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
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
|
package spark.api.java
import java.util.{List => JList}
import scala.Tuple2
import scala.collection.JavaConversions._
import spark.{SparkContext, Split, RDD, TaskContext}
import spark.api.java.JavaPairRDD._
import spark.api.java.function.{Function2 => JFunction2, Function => JFunction, _}
import spark.partial.{PartialResult, BoundedDouble}
import spark.storage.StorageLevel
trait JavaRDDLike[T, This <: JavaRDDLike[T, This]] extends Serializable {
def wrapRDD(rdd: RDD[T]): This
implicit val classManifest: ClassManifest[T]
def rdd: RDD[T]
/** Set of partitions in this RDD. */
def splits: JList[Split] = new java.util.ArrayList(rdd.splits.toSeq)
/** The [[spark.SparkContext]] that this RDD was created on. */
def context: SparkContext = rdd.context
/** A unique ID for this RDD (within its SparkContext). */
def id: Int = rdd.id
/** Get the RDD's current storage level, or StorageLevel.NONE if none is set. */
def getStorageLevel: StorageLevel = rdd.getStorageLevel
/**
* Internal method to this RDD; will read from cache if applicable, or otherwise compute it.
* This should ''not'' be called by users directly, but is available for implementors of custom
* subclasses of RDD.
*/
def iterator(split: Split, taskContext: TaskContext): java.util.Iterator[T] =
asJavaIterator(rdd.iterator(split, taskContext))
// Transformations (return a new RDD)
/**
* Return a new RDD by applying a function to all elements of this RDD.
*/
def map[R](f: JFunction[T, R]): JavaRDD[R] =
new JavaRDD(rdd.map(f)(f.returnType()))(f.returnType())
/**
* Return a new RDD by applying a function to all elements of this RDD.
*/
def map[R](f: DoubleFunction[T]): JavaDoubleRDD =
new JavaDoubleRDD(rdd.map(x => f(x).doubleValue()))
/**
* Return a new RDD by applying a function to all elements of this RDD.
*/
def map[K2, V2](f: PairFunction[T, K2, V2]): JavaPairRDD[K2, V2] = {
def cm = implicitly[ClassManifest[AnyRef]].asInstanceOf[ClassManifest[Tuple2[K2, V2]]]
new JavaPairRDD(rdd.map(f)(cm))(f.keyType(), f.valueType())
}
/**
* Return a new RDD by first applying a function to all elements of this
* RDD, and then flattening the results.
*/
def flatMap[U](f: FlatMapFunction[T, U]): JavaRDD[U] = {
import scala.collection.JavaConverters._
def fn = (x: T) => f.apply(x).asScala
JavaRDD.fromRDD(rdd.flatMap(fn)(f.elementType()))(f.elementType())
}
/**
* Return a new RDD by first applying a function to all elements of this
* RDD, and then flattening the results.
*/
def flatMap(f: DoubleFlatMapFunction[T]): JavaDoubleRDD = {
import scala.collection.JavaConverters._
def fn = (x: T) => f.apply(x).asScala
new JavaDoubleRDD(rdd.flatMap(fn).map((x: java.lang.Double) => x.doubleValue()))
}
/**
* Return a new RDD by first applying a function to all elements of this
* RDD, and then flattening the results.
*/
def flatMap[K, V](f: PairFlatMapFunction[T, K, V]): JavaPairRDD[K, V] = {
import scala.collection.JavaConverters._
def fn = (x: T) => f.apply(x).asScala
def cm = implicitly[ClassManifest[AnyRef]].asInstanceOf[ClassManifest[Tuple2[K, V]]]
JavaPairRDD.fromRDD(rdd.flatMap(fn)(cm))(f.keyType(), f.valueType())
}
/**
* Return a new RDD by applying a function to each partition of this RDD.
*/
def mapPartitions[U](f: FlatMapFunction[java.util.Iterator[T], U]): JavaRDD[U] = {
def fn = (x: Iterator[T]) => asScalaIterator(f.apply(asJavaIterator(x)).iterator())
JavaRDD.fromRDD(rdd.mapPartitions(fn)(f.elementType()))(f.elementType())
}
/**
* Return a new RDD by applying a function to each partition of this RDD.
