1 files changed, 63 insertions, 0 deletions
diff --git a/examples/src/main/r/ml/randomForest.R b/examples/src/main/r/ml/randomForest.R
new file mode 100644
index 0000000000..d1b96b62a0
--- /dev/null
+++ b/examples/src/main/r/ml/randomForest.R
@@ -0,0 +1,63 @@
+#
+# 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/spark-submit examples/src/main/r/ml/randomForest.R
+
+# Load SparkR library into your R session
+library(SparkR)
+
+# Initialize SparkSession
+sparkR.session(appName = "SparkR-ML-randomForest-example")
+
+# Random forest classification model
+
+# $example on:classification$
+# Load training data
+df <- read.df("data/mllib/sample_libsvm_data.txt", source = "libsvm")
+training <- df
+test <- df
+
+# Fit a random forest classification model with spark.randomForest
+model <- spark.randomForest(training, label ~ features, "classification", numTrees = 10)
+
+# Model summary
+summary(model)
+
+# Prediction
+predictions <- predict(model, test)
+showDF(predictions)
+# $example off:classification$
+
+# Random forest regression model
+
+# $example on:regression$
+# Load training data
+df <- read.df("data/mllib/sample_linear_regression_data.txt", source = "libsvm")
+training <- df
+test <- df
+
+# Fit a random forest regression model with spark.randomForest
+model <- spark.randomForest(training, label ~ features, "regression", numTrees = 10)
+
+# Model summary
+summary(model)
+
+# Prediction
+predictions <- predict(model, test)
+showDF(predictions)
+# $example off:regression$