package Spark_MLlib

import org.apache.spark.ml.feature.StringIndexer

import org.apache.spark.sql.SparkSession

object 特征变换_StringIndexer {

     val spark = SparkSession.builder().master("local[2]").appName("标签和索引的转换").getOrCreate()

     import spark.implicits._

  def main(args: Array[String]): Unit = {

       val df=spark.createDataFrame(Seq(

         (,"log"),

         (,"text"),

         (,"text"),

         (,"soyo"),

         (,"text"),

         (,"log"),

         (,"log"),

         (,"log")

       )).toDF("id","type")

     val indexer=new StringIndexer().setInputCol("type").setOutputCol("type_index")

     val model=indexer.fit(df)

       model.labels.foreach(println)   //类型的频率顺序(高-->低)

     val index=model.transform(df)     //索引先排频率高的即log为0

      index.show(false)

  }

}