UDF:User-defined Function,用户自定义函数。一般为单输出类型,这里以scala代码为例:
/**
* @function 自定义UDF————依照姓名字符长短倒排学生姓名,并统计姓名字符长度
* @author Dongh.Wang
* 郑重声明,scala中自定义函数需继承UDF类
*/
object UDF {
def main(args: Array[String]): Unit = {
val spark = SparkSession.builder().master("local").appName("UDF").getOrCreate()
val nameList: List[String] = List[String]("zhangsan", "lisi", "wangwu", "zhaoliu", "tianqi")
import spark.implicits._
val nameDF: DataFrame = nameList.toDF("name")
nameDF.createOrReplaceTempView("students")
nameDF.show()
spark.udf.register("STRLEN",(name:String)=>{
name.length
})
spark.sql("select name ,STRLEN(name) as length from students order by length desc").show(100)
}
}
UDAF:User- Defined Aggregation Funcationÿ