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
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
|
/*
* 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.api.java
import spark.RDD
import spark.SparkContext.doubleRDDToDoubleRDDFunctions
import spark.api.java.function.{Function => JFunction}
import spark.util.StatCounter
import spark.partial.{BoundedDouble, PartialResult}
import spark.storage.StorageLevel
import java.lang.Double
import spark.Partitioner
class JavaDoubleRDD(val srdd: RDD[scala.Double]) extends JavaRDDLike[Double, JavaDoubleRDD] {
override val classManifest: ClassManifest[Double] = implicitly[ClassManifest[Double]]
override val rdd: RDD[Double] = srdd.map(x => Double.valueOf(x))
override def wrapRDD(rdd: RDD[Double]): JavaDoubleRDD =
new JavaDoubleRDD(rdd.map(_.doubleValue))
// Common RDD functions
import JavaDoubleRDD.fromRDD
/** Persist this RDD with the default storage level (`MEMORY_ONLY`). */
def cache(): JavaDoubleRDD = fromRDD(srdd.cache())
/**
* Set this RDD's storage level to persist its values across operations after the first time
* it is computed. Can only be called once on each RDD.
*/
def persist(newLevel: StorageLevel): JavaDoubleRDD = fromRDD(srdd.persist(newLevel))
// first() has to be overriden here in order for its return type to be Double instead of Object.
override def first(): Double = srdd.first()
// Transformations (return a new RDD)
/**
* Return a new RDD containing the distinct elements in this RDD.
*/
def distinct(): JavaDoubleRDD = fromRDD(srdd.distinct())
/**
* Return a new RDD containing the distinct elements in this RDD.
*/
def distinct(numPartitions: Int): JavaDoubleRDD = fromRDD(srdd.distinct(numPartitions))
/**
* Return a new RDD containing only the elements that satisfy a predicate.
*/
def filter(f: JFunction[Double, java.lang.Boolean]): JavaDoubleRDD =
fromRDD(srdd.filter(x => f(x).booleanValue()))
/**
* Return a new RDD that is reduced into `numPartitions` partitions.
*/
def coalesce(numPartitions: Int): JavaDoubleRDD = fromRDD(srdd.coalesce(numPartitions))
/**
* Return a new RDD that is reduced into `numPartitions` partitions.
*/
def coalesce(numPartitions: Int, shuffle: Boolean): JavaDoubleRDD =
fromRDD(srdd.coalesce(numPartitions, shuffle))
/**
* Return an RDD with the elements from `this` that are not in `other`.
*
* Uses `this` partitioner/partition size, because even if `other` is huge, the resulting
* RDD will be <= us.
*/
def subtract(other: JavaDoubleRDD): JavaDoubleRDD =
fromRDD(srdd.subtract(other))
/**
* Return an RDD with the elements from `this` that are not in `other`.
*/
def subtract(other: JavaDoubleRDD, numPartitions: Int): JavaDoubleRDD =
fromRDD(srdd.subtract(other, numPartitions))
/**
* Return an RDD with the elements from `this` that are not in `other`.
*/
def subtract(other: JavaDoubleRDD, p: Partitioner): JavaDoubleRDD =
fromRDD(srdd.subtract(other, p))
/**
* Return a sampled subset of this RDD.
*/
def sample(withReplacement: Boolean, fraction: Double, seed: Int): JavaDoubleRDD =
fromRDD(srdd.sample(withReplacement, fraction, seed))
/**
* Return the union of this RDD and another one. Any identical elements will appear multiple
* times (use `.distinct()` to eliminate them).
*/
def union(other: JavaDoubleRDD): JavaDoubleRDD = fromRDD(srdd.union(other.srdd))
// Double RDD functions
/** Return the sum of the elements in this RDD. */
def sum(): Double = srdd.sum()
/** Return a [[spark.StatCounter]] describing the elements in this RDD. */
def stats(): StatCounter = srdd.stats()
/** Return the mean of the elements in this RDD. */
def mean(): Double = srdd.mean()
/** Return the variance of the elements in this RDD. */
def variance(): Double = srdd.variance()
/** Return the standard deviation of the elements in this RDD. */
def stdev(): Double = srdd.stdev()
/** Return the approximate mean of the elements in this RDD. */
def meanApprox(timeout: Long, confidence: Double): PartialResult[BoundedDouble] =
srdd.meanApprox(timeout, confidence)
/** Return the approximate mean of the elements in this RDD. */
def meanApprox(timeout: Long): PartialResult[BoundedDouble] = srdd.meanApprox(timeout)
/** Return the approximate sum of the elements in this RDD. */
def sumApprox(timeout: Long, confidence: Double): PartialResult[BoundedDouble] =
srdd.sumApprox(timeout, confidence)
/** Return the approximate sum of the elements in this RDD. */
def sumApprox(timeout: Long): PartialResult[BoundedDouble] = srdd.sumApprox(timeout)
}
object JavaDoubleRDD {
def fromRDD(rdd: RDD[scala.Double]): JavaDoubleRDD = new JavaDoubleRDD(rdd)
implicit def toRDD(rdd: JavaDoubleRDD): RDD[scala.Double] = rdd.srdd
}
|
