diff --git a/mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeans.scala b/mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeans.scala index 7168aac32c9979bd337eb9526e0ce83ea1f772a4..2895db7c9061bd635b41113a838589cd1fae0b65 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeans.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeans.scala @@ -107,7 +107,7 @@ class KMeans private ( * Number of runs of the algorithm to execute in parallel. */ @Since("1.4.0") - @Experimental + @deprecated("Support for runs is deprecated. This param will have no effect in 1.7.0.", "1.6.0") def getRuns: Int = runs /** @@ -117,7 +117,7 @@ class KMeans private ( * return the best clustering found over any run. Default: 1. */ @Since("0.8.0") - @Experimental + @deprecated("Support for runs is deprecated. This param will have no effect in 1.7.0.", "1.6.0") def setRuns(runs: Int): this.type = { if (runs <= 0) { throw new IllegalArgumentException("Number of runs must be positive") diff --git a/python/pyspark/mllib/clustering.py b/python/pyspark/mllib/clustering.py index d1c3755a785f2fac326943ae205c9d7a609194e9..8629aa5a17164bef35dce38e4aba2302bf69884b 100644 --- a/python/pyspark/mllib/clustering.py +++ b/python/pyspark/mllib/clustering.py @@ -17,6 +17,7 @@ import sys import array as pyarray +import warnings if sys.version > '3': xrange = range @@ -170,6 +171,9 @@ class KMeans(object): def train(cls, rdd, k, maxIterations=100, runs=1, initializationMode="k-means||", seed=None, initializationSteps=5, epsilon=1e-4, initialModel=None): """Train a k-means clustering model.""" + if runs != 1: + warnings.warn( + "Support for runs is deprecated in 1.6.0. This param will have no effect in 1.7.0.") clusterInitialModel = [] if initialModel is not None: if not isinstance(initialModel, KMeansModel):