Repository: systemml
Updated Branches:
  refs/heads/gh-pages b5a248a4b -> e184e966e


[SYSTEMML-1929] Update Spark parameters in sparkDML.sh and docs

Closes #670.


Project: http://git-wip-us.apache.org/repos/asf/systemml/repo
Commit: http://git-wip-us.apache.org/repos/asf/systemml/commit/e184e966
Tree: http://git-wip-us.apache.org/repos/asf/systemml/tree/e184e966
Diff: http://git-wip-us.apache.org/repos/asf/systemml/diff/e184e966

Branch: refs/heads/gh-pages
Commit: e184e966e2103062e5381c11a48c9e2bb53b5687
Parents: b5a248a
Author: Glenn Weidner <[email protected]>
Authored: Sat Oct 7 17:22:18 2017 -0700
Committer: Glenn Weidner <[email protected]>
Committed: Sat Oct 7 17:22:18 2017 -0700

----------------------------------------------------------------------
 algorithms-classification.md         | 88 +++++++++++++++----------------
 algorithms-clustering.md             | 28 +++++-----
 algorithms-descriptive-statistics.md | 28 +++++-----
 algorithms-matrix-factorization.md   | 36 ++++++-------
 algorithms-regression.md             | 72 ++++++++++++-------------
 algorithms-survival-analysis.md      | 32 +++++------
 spark-batch-mode.md                  |  8 +--
 spark-mlcontext-programming-guide.md |  4 +-
 8 files changed, 148 insertions(+), 148 deletions(-)
----------------------------------------------------------------------


http://git-wip-us.apache.org/repos/asf/systemml/blob/e184e966/algorithms-classification.md
----------------------------------------------------------------------
diff --git a/algorithms-classification.md b/algorithms-classification.md
index 1895103..62e40e7 100644
--- a/algorithms-classification.md
+++ b/algorithms-classification.md
@@ -160,9 +160,9 @@ val prediction = model.transform(X_test_df)
                                     fmt=[format]
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f MultiLogReg.dml
                                  -config SystemML-config.xml
@@ -331,9 +331,9 @@ prediction.show()
                                     Log=/user/ml/log.csv
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f MultiLogReg.dml
                                  -config SystemML-config.xml
@@ -527,9 +527,9 @@ val model = svm.fit(X_train_df)
                                     fmt=[format]
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f l2-svm.dml
                                  -config SystemML-config.xml
@@ -574,9 +574,9 @@ val prediction = model.transform(X_test_df)
                                     fmt=[format]
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f l2-svm-predict.dml
                                  -config SystemML-config.xml
@@ -658,9 +658,9 @@ more details on the Python API.
                                     Log=/user/ml/Log.csv
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f l2-svm.dml
                                  -config SystemML-config.xml
@@ -692,9 +692,9 @@ more details on the Python API.
                                     confusion=/user/ml/confusion.csv
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f l2-svm-predict.dml
                                  -config SystemML-config.xml
@@ -797,9 +797,9 @@ val model = svm.fit(X_train_df)
                                     fmt=[format]
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f m-svm.dml
                                  -config SystemML-config.xml
@@ -844,9 +844,9 @@ val prediction = model.transform(X_test_df)
                                     fmt=[format]
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f m-svm-predict.dml
                                  -config SystemML-config.xml
@@ -1009,9 +1009,9 @@ prediction.show()
                                     Log=/user/ml/Log.csv
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f m-svm.dml
                                  -config SystemML-config.xml
@@ -1043,9 +1043,9 @@ prediction.show()
                                     confusion=/user/ml/confusion.csv
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f m-svm-predict.dml
                                  -config SystemML-config.xml
@@ -1148,9 +1148,9 @@ val model = nb.fit(X_train_df)
                                     fmt=[format]
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f naive-bayes.dml
                                  -config SystemML-config.xml
@@ -1193,9 +1193,9 @@ val prediction = model.transform(X_test_df)
                                     probabilities=[file]
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f naive-bayes-predict.dml
                                  -config SystemML-config.xml
@@ -1284,9 +1284,9 @@ metrics.f1_score(newsgroups_test.target, pred, 
average='weighted')
                                     accuracy=/user/ml/accuracy.csv
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f naive-bayes.dml
                                  -config SystemML-config.xml
@@ -1316,9 +1316,9 @@ metrics.f1_score(newsgroups_test.target, pred, 
average='weighted')
                                     confusion=/user/ml/confusion.csv
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f naive-bayes-predict.dml
                                  -config SystemML-config.xml
@@ -1415,9 +1415,9 @@ implementation is well-suited to handle large-scale data 
and builds a
                                     fmt=[format]
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f decision-tree.dml
                                  -config SystemML-config.xml
@@ -1453,9 +1453,9 @@ implementation is well-suited to handle large-scale data 
and builds a
                                     fmt=[format]
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f decision-tree-predict.dml
                                  -config SystemML-config.xml
@@ -1553,9 +1553,9 @@ SystemML Language Reference for details.
                                     fmt=csv
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f decision-tree.dml
                                  -config SystemML-config.xml
@@ -1588,9 +1588,9 @@ SystemML Language Reference for details.
                                     fmt=csv
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f decision-tree-predict.dml
                                  -config SystemML-config.xml
@@ -1823,9 +1823,9 @@ for classification in parallel.
                                     fmt=[format]
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f random-forest.dml
                                  -config SystemML-config.xml
@@ -1866,9 +1866,9 @@ for classification in parallel.
                                     fmt=[format]
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f random-forest-predict.dml
                                  -config SystemML-config.xml
@@ -1989,9 +1989,9 @@ SystemML Language Reference for details.
                                     fmt=csv
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f random-forest.dml
                                  -config SystemML-config.xml
@@ -2027,9 +2027,9 @@ To compute predictions:
                                     fmt=csv
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f random-forest-predict.dml
                                  -config SystemML-config.xml

