org.apache.spark.examples.ml.FPGrowthExample.scala Maven / Gradle / Ivy

Go to download
/*
 * 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

// $example on$
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._

    // $example on$
    val dataset = spark.createDataset(Seq(
      "1 2 5",
      "1 2 3 5",
      "1 2")
    ).map(t => t.split(" ")).toDF("items")

    val fpgrowth = new FPGrowth().setItemsCol("items").setMinSupport(0.5).setMinConfidence(0.6)
    val model = fpgrowth.fit(dataset)

    // Display frequent itemsets.
    model.freqItemsets.show()

    // Display 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()
    // $example off$

    spark.stop()
  }
}