spark-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From m...@apache.org
Subject git commit: [SPARK-2724] Python version of RandomRDDGenerators
Date Fri, 01 Aug 2014 03:33:04 GMT
Repository: spark
Updated Branches:
  refs/heads/master 8f51491ea -> d8430148e


[SPARK-2724] Python version of RandomRDDGenerators

RandomRDDGenerators but without support for randomRDD and randomVectorRDD, which take in arbitrary
DistributionGenerator.

`randomRDD.py` is named to avoid collision with the built-in Python `random` package.

Author: Doris Xin <doris.s.xin@gmail.com>

Closes #1628 from dorx/pythonRDD and squashes the following commits:

55c6de8 [Doris Xin] review comments. all python units passed.
f831d9b [Doris Xin] moved default args logic into PythonMLLibAPI
2d73917 [Doris Xin] fix for linalg.py
8663e6a [Doris Xin] reverting back to a single python file for random
f47c481 [Doris Xin] docs update
687aac0 [Doris Xin] add RandomRDDGenerators.py to run-tests
4338f40 [Doris Xin] renamed randomRDD to rand and import as random
29d205e [Doris Xin] created mllib.random package
bd2df13 [Doris Xin] typos
07ddff2 [Doris Xin] units passed.
23b2ecd [Doris Xin] WIP


Project: http://git-wip-us.apache.org/repos/asf/spark/repo
Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/d8430148
Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/d8430148
Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/d8430148

Branch: refs/heads/master
Commit: d8430148ee1f6ba02569db0538eeae473a32c78e
Parents: 8f51491
Author: Doris Xin <doris.s.xin@gmail.com>
Authored: Thu Jul 31 20:32:57 2014 -0700
Committer: Xiangrui Meng <meng@databricks.com>
Committed: Thu Jul 31 20:32:57 2014 -0700

----------------------------------------------------------------------
 .../spark/mllib/api/python/PythonMLLibAPI.scala |  97 ++++++++++
 .../mllib/random/RandomRDDGenerators.scala      |  90 +++++----
 python/pyspark/__init__.py                      |  10 +
 python/pyspark/mllib/linalg.py                  |   4 +
 python/pyspark/mllib/random.py                  | 182 +++++++++++++++++++
 python/run-tests                                |   1 +
 6 files changed, 348 insertions(+), 36 deletions(-)
----------------------------------------------------------------------


http://git-wip-us.apache.org/repos/asf/spark/blob/d8430148/mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala b/mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala
index 954621e..d2e8ccf 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala
@@ -24,10 +24,12 @@ import org.apache.spark.api.java.{JavaSparkContext, JavaRDD}
 import org.apache.spark.mllib.classification._
 import org.apache.spark.mllib.clustering._
 import org.apache.spark.mllib.linalg.{SparseVector, Vector, Vectors}
+import org.apache.spark.mllib.random.{RandomRDDGenerators => RG}
 import org.apache.spark.mllib.recommendation._
 import org.apache.spark.mllib.regression._
 import org.apache.spark.mllib.util.MLUtils
 import org.apache.spark.rdd.RDD
+import org.apache.spark.util.Utils
 
