Spark Scala CSV列名称转换为小写

Question

请在下面找到代码，然后让我知道如何将列名更改为小写。我尝试了withColumnRename，但是我必须为每个列都做一次，然后键入所有列名。我只想在列上这样做，所以我不想提及所有列名，因为它们太多了。

Scala版本：2.11 Spark：2.2

import org.apache.spark.sql.SparkSession
import org.apache.log4j.{Level, Logger}
import com.datastax


import org.apache.spark.SparkContext
import org.apache.spark.SparkConf
import com.datastax.spark.connector._
import org.apache.spark.sql._

object dataframeset {

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

    val conf = new SparkConf().setAppName("Sample1").setMaster("local[*]")
    val sc = new SparkContext(conf)
    sc.setLogLevel("ERROR")
    val rdd1 = sc.cassandraTable("tdata", "map3")
    Logger.getLogger("org").setLevel(Level.ERROR)
    Logger.getLogger("akka").setLevel(Level.ERROR)
    val spark1 = org.apache.spark.sql.SparkSession.builder().master("local").config("spark.cassandra.connection.host","127.0.0.1")
      .appName("Spark SQL basic example").getOrCreate()

    val df = spark1.read.format("csv").option("header","true").option("inferschema", "true").load("/Users/Desktop/del2.csv")
    import spark1.implicits._
    println("\nTop Records are:")
    df.show(1)


    val dfprev1 = df.select(col = "sno", "year", "StateAbbr")

    dfprev1.show(1)
}
}

要求的输出：

import org.apache.spark.sql.SparkSession
import org.apache.log4j.{Level, Logger}
import com.datastax


import org.apache.spark.SparkContext
import org.apache.spark.SparkConf
import com.datastax.spark.connector._
import org.apache.spark.sql._

object dataframeset {

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

    val conf = new SparkConf().setAppName("Sample1").setMaster("local[*]")
    val sc = new SparkContext(conf)
    sc.setLogLevel("ERROR")
    val rdd1 = sc.cassandraTable("tdata", "map3")
    Logger.getLogger("org").setLevel(Level.ERROR)
    Logger.getLogger("akka").setLevel(Level.ERROR)
    val spark1 = org.apache.spark.sql.SparkSession.builder().master("local").config("spark.cassandra.connection.host","127.0.0.1")
      .appName("Spark SQL basic example").getOrCreate()

    val df = spark1.read.format("csv").option("header","true").option("inferschema", "true").load("/Users/Desktop/del2.csv")
    import spark1.implicits._
    println("\nTop Records are:")
    df.show(1)


    val dfprev1 = df.select(col = "sno", "year", "StateAbbr")

    dfprev1.show(1)
}
}

实际输出：

|sno|year|stateabbr|    statedesc|cityname|geographiclevel

All the Columns names should be in lower case. 

Answer 1

只需使用toDF：

df.toDF(df.columns map(_.toLowerCase): _*)