You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spark.apache.org by jk...@apache.org on 2015/12/16 21:59:29 UTC

spark git commit: [SPARK-12364][ML][SPARKR] Add ML example for SparkR

Repository: spark
Updated Branches:
  refs/heads/master 8148cc7a5 -> 1a8b2a17d


[SPARK-12364][ML][SPARKR] Add ML example for SparkR

We have DataFrame example for SparkR, we also need to add ML example under ```examples/src/main/r```.

cc mengxr jkbradley shivaram

Author: Yanbo Liang <yb...@gmail.com>

Closes #10324 from yanboliang/spark-12364.


Project: http://git-wip-us.apache.org/repos/asf/spark/repo
Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/1a8b2a17
Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/1a8b2a17
Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/1a8b2a17

Branch: refs/heads/master
Commit: 1a8b2a17db7ab7a213d553079b83274aeebba86f
Parents: 8148cc7
Author: Yanbo Liang <yb...@gmail.com>
Authored: Wed Dec 16 12:59:22 2015 -0800
Committer: Joseph K. Bradley <jo...@databricks.com>
Committed: Wed Dec 16 12:59:22 2015 -0800

----------------------------------------------------------------------
 examples/src/main/r/ml.R | 54 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 54 insertions(+)
----------------------------------------------------------------------


http://git-wip-us.apache.org/repos/asf/spark/blob/1a8b2a17/examples/src/main/r/ml.R
----------------------------------------------------------------------
diff --git a/examples/src/main/r/ml.R b/examples/src/main/r/ml.R
new file mode 100644
index 0000000..a0c9039
--- /dev/null
+++ b/examples/src/main/r/ml.R
@@ -0,0 +1,54 @@
+#
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+# To run this example use
+# ./bin/sparkR examples/src/main/r/ml.R
+
+# Load SparkR library into your R session
+library(SparkR)
+
+# Initialize SparkContext and SQLContext
+sc <- sparkR.init(appName="SparkR-ML-example")
+sqlContext <- sparkRSQL.init(sc)
+
+# Train GLM of family 'gaussian'
+training1 <- suppressWarnings(createDataFrame(sqlContext, iris))
+test1 <- training1
+model1 <- glm(Sepal_Length ~ Sepal_Width + Species, training1, family = "gaussian")
+
+# Model summary
+summary(model1)
+
+# Prediction
+predictions1 <- predict(model1, test1)
+head(select(predictions1, "Sepal_Length", "prediction"))
+
+# Train GLM of family 'binomial'
+training2 <- filter(training1, training1$Species != "setosa")
+test2 <- training2
+model2 <- glm(Species ~ Sepal_Length + Sepal_Width, data = training2, family = "binomial")
+
+# Model summary
+summary(model2)
+
+# Prediction (Currently the output of prediction for binomial GLM is the indexed label,
+# we need to transform back to the original string label later)
+predictions2 <- predict(model2, test2)
+head(select(predictions2, "Species", "prediction"))
+
+# Stop the SparkContext now
+sparkR.stop()


---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org