 /**
  * :: DeveloperApi ::
@@ -453,4 +455,99 @@ class PythonMLLibAPI extends Serializable {
     val ratings = ratingsBytesJRDD.rdd.map(unpackRating)
     ALS.trainImplicit(ratings, rank, iterations, lambda, blocks, alpha)
   }
+
+  // Used by the *RDD methods to get default seed if not passed in from pyspark
+  private def getSeedOrDefault(seed: java.lang.Long): Long = {
+    if (seed == null) Utils.random.nextLong else seed
+  }
+
+  // Used by *RDD methods to get default numPartitions if not passed in from pyspark
+  private def getNumPartitionsOrDefault(numPartitions: java.lang.Integer,
+      jsc: JavaSparkContext): Int = {
+    if (numPartitions == null) {
+      jsc.sc.defaultParallelism
+    } else {
+      numPartitions
+    }
+  }
+
+  // Note: for the following methods, numPartitions and seed are boxed to allow nulls to
be passed
+  // in for either argument from pyspark
+
+  /**
+   * Java stub for Python mllib RandomRDDGenerators.uniformRDD()
+   */
+  def uniformRDD(jsc: JavaSparkContext,
+      size: Long,
+      numPartitions: java.lang.Integer,
+      seed: java.lang.Long): JavaRDD[Array[Byte]] = {
+    val parts = getNumPartitionsOrDefault(numPartitions, jsc)
+    val s = getSeedOrDefault(seed)
+    RG.uniformRDD(jsc.sc, size, parts, s).map(serializeDouble)
+  }
+
+  /**
+   * Java stub for Python mllib RandomRDDGenerators.normalRDD()
+   */
+  def normalRDD(jsc: JavaSparkContext,
+      size: Long,
+      numPartitions: java.lang.Integer,
+      seed: java.lang.Long): JavaRDD[Array[Byte]] = {
+    val parts = getNumPartitionsOrDefault(numPartitions, jsc)
+    val s = getSeedOrDefault(seed)
+    RG.normalRDD(jsc.sc, size, parts, s).map(serializeDouble)
+  }
+
+  /**
+   * Java stub for Python mllib RandomRDDGenerators.poissonRDD()
+   */
+  def poissonRDD(jsc: JavaSparkContext,
+      mean: Double,
+      size: Long,
+      numPartitions: java.lang.Integer,
+      seed: java.lang.Long): JavaRDD[Array[Byte]] = {
+    val parts = getNumPartitionsOrDefault(numPartitions, jsc)
+    val s = getSeedOrDefault(seed)
+    RG.poissonRDD(jsc.sc, mean, size, parts, s).map(serializeDouble)
+  }
+
+  /**
+   * Java stub for Python mllib RandomRDDGenerators.uniformVectorRDD()
+   */
+  def uniformVectorRDD(jsc: JavaSparkContext,
+      numRows: Long,
+      numCols: Int,
+      numPartitions: java.lang.Integer,
+      seed: java.lang.Long): JavaRDD[Array[Byte]] = {
+    val parts = getNumPartitionsOrDefault(numPartitions, jsc)
+    val s = getSeedOrDefault(seed)
+    RG.uniformVectorRDD(jsc.sc, numRows, numCols, parts, s).map(serializeDoubleVector)
+  }
+
+  /**
+   * Java stub for Python mllib RandomRDDGenerators.normalVectorRDD()
+   */
+  def normalVectorRDD(jsc: JavaSparkContext,
+      numRows: Long,
+      numCols: Int,
+      numPartitions: java.lang.Integer,
+      seed: java.lang.Long): JavaRDD[Array[Byte]] = {
+    val parts = getNumPartitionsOrDefault(numPartitions, jsc)
+    val s = getSeedOrDefault(seed)
+    RG.normalVectorRDD(jsc.sc, numRows, numCols, parts, s).map(serializeDoubleVector)
+  }
+
+  /**
+   * Java stub for Python mllib RandomRDDGenerators.poissonVectorRDD()
+   */
+  def poissonVectorRDD(jsc: JavaSparkContext,
+      mean: Double,
+      numRows: Long,
+      numCols: Int,
+      numPartitions: java.lang.Integer,
+      seed: java.lang.Long): JavaRDD[Array[Byte]] = {
+    val parts = getNumPartitionsOrDefault(numPartitions, jsc)
+    val s = getSeedOrDefault(seed)
+    RG.poissonVectorRDD(jsc.sc, mean, numRows, numCols, parts, s).map(serializeDoubleVector)
+  }
 }

http://git-wip-us.apache.org/repos/asf/spark/blob/d8430148/mllib/src/main/scala/org/apache/spark/mllib/random/RandomRDDGenerators.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/random/RandomRDDGenerators.scala
b/mllib/src/main/scala/org/apache/spark/mllib/random/RandomRDDGenerators.scala
index d7ee2d3..021d651 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/random/RandomRDDGenerators.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/random/RandomRDDGenerators.scala
@@ -26,14 +26,17 @@ import org.apache.spark.util.Utils
 
 /**
  * :: Experimental ::
- * Generator methods for creating RDDs comprised of i.i.d samples from some distribution.
+ * Generator methods for creating RDDs comprised of i.i.d. samples from some distribution.
  */
 @Experimental
 object RandomRDDGenerators {
 
   /**
    * :: Experimental ::
-   * Generates an RDD comprised of i.i.d samples from the uniform distribution on [0.0, 1.0].
+   * Generates an RDD comprised of i.i.d. samples from the uniform distribution on [0.0,
1.0].
+   *
+   * To transform the distribution in the generated RDD from U[0.0, 1.0] to U[a, b], use
+   * `RandomRDDGenerators.uniformRDD(sc, n, p, seed).map(v => a + (b - a) * v)`.
    *
    * @param sc SparkContext used to create the RDD.
    * @param size Size of the RDD.
@@ -49,7 +52,10 @@ object RandomRDDGenerators {
 
