diff options
author | Zheng RuiFeng <ruifengz@foxmail.com> | 2016-10-28 00:40:06 -0700 |
---|---|---|
committer | Yanbo Liang <ybliang8@gmail.com> | 2016-10-28 00:40:06 -0700 |
commit | 569788a55e4c6b218fb697e1e54c6138ffe657a6 (patch) | |
tree | d9b27848c128dbad16f256b50bd0c40717f489d5 /mllib/src | |
parent | ab5f938bc7c3c9b137d63e479fced2b7e9c9d75b (diff) | |
download | spark-569788a55e4c6b218fb697e1e54c6138ffe657a6.tar.gz spark-569788a55e4c6b218fb697e1e54c6138ffe657a6.tar.bz2 spark-569788a55e4c6b218fb697e1e54c6138ffe657a6.zip |
[SPARK-18109][ML] Add instrumentation to GMM
## What changes were proposed in this pull request?
Add instrumentation to GMM
## How was this patch tested?
Test in spark-shell
Author: Zheng RuiFeng <ruifengz@foxmail.com>
Closes #15636 from zhengruifeng/gmm_instr.
Diffstat (limited to 'mllib/src')
-rw-r--r-- | mllib/src/main/scala/org/apache/spark/ml/clustering/GaussianMixture.scala | 6 |
1 files changed, 6 insertions, 0 deletions
diff --git a/mllib/src/main/scala/org/apache/spark/ml/clustering/GaussianMixture.scala b/mllib/src/main/scala/org/apache/spark/ml/clustering/GaussianMixture.scala index e3cb92f4f1..8fac63fefb 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/clustering/GaussianMixture.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/clustering/GaussianMixture.scala @@ -323,6 +323,9 @@ class GaussianMixture @Since("2.0.0") ( case Row(point: Vector) => OldVectors.fromML(point) } + val instr = Instrumentation.create(this, rdd) + instr.logParams(featuresCol, predictionCol, probabilityCol, k, maxIter, seed, tol) + val algo = new MLlibGM() .setK($(k)) .setMaxIterations($(maxIter)) @@ -337,6 +340,9 @@ class GaussianMixture @Since("2.0.0") ( val summary = new GaussianMixtureSummary(model.transform(dataset), $(predictionCol), $(probabilityCol), $(featuresCol), $(k)) model.setSummary(summary) + instr.logNumFeatures(model.gaussians.head.mean.size) + instr.logSuccess(model) + model } @Since("2.0.0") |