From d7dbce8f7da8a7fd01df6633a6043f51161b7d18 Mon Sep 17 00:00:00 2001 From: Burak Yavuz Date: Wed, 29 Apr 2015 15:34:05 -0700 Subject: [SPARK-7156][SQL] support RandomSplit in DataFrames This is built on top of kaka1992 's PR #5711 using Logical plans. Author: Burak Yavuz Closes #5761 from brkyvz/random-sample and squashes the following commits: a1fb0aa [Burak Yavuz] remove unrelated file 69669c3 [Burak Yavuz] fix broken test 1ddb3da [Burak Yavuz] copy base 6000328 [Burak Yavuz] added python api and fixed test 3c11d1b [Burak Yavuz] fixed broken test f400ade [Burak Yavuz] fix build errors 2384266 [Burak Yavuz] addressed comments v0.1 e98ebac [Burak Yavuz] [SPARK-7156][SQL] support RandomSplit in DataFrames --- .../org/apache/spark/sql/catalyst/dsl/package.scala | 6 ------ .../sql/catalyst/plans/logical/basicOperators.scala | 18 ++++++++++++++++-- 2 files changed, 16 insertions(+), 8 deletions(-) (limited to 'sql/catalyst') diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/dsl/package.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/dsl/package.scala index 5d5aba9644..fa6cc7a1a3 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/dsl/package.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/dsl/package.scala @@ -278,12 +278,6 @@ package object dsl { def sfilter[T1](arg1: Symbol)(udf: (T1) => Boolean): LogicalPlan = Filter(ScalaUdf(udf, BooleanType, Seq(UnresolvedAttribute(arg1.name))), logicalPlan) - def sample( - fraction: Double, - withReplacement: Boolean = true, - seed: Int = (math.random * 1000).toInt): LogicalPlan = - Sample(fraction, withReplacement, seed, logicalPlan) - // TODO specify the output column names def generate( generator: Generator, diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/basicOperators.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/basicOperators.scala index 608e272da7..21208c8a5c 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/basicOperators.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/basicOperators.scala @@ -300,8 +300,22 @@ case class Subquery(alias: String, child: LogicalPlan) extends UnaryNode { override def output: Seq[Attribute] = child.output.map(_.withQualifiers(alias :: Nil)) } -case class Sample(fraction: Double, withReplacement: Boolean, seed: Long, child: LogicalPlan) - extends UnaryNode { +/** + * Sample the dataset. + * + * @param lowerBound Lower-bound of the sampling probability (usually 0.0) + * @param upperBound Upper-bound of the sampling probability. The expected fraction sampled + * will be ub - lb. + * @param withReplacement Whether to sample with replacement. + * @param seed the random seed + * @param child the LogicalPlan + */ +case class Sample( + lowerBound: Double, + upperBound: Double, + withReplacement: Boolean, + seed: Long, + child: LogicalPlan) extends UnaryNode { override def output: Seq[Attribute] = child.output } -- cgit v1.2.3