   /**
    * :: Experimental ::
-   * Generates an RDD comprised of i.i.d samples from the uniform distribution on [0.0, 1.0].
+   * Generates an RDD comprised of i.i.d. samples from the uniform distribution on [0.0,
1.0].
+   *
+   * To transform the distribution in the generated RDD from U[0.0, 1.0] to U[a, b], use
+   * `RandomRDDGenerators.uniformRDD(sc, n, p).map(v => a + (b - a) * v)`.
    *
    * @param sc SparkContext used to create the RDD.
    * @param size Size of the RDD.
@@ -63,9 +69,12 @@ object RandomRDDGenerators {
 
   /**
    * :: Experimental ::
-   * Generates an RDD comprised of i.i.d samples from the uniform distribution on [0.0, 1.0].
+   * Generates an RDD comprised of i.i.d. samples from the uniform distribution on [0.0,
1.0].
    * sc.defaultParallelism used for the number of partitions in the RDD.
    *
+   * To transform the distribution in the generated RDD from U[0.0, 1.0] to U[a, b], use
+   * `RandomRDDGenerators.uniformRDD(sc, n).map(v => a + (b - a) * v)`.
+   *
    * @param sc SparkContext used to create the RDD.
    * @param size Size of the RDD.
    * @return RDD[Double] comprised of i.i.d. samples ~ U[0.0, 1.0].
@@ -77,7 +86,10 @@ object RandomRDDGenerators {
 
   /**
    * :: Experimental ::
-   * Generates an RDD comprised of i.i.d samples from the standard normal distribution.
+   * Generates an RDD comprised of i.i.d. samples from the standard normal distribution.
+   *
+   * To transform the distribution in the generated RDD from standard normal to some other
normal
+   * N(mean, sigma), use `RandomRDDGenerators.normalRDD(sc, n, p, seed).map(v => mean
+ sigma * v)`.
    *
    * @param sc SparkContext used to create the RDD.
    * @param size Size of the RDD.
@@ -93,7 +105,10 @@ object RandomRDDGenerators {
 
   /**
    * :: Experimental ::
-   * Generates an RDD comprised of i.i.d samples from the standard normal distribution.
+   * Generates an RDD comprised of i.i.d. samples from the standard normal distribution.
+   *
+   * To transform the distribution in the generated RDD from standard normal to some other
normal
+   * N(mean, sigma), use `RandomRDDGenerators.normalRDD(sc, n, p).map(v => mean + sigma
* v)`.
    *
    * @param sc SparkContext used to create the RDD.
    * @param size Size of the RDD.
@@ -107,9 +122,12 @@ object RandomRDDGenerators {
 
   /**
    * :: Experimental ::
-   * Generates an RDD comprised of i.i.d samples from the standard normal distribution.
+   * Generates an RDD comprised of i.i.d. samples from the standard normal distribution.
    * sc.defaultParallelism used for the number of partitions in the RDD.
    *
+   * To transform the distribution in the generated RDD from standard normal to some other
normal
+   * N(mean, sigma), use `RandomRDDGenerators.normalRDD(sc, n).map(v => mean + sigma *
v)`.
+   *
    * @param sc SparkContext used to create the RDD.
    * @param size Size of the RDD.
    * @return RDD[Double] comprised of i.i.d. samples ~ N(0.0, 1.0).
@@ -121,7 +139,7 @@ object RandomRDDGenerators {
 
   /**
    * :: Experimental ::
-   * Generates an RDD comprised of i.i.d samples from the Poisson distribution with the input
mean.
+   * Generates an RDD comprised of i.i.d. samples from the Poisson distribution with the
input mean.
    *
    * @param sc SparkContext used to create the RDD.
    * @param mean Mean, or lambda, for the Poisson distribution.
@@ -142,7 +160,7 @@ object RandomRDDGenerators {
 
   /**
    * :: Experimental ::
-   * Generates an RDD comprised of i.i.d samples from the Poisson distribution with the input
mean.
+   * Generates an RDD comprised of i.i.d. samples from the Poisson distribution with the
input mean.
    *
    * @param sc SparkContext used to create the RDD.
    * @param mean Mean, or lambda, for the Poisson distribution.
@@ -157,7 +175,7 @@ object RandomRDDGenerators {
 
