DataFrame API 操作

package bl.test.spark

import org.apache.spark.sql.SparkSession

/**
  * DataFrame中的操作操作
  */
object DataFrameCase {

  def main(args: Array[String]) {
    val spark = SparkSession.builder().appName("DataFrameRDDApp").master("local[2]").getOrCreate()

    // RDD ==> DataFrame
    val rdd = spark.sparkContext.textFile("file:///Users/rocky/data/student.data")

    //注意：需要导入隐式转换
    import spark.implicits._
    val studentDF = rdd.map(_.split("\\|")).map(line => Student(line(0).toInt, line(1), line(2), line(3))).toDF()

    //show默认只显示前20条
    studentDF.show
    studentDF.show(30)
    studentDF.show(30, false)
    //前10行
    studentDF.take(10)
    //第一行
    studentDF.first()
    studentDF.head(3)

    //获取emaill的前30行 不截取
    studentDF.select("email").show(30, false)

    //名称为空的 或 Null
    studentDF.filter("name=''").show
    studentDF.filter("name='' OR name='NULL'").show


    //name以M开头的人
    studentDF.filter("SUBSTR(name,0,1)='M'").show
    //按照name排序 默认升序
    studentDF.sort(studentDF("name")).show
    studentDF.sort(studentDF("name").desc).show
    //按照name和id排序
    studentDF.sort("name", "id").show
    //按照name升序 id降序列
    studentDF.sort(studentDF("name").asc, studentDF("id").desc).show
    //别名查询
    studentDF.select(studentDF("name").as("student_name")).show

    //join查询
    val studentDF2 = rdd.map(_.split("\\|")).map(line => Student(line(0).toInt, line(1), line(2), line(3))).toDF()

    studentDF.join(studentDF2, studentDF.col("id") === studentDF2.col("id")).show

    spark.stop()
  }

  case class Student(id: Int, name: String, phone: String, email: String)

}