code snippets for Hyperparameters (part II): Random Search on Spark

randomSearch_sparkml

import org.apache.spark.ml.Pipeline
import org.apache.spark.ml.tuning.CrossValidatorModel
import org.apache.spark.ml.param.ParamMap

val pipeline: Pipeline = ...
val paramGrid: Array[ParamMap] = new ParamGridBuilder().
  addGrid(...).
  addGrid(...).
  build

val cv = new CrossValidator().
  setEstimator(pipeline).
  setEvaluator(...).
  setEstimatorParamMaps(paramGrid).
  setNumFolds(...).
  setParallelism(...)

val bestModel: CrossValidatorModel = cv.fit(training)