*/
def mapPartitions(f: DoubleFlatMapFunction[java.util.Iterator[T]]): JavaDoubleRDD = {
def fn = (x: Iterator[T]) => asScalaIterator(f.apply(asJavaIterator(x)).iterator())
new JavaDoubleRDD(rdd.mapPartitions(fn).map((x: java.lang.Double) => x.doubleValue()))
}
/**
* Return a new RDD by applying a function to each partition of this RDD.
*/
def mapPartitions[K, V](f: PairFlatMapFunction[java.util.Iterator[T], K, V]):
JavaPairRDD[K, V] = {
def fn = (x: Iterator[T]) => asScalaIterator(f.apply(asJavaIterator(x)).iterator())
JavaPairRDD.fromRDD(rdd.mapPartitions(fn))(f.keyType(), f.valueType())
}
/**
* Return an RDD created by coalescing all elements within each partition into an array.
*/
def glom(): JavaRDD[JList[T]] =
new JavaRDD(rdd.glom().map(x => new java.util.ArrayList[T](x.toSeq)))
/**
* Return the Cartesian product of this RDD and another one, that is, the RDD of all pairs of
* elements (a, b) where a is in `this` and b is in `other`.
*/
def cartesian[U](other: JavaRDDLike[U, _]): JavaPairRDD[T, U] =
JavaPairRDD.fromRDD(rdd.cartesian(other.rdd)(other.classManifest))(classManifest,
other.classManifest)
/**
* Return an RDD of grouped elements. Each group consists of a key and a sequence of elements
* mapping to that key.
*/
def groupBy[K](f: JFunction[T, K]): JavaPairRDD[K, JList[T]] = {
implicit val kcm: ClassManifest[K] =
implicitly[ClassManifest[AnyRef]].asInstanceOf[ClassManifest[K]]
implicit val vcm: ClassManifest[JList[T]] =
implicitly[ClassManifest[AnyRef]].asInstanceOf[ClassManifest[JList[T]]]
JavaPairRDD.fromRDD(groupByResultToJava(rdd.groupBy(f)(f.returnType)))(kcm, vcm)
}
/**
* Return an RDD of grouped elements. Each group consists of a key and a sequence of elements
* mapping to that key.
*/
def groupBy[K](f: JFunction[T, K], numSplits: Int): JavaPairRDD[K, JList[T]] = {
implicit val kcm: ClassManifest[K] =
implicitly[ClassManifest[AnyRef]].asInstanceOf[ClassManifest[K]]
implicit val vcm: ClassManifest[JList[T]] =
implicitly[ClassManifest[AnyRef]].asInstanceOf[ClassManifest[JList[T]]]
JavaPairRDD.fromRDD(groupByResultToJava(rdd.groupBy(f, numSplits)(f.returnType)))(kcm, vcm)
}
/**
* Return an RDD created by piping elements to a forked external process.
*/
def pipe(command: String): JavaRDD[String] = rdd.pipe(command)
/**
* Return an RDD created by piping elements to a forked external process.
*/
def pipe(command: JList[String]): JavaRDD[String] =
rdd.pipe(asScalaBuffer(command))
/**
* Return an RDD created by piping elements to a forked external process.
*/
def pipe(command: JList[String], env: java.util.Map[String, String]): JavaRDD[String] =
rdd.pipe(asScalaBuffer(command), mapAsScalaMap(env))
/**
* Zips this RDD with another one, returning key-value pairs with the first element in each RDD,
* second element in each RDD, etc. Assumes that the two RDDs have the *same number of
* partitions* and the *same number of elements in each partition* (e.g. one was made through
* a map on the other).
*/
def zip[U](other: JavaRDDLike[U, _]): JavaPairRDD[T, U] = {
JavaPairRDD.fromRDD(rdd.zip(other.rdd)(other.classManifest))(classManifest, other.classManifest)
}
// Actions (launch a job to return a value to the user program)
/**
* Applies a function f to all elements of this RDD.
