* setup_metrics.do -- the three-frame metrics quoted in the "Setting up the H2O
* frames" section of the blog.
*
* Same construction and same model as figures.do, which produced figure 1.


clear all
set more off
set seed 20260729
set obs 4000
gen double x1 = runiform(-3,3)
gen double x2 = rnormal()
gen double x3 = 0.9*x2 + sqrt(1-0.9^2)*rnormal()
gen double x4 = runiform(-2,2)
gen byte   g  = runiform()<0.5
gen double x5 = runiform()
gen byte   x6 = runiform()<0.5
gen double y  = 4*sin(1.5*x1) + 2*x2 + 3*x4*(2*g-1) + rnormal(0,1.5)

h2o init
_h2oframe put, into(all)
_h2oframe split all, into(train valid test) split(0.6 0.2 0.2) rseed(19)
_h2oframe change train

quietly h2oml gbregress y x1 x2 x3 x4 g x5 x6, validframe(valid) ///
    ntrees(500) maxdepth(12) minobsleaf(1) lrate(0.1) h2orseed(19)

di _n "===== TRAINING ====="
h2omlpostestframe _train
h2omlestat metrics

di _n "===== VALIDATION ====="
h2omlpostestframe valid
h2omlestat metrics

di "----setup_metrics.do successful----"