dials (version 0.0.2)

finalize: Functions to finalize data-specific parameter ranges

Description

These functions take a parameter object and modify the unknown parts of ranges based on simple heuristics.

Usage

finalize(object, ...)
# S3 method for list
finalize(object, x, force = TRUE, ...)
# S3 method for param
finalize(object, x, force = TRUE, ...)
get_p(object, x, log_vals = FALSE, ...)
get_log_p(object, x, ...)
get_n_frac(object, x, log_vals = FALSE, frac = 1/3, ...)
get_n_frac_range(object, x, log_vals = FALSE, frac = c(1/10, 5/10),
  ...)
get_n(object, x, log_vals = FALSE, ...)
get_rbf_range(object, x, seed = sample.int(10^5, 1), ...)
get_batch_sizes(object, x, frac = c(1/10, 1/3), ...)

Arguments

object

A param object or list.

...

Other arguments to pass to kernlab::sigest.

x

The predictor data. In some cases (see below) this should only include numeric data.

force

A single logical that indicates that, even if the parameter object is complete, should it update the ranges anyway?

log_vals

A logical: should the ranges be set on the log10 scale?

frac

A double for the fraction of the data to be used for the upper bound. For get_n_frac_range and get_batch_sizes, two fractional values are required.

seed

An integer to control the randomness of the calculations.

Value

An updated param object.

Details

finalize runes the embedded finalization code contained in the param object and returns the updated version.

The "get" helper functions are designed to be used with the pipe and update the parameter object in-place.

get_p and get_log_p set the upper value of the range to be the number of columns in the data (on the natural and log10 scale, respectively). get_n and get_n_frac set the upper value to be a value that uses the number of rows.

get_rbf_range sets both bounds based on the heuristic defined in kernlab::sigest. It requires that all columns in x be numeric.

Examples

# NOT RUN {
library(dplyr)
car_pred <- mtcars %>% select(-mpg)

# Needs an upper bound
mtry
finalize(mtry, car_pred)

# Nothing to do here since no unknowns
penalty
finalize(penalty, car_pred)

library(kernlab)
library(tibble)
library(purrr)

params <- 
  tribble(
     ~parameter,   ~object,
         "mtry",      mtry, 
    "num_terms", num_terms, 
    "rbf_sigma", rbf_sigma
  ) 
params
  
# Note that `rbf_sigma` has a default range that does not need to be
# finalized but will be changed if used in the function:
complete_params <- 
  params %>%
  mutate(object = map(object, finalize, car_pred))
complete_params

params %>% dplyr::filter(parameter == "rbf_sigma") %>% pull(object)
complete_params %>% dplyr::filter(parameter == "rbf_sigma") %>% pull(object)

# }