http://git-wip-us.apache.org/repos/asf/systemml/blob/e184e966/algorithms-clustering.md
----------------------------------------------------------------------
diff --git a/algorithms-clustering.md b/algorithms-clustering.md
index 7554660..358a53a 100644
--- a/algorithms-clustering.md
+++ b/algorithms-clustering.md
@@ -129,9 +129,9 @@ apart is a "false negative" etc.
                                     verb=[boolean]
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f Kmeans.dml
                                  -config SystemML-config.xml
@@ -163,9 +163,9 @@ apart is a "false negative" etc.
                                     O=[file]
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f Kmeans-predict.dml
                                  -config SystemML-config.xml
@@ -255,9 +255,9 @@ standard output
                                     fmt=csv
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f Kmeans.dml
                                  -config SystemML-config.xml
@@ -284,9 +284,9 @@ standard output
                                     verb=1
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f Kmeans.dml
                                  -config SystemML-config.xml
@@ -317,9 +317,9 @@ To predict Y given X and C:
                                     O=/user/ml/stats.csv
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f Kmeans-predict.dml
                                  -config SystemML-config.xml
@@ -343,9 +343,9 @@ given X and C:
                                     O=/user/ml/stats.csv
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f Kmeans-predict.dml
                                  -config SystemML-config.xml
@@ -368,9 +368,9 @@ labels prY:
                                     O=/user/ml/stats.csv
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f Kmeans-predict.dml
                                  -config SystemML-config.xml

