns: Seq[String], baseNumPartition: Int)

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
final val PARTITIONBUFSIZE: Int(10)
def append(rows: RDD[Row], time: Long): Unit

Append a given RDD or rows into the relation.
Append a given RDD or rows into the relation.

Definition Classes
ColumnFormatSamplingRelation → SchemaInsertableRelation
final def asInstanceOf[T0]: T0

Definition Classes
Any
val baseNumPartition: Int
val basePartitioningColumns: Seq[String]
val baseRelation: BaseColumnFormatRelation

The underlying column table used to store data.
The underlying column table used to store data.

Definition Classes
ColumnFormatSamplingRelation → SamplingRelation
val baseSchema: StructType
val baseTable: Option[String]

Base table of this relation.
Base table of this relation.

Definition Classes
ColumnFormatSamplingRelation → SamplingRelation
def buildUnsafeScan(requiredColumns: Array[String], filters: Array[Expression]): (RDD[Any], Seq[RDD[InternalRow]])

Definition Classes
ColumnFormatSamplingRelation → PrunedUnsafeFilteredScan
def canBeOnBuildSide: Boolean

Definition Classes
ColumnFormatSamplingRelation → SamplingRelation
def clone(): AnyRef

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( ... )
def connectionType: execution.columnar.ConnectionType.Value

Definition Classes
ColumnFormatSamplingRelation → PartitionedDataSourceScan
def destroy(ifExists: Boolean): Unit

Destroy and cleanup this relation.
Destroy and cleanup this relation. It may include, but not limited to, dropping the external table that this relation represents.

Definition Classes
ColumnFormatSamplingRelation → DestroyRelation
final def eq(arg0: AnyRef): Boolean

Definition Classes
AnyRef
def finalize(): Unit

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( classOf[java.lang.Throwable] )
def flushReservoir(): Unit
final def getClass(): Class[_]

Definition Classes
AnyRef → Any
def getColocatedTable: Option[String]

Definition Classes
ColumnFormatSamplingRelation → PartitionedDataSourceScan
def getExternalStoreMetaData: ExternalTableMetaData
def initializeLogIfNecessary(): Unit

Attributes
protected
Definition Classes
Logging
def insert(data: DataFrame, overwrite: Boolean): Unit

Definition Classes
ColumnFormatSamplingRelation → InsertableRelation
def insertableRelation(sourceSchema: Seq[Attribute]): Option[InsertableRelation]

Return the actual relation to be used for insertion into the relation or None if sourceSchema cannot be inserted.
Return the actual relation to be used for insertion into the relation or None if sourceSchema cannot be inserted.

Definition Classes
ColumnFormatSamplingRelation → SchemaInsertableRelation
final def isDebugEnabled: Boolean

Definition Classes
Logging
final def isInfoEnabled: Boolean

Definition Classes
Logging
final def isInstanceOf[T0]: Boolean

Definition Classes
Any
val isPartitioned: Boolean

If underlying sample table is partitioned
If underlying sample table is partitioned

Definition Classes
ColumnFormatSamplingRelation → PartitionedDataSourceScan → SamplingRelation
val isReservoirAsRegion: Boolean

True if underlying sample table is using a row table as reservoir store.
True if underlying sample table is using a row table as reservoir store.

Definition Classes
ColumnFormatSamplingRelation → SamplingRelation
final def isTraceEnabled: Boolean

Definition Classes
Logging
final var levelFlags: Int

Attributes
protected
Definition Classes
Logging
def log: Logger

Attributes
protected
Definition Classes
Logging
def logDebug(msg: ⇒ String, throwable: Throwable): Unit

Definition Classes
Logging
def logDebug(msg: ⇒ String): Unit

Definition Classes
Logging
def logError(msg: ⇒ String, throwable: Throwable): Unit

Definition Classes
Logging
def logError(msg: ⇒ String): Unit

Definition Classes
Logging
def logInfo(msg: ⇒ String, throwable: Throwable): Unit

Definition Classes
Logging
def logInfo(msg: ⇒ String): Unit

Definition Classes
Logging
def logName: String

Attributes
protected
Definition Classes
Logging
def logTrace(msg: ⇒ String, throwable: Throwable): Unit

Definition Classes
Logging
def logTrace(msg: ⇒ String): Unit

Definition Classes
Logging
def logWarning(msg: ⇒ String, throwable: Throwable): Unit

Definition Classes
Logging
def logWarning(msg: ⇒ String): Unit

Definition Classes
Logging
final var log_: Logger

Attributes
protected
Definition Classes
Logging
final def ne(arg0: AnyRef): Boolean

Definition Classes
AnyRef
val needConversion: Boolean

Whether does it need to convert the objects in Row to internal representation, for example: java.lang.String to UTF8String java.lang.Decimal to Decimal
Whether does it need to convert the objects in Row to internal representation, for example: java.lang.String to UTF8String java.lang.Decimal to Decimal
If needConversion is false, buildScan() should return an RDD of InternalRow

Definition Classes
ColumnFormatSamplingRelation → BaseRelation
Since
1.4.0
Note
The internal representation is not stable across releases and thus data sources outside of Spark SQL should leave this as true.
final def notify(): Unit

Definition Classes
AnyRef
final def notifyAll(): Unit

Definition Classes
AnyRef
def numBuckets: Int

Definition Classes
ColumnFormatSamplingRelation → PartitionedDataSourceScan
lazy val options: SampleOptions
val origOptions: Map[String, String]
def partitionColumns: Seq[String]

Definition Classes
ColumnFormatSamplingRelation → PartitionedDataSourceScan
def qcs: Array[String]

The QCS columns for the sample.
The QCS columns for the sample.

