Spark RDD转DataFrame

Posted 2021-02-27 zxbdboke

import org.apache.spark.sql.{Row, SparkSession}
import org.apache.spark.sql.types.{IntegerType, StringType, StructField, StructType}

/**
  * RDD转DataFrame
  */
object DataFrameRDD {

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

    val spark = SparkSession.builder()
      .appName("")
      .master("local")
      .getOrCreate()

    val rdd = spark.sparkContext.textFile("person.text")

    /**
      * 1.RDD转DataFrame
      * 导入包，支持把一个RDD隐式转换为DataFrame,
      * 这里的spark不是某个包下的东西，而是上面声明的变量
      */
    import spark.implicits._
    val df = rdd.map(_.split(",")).map(attributes=>Person(attributes(0),attributes(1).trim.toInt)).toDF()

    //注册表
    df.createOrReplaceTempView("person")
    val frame = spark.sql("select * from person where age > 20")

    df.map(t=>
      "name:"+t(0) + "," + "age:"+t(1)
    ).show()


    /**
      * 2.RDD转DataFrame
      */
    //构建表头
    val fields = Array(StructField("name",StringType,true),StructField("age",IntegerType,true))
    val schema = StructType(fields)

    //表中的记录
    val rowRdd = rdd.map(_.split(",")).map(attributes=> Row(attributes(0),attributes(1).trim.toInt))

    //把表头和表中的记录拼接起来
    val dataframe = spark.createDataFrame(rowRdd,schema)

    //注册表
    dataframe.createOrReplaceTempView("person")
    val dataframe2 = spark.sql("select * from person where age > 20")

    dataframe2.map(t=>
      "name:"+t(0) + "," + "age:"+t(1)
    ).show()


  }
}