DoubleRDDFunctions

Instance Constructors

new DoubleRDDFunctions(self: RDD[Double])

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 def asInstanceOf[T0]: T0

Definition Classes
Any
def clone(): AnyRef

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( ... )
final def eq(arg0: AnyRef): Boolean

Definition Classes
AnyRef
def equals(arg0: Any): Boolean

Definition Classes
AnyRef → Any
def finalize(): Unit

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

Definition Classes
AnyRef → Any
def hashCode(): Int

Definition Classes
AnyRef → Any
def histogram(buckets: Array[Double], evenBuckets: Boolean = false): Array[Long]

Compute a histogram using the provided buckets.
Compute a histogram using the provided buckets. The buckets are all open to the right except for the last which is closed. e.g. for the array [1, 10, 20, 50] the buckets are [1, 10) [10, 20) [20, 50] e.g <=x<10, 10<=x<20, 20<=x<=50 And on the input of 1 and 50 we would have a histogram of 1, 0, 1

Note
If your histogram is evenly spaced (e.g. [0, 10, 20, 30]) this can be switched from an O(log n) insertion to O(1) per element. (where n = # buckets) if you set evenBuckets to true. buckets must be sorted and not contain any duplicates. buckets array must be at least two elements All NaN entries are treated the same. If you have a NaN bucket it must be the maximum value of the last position and all NaN entries will be counted in that bucket.
def histogram(bucketCount: Int): (Array[Double], Array[Long])

Compute a histogram of the data using bucketCount number of buckets evenly spaced between the minimum and maximum of the RDD.
Compute a histogram of the data using bucketCount number of buckets evenly spaced between the minimum and maximum of the RDD. For example if the min value is 0 and the max is 100 and there are two buckets the resulting buckets will be [0, 50) [50, 100]. bucketCount must be at least 1 If the RDD contains infinity, NaN throws an exception If the elements in RDD do not vary (max == min) always returns a single bucket.
def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean = false): Boolean

Attributes
protected
Definition Classes
Logging
def initializeLogIfNecessary(isInterpreter: Boolean): Unit

Attributes
protected
Definition Classes
Logging
final def isInstanceOf[T0]: Boolean

Definition Classes
Any
def isTraceEnabled(): Boolean

Attributes
protected
Definition Classes
Logging
def log: Logger

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

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

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

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

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

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

Attributes
protected
Definition Classes
Logging
def logName: String

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

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

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

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

Attributes
protected
Definition Classes
Logging
def mean(): Double

Compute the mean of this RDD's elements.
def meanApprox(timeout: Long, confidence: Double = 0.95): PartialResult[BoundedDouble]

Approximate operation to return the mean within a timeout.
final def ne(arg0: AnyRef): Boolean

Definition Classes
AnyRef
final def notify(): Unit

Definition Classes
AnyRef
final def notifyAll(): Unit

Definition Classes
AnyRef
def popStdev(): Double

Compute the population standard deviation of this RDD's elements.
Compute the population standard deviation of this RDD's elements.

Annotations
@Since( "2.1.0" )
def popVariance(): Double

Compute the population variance of this RDD's elements.
Compute the population variance of this RDD's elements.

Annotations
@Since( "2.1.0" )
def sampleStdev(): Double

Compute the sample standard deviation of this RDD's elements (which corrects for bias in estimating the standard deviation by dividing by N-1 instead of N).
def sampleVariance(): Double

Compute the sample variance of this RDD's elements (which corrects for bias in estimating the variance by dividing by N-1 instead of N).
def stats(): StatCounter

Return a org.apache.spark.util.StatCounter object that captures the mean, variance and count of the RDD's elements in one operation.
def stdev(): Double

Compute the population standard deviation of this RDD's elements.
def sum(): Double

Add up the elements in this RDD.
def sumApprox(timeout: Long, confidence: Double = 0.95): PartialResult[BoundedDouble]

Approximate operation to return the sum within a timeout.
final def synchronized[T0](arg0: ⇒ T0): T0

Definition Classes
AnyRef
def toString(): String

Definition Classes
AnyRef → Any
def variance(): Double

Compute the population variance of this RDD's elements.
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 rdd

class DoubleRDDFunctions extends Logging with Serializable

Instance Constructors

new DoubleRDDFunctions(self: RDD[Double])

Value Members

final def !=(arg0: Any): Boolean

final def ##(): Int

final def ==(arg0: Any): Boolean

final def asInstanceOf[T0]: T0

def clone(): AnyRef

final def eq(arg0: AnyRef): Boolean

def equals(arg0: Any): Boolean

def finalize(): Unit

final def getClass(): Class[_]

def hashCode(): Int

def histogram(buckets: Array[Double], evenBuckets: Boolean = false): Array[Long]

def histogram(bucketCount: Int): (Array[Double], Array[Long])

def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean = false): Boolean

def initializeLogIfNecessary(isInterpreter: Boolean): Unit

final def isInstanceOf[T0]: Boolean

def isTraceEnabled(): Boolean

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

def mean(): Double

def meanApprox(timeout: Long, confidence: Double = 0.95): PartialResult[BoundedDouble]

final def ne(arg0: AnyRef): Boolean

final def notify(): Unit

final def notifyAll(): Unit

def popStdev(): Double

def popVariance(): Double

def sampleStdev(): Double

def sampleVariance(): Double

def stats(): StatCounter

def stdev(): Double

def sum(): Double

def sumApprox(timeout: Long, confidence: Double = 0.95): PartialResult[BoundedDouble]

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

def toString(): String

def variance(): Double

final def wait(): Unit

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

final def wait(arg0: Long): Unit

Inherited from Serializable

Inherited from Serializable

Inherited from Logging

Inherited from AnyRef

Inherited from Any

Ungrouped