   /**
    * :: Experimental ::
-   * Generates an RDD comprised of i.i.d samples from the Poisson distribution with the input
mean.
+   * Generates an RDD comprised of i.i.d. samples from the Poisson distribution with the
input mean.
    * sc.defaultParallelism used for the number of partitions in the RDD.
    *
    * @param sc SparkContext used to create the RDD.
@@ -172,7 +190,7 @@ object RandomRDDGenerators {
 
   /**
    * :: Experimental ::
-   * Generates an RDD comprised of i.i.d samples produced by the input DistributionGenerator.
+   * Generates an RDD comprised of i.i.d. samples produced by the input DistributionGenerator.
    *
    * @param sc SparkContext used to create the RDD.
    * @param generator DistributionGenerator used to populate the RDD.
@@ -192,7 +210,7 @@ object RandomRDDGenerators {
 
   /**
    * :: Experimental ::
-   * Generates an RDD comprised of i.i.d samples produced by the input DistributionGenerator.
+   * Generates an RDD comprised of i.i.d. samples produced by the input DistributionGenerator.
    *
    * @param sc SparkContext used to create the RDD.
    * @param generator DistributionGenerator used to populate the RDD.
@@ -210,7 +228,7 @@ object RandomRDDGenerators {
 
   /**
    * :: Experimental ::
-   * Generates an RDD comprised of i.i.d samples produced by the input DistributionGenerator.
+   * Generates an RDD comprised of i.i.d. samples produced by the input DistributionGenerator.
    * sc.defaultParallelism used for the number of partitions in the RDD.
    *
    * @param sc SparkContext used to create the RDD.
@@ -229,7 +247,7 @@ object RandomRDDGenerators {
 
   /**
    * :: Experimental ::
-   * Generates an RDD[Vector] with vectors containing i.i.d samples drawn from the
+   * Generates an RDD[Vector] with vectors containing i.i.d. samples drawn from the
    * uniform distribution on [0.0 1.0].
    *
    * @param sc SparkContext used to create the RDD.
@@ -251,14 +269,14 @@ object RandomRDDGenerators {
 
   /**
    * :: Experimental ::
-   * Generates an RDD[Vector] with vectors containing i.i.d samples drawn from the
+   * Generates an RDD[Vector] with vectors containing i.i.d. samples drawn from the
    * uniform distribution on [0.0 1.0].
    *
    * @param sc SparkContext used to create the RDD.
    * @param numRows Number of Vectors in the RDD.
    * @param numCols Number of elements in each Vector.
    * @param numPartitions Number of partitions in the RDD.
-   * @return RDD[Vector] with vectors containing i.i.d samples ~ U[0.0, 1.0].
+   * @return RDD[Vector] with vectors containing i.i.d. samples ~ U[0.0, 1.0].
    */
   @Experimental
   def uniformVectorRDD(sc: SparkContext,
@@ -270,14 +288,14 @@ object RandomRDDGenerators {
 
   /**
    * :: Experimental ::
-   * Generates an RDD[Vector] with vectors containing i.i.d samples drawn from the
+   * Generates an RDD[Vector] with vectors containing i.i.d. samples drawn from the
    * uniform distribution on [0.0 1.0].
    * sc.defaultParallelism used for the number of partitions in the RDD.
    *
    * @param sc SparkContext used to create the RDD.
    * @param numRows Number of Vectors in the RDD.
    * @param numCols Number of elements in each Vector.
-   * @return RDD[Vector] with vectors containing i.i.d samples ~ U[0.0, 1.0].
+   * @return RDD[Vector] with vectors containing i.i.d. samples ~ U[0.0, 1.0].
    */
   @Experimental
   def uniformVectorRDD(sc: SparkContext, numRows: Long, numCols: Int): RDD[Vector] = {
@@ -286,7 +304,7 @@ object RandomRDDGenerators {
 
