spark-histogram.scala

// NOTE: add minimum and maximum values to thresholds
val thresholds: Array[Double] = Array(Double.MinValue, 0.0) ++ (((0.0 until 50.0 by 10).toArray ++ Array(Double.MaxValue)).map(_.toDouble))

// Convert DataFrame to RDD and calculate histogram values
val _tmpHist = df
    .select($"column" cast "double")
    .rdd.map(r => r.getDouble(0))
    .histogram(thresholds)

// Result DataFrame contains `from`, `to` range and the `value`.
val histogram = sc.parallelize((thresholds, thresholds.tail, _tmpHist).zipped.toList).toDF("from", "to", "value")