Spark-SQL 读写csv文件

name,age,fv_value
libai,18,9999.99
xuance,30,99.99
diaochan,28,99.99

libai,18,9999.99

xuance,30,99.99

diaochan,28,99.99

• 读csv文件

import org.apache.spark.sql.{DataFrame, SparkSession}

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

    //创建SparkSession(是对SparkContext的包装和增强)
    val spark: SparkSession = SparkSession.builder()
      .appName(this.getClass.getSimpleName)
      .master("local[*]")
      .getOrCreate()
    //①文件中有表头
    val df: DataFrame = spark.read
      .option("header", "true") //将第一行当作表头
      .option("inferSchema", "true") //推断数据类型
      .csv("src/main/scala/data/user.csv")

//    df.printSchema()
//    df.show()


    //②文件中没有表头
    val df2: DataFrame = spark.read
      .option("inferSchema","true")
      .csv("src/main/scala/data/user2.csv")

    df2.toDF("name","age","fv")

    df2.printSchema()
    df2.show()

    spark.stop()
  }

}

• 写入csv类型的文件中

import org.apache.spark.SparkContext
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.{DataFrame, Row, SparkSession}
import org.apache.spark.sql.types.{DoubleType, IntegerType, StringType, StructField, StructType}

object WriteToCsv{
  def main(args: Array[String]): Unit = {
    //创建SparkSession
    val spark: SparkSession = SparkSession.builder()
      .appName(this.getClass.getSimpleName)
      .master("local[*]")
      .getOrCreate()

    val sc: SparkContext = spark.sparkContext

    val lines: RDD[String] = sc.textFile("src/main/scala/data/user.txt")
    //row的字段没有名字 没有类型
    val rdd1: RDD[Row] = lines.map(e => {
      val split = e.split(",")
      Row(split(0), split(1).toInt, split(2).toDouble)
    })

    //关联schema(字段名称、字段类型、是否可以为空)
    val schema: StructType = StructType(
      Array(
        StructField("name", StringType),
        StructField("age", IntegerType),
        StructField("fv", DoubleType)
      )
    )
    //将RowRDD与StructType中的schema关联
    val df1: DataFrame = spark.createDataFrame(rdd1, schema)

    df1.write.csv("src/main/scala/data/outcsv")
  }
}