From 33ae7a35daa86c34f1f9f72f997e0c2d4cd8abec Mon Sep 17 00:00:00 2001
From: Xiangrui Meng <meng@databricks.com>
Date: Mon, 2 Nov 2015 13:42:16 -0800
Subject: [PATCH] [SPARK-11358][MLLIB] deprecate runs in k-means
This PR deprecates `runs` in k-means. `runs` introduces extra complexity and overhead in MLlib's k-means implementation. I haven't seen much usage with `runs` not equal to `1`. We don't have a unit test for it either. We can deprecate this method in 1.6, and void it in 1.7. It helps us simplify the implementation.
cc: srowen
Author: Xiangrui Meng <meng@databricks.com>
Closes #9322 from mengxr/SPARK-11358.
---
.../main/scala/org/apache/spark/mllib/clustering/KMeans.scala | 4 ++--
python/pyspark/mllib/clustering.py | 4 ++++
2 files changed, 6 insertions(+), 2 deletions(-)
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 7168aac32c..2895db7c90 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 d1c3755a78..8629aa5a17 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):
--
GitLab