   /**
    * :: Experimental ::
-   * Generates an RDD[Vector] with vectors containing i.i.d samples drawn from the
+   * Generates an RDD[Vector] with vectors containing i.i.d. samples drawn from the
    * standard normal distribution.
    *
    * @param sc SparkContext used to create the RDD.
@@ -294,7 +312,7 @@ object RandomRDDGenerators {
    * @param numCols Number of elements in each Vector.
    * @param numPartitions Number of partitions in the RDD.
    * @param seed Seed for the RNG that generates the seed for the generator in each partition.
-   * @return RDD[Vector] with vectors containing i.i.d samples ~ N(0.0, 1.0).
+   * @return RDD[Vector] with vectors containing i.i.d. samples ~ N(0.0, 1.0).
    */
   @Experimental
   def normalVectorRDD(sc: SparkContext,
@@ -308,14 +326,14 @@ object RandomRDDGenerators {
 
   /**
    * :: Experimental ::
-   * Generates an RDD[Vector] with vectors containing i.i.d samples drawn from the
+   * Generates an RDD[Vector] with vectors containing i.i.d. samples drawn from the
    * standard normal distribution.
    *
    * @param sc SparkContext used to create the RDD.
    * @param numRows Number of Vectors in the RDD.
    * @param numCols Number of elements in each Vector.
    * @param numPartitions Number of partitions in the RDD.
-   * @return RDD[Vector] with vectors containing i.i.d samples ~ N(0.0, 1.0).
+   * @return RDD[Vector] with vectors containing i.i.d. samples ~ N(0.0, 1.0).
    */
   @Experimental
   def normalVectorRDD(sc: SparkContext,
@@ -327,14 +345,14 @@ object RandomRDDGenerators {
 
   /**
    * :: Experimental ::
-   * Generates an RDD[Vector] with vectors containing i.i.d samples drawn from the
+   * Generates an RDD[Vector] with vectors containing i.i.d. samples drawn from the
    * standard normal distribution.
    * sc.defaultParallelism used for the number of partitions in the RDD.
    *
    * @param sc SparkContext used to create the RDD.
    * @param numRows Number of Vectors in the RDD.
    * @param numCols Number of elements in each Vector.
-   * @return RDD[Vector] with vectors containing i.i.d samples ~ N(0.0, 1.0).
+   * @return RDD[Vector] with vectors containing i.i.d. samples ~ N(0.0, 1.0).
    */
   @Experimental
   def normalVectorRDD(sc: SparkContext, numRows: Long, numCols: Int): RDD[Vector] = {
@@ -343,7 +361,7 @@ object RandomRDDGenerators {
 
   /**
    * :: Experimental ::
-   * Generates an RDD[Vector] with vectors containing i.i.d samples drawn from the
+   * Generates an RDD[Vector] with vectors containing i.i.d. samples drawn from the
    * Poisson distribution with the input mean.
    *
    * @param sc SparkContext used to create the RDD.
@@ -352,7 +370,7 @@ object RandomRDDGenerators {
    * @param numCols Number of elements in each Vector.
    * @param numPartitions Number of partitions in the RDD.
    * @param seed Seed for the RNG that generates the seed for the generator in each partition.
-   * @return RDD[Vector] with vectors containing i.i.d samples ~ Pois(mean).
+   * @return RDD[Vector] with vectors containing i.i.d. samples ~ Pois(mean).
    */
   @Experimental
   def poissonVectorRDD(sc: SparkContext,
@@ -367,7 +385,7 @@ object RandomRDDGenerators {
 
   /**
    * :: Experimental ::
-   * Generates an RDD[Vector] with vectors containing i.i.d samples drawn from the
+   * Generates an RDD[Vector] with vectors containing i.i.d. samples drawn from the
    * Poisson distribution with the input mean.
    *
    * @param sc SparkContext used to create the RDD.
@@ -375,7 +393,7 @@ object RandomRDDGenerators {
    * @param numRows Number of Vectors in the RDD.
    * @param numCols Number of elements in each Vector.
    * @param numPartitions Number of partitions in the RDD.
-   * @return RDD[Vector] with vectors containing i.i.d samples ~ Pois(mean).
+   * @return RDD[Vector] with vectors containing i.i.d. samples ~ Pois(mean).
    */
   @Experimental
   def poissonVectorRDD(sc: SparkContext,
@@ -388,7 +406,7 @@ object RandomRDDGenerators {
 
