as_simple_factor: Convert modified predictor back into simple predictor

In realgabon/insuRglm: Tools for GLM Modeling in Insurance Context

Convert modified predictor back into simple predictor

Description

Converts custom factor, variate or offset back into the simple predictor. This may be also needed as a transition step when converting for example from custom factor to variate

Usage

as_simple_factor(x)

Arguments

x	Unquoted symbol. Predictor to be converted back to simple factor. Must be present in the modeling dataset.

Value

Original vector with updated attributes.

See Also

factor_modify

Examples

require(dplyr) # for the pipe operator
data('sev_train')

setup <- setup(
  data_train = sev_train,
  target = 'sev',
  weight = 'numclaims',
  family = 'gamma',
  keep_cols = c('pol_nbr', 'exposure', 'premium')
)

modeling <- setup %>%
  factor_add(pol_yr) %>%
  factor_add(veh_value) %>%
  model_fit() %>%
  model_save('model1') %>%
  factor_modify(veh_value = custom_factor(veh_value, mapping = c(1, 2, 3, 3, 3))) %>%
  model_fit() %>%
  model_save('model2') %>%
  factor_modify(veh_value = as_simple_factor(veh_value)) %>%
  factor_modify(veh_value = variate(veh_value, type = 'prop')) %>%
  model_fit()

realgabon/insuRglm documentation built on Jan. 2, 2023, 2:51 a.m.