From 6a45dc8a2d382d6097ee7e1ad84906652eee4f76 Mon Sep 17 00:00:00 2001
From: ludatabricks <38018689+ludatabricks@users.noreply.github.com>
Date: Tue, 12 Jun 2018 10:32:02 -0700
Subject: [PATCH] [ML-3581] Add benchmarks to mllib-large.yaml for regression
 (#150)

Benchmark for regression is added to mllib-large.yaml.
DecisionTreeRegression, GLMRegression, LinearRegression, and RandomForestRegression are added.

GBT, AFTSurvivalRegression, and IsotonicRegression are missing in spark-sql-perf.
---
 .../sql/perf/mllib/config/mllib-large.yaml    | 24 ++++++++++++++++++-
 1 file changed, 23 insertions(+), 1 deletion(-)

diff --git a/src/main/resources/com/databricks/spark/sql/perf/mllib/config/mllib-large.yaml b/src/main/resources/com/databricks/spark/sql/perf/mllib/config/mllib-large.yaml
index 741359d..93e39f4 100644
--- a/src/main/resources/com/databricks/spark/sql/perf/mllib/config/mllib-large.yaml
+++ b/src/main/resources/com/databricks/spark/sql/perf/mllib/config/mllib-large.yaml
@@ -67,4 +67,26 @@ benchmarks:
       numItems: 6000000
       regParam: 0.01
       rank: 10
-      maxIter: 10
\ No newline at end of file
+      maxIter: 10
+  - name: regression.DecisionTreeRegression
+    params:
+      depth: [5, 10]
+  - name: regression.GLMRegression
+    params:
+      numExamples: 500000
+      numTestExamples: 500000
+      numFeatures: 1000
+      link: log
+      family: gaussian
+      tol: 0.0
+      maxIter: 10
+      regParam: 0.1
+  - name: regression.LinearRegression
+    params:
+      regParam: 0.01
+      tol: 0.0
+      maxIter: 20
+  - name: regression.RandomForestRegression
+    params:
+      depth: 10
+      maxIter: 4
\ No newline at end of file