   /**
    * :: Experimental ::
-   * Generates an RDD[Vector] with vectors containing i.i.d samples drawn from the
+   * Generates an RDD[Vector] with vectors containing i.i.d. samples drawn from the
    * Poisson distribution with the input mean.
    * sc.defaultParallelism used for the number of partitions in the RDD.
    *
@@ -396,7 +414,7 @@ object RandomRDDGenerators {
    * @param mean Mean, or lambda, for the Poisson distribution.
    * @param numRows Number of Vectors in the RDD.
    * @param numCols Number of elements in each Vector.
-   * @return RDD[Vector] with vectors containing i.i.d samples ~ Pois(mean).
+   * @return RDD[Vector] with vectors containing i.i.d. samples ~ Pois(mean).
    */
   @Experimental
   def poissonVectorRDD(sc: SparkContext,
@@ -408,7 +426,7 @@ object RandomRDDGenerators {
 
   /**
    * :: Experimental ::
-   * Generates an RDD[Vector] with vectors containing i.i.d samples produced by the
+   * Generates an RDD[Vector] with vectors containing i.i.d. samples produced by the
    * input DistributionGenerator.
    *
    * @param sc SparkContext used to create the RDD.
@@ -417,7 +435,7 @@ object RandomRDDGenerators {
    * @param numCols Number of elements in each Vector.
    * @param numPartitions Number of partitions in the RDD.
    * @param seed Seed for the RNG that generates the seed for the generator in each partition.
-   * @return RDD[Vector] with vectors containing i.i.d samples produced by generator.
+   * @return RDD[Vector] with vectors containing i.i.d. samples produced by generator.
    */
   @Experimental
   def randomVectorRDD(sc: SparkContext,
@@ -431,7 +449,7 @@ object RandomRDDGenerators {
 
   /**
    * :: Experimental ::
-   * Generates an RDD[Vector] with vectors containing i.i.d samples produced by the
+   * Generates an RDD[Vector] with vectors containing i.i.d. samples produced by the
    * input DistributionGenerator.
    *
    * @param sc SparkContext used to create the RDD.
@@ -439,7 +457,7 @@ object RandomRDDGenerators {
    * @param numRows Number of Vectors in the RDD.
    * @param numCols Number of elements in each Vector.
    * @param numPartitions Number of partitions in the RDD.
-   * @return RDD[Vector] with vectors containing i.i.d samples produced by generator.
+   * @return RDD[Vector] with vectors containing i.i.d. samples produced by generator.
    */
   @Experimental
   def randomVectorRDD(sc: SparkContext,
@@ -452,7 +470,7 @@ object RandomRDDGenerators {
 
   /**
    * :: Experimental ::
-   * Generates an RDD[Vector] with vectors containing i.i.d samples produced by the
+   * Generates an RDD[Vector] with vectors containing i.i.d. samples produced by the
    * input DistributionGenerator.
    * sc.defaultParallelism used for the number of partitions in the RDD.
    *
@@ -460,7 +478,7 @@ object RandomRDDGenerators {
    * @param generator DistributionGenerator used to populate the RDD.
    * @param numRows Number of Vectors in the RDD.
    * @param numCols Number of elements in each Vector.
-   * @return RDD[Vector] with vectors containing i.i.d samples produced by generator.
+   * @return RDD[Vector] with vectors containing i.i.d. samples produced by generator.
    */
   @Experimental
   def randomVectorRDD(sc: SparkContext,

http://git-wip-us.apache.org/repos/asf/spark/blob/d8430148/python/pyspark/__init__.py
----------------------------------------------------------------------
diff --git a/python/pyspark/__init__.py b/python/pyspark/__init__.py
index 312c75d..c58555f 100644
--- a/python/pyspark/__init__.py
+++ b/python/pyspark/__init__.py
@@ -49,6 +49,16 @@ Hive:
       Main entry point for accessing data stored in Apache Hive..
 """
 
+# The following block allows us to import python's random instead of mllib.random for scripts
in
+# mllib that depend on top level pyspark packages, which transitively depend on python's
random.
+# Since Python's import logic looks for modules in the current package first, we eliminate
+# mllib.random as a candidate for C{import random} by removing the first search path, the
script's
+# location, in order to force the loader to look in Python's top-level modules for C{random}.
+import sys
+s = sys.path.pop(0)
+import random
+sys.path.insert(0, s)
+
 from pyspark.conf import SparkConf
 from pyspark.context import SparkContext
 from pyspark.sql import SQLContext

http://git-wip-us.apache.org/repos/asf/spark/blob/d8430148/python/pyspark/mllib/linalg.py
----------------------------------------------------------------------
diff --git a/python/pyspark/mllib/linalg.py b/python/pyspark/mllib/linalg.py
index 71f4ad1..54720c2 100644
--- a/python/pyspark/mllib/linalg.py
+++ b/python/pyspark/mllib/linalg.py
@@ -255,4 +255,8 @@ def _test():
         exit(-1)
 
