I would like to run a naive implementation of grid search with MLlib but
I am a bit confused about choosing the 'best' range of parameters.
Apparently, I do not want to waste too much resources for a combination
of parameters that will probably not give a better mode. Any suggestions
from your experience?
val intercept : List[Boolean] = List(false)
val classes : List[Int] = List(2)
val validate : List[Boolean] = List(true)
val tolerance : List[Double] = List(0.0000001 , 0.000001 , 0.00001 ,
0.0001 , 0.001 , 0.01 , 0.1 , 1.0)
val gradient : List[Gradient] = List(new LogisticGradient() , new
LeastSquaresGradient() , new HingeGradient())
val corrections : List[Int] = List(5 , 10 , 15)
val iters : List[Int] = List(1 , 10 , 100 , 1000 , 10000)
val regparam : List[Double] = List(0.0 , 0.0001 , 0.001 , 0.01 ,
0.1 , 1.0 , 10.0 , 100.0)
val updater : List[Updater] = List(new SimpleUpdater() , new
L1Updater() , new SquaredL2Updater())
val combinations = for (a <- intercept;
b <- classes;
c <- validate;
d <- tolerance;
e <- gradient;
f <- corrections;
g <- iters;
h <- regparam;
i <- updater) yield (a,b,c,d,e,f,g,h,i)
for( ( interceptS , classesS , validateS , toleranceS , gradientS ,
correctionsS , itersS , regParamS , updaterS ) <- combinations.take(3) ) {
val lr : LogisticRegressionWithLBFGS = new
LogisticRegressionWithLBFGS().
setIntercept(addIntercept=interceptS).
setNumClasses(numClasses=classesS).
setValidateData(validateData=validateS)
lr.
optimizer.
setConvergenceTol(tolerance=toleranceS).
setGradient(gradient=gradientS).
setNumCorrections(corrections=correctionsS).
setNumIterations(iters=itersS).
setRegParam(regParam=regParamS).
setUpdater(updater=updaterS)
}
---------------------------------------------------------------------
To unsubscribe e-mail: user-unsubscr...@spark.apache.org
