一、測試數據

7369,SMITH,CLERK,7902,1980/12/17,800,20
7499,ALLEN,SALESMAN,7698,1981/2/20,1600,300,30
7521,WARD,SALESMAN,7698,1981/2/22,1250,500,30
7566,JONES,MANAGER,7839,1981/4/2,2975,20
7654,MARTIN,SALESMAN,7698,1981/9/28,1250,1400,30
7698,BLAKE,MANAGER,7839,1981/5/1,2850,30
7782,CLARK,MANAGER,7839,1981/6/9,2450,10
7788,SCOTT,ANALYST,7566,1987/4/19,3000,20
7839,KING,PRESIDENT,1981/11/17,5000,10
7844,TURNER,SALESMAN,7698,1981/9/8,1500,0,30
7876,ADAMS,CLERK,7788,1987/5/23,1100,20
7900,JAMES,CLERK,7698,1981/12/3,9500,30
7902,FORD,ANALYST,7566,1981/12/3,3000,20
7934,MILLER,CLERK,7782,1982/1/23,1300,10

二、創建DataFrame

方式一：DSL方式操作

• 實例化SparkContext和SparkSession對象
• 利用StructType類型構建schema，用于定義數據的結構信息
• 通過SparkContext對象讀取文件，生成RDD
• 將RDD[String]轉換成RDD[Row]
• 通過SparkSession對象創建dataframe
• 完整代碼如下：

package com.scala.demo.sql

import org.apache.spark.{SparkConf, SparkContext}
import org.apache.spark.sql.{Row, SparkSession}
import org.apache.spark.sql.types.{DataType, DataTypes, StructField, StructType}

object Demo01 {
  def main(args: Array[String]): Unit = {
    // 1.創建SparkContext和SparkSession對象
    val sc = new SparkContext(new SparkConf().setAppName("Demo01").setMaster("local[2]"))
    val sparkSession = SparkSession.builder().getOrCreate()

    // 2. 使用StructType來定義Schema
    val mySchema = StructType(List(
      StructField("empno", DataTypes.IntegerType, false),
      StructField("ename", DataTypes.StringType, false),
      StructField("job", DataTypes.StringType, false),
      StructField("mgr", DataTypes.StringType, false),
      StructField("hiredate", DataTypes.StringType, false),
      StructField("sal", DataTypes.IntegerType, false),
      StructField("comm", DataTypes.StringType, false),
      StructField("deptno", DataTypes.IntegerType, false)
    ))
    // 3. 讀取數據
    val empRDD = sc.textFile("file:///D:\TestDatas\emp.csv")

    // 4. 將其映射成ROW對象
    val rowRDD = empRDD.map(line => {
      val strings = line.split(",")
      Row(strings(0).toInt, strings(1), strings(2), strings(3), strings(4), strings(5).toInt,strings(6), strings(7).toInt)
    })

    // 5. 創建DataFrame
    val dataFrame = sparkSession.createDataFrame(rowRDD, mySchema)

    // 6. 展示內容 DSL
	dataFrame.groupBy("deptno").sum("sal").as("result").sort("sum(sal)").show()
  }
}