Definition Classes
ColumnFormatSamplingRelation → SamplingRelation
lazy val region: LocalRegion

Definition Classes
ColumnFormatSamplingRelation → PartitionedDataSourceScan
val reservoirRegionName: String
def resetLogger(): Unit

Attributes
protected
Definition Classes
Logging
val sampleTable: String
val samplingOptions: Map[String, String]

Options set for this sampling relation.
Options set for this sampling relation.

Definition Classes
ColumnFormatSamplingRelation → SamplingRelation
val schema: StructType

Definition Classes
ColumnFormatSamplingRelation → PartitionedDataSourceScan → BaseRelation
def sizeInBytes: Long

Returns an estimated size of this relation in bytes.
Returns an estimated size of this relation in bytes. This information is used by the planner to decide when it is safe to broadcast a relation and can be overridden by sources that know the size ahead of time. By default, the system will assume that tables are too large to broadcast. This method will be called multiple times during query planning and thus should not perform expensive operations for each invocation.

Definition Classes
ColumnFormatSamplingRelation → BaseRelation
Since
1.3.0
Note
It is always better to overestimate size than underestimate, because underestimation could lead to execution plans that are suboptimal (i.e. broadcasting a very large table).
val sqlContext: SQLContext

Definition Classes
ColumnFormatSamplingRelation → BaseRelation
final def synchronized[T0](arg0: ⇒ T0): T0

Definition Classes
AnyRef
def table: String

Definition Classes
ColumnFormatSamplingRelation → PartitionedDataSourceScan
def toString(): String

Definition Classes
ColumnFormatSamplingRelation → AnyRef → Any
def truncate(): Unit

Truncate the table represented by this relation.
Truncate the table represented by this relation.

Definition Classes
ColumnFormatSamplingRelation → DestroyRelation
def unhandledFilters(filters: Seq[Expression]): Seq[Expression]

Returns the list of Expressions that this datasource may not be able to handle.
Returns the list of Expressions that this datasource may not be able to handle. By default, this function will return all filters, as it is always safe to double evaluate an Expression.

Definition Classes
ColumnFormatSamplingRelation → PrunedUnsafeFilteredScan
def unhandledFilters(filters: Array[Filter]): Array[Filter]

Returns the list of Filters that this datasource may not be able to handle.
Returns the list of Filters that this datasource may not be able to handle. These returned Filters will be evaluated by Spark SQL after data is output by a scan. By default, this function will return all filters, as it is always safe to double evaluate a Filter. However, specific implementations can override this function to avoid double filtering when they are capable of processing a filter internally.

Definition Classes
BaseRelation
Since
1.6.0
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( ... )

Related Doc: package sampling

Instance Constructors

Value Members

final def !=(arg0: Any): Boolean

final def ##(): Int

final def ==(arg0: Any): Boolean

final val PARTITIONBUFSIZE: Int(10)

def append(rows: RDD[Row], time: Long): Unit

final def asInstanceOf[T0]: T0

val baseNumPartition: Int

val basePartitioningColumns: Seq[String]

val baseRelation: BaseColumnFormatRelation

val baseSchema: StructType

val baseTable: Option[String]

def buildUnsafeScan(requiredColumns: Array[String], filters: Array[Expression]): (RDD[Any], Seq[RDD[InternalRow]])

def canBeOnBuildSide: Boolean

def clone(): AnyRef

def connectionType: execution.columnar.ConnectionType.Value

def destroy(ifExists: Boolean): Unit

final def eq(arg0: AnyRef): Boolean

def finalize(): Unit

def flushReservoir(): Unit

final def getClass(): Class[_]

def getColocatedTable: Option[String]

def getExternalStoreMetaData: ExternalTableMetaData

def initializeLogIfNecessary(): Unit

def insert(data: DataFrame, overwrite: Boolean): Unit

def insertableRelation(sourceSchema: Seq[Attribute]): Option[InsertableRelation]

final def isDebugEnabled: Boolean

final def isInfoEnabled: Boolean

final def isInstanceOf[T0]: Boolean

val isPartitioned: Boolean

val isReservoirAsRegion: Boolean

final def isTraceEnabled: Boolean

final var levelFlags: Int

def log: Logger

def logDebug(msg: ⇒ String, throwable: Throwable): Unit

def logDebug(msg: ⇒ String): Unit

def logError(msg: ⇒ String, throwable: Throwable): Unit

def logError(msg: ⇒ String): Unit

def logInfo(msg: ⇒ String, throwable: Throwable): Unit

def logInfo(msg: ⇒ String): Unit

def logName: String

def logTrace(msg: ⇒ String, throwable: Throwable): Unit

def logTrace(msg: ⇒ String): Unit

def logWarning(msg: ⇒ String, throwable: Throwable): Unit

def logWarning(msg: ⇒ String): Unit

final var log_: Logger

final def ne(arg0: AnyRef): Boolean

val needConversion: Boolean

final def notify(): Unit

final def notifyAll(): Unit

def numBuckets: Int

lazy val options: SampleOptions

val origOptions: Map[String, String]

def partitionColumns: Seq[String]

def qcs: Array[String]

lazy val region: LocalRegion

val reservoirRegionName: String

def resetLogger(): Unit

val sampleTable: String

val samplingOptions: Map[String, String]

val schema: StructType

def sizeInBytes: Long

val sqlContext: SQLContext

final def synchronized[T0](arg0: ⇒ T0): T0

def table: String

def toString(): String

def truncate(): Unit

def unhandledFilters(filters: Seq[Expression]): Seq[Expression]

def unhandledFilters(filters: Array[Filter]): Array[Filter]

final def wait(): Unit

final def wait(arg0: Long, arg1: Int): Unit

final def wait(arg0: Long): Unit

Inherited from Product

Inherited from Equals

Inherited from Serializable

Inherited from Serializable

Inherited from Logging