Github user BryanCutler commented on a diff in the pull request:
https://github.com/apache/spark/pull/17130#discussion_r104008090
--- Diff:
examples/src/main/scala/org/apache/spark/examples/ml/FPGrowthExample.scala ---
@@ -0,0 +1,71 @@
+/*
+ * 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.
+ */
+
+package org.apache.spark.examples.ml
+
+// scalastyle:off println
+
+// $example on$
+import org.apache.spark.ml.fpm.FPGrowth
+// $example off$
+import org.apache.spark.sql.SparkSession
+
+/**
+ * An example demonstrating FP-Growth.
+ * Run with
+ * {{{
+ * bin/run-example ml.FPGrowthExample
+ * }}}
+ */
+object FPGrowthExample {
+
+ def main(args: Array[String]): Unit = {
+
+ val spark = SparkSession
+ .builder
+ .appName(s"${this.getClass.getSimpleName}")
+ .getOrCreate()
+ import spark.implicits._
+
+ // $example on$
+ // Loads data.
+ val dataset = spark.createDataset(Seq(
+ "1 2 5",
+ "1 2 3 5",
+ "1 2")
+ ).map(t => t.split(" ")).toDF("features")
+
+ // Trains a FPGrowth model.
+ val fpgrowth = new FPGrowth().setMinSupport(0.5).setMinConfidence(0.6)
+ val model = fpgrowth.fit(dataset)
+
+ // get frequent itemsets.
+ model.freqItemsets.show()
+
+ // get generated association rules.
+ model.associationRules.show()
+
+ // transform examines the input items against all the association
rules and summarize the
+ // consequents as prediction
+ model.transform(dataset).show()
+
--- End diff --
nit: remove blank line
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
