From 569788a55e4c6b218fb697e1e54c6138ffe657a6 Mon Sep 17 00:00:00 2001
From: Zheng RuiFeng <ruifengz@foxmail.com>
Date: Fri, 28 Oct 2016 00:40:06 -0700
Subject: [PATCH] [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.
---
.../org/apache/spark/ml/clustering/GaussianMixture.scala | 6 ++++++
1 file changed, 6 insertions(+)
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")
--
GitLab