You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spark.apache.org by ml...@apache.org on 2016/02/22 12:00:05 UTC
spark git commit: [SPARK-13334][ML] ML KMeansModel /
BisectingKMeansModel / QuantileDiscretizer should set parent
Repository: spark
Updated Branches:
refs/heads/master e298ac91e -> 40e6d40fe
[SPARK-13334][ML] ML KMeansModel / BisectingKMeansModel / QuantileDiscretizer should set parent
ML ```KMeansModel / BisectingKMeansModel / QuantileDiscretizer``` should set parent.
cc mengxr
Author: Yanbo Liang <yb...@gmail.com>
Closes #11214 from yanboliang/spark-13334.
Project: http://git-wip-us.apache.org/repos/asf/spark/repo
Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/40e6d40f
Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/40e6d40f
Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/40e6d40f
Branch: refs/heads/master
Commit: 40e6d40fe79ce45d511e049133d2f30a2963740b
Parents: e298ac9
Author: Yanbo Liang <yb...@gmail.com>
Authored: Mon Feb 22 12:59:50 2016 +0200
Committer: Nick Pentreath <ni...@gmail.com>
Committed: Mon Feb 22 12:59:50 2016 +0200
----------------------------------------------------------------------
.../scala/org/apache/spark/ml/clustering/BisectingKMeans.scala | 2 +-
mllib/src/main/scala/org/apache/spark/ml/clustering/KMeans.scala | 2 +-
.../scala/org/apache/spark/ml/feature/QuantileDiscretizer.scala | 2 +-
.../org/apache/spark/ml/clustering/BisectingKMeansSuite.scala | 1 +
.../test/scala/org/apache/spark/ml/clustering/KMeansSuite.scala | 1 +
.../org/apache/spark/ml/feature/QuantileDiscretizerSuite.scala | 4 +++-
6 files changed, 8 insertions(+), 4 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/spark/blob/40e6d40f/mllib/src/main/scala/org/apache/spark/ml/clustering/BisectingKMeans.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/ml/clustering/BisectingKMeans.scala b/mllib/src/main/scala/org/apache/spark/ml/clustering/BisectingKMeans.scala
index 0b47cbb..45d293b 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/clustering/BisectingKMeans.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/clustering/BisectingKMeans.scala
@@ -185,7 +185,7 @@ class BisectingKMeans @Since("2.0.0") (
.setSeed($(seed))
val parentModel = bkm.run(rdd)
val model = new BisectingKMeansModel(uid, parentModel)
- copyValues(model)
+ copyValues(model.setParent(this))
}
@Since("2.0.0")
http://git-wip-us.apache.org/repos/asf/spark/blob/40e6d40f/mllib/src/main/scala/org/apache/spark/ml/clustering/KMeans.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/ml/clustering/KMeans.scala b/mllib/src/main/scala/org/apache/spark/ml/clustering/KMeans.scala
index dc6d5d9..b2292e2 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/clustering/KMeans.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/clustering/KMeans.scala
@@ -250,7 +250,7 @@ class KMeans @Since("1.5.0") (
.setEpsilon($(tol))
val parentModel = algo.run(rdd)
val model = new KMeansModel(uid, parentModel)
- copyValues(model)
+ copyValues(model.setParent(this))
}
@Since("1.5.0")
http://git-wip-us.apache.org/repos/asf/spark/blob/40e6d40f/mllib/src/main/scala/org/apache/spark/ml/feature/QuantileDiscretizer.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/QuantileDiscretizer.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/QuantileDiscretizer.scala
index 2a294d3..1f4cca1 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/QuantileDiscretizer.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/QuantileDiscretizer.scala
@@ -95,7 +95,7 @@ final class QuantileDiscretizer(override val uid: String)
val candidates = QuantileDiscretizer.findSplitCandidates(samples, $(numBuckets) - 1)
val splits = QuantileDiscretizer.getSplits(candidates)
val bucketizer = new Bucketizer(uid).setSplits(splits)
- copyValues(bucketizer)
+ copyValues(bucketizer.setParent(this))
}
override def copy(extra: ParamMap): QuantileDiscretizer = defaultCopy(extra)
http://git-wip-us.apache.org/repos/asf/spark/blob/40e6d40f/mllib/src/test/scala/org/apache/spark/ml/clustering/BisectingKMeansSuite.scala
----------------------------------------------------------------------
diff --git a/mllib/src/test/scala/org/apache/spark/ml/clustering/BisectingKMeansSuite.scala b/mllib/src/test/scala/org/apache/spark/ml/clustering/BisectingKMeansSuite.scala
index b26571e..fc4a4ad 100644
--- a/mllib/src/test/scala/org/apache/spark/ml/clustering/BisectingKMeansSuite.scala
+++ b/mllib/src/test/scala/org/apache/spark/ml/clustering/BisectingKMeansSuite.scala
@@ -81,5 +81,6 @@ class BisectingKMeansSuite extends SparkFunSuite with MLlibTestSparkContext {
assert(clusters.size === k)
assert(clusters === Set(0, 1, 2, 3, 4))
assert(model.computeCost(dataset) < 0.1)
+ assert(model.hasParent)
}
}
http://git-wip-us.apache.org/repos/asf/spark/blob/40e6d40f/mllib/src/test/scala/org/apache/spark/ml/clustering/KMeansSuite.scala
----------------------------------------------------------------------
diff --git a/mllib/src/test/scala/org/apache/spark/ml/clustering/KMeansSuite.scala b/mllib/src/test/scala/org/apache/spark/ml/clustering/KMeansSuite.scala
index 2724e51..e5357ba 100644
--- a/mllib/src/test/scala/org/apache/spark/ml/clustering/KMeansSuite.scala
+++ b/mllib/src/test/scala/org/apache/spark/ml/clustering/KMeansSuite.scala
@@ -97,6 +97,7 @@ class KMeansSuite extends SparkFunSuite with MLlibTestSparkContext with DefaultR
assert(clusters.size === k)
assert(clusters === Set(0, 1, 2, 3, 4))
assert(model.computeCost(dataset) < 0.1)
+ assert(model.hasParent)
}
test("read/write") {
http://git-wip-us.apache.org/repos/asf/spark/blob/40e6d40f/mllib/src/test/scala/org/apache/spark/ml/feature/QuantileDiscretizerSuite.scala
----------------------------------------------------------------------
diff --git a/mllib/src/test/scala/org/apache/spark/ml/feature/QuantileDiscretizerSuite.scala b/mllib/src/test/scala/org/apache/spark/ml/feature/QuantileDiscretizerSuite.scala
index 4fde429..6a2c601 100644
--- a/mllib/src/test/scala/org/apache/spark/ml/feature/QuantileDiscretizerSuite.scala
+++ b/mllib/src/test/scala/org/apache/spark/ml/feature/QuantileDiscretizerSuite.scala
@@ -94,7 +94,9 @@ private object QuantileDiscretizerSuite extends SparkFunSuite {
val df = sc.parallelize(data.map(Tuple1.apply)).toDF("input")
val discretizer = new QuantileDiscretizer().setInputCol("input").setOutputCol("result")
.setNumBuckets(numBucket).setSeed(1)
- val result = discretizer.fit(df).transform(df)
+ val model = discretizer.fit(df)
+ assert(model.hasParent)
+ val result = model.transform(df)
val transformedFeatures = result.select("result").collect()
.map { case Row(transformedFeature: Double) => transformedFeature }
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org