 if __name__ == "__main__":
+    # remove current path from list of search paths to avoid importing mllib.random
+    # for C{import random}, which is done in an external dependency of pyspark during doctests.
+    import sys
+    sys.path.pop(0)
     _test()

http://git-wip-us.apache.org/repos/asf/spark/blob/d8430148/python/pyspark/mllib/random.py
----------------------------------------------------------------------
diff --git a/python/pyspark/mllib/random.py b/python/pyspark/mllib/random.py
new file mode 100644
index 0000000..36e710d
--- /dev/null
+++ b/python/pyspark/mllib/random.py
@@ -0,0 +1,182 @@
+#
+# 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.
+#
+
+"""
+Python package for random data generation.
+"""
+
+
+from pyspark.rdd import RDD
+from pyspark.mllib._common import _deserialize_double, _deserialize_double_vector
+from pyspark.serializers import NoOpSerializer
+
+class RandomRDDGenerators:
+    """
+    Generator methods for creating RDDs comprised of i.i.d samples from
+    some distribution.
+    """
+
+    @staticmethod
+    def uniformRDD(sc, size, numPartitions=None, seed=None):
+        """
+        Generates an RDD comprised of i.i.d. samples from the
+        uniform distribution on [0.0, 1.0].
+
+        To transform the distribution in the generated RDD from U[0.0, 1.0]
+        to U[a, b], use
+        C{RandomRDDGenerators.uniformRDD(sc, n, p, seed)\
+          .map(lambda v: a + (b - a) * v)}
+
+        >>> x = RandomRDDGenerators.uniformRDD(sc, 100).collect()
+        >>> len(x)
+        100
+        >>> max(x) <= 1.0 and min(x) >= 0.0
+        True
+        >>> RandomRDDGenerators.uniformRDD(sc, 100, 4).getNumPartitions()
+        4
+        >>> parts = RandomRDDGenerators.uniformRDD(sc, 100, seed=4).getNumPartitions()
+        >>> parts == sc.defaultParallelism
+        True
+        """
+        jrdd = sc._jvm.PythonMLLibAPI().uniformRDD(sc._jsc, size, numPartitions, seed)
+        uniform =  RDD(jrdd, sc, NoOpSerializer())
+        return uniform.map(lambda bytes: _deserialize_double(bytearray(bytes)))
+
+    @staticmethod
+    def normalRDD(sc, size, numPartitions=None, seed=None):
+        """
+        Generates an RDD comprised of i.i.d samples from the standard normal
+        distribution.
+
+        To transform the distribution in the generated RDD from standard normal
+        to some other normal N(mean, sigma), use
+        C{RandomRDDGenerators.normal(sc, n, p, seed)\
+          .map(lambda v: mean + sigma * v)}
+
+        >>> x = RandomRDDGenerators.normalRDD(sc, 1000, seed=1L)
+        >>> stats = x.stats()
+        >>> stats.count()
+        1000L
+        >>> abs(stats.mean() - 0.0) < 0.1
+        True
+        >>> abs(stats.stdev() - 1.0) < 0.1
+        True
+        """
+        jrdd = sc._jvm.PythonMLLibAPI().normalRDD(sc._jsc, size, numPartitions, seed)
+        normal =  RDD(jrdd, sc, NoOpSerializer())
+        return normal.map(lambda bytes: _deserialize_double(bytearray(bytes)))
+
+    @staticmethod
+    def poissonRDD(sc, mean, size, numPartitions=None, seed=None):
+        """
+        Generates an RDD comprised of i.i.d samples from the Poisson
+        distribution with the input mean.
+
+        >>> mean = 100.0
+        >>> x = RandomRDDGenerators.poissonRDD(sc, mean, 1000, seed=1L)
+        >>> stats = x.stats()
+        >>> stats.count()
+        1000L
+        >>> abs(stats.mean() - mean) < 0.5
+        True
+        >>> from math import sqrt
+        >>> abs(stats.stdev() - sqrt(mean)) < 0.5
+        True
+        """
+        jrdd = sc._jvm.PythonMLLibAPI().poissonRDD(sc._jsc, mean, size, numPartitions, seed)
+        poisson =  RDD(jrdd, sc, NoOpSerializer())
