aboutsummaryrefslogtreecommitdiff
path: root/examples
diff options
context:
space:
mode:
authorzero323 <zero323@users.noreply.github.com>2017-04-18 19:59:18 -0700
committerFelix Cheung <felixcheung@apache.org>2017-04-18 19:59:18 -0700
commit702d85af2df9433254af6fa029683aa19c52a276 (patch)
treefea6ff94f7b3e2e78e71b22cc45a53be63783d15 /examples
parente468a96c404eb54261ab219734f67dc2f5b06dc0 (diff)
downloadspark-702d85af2df9433254af6fa029683aa19c52a276.tar.gz
spark-702d85af2df9433254af6fa029683aa19c52a276.tar.bz2
spark-702d85af2df9433254af6fa029683aa19c52a276.zip
[SPARK-20208][R][DOCS] Document R fpGrowth support
## What changes were proposed in this pull request? Document fpGrowth in: - vignettes - programming guide - code example ## How was this patch tested? Manual tests. Author: zero323 <zero323@users.noreply.github.com> Closes #17557 from zero323/SPARK-20208.
Diffstat (limited to 'examples')
-rw-r--r--examples/src/main/r/ml/fpm.R50
1 files changed, 50 insertions, 0 deletions
diff --git a/examples/src/main/r/ml/fpm.R b/examples/src/main/r/ml/fpm.R
new file mode 100644
index 0000000000..89c4564457
--- /dev/null
+++ b/examples/src/main/r/ml/fpm.R
@@ -0,0 +1,50 @@
+#
+# 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/fpm.R
+
+# Load SparkR library into your R session
+library(SparkR)
+
+# Initialize SparkSession
+sparkR.session(appName = "SparkR-ML-fpm-example")
+
+# $example on$
+# Load training data
+
+df <- selectExpr(createDataFrame(data.frame(rawItems = c(
+ "1,2,5", "1,2,3,5", "1,2"
+))), "split(rawItems, ',') AS items")
+
+fpm <- spark.fpGrowth(df, itemsCol="items", minSupport=0.5, minConfidence=0.6)
+
+# Extracting frequent itemsets
+
+spark.freqItemsets(fpm)
+
+# Extracting association rules
+
+spark.associationRules(fpm)
+
+# Predict uses association rules to and combines possible consequents
+
+predict(fpm, df)
+
+# $example off$
+
+sparkR.session.stop()