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
73
74
75
76
77
78
79
80
81
82
|
/*
* 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.partial
import java.util.{HashMap => JHashMap}
import java.util.{Map => JMap}
import scala.collection.mutable.HashMap
import scala.collection.Map
import scala.collection.JavaConversions.mapAsScalaMap
import spark.util.StatCounter
/**
* An ApproximateEvaluator for means by key. Returns a map of key to confidence interval.
*/
private[spark] class GroupedMeanEvaluator[T](totalOutputs: Int, confidence: Double)
extends ApproximateEvaluator[JHashMap[T, StatCounter], Map[T, BoundedDouble]] {
var outputsMerged = 0
var sums = new JHashMap[T, StatCounter] // Sum of counts for each key
override def merge(outputId: Int, taskResult: JHashMap[T, StatCounter]) {
outputsMerged += 1
val iter = taskResult.entrySet.iterator()
while (iter.hasNext) {
val entry = iter.next()
val old = sums.get(entry.getKey)
if (old != null) {
old.merge(entry.getValue)
} else {
sums.put(entry.getKey, entry.getValue)
}
}
}
override def currentResult(): Map[T, BoundedDouble] = {
if (outputsMerged == totalOutputs) {
val result = new JHashMap[T, BoundedDouble](sums.size)
val iter = sums.entrySet.iterator()
while (iter.hasNext) {
val entry = iter.next()
val mean = entry.getValue.mean
result(entry.getKey) = new BoundedDouble(mean, 1.0, mean, mean)
}
result
} else if (outputsMerged == 0) {
new HashMap[T, BoundedDouble]
} else {
val p = outputsMerged.toDouble / totalOutputs
val studentTCacher = new StudentTCacher(confidence)
val result = new JHashMap[T, BoundedDouble](sums.size)
val iter = sums.entrySet.iterator()
while (iter.hasNext) {
val entry = iter.next()
val counter = entry.getValue
val mean = counter.mean
val stdev = math.sqrt(counter.sampleVariance / counter.count)
val confFactor = studentTCacher.get(counter.count)
val low = mean - confFactor * stdev
val high = mean + confFactor * stdev
result(entry.getKey) = new BoundedDouble(mean, confidence, low, high)
}
result
}
}
}
|
