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
|
/*
* 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 org.apache.spark.partial
import org.apache.commons.math3.distribution.{NormalDistribution, TDistribution}
import org.apache.spark.util.StatCounter
/**
* An ApproximateEvaluator for sums. It estimates the mean and the count and multiplies them
* together, then uses the formula for the variance of two independent random variables to get
* a variance for the result and compute a confidence interval.
*/
private[spark] class SumEvaluator(totalOutputs: Int, confidence: Double)
extends ApproximateEvaluator[StatCounter, BoundedDouble] {
var outputsMerged = 0
var counter = new StatCounter
override def merge(outputId: Int, taskResult: StatCounter) {
outputsMerged += 1
counter.merge(taskResult)
}
override def currentResult(): BoundedDouble = {
if (outputsMerged == totalOutputs) {
new BoundedDouble(counter.sum, 1.0, counter.sum, counter.sum)
} else if (outputsMerged == 0) {
new BoundedDouble(0, 0.0, Double.NegativeInfinity, Double.PositiveInfinity)
} else {
val p = outputsMerged.toDouble / totalOutputs
val meanEstimate = counter.mean
val meanVar = counter.sampleVariance / counter.count
val countEstimate = (counter.count + 1 - p) / p
val countVar = (counter.count + 1) * (1 - p) / (p * p)
val sumEstimate = meanEstimate * countEstimate
val sumVar = (meanEstimate * meanEstimate * countVar) +
(countEstimate * countEstimate * meanVar) +
(meanVar * countVar)
val sumStdev = math.sqrt(sumVar)
val confFactor = {
if (counter.count > 100) {
new NormalDistribution().inverseCumulativeProbability(1 - (1 - confidence) / 2)
} else {
val degreesOfFreedom = (counter.count - 1).toInt
new TDistribution(degreesOfFreedom).inverseCumulativeProbability(1 - (1 - confidence) / 2)
}
}
val low = sumEstimate - confFactor * sumStdev
val high = sumEstimate + confFactor * sumStdev
new BoundedDouble(sumEstimate, confidence, low, high)
}
}
}
|
