How to pivot Spark DataFrame?

Question

I am starting to use Spark DataFrames and I need to be able to pivot the data to create multiple columns out of 1 column with multiple rows. There is built in functionality

Answer 1

Initially i adopted Al M's solution. Later took the same thought and rewrote this function as a transpose function.

This method transposes any df rows to columns of any data-format with using key and value column

for input csv

id,tag,value
1,US,50a
1,UK,100
1,Can,125
2,US,75
2,UK,150
2,Can,175

ouput

+--+---+---+---+
|id| UK| US|Can|
+--+---+---+---+
| 2|150| 75|175|
| 1|100|50a|125|
+--+---+---+---+

transpose method :

def transpose(hc : HiveContext , df: DataFrame,compositeId: List[String], key: String, value: String) = {

val distinctCols =   df.select(key).distinct.map { r => r(0) }.collect().toList

val rdd = df.map { row =>
(compositeId.collect { case id => row.getAs(id).asInstanceOf[Any] },
scala.collection.mutable.Map(row.getAs(key).asInstanceOf[Any] -> row.getAs(value).asInstanceOf[Any]))
}
val pairRdd = rdd.reduceByKey(_ ++ _)
val rowRdd = pairRdd.map(r => dynamicRow(r, distinctCols))
hc.createDataFrame(rowRdd, getSchema(df.schema, compositeId, (key, distinctCols)))

}

private def dynamicRow(r: (List[Any], scala.collection.mutable.Map[Any, Any]), colNames: List[Any]) = {
val cols = colNames.collect { case col => r._2.getOrElse(col.toString(), null) }
val array = r._1 ++ cols
Row(array: _*)
}

private  def getSchema(srcSchema: StructType, idCols: List[String], distinctCols: (String, List[Any])): StructType = {
val idSchema = idCols.map { idCol => srcSchema.apply(idCol) }
val colSchema = srcSchema.apply(distinctCols._1)
val colsSchema = distinctCols._2.map { col => StructField(col.asInstanceOf[String], colSchema.dataType, colSchema.nullable) }
StructType(idSchema ++ colsSchema)
}

main snippet

import java.util.Date
import org.apache.spark.SparkConf
import org.apache.spark.SparkContext
import org.apache.spark.sql.Row
import org.apache.spark.sql.DataFrame
import org.apache.spark.sql.types.StructType
import org.apache.spark.sql.hive.HiveContext
import org.apache.spark.sql.types.StructField


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

    val sc = new SparkContext(conf)
    val sqlContext = new org.apache.spark.sql.SQLContext(sc)
    val dfdata1 = sqlContext.read.format("com.databricks.spark.csv").option("header", "true").option("inferSchema", "true")
    .load("data.csv")
    dfdata1.show()  
    val dfOutput = transpose(new HiveContext(sc), dfdata1, List("id"), "tag", "value")
    dfOutput.show

}