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

Go to download

Show more of this group Show more artifacts with this name
Show all versions of snappy-spark-examples_2.11 Show documentation

SnappyData distributed data store and execution engine

There is a newer version: 2.1.3.2

Show newest version

/*
 * 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.{RegexTokenizer, Tokenizer}
import org.apache.spark.sql.functions._
// $example off$
import org.apache.spark.sql.SparkSession

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

    // $example on$
    val sentenceDataFrame = spark.createDataFrame(Seq(
      (0, "Hi I heard about Spark"),
      (1, "I wish Java could use case classes"),
      (2, "Logistic,regression,models,are,neat")
    )).toDF("id", "sentence")

    val tokenizer = new Tokenizer().setInputCol("sentence").setOutputCol("words")
    val regexTokenizer = new RegexTokenizer()
      .setInputCol("sentence")
      .setOutputCol("words")
      .setPattern("\\W") // alternatively .setPattern("\\w+").setGaps(false)

    val countTokens = udf { (words: Seq[String]) => words.length }

    val tokenized = tokenizer.transform(sentenceDataFrame)
    tokenized.select("sentence", "words")
        .withColumn("tokens", countTokens(col("words"))).show(false)

    val regexTokenized = regexTokenizer.transform(sentenceDataFrame)
    regexTokenized.select("sentence", "words")
        .withColumn("tokens", countTokens(col("words"))).show(false)
    // $example off$

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