您可以使用UserDefinedAggregateFunction。下面的代碼在火花1.6.2中測試
首先創建一個擴展UserDefinedAggregateFunction的類。
import org.apache.spark.sql.Row
import org.apache.spark.sql.expressions.{MutableAggregationBuffer, UserDefinedAggregateFunction}
import org.apache.spark.sql.types._
class ModeUDAF extends UserDefinedAggregateFunction{
override def dataType: DataType = StringType
override def inputSchema: StructType = new StructType().add("input", StringType)
override def deterministic: Boolean = true
override def bufferSchema: StructType = new StructType().add("mode", MapType(StringType, LongType))
override def initialize(buffer: MutableAggregationBuffer): Unit = {
buffer(0) = Map.empty[Any, Long]
}
override def update(buffer: MutableAggregationBuffer, input: Row): Unit = {
val buff0 = buffer.getMap[Any, Long](0)
val inp = input.get(0)
buffer(0) = buff0.updated(inp, buff0.getOrElse(inp, 0L) + 1L)
}
override def merge(buffer1: MutableAggregationBuffer, buffer2: Row): Unit = {
val mp1 = buffer1.getMap[Any, Long](0)
val mp2 = buffer2.getMap[Any, Long](0)
buffer1(0) = mp1 ++ mp2.map { case (k, v) => k -> (v + mp1.getOrElse(k, 0L)) }
}
override def evaluate(buffer: Row): Any = {
lazy val st = buffer.getMap[Any, Long](0).toStream
val mode = st.foldLeft(st.head){case (e, s) => if (s._2 > e._2) s else e}
mode._1
}
}
後續字符可以按照以下方式在數據框中使用它。
val modeColumnList = List("some", "column", "names") // or df.columns.toList
val modeAgg = new ModeUDAF()
val aggCols = modeColumnList.map(c => modeAgg(df(c)))
val aggregatedModeDF = df.agg(aggCols.head, aggCols.tail: _*)
aggregatedModeDF.show()
你也可以在最後的數據框上使用.collect來收集一個scala數據結構的結果。
注意:此解決方案的性能取決於輸入列的基數。
謝謝,我發現它只有在基數低時才合理。我在我生成的數據上嘗試這種方法,其中每個類別只有1,2,3個值,並且此方法非常慢。 –