This function calculate candidate splits for each selected variable. For numerical variables splits are calculated as percentiles (in general uniform quantiles of the length grid_points). For all other variables splits are calculated as unique values.
calculate_variable_split(
data,
variables = colnames(data),
grid_points = 101,
variable_splits_type = "quantiles",
new_observation = NA
)# S3 method for default
calculate_variable_split(
data,
variables = colnames(data),
grid_points = 101,
variable_splits_type = "quantiles",
new_observation = NA
)
A named list with splits for selected variables
validation dataset. Is used to determine distribution of observations.
names of variables for which splits shall be calculated
number of points used for response path
how variable grids shall be calculated? Use "quantiles" (default) for percentiles or "uniform" to get uniform grid of points
if specified (not NA) then all values in new_observation will be included in variable_splits
Note that calculate_variable_split function is S3 generic.
If you want to work on non standard data sources (like H2O ddf, external databases)
you should overload it.