Univariate Grid

Creates evaluation grid for any numeric or non-numeric vector z.

For discrete z (non-numeric, or numeric with at most grid_size unique values), this is simply sort(unique(z)).

Otherwise, if strategy = "uniform" (default), the evaluation points form a regular grid over the trimmed range of z. By trimmed range we mean the range of z after removing values outside trim[1] and trim[2] quantiles. Set trim = 0:1 for no trimming.

If strategy = "quantile", the evaluation points are quantiles over a regular grid of probabilities from trim[1] to trim[2].

Quantiles are calculated via the inverse of the ECDF, i.e., via stats::quantile(..., type = 1).

univariate_grid(
  z,
  grid_size = 49L,
  trim = c(0.01, 0.99),
  strategy = c("uniform", "quantile"),
  na.rm = TRUE
)

Arguments

z

A vector or factor.

grid_size

Approximate grid size.

trim

The default c(0.01, 0.99) means that values outside the 1% and 99% quantiles of non-discrete numeric columns are removed before calculation of grid values. Set to 0:1 for no trimming.

strategy

How to find grid values of non-discrete numeric columns? Either "uniform