*/
def foreach(f: VoidFunction[T]) {
val cleanF = rdd.context.clean(f)
rdd.foreach(cleanF)
}
/**
* Return an array that contains all of the elements in this RDD.
*/
def collect(): JList[T] = {
import scala.collection.JavaConversions._
val arr: java.util.Collection[T] = rdd.collect().toSeq
new java.util.ArrayList(arr)
}
/**
* Reduces the elements of this RDD using the specified commutative and associative binary operator.
*/
def reduce(f: JFunction2[T, T, T]): T = rdd.reduce(f)
/**
* Aggregate the elements of each partition, and then the results for all the partitions, using a
* given associative function and a neutral "zero value". The function op(t1, t2) is allowed to
* modify t1 and return it as its result value to avoid object allocation; however, it should not
* modify t2.
*/
def fold(zeroValue: T)(f: JFunction2[T, T, T]): T =
rdd.fold(zeroValue)(f)
/**
* Aggregate the elements of each partition, and then the results for all the partitions, using
* given combine functions and a neutral "zero value". This function can return a different result
* type, U, than the type of this RDD, T. Thus, we need one operation for merging a T into an U
* and one operation for merging two U's, as in scala.TraversableOnce. Both of these functions are
* allowed to modify and return their first argument instead of creating a new U to avoid memory
* allocation.
*/
def aggregate[U](zeroValue: U)(seqOp: JFunction2[U, T, U],
combOp: JFunction2[U, U, U]): U =
rdd.aggregate(zeroValue)(seqOp, combOp)(seqOp.returnType)
/**
* Return the number of elements in the RDD.
*/
def count(): Long = rdd.count()
/**
* (Experimental) Approximate version of count() that returns a potentially incomplete result
* within a timeout, even if not all tasks have finished.
*/
def countApprox(timeout: Long, confidence: Double): PartialResult[BoundedDouble] =
rdd.countApprox(timeout, confidence)
/**
* (Experimental) Approximate version of count() that returns a potentially incomplete result
* within a timeout, even if not all tasks have finished.
*/
def countApprox(timeout: Long): PartialResult[BoundedDouble] =
rdd.countApprox(timeout)
/**
* Return the count of each unique value in this RDD as a map of (value, count) pairs. The final
* combine step happens locally on the master, equivalent to running a single reduce task.
*/
def countByValue(): java.util.Map[T, java.lang.Long] =
mapAsJavaMap(rdd.countByValue().map((x => (x._1, new java.lang.Long(x._2)))))
/**
* (Experimental) Approximate version of countByValue().
*/
def countByValueApprox(
timeout: Long,
confidence: Double
): PartialResult[java.util.Map[T, BoundedDouble]] =
rdd.countByValueApprox(timeout, confidence).map(mapAsJavaMap)
/**
* (Experimental) Approximate version of countByValue().
*/
def countByValueApprox(timeout: Long): PartialResult[java.util.Map[T, BoundedDouble]] =
rdd.countByValueApprox(timeout).map(mapAsJavaMap)
/**
* Take the first num elements of the RDD. This currently scans the partitions *one by one*, so
* it will be slow if a lot of partitions are required. In that case, use collect() to get the
* whole RDD instead.
*/
def take(num: Int): JList[T] = {
import scala.collection.JavaConversions._
val arr: java.util.Collection[T] = rdd.take(num).toSeq
new java.util.ArrayList(arr)
}
def takeSample(withReplacement: Boolean, num: Int, seed: Int): JList[T] = {
import scala.collection.JavaConversions._
val arr: java.util.Collection[T] = rdd.takeSample(withReplacement, num, seed).toSeq
new java.util.ArrayList(arr)
}
/**
* Return the first element in this RDD.
*/
def first(): T = rdd.first()
/**
* Save this RDD as a text file, using string representations of elements.
*/
def saveAsTextFile(path: String) = rdd.saveAsTextFile(path)
/**
* Save this RDD as a SequenceFile of serialized objects.
*/
def saveAsObjectFile(path: String) = rdd.saveAsObjectFile(path)
}
|