1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
|
/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package spark
import spark.partial.BoundedDouble
import spark.partial.MeanEvaluator
import spark.partial.PartialResult
import spark.partial.SumEvaluator
import spark.util.StatCounter
/**
* Extra functions available on RDDs of Doubles through an implicit conversion.
* Import `spark.SparkContext._` at the top of your program to use these functions.
*/
class DoubleRDDFunctions(self: RDD[Double]) extends Logging with Serializable {
/** Add up the elements in this RDD. */
def sum(): Double = {
self.reduce(_ + _)
}
/**
* Return a [[spark.util.StatCounter]] object that captures the mean, variance and count
* of the RDD's elements in one operation.
*/
def stats(): StatCounter = {
self.mapPartitions(nums => Iterator(StatCounter(nums))).reduce((a, b) => a.merge(b))
}
/** Compute the mean of this RDD's elements. */
def mean(): Double = stats().mean
/** Compute the variance of this RDD's elements. */
def variance(): Double = stats().variance
/** Compute the standard deviation of this RDD's elements. */
def stdev(): Double = stats().stdev
/**
* 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 sampleStdev(): Double = stats().stdev
/** (Experimental) Approximate operation to return the mean within a timeout. */
def meanApprox(timeout: Long, confidence: Double = 0.95): PartialResult[BoundedDouble] = {
val processPartition = (ctx: TaskContext, ns: Iterator[Double]) => StatCounter(ns)
val evaluator = new MeanEvaluator(self.partitions.size, confidence)
self.context.runApproximateJob(self, processPartition, evaluator, timeout)
}
/** (Experimental) Approximate operation to return the sum within a timeout. */
def sumApprox(timeout: Long, confidence: Double = 0.95): PartialResult[BoundedDouble] = {
val processPartition = (ctx: TaskContext, ns: Iterator[Double]) => StatCounter(ns)
val evaluator = new SumEvaluator(self.partitions.size, confidence)
self.context.runApproximateJob(self, processPartition, evaluator, timeout)
}
}
|