+        return poisson.map(lambda bytes: _deserialize_double(bytearray(bytes)))
+
+    @staticmethod
+    def uniformVectorRDD(sc, numRows, numCols, numPartitions=None, seed=None):
+        """
+        Generates an RDD comprised of vectors containing i.i.d samples drawn
+        from the uniform distribution on [0.0 1.0].
+
+        >>> import numpy as np
+        >>> mat = np.matrix(RandomRDDGenerators.uniformVectorRDD(sc, 10, 10).collect())
+        >>> mat.shape
+        (10, 10)
+        >>> mat.max() <= 1.0 and mat.min() >= 0.0
+        True
+        >>> RandomRDDGenerators.uniformVectorRDD(sc, 10, 10, 4).getNumPartitions()
+        4
+        """
+        jrdd = sc._jvm.PythonMLLibAPI() \
+            .uniformVectorRDD(sc._jsc, numRows, numCols, numPartitions, seed)
+        uniform =  RDD(jrdd, sc, NoOpSerializer())
+        return uniform.map(lambda bytes: _deserialize_double_vector(bytearray(bytes)))
+
+    @staticmethod
+    def normalVectorRDD(sc, numRows, numCols, numPartitions=None, seed=None):
+        """
+        Generates an RDD comprised of vectors containing i.i.d samples drawn
+        from the standard normal distribution.
+
+        >>> import numpy as np
+        >>> mat = np.matrix(RandomRDDGenerators.normalVectorRDD(sc, 100, 100, seed=1L).collect())
+        >>> mat.shape
+        (100, 100)
+        >>> abs(mat.mean() - 0.0) < 0.1
+        True
+        >>> abs(mat.std() - 1.0) < 0.1
+        True
+        """
+        jrdd = sc._jvm.PythonMLLibAPI() \
+            .normalVectorRDD(sc._jsc, numRows, numCols, numPartitions, seed)
+        normal =  RDD(jrdd, sc, NoOpSerializer())
+        return normal.map(lambda bytes: _deserialize_double_vector(bytearray(bytes)))
+
+    @staticmethod
+    def poissonVectorRDD(sc, mean, numRows, numCols, numPartitions=None, seed=None):
+        """
+        Generates an RDD comprised of vectors containing i.i.d samples drawn
+        from the Poisson distribution with the input mean.
+
+        >>> import numpy as np
+        >>> mean = 100.0
+        >>> rdd = RandomRDDGenerators.poissonVectorRDD(sc, mean, 100, 100, seed=1L)
+        >>> mat = np.mat(rdd.collect())
+        >>> mat.shape
+        (100, 100)
+        >>> abs(mat.mean() - mean) < 0.5
+        True
+        >>> from math import sqrt
+        >>> abs(mat.std() - sqrt(mean)) < 0.5
+        True
+        """
+        jrdd = sc._jvm.PythonMLLibAPI() \
+            .poissonVectorRDD(sc._jsc, mean, numRows, numCols, numPartitions, seed)
+        poisson =  RDD(jrdd, sc, NoOpSerializer())
+        return poisson.map(lambda bytes: _deserialize_double_vector(bytearray(bytes)))
+
+
+def _test():
+    import doctest
+    from pyspark.context import SparkContext
+    globs = globals().copy()
+    # The small batch size here ensures that we see multiple batches,
+    # even in these small test examples:
+    globs['sc'] = SparkContext('local[2]', 'PythonTest', batchSize=2)
+    (failure_count, test_count) = doctest.testmod(globs=globs, optionflags=doctest.ELLIPSIS)
+    globs['sc'].stop()
+    if failure_count:
+        exit(-1)
+
+
+if __name__ == "__main__":
+    _test()

http://git-wip-us.apache.org/repos/asf/spark/blob/d8430148/python/run-tests
----------------------------------------------------------------------
diff --git a/python/run-tests b/python/run-tests
index 29f755f..5049e15 100755
--- a/python/run-tests
+++ b/python/run-tests
@@ -67,6 +67,7 @@ run_test "pyspark/mllib/_common.py"
 run_test "pyspark/mllib/classification.py"
 run_test "pyspark/mllib/clustering.py"
 run_test "pyspark/mllib/linalg.py"
+run_test "pyspark/mllib/random.py"
 run_test "pyspark/mllib/recommendation.py"
 run_test "pyspark/mllib/regression.py"
 run_test "pyspark/mllib/tests.py"


Mime
View raw message