xgb_autotune: xgb_autotune
In gm209/gmtools: A collection of generic ML functions for Insurance Risk Modelling

Run an automatic bayesian optimisation of xgboost

1
2
3

xgb_autotune(dtrain, x, y, w = NULL, base_margin = NULL, xgbParams, nrounds,
  early_stopping_rounds, nfold, folds = NULL, verbose = TRUE, seed = 1921,
  maximize = FALSE, bounds, init_points, n_iter, init_grid_dt = NULL, ...)

`dtrain`	The training data for the optimisation
`x`	A list that identifies the features
`y`	A string that identifies the label
`w`	A string that identifies the weight column. Defaults to NULL.
`base_margin`	A string that identifies the base_margin (offset). Defaults to NULL
`xgbParams`	A list of extra parameters to be passed to xgb.cv
`nrounds`	the max number of iterations
`early_stopping_rounds`	If set to an integer k, training with a validation set will stop if the performance doesn't improve for k rounds.
`nfold`	the original dataset is randomly partitioned into nfold equal size subsamples.
`folds`	list provides a possibility to use a list of pre-defined CV folds (each element must be a vector of test fold's indices).
`verbose`	Whether or not to print progress.
`seed`	Random State
`maximize`	Should the loss function be maximized or not?
`bounds`	A named list of lower and upper bounds for each hyperparameter. Please use "L" suffix to indicate integer hyperparameter.
`init_points`	Number of randomly chosen points to sample the target function before Bayesian Optimization fitting the Gaussian Process.
`n_iter`	Total number of times the Bayesian Optimization is to repeated.
`init_grid_dt`	User specified points to sample the target function, should be a data.frame or data.table with identical column names as bounds.
`...`	Additional args to be passed to BayesOptim