callUDF使用

callUDF用與將sql註冊的UDF轉爲外部DataFrame可見

import org.apache.spark.sql.SparkSession
import org.apache.spark.sql.functions._

object TestDemo {
  def main(args: Array[String]): Unit = {
    val spark = SparkSession.builder()
      .master("local[*]")
      .appName("test-demo")
      .getOrCreate()

    import spark.implicits._

    val df = Seq(("id1", 1, 100), ("id2", 4, 300), ("id3", 5, 800)).toDF("id", "value", "cnt")
    df.printSchema()

    // 註冊自定義UDF函數
    spark.udf.register("simpleUDF", (v: Int, w: Int) => v * v + w * w)

    df.select($"id", callUDF("simpleUDF", $"value", $"cnt")).toDF("id", "value").show


  }

}