Linear Regression Example using Apache Spark

Example code

import org.apache.spark.ml.feature.VectorAssembler
import org.apache.spark.ml.regression.LinearRegression
import org.apache.spark.sql.SparkSession
 
object LinearRegressionExample {
  def main(args: Array[String]): Unit = {
    val spark = SparkSession
        .builder()
        .appName("Linear Regression Example")
        .getOrCreate()
 
    val loadOptions =
      Map("sep" -> "\t", "header" -> "true", "mode" -> "FAILFAST", "inferSchema" -> "true")
    val dataPath = "mtcars.tsv"
    val mtcars = spark.read.options(loadOptions).csv(dataPath)
 
    val assembler = new VectorAssembler()
        .setInputCols(Array("wt", "cyl"))
        .setOutputCol("features")
 
    val output = assembler.transform(mtcars)
    val extractedData = output.select("features", "mpg")
 
    val linearRegression = new LinearRegression()
        .setFeaturesCol("features")
        .setLabelCol("mpg")
 
    val model = linearRegression.fit(extractedData)
    println(s"Weights: ${model.coefficients} Intercept: ${model.intercept}")
 
    spark.close()
  }
}

scikit-learn이나 R과 비교하면 복잡하긴하다...

Todo: PipeLine() 사용한 코드로 수정할 것.