h2o.cv.rnd.grid.shrinkage: h2o.cv.rnd.grid.shrinkage

In rocalabern/h2otools: Tools for H2O

Description

It does a grid search for shrinkage.
Check h2o.cv.rnd.opt.param for a parameter optimization that can work with different algorithms and differents parameters to optimize.

Usage

h2o.cv.rnd.grid.shrinkage(dataset.h2o, listVars, split.perc = 0.6,
  model_algorithm = h2o.gbm, nfolds = 10, seq_shrinkage = c(0, seq(from =
  0.002, to = 0.008, by = 0.002), seq(from = 0.01, to = 0.2, by = 0.05)),
  model_params = list(shrinkage = 0.1, n.trees = 30, interaction.depth = 5,
  n.bins = 50, n.minobsinnode = 1000, distribution = "bernoulli", importance =
  FALSE, balance.classes = TRUE), gain.calculate = TRUE, gain.ngroups = 100,
  col.pred = 3, col.target = tail(h2o::colnames(dataset.h2o), n = 1))

See Also

h2o.cv.rnd.grid.shrinkage h2o.cv.rnd.opt.param h2o.cv.rnd.opt.param.get_best h2o.ggplot.dfResultsCV

rocalabern/h2otools documentation built on May 27, 2019, 12:13 p.m.