org.apache.spark.examples.ml.VectorIndexerExample.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.
 */

// scalastyle:off println
package org.apache.spark.examples.ml

// $example on$
import org.apache.spark.ml.feature.VectorIndexer
// $example off$
import org.apache.spark.sql.SparkSession

object VectorIndexerExample {
  def main(args: Array[String]): Unit = {
    val spark = SparkSession
      .builder
      .appName("VectorIndexerExample")
      .getOrCreate()

    // $example on$
    val data = spark.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt")

    val indexer = new VectorIndexer()
      .setInputCol("features")
      .setOutputCol("indexed")
      .setMaxCategories(10)

    val indexerModel = indexer.fit(data)

    val categoricalFeatures: Set[Int] = indexerModel.categoryMaps.keys.toSet
    println(s"Chose ${categoricalFeatures.size} " +
      s"categorical features: ${categoricalFeatures.mkString(", ")}")

    // Create new column "indexed" with categorical values transformed to indices
    val indexedData = indexerModel.transform(data)
    indexedData.show()
    // $example off$

    spark.stop()
  }
}
// scalastyle:on println