Change nullable property of column in spark dataframe

Answer

With the imports

import org.apache.spark.sql.types.{StructField, StructType}
import org.apache.spark.sql.{DataFrame, SQLContext}
import org.apache.spark.{SparkConf, SparkContext}

you can use

/**
 * Set nullable property of column.
 * @param df source DataFrame
 * @param cn is the column name to change
 * @param nullable is the flag to set, such that the column is  either nullable or not
 */
def setNullableStateOfColumn( df: DataFrame, cn: String, nullable: Boolean) : DataFrame = {

  // get schema
  val schema = df.schema
  // modify [[StructField] with name `cn`
  val newSchema = StructType(schema.map {
    case StructField( c, t, _, m) if c.equals(cn) => StructField( c, t, nullable = nullable, m)
    case y: StructField => y
  })
  // apply new schema
  df.sqlContext.createDataFrame( df.rdd, newSchema )
}

directly.

Also you can make the method available via the “pimp my library” library pattern ( see my SO post What is the best way to define custom methods on a DataFrame? ), such that you can call

val df = ....
val df2 = df.setNullableStateOfColumn( "id", true )

Edit

Alternative solution 1

Use a slight modified version of setNullableStateOfColumn

def setNullableStateForAllColumns( df: DataFrame, nullable: Boolean) : DataFrame = {
  // get schema
  val schema = df.schema
  // modify [[StructField] with name `cn`
  val newSchema = StructType(schema.map {
    case StructField( c, t, _, m) ⇒ StructField( c, t, nullable = nullable, m)
  })
  // apply new schema
  df.sqlContext.createDataFrame( df.rdd, newSchema )
}

Alternative solution 2

Explicitely define the schema. (Use reflection to create a solution that is more general)

configuredUnitTest("Stackoverflow.") { sparkContext =>

  case class Input(id:Long, var1:Int, var2:Int, var3:Double)

  val sqlContext = new SQLContext(sparkContext)
  import sqlContext.implicits._


  // use this to set the schema explicitly or
  // use refelection on the case class member to construct the schema
  val schema = StructType( Seq (
    StructField( "id", LongType, true),
    StructField( "var1", IntegerType, true),
    StructField( "var2", IntegerType, true),
    StructField( "var3", DoubleType, true)
  ))

  val is: List[Input] = List(
    Input(1110, 0, 1001,-10.00),
    Input(1111, 1, 1001, 10.00),
    Input(1111, 0, 1002, 10.00)
  )

  val rdd: RDD[Input] =  sparkContext.parallelize( is )
  val rowRDD: RDD[Row] = rdd.map( (i: Input) ⇒ Row(i.id, i.var1, i.var2, i.var3))
  val inputDF = sqlContext.createDataFrame( rowRDD, schema ) 

  inputDF.printSchema
  inputDF.show()
}