http://git-wip-us.apache.org/repos/asf/systemml/blob/e184e966/algorithms-descriptive-statistics.md
----------------------------------------------------------------------
diff --git a/algorithms-descriptive-statistics.md 
b/algorithms-descriptive-statistics.md
index f45ffae..1c86368 100644
--- a/algorithms-descriptive-statistics.md
+++ b/algorithms-descriptive-statistics.md
@@ -125,9 +125,9 @@ to compute the mean of a categorical attribute like ‘Hair 
Color’.
                                     STATS=<file>
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f Univar-Stats.dml
                                  -config SystemML-config.xml
@@ -164,9 +164,9 @@ be stored. The format of the output matrix is defined by
                                     STATS=/user/ml/stats.mtx
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f Univar-Stats.dml
                                  -config SystemML-config.xml
@@ -585,9 +585,9 @@ attributes like ‘Hair Color’.
                                     OUTDIR=<directory>
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f bivar-stats.dml
                                  -config SystemML-config.xml
@@ -654,9 +654,9 @@ are defined in [**Table 
2**](algorithms-descriptive-statistics.html#table2).
                                     OUTDIR=/user/ml/stats.mtx
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f bivar-stats.dml
                                  -config SystemML-config.xml
@@ -1147,9 +1147,9 @@ becomes reversed and amplified (from $+0.1$ to $-0.5$) if 
we ignore the months.
                                     fmt=[format]
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f stratstats.dml
                                  -config SystemML-config.xml
@@ -1355,9 +1355,9 @@ SystemML Language Reference for details.
                                     fmt=csv
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f stratstats.dml
                                  -config SystemML-config.xml
@@ -1383,9 +1383,9 @@ SystemML Language Reference for details.
                                     O=/user/ml/Out.mtx
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f stratstats.dml
                                  -config SystemML-config.xml

http://git-wip-us.apache.org/repos/asf/systemml/blob/e184e966/algorithms-matrix-factorization.md
----------------------------------------------------------------------
diff --git a/algorithms-matrix-factorization.md 
b/algorithms-matrix-factorization.md
index 8777130..b559cb5 100644
--- a/algorithms-matrix-factorization.md
+++ b/algorithms-matrix-factorization.md
@@ -56,9 +56,9 @@ top-$K$ (for a given value of $K$) principal components.
                                     OUTPUT=<file>
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f PCA.dml
                                  -config SystemML-config.xml
@@ -119,9 +119,9 @@ SystemML Language Reference for details.
                                     OUTPUT=/user/ml/pca_output/
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f PCA.dml
                                  -config SystemML-config.xml
@@ -149,9 +149,9 @@ SystemML Language Reference for details.
                                     OUTPUT=/user/ml/test_output.mtx
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f PCA.dml
                                  -config SystemML-config.xml
@@ -257,9 +257,9 @@ problems.
                                     fmt=[format]
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f ALS.dml
                                  -config SystemML-config.xml
@@ -291,9 +291,9 @@ problems.
                                     fmt=[format]
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f ALS_predict.dml
                                  -config SystemML-config.xml
@@ -322,9 +322,9 @@ problems.
                                     fmt=[format]
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f ALS_topk_predict.dml
                                  -config SystemML-config.xml
@@ -431,9 +431,9 @@ SystemML Language Reference for details.
                                     fmt=csv
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f ALS.dml
                                  -config SystemML-config.xml
@@ -467,9 +467,9 @@ To compute predicted ratings for a given list of users and 
items:
                                     fmt=csv
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f ALS_predict.dml
                                  -config SystemML-config.xml
@@ -501,9 +501,9 @@ predicted ratings for a given list of users:
                                     fmt=csv
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f ALS_topk_predict.dml
                                  -config SystemML-config.xml

http://git-wip-us.apache.org/repos/asf/systemml/blob/e184e966/algorithms-regression.md
----------------------------------------------------------------------
diff --git a/algorithms-regression.md b/algorithms-regression.md
index df2ad3e..18640b8 100644
--- a/algorithms-regression.md
+++ b/algorithms-regression.md
@@ -102,9 +102,9 @@ y_test = lr.fit(df_train)
                                     fmt=[format]
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f LinearRegDS.dml
                                  -config SystemML-config.xml
@@ -147,9 +147,9 @@ y_test = lr.fit(df_train)
                                     fmt=[format]
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f LinearRegCG.dml
                                  -config SystemML-config.xml
@@ -254,9 +254,9 @@ print("Residual sum of squares: %.2f" % 
np.mean((regr.predict(diabetes_X_test) -
                                     reg=1.0
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f LinearRegDS.dml
                                  -config SystemML-config.xml
@@ -311,9 +311,9 @@ print("Residual sum of squares: %.2f" % 
np.mean((regr.predict(diabetes_X_test) -
                                     Log=/user/ml/log.csv
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f LinearRegCG.dml
                                  -config SystemML-config.xml
@@ -552,9 +552,9 @@ lowest AIC is computed.
                                     fmt=[format]
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f StepLinearRegDS.dml
                                  -config SystemML-config.xml
@@ -623,9 +623,9 @@ SystemML Language Reference for details.
                                     fmt=csv
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f StepLinearRegDS.dml
                                  -config SystemML-config.xml
@@ -755,9 +755,9 @@ distributions and link functions, see below for details.
                                     mii=[int]
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f GLM.dml
                                  -config SystemML-config.xml
@@ -893,9 +893,9 @@ if no maximum limit provided
                                     Log=/user/ml/log.csv
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f GLM.dml
                                  -config SystemML-config.xml
@@ -1230,9 +1230,9 @@ distribution family is supported (see below for details).
                                     fmt=[format]
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f StepGLM.dml
                                  -config SystemML-config.xml
@@ -1335,9 +1335,9 @@ SystemML Language Reference for details.
                                     fmt=csv
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f StepGLM.dml
                                  -config SystemML-config.xml
@@ -1481,9 +1481,9 @@ this step outside the scope of `GLM-predict.dml` for now.
                                     fmt=[format]
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f GLM-predict.dml
                                  -config SystemML-config.xml
@@ -1620,9 +1620,9 @@ unknown (which sets it to `1.0`).
                                     O=/user/ml/stats.csv
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f GLM-predict.dml
                                  -config SystemML-config.xml
@@ -1656,9 +1656,9 @@ unknown (which sets it to `1.0`).
                                     fmt=csv
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f GLM-predict.dml
                                  -config SystemML-config.xml
@@ -1690,9 +1690,9 @@ unknown (which sets it to `1.0`).
                                     O=/user/ml/stats.csv
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f GLM-predict.dml
                                  -config SystemML-config.xml
@@ -1725,9 +1725,9 @@ unknown (which sets it to `1.0`).
                                     O=/user/ml/stats.csv
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f GLM-predict.dml
                                  -config SystemML-config.xml
@@ -1758,9 +1758,9 @@ unknown (which sets it to `1.0`).
                                     O=/user/ml/stats.csv
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f GLM-predict.dml
                                  -config SystemML-config.xml
@@ -1793,9 +1793,9 @@ unknown (which sets it to `1.0`).
                                     O=/user/ml/stats.csv
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f GLM-predict.dml
                                  -config SystemML-config.xml
@@ -1832,9 +1832,9 @@ unknown (which sets it to `1.0`).
                                     O=/user/ml/stats.csv
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f GLM-predict.dml
                                  -config SystemML-config.xml

http://git-wip-us.apache.org/repos/asf/systemml/blob/e184e966/algorithms-survival-analysis.md
----------------------------------------------------------------------
diff --git a/algorithms-survival-analysis.md b/algorithms-survival-analysis.md
index 239ab08..943d4d7 100644
--- a/algorithms-survival-analysis.md
+++ b/algorithms-survival-analysis.md
@@ -57,9 +57,9 @@ censored and uncensored survival times.
                                     fmt=[format]
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f KM.dml
                                  -config SystemML-config.xml
@@ -152,9 +152,9 @@ SystemML Language Reference for details.
                                     fmt=csv
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f KM.dml
                                  -config SystemML-config.xml
@@ -189,9 +189,9 @@ SystemML Language Reference for details.
                                     fmt=csv
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f KM.dml
                                  -config SystemML-config.xml
@@ -461,9 +461,9 @@ may be categorical (ordinal or nominal) as well as 
continuous-valued.
                                     fmt=[format]
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f Cox.dml
                                  -config SystemML-config.xml
@@ -503,9 +503,9 @@ may be categorical (ordinal or nominal) as well as 
continuous-valued.
                                     fmt=[format]
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f Cox-predict.dml
                                  -config SystemML-config.xml
@@ -612,9 +612,9 @@ SystemML Language Reference for details.
                                     fmt=csv
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f Cox.dml
                                  -config SystemML-config.xml
@@ -651,9 +651,9 @@ SystemML Language Reference for details.
                                     fmt=csv
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f Cox.dml
                                  -config SystemML-config.xml
@@ -691,9 +691,9 @@ SystemML Language Reference for details.
                                     fmt=csv
 </div>
 <div data-lang="Spark" markdown="1">
-    $SPARK_HOME/bin/spark-submit --master yarn-cluster
+    $SPARK_HOME/bin/spark-submit --master yarn
+                                 --deploy-mode cluster
                                  --conf spark.driver.maxResultSize=0
-                                 --conf spark.akka.frameSize=128
                                  SystemML.jar
                                  -f Cox-predict.dml
                                  -config SystemML-config.xml

http://git-wip-us.apache.org/repos/asf/systemml/blob/e184e966/spark-batch-mode.md
----------------------------------------------------------------------
diff --git a/spark-batch-mode.md b/spark-batch-mode.md
index 7f8f4c0..349f17c 100644
--- a/spark-batch-mode.md
+++ b/spark-batch-mode.md
@@ -41,7 +41,7 @@ mode in more depth.
 
 # Spark Batch Mode Invocation Syntax
 
-SystemML can be invoked in Hadoop Batch mode using the following syntax:
+SystemML can be invoked in Spark Batch mode using the following syntax:
 
     spark-submit SystemML.jar [-? | -help | -f <filename>] (-config 
<config_filename>) ([-args | -nvargs] <args-list>)
 
@@ -63,7 +63,7 @@ to be deprecated. All the primary algorithm scripts included 
with SystemML use n
 # Execution modes
 
 SystemML works seamlessly with all Spark execution modes, including *local* 
(`--master local[*]`),
-*yarn client* (`--master yarn-client`), *yarn cluster* (`--master 
yarn-cluster`), *etc*.  More
+*yarn client* (`--master yarn --deploy-mode client`), *yarn cluster* 
(`--master yarn --deploy-mode cluster`), *etc*.  More
 information on Spark cluster execution modes can be found on the
 [official Spark cluster deployment 
documentation](https://spark.apache.org/docs/latest/cluster-overview.html).
 *Note* that Spark can be easily run on a laptop in local mode using the 
`--master local[*]` described
@@ -71,8 +71,8 @@ above, which SystemML supports.
 
 # Recommended Spark Configuration Settings
 
-For best performance, we recommend setting the following flags when running 
SystemML with Spark:
-`--conf spark.driver.maxResultSize=0 --conf spark.akka.frameSize=128`.
+For best performance, we recommend setting the following configuration value 
when running SystemML with Spark:
+`--conf spark.driver.maxResultSize=0`.
 
 # Examples
 

http://git-wip-us.apache.org/repos/asf/systemml/blob/e184e966/spark-mlcontext-programming-guide.md
----------------------------------------------------------------------
diff --git a/spark-mlcontext-programming-guide.md 
b/spark-mlcontext-programming-guide.md
index e935c65..63e48be 100644
--- a/spark-mlcontext-programming-guide.md
+++ b/spark-mlcontext-programming-guide.md
@@ -2814,5 +2814,5 @@ plt.title('PNMF Training Loss')
 
 # Recommended Spark Configuration Settings
 
-For best performance, we recommend setting the following flags when running 
SystemML with Spark:
-`--conf spark.driver.maxResultSize=0 --conf spark.akka.frameSize=128`.
+For best performance, we recommend setting the following configuration value 
when running SystemML with Spark:
+`--conf spark.driver.maxResultSize=0`.

Reply via email to