使用Scala在Spark DataFrame中将某些DataType的所有列的DataType转换为另一个DataFrame

import org.apache.spark.sql.{DataFrame, SparkSession}
import org.apache.spark.sql.functions._
import org.apache.spark.sql.types._

val spark = SparkSession.builder()
  .appName("DataType Conversion")
  .getOrCreate()

def convertColumns(dataFrame: DataFrame, sourceDataType: DataType, targetDataType: DataType): DataFrame = {
  val columns = dataFrame.schema.fields.filter(_.dataType == sourceDataType).map(_.name)
  columns.foldLeft(dataFrame) { (df, col) =>
    df.withColumn(col, col.cast(targetDataType))
  }
}

val data = Seq(
  (1, "John", 25),
  (2, "Jane", 30),
  (3, "Bob", 35)
)
val schema = StructType(Seq(
  StructField("id", IntegerType),
  StructField("name", StringType),
  StructField("age", IntegerType)
))
val originalDF = spark.createDataFrame(data.toDF(), schema)

val convertedDF = convertColumns(originalDF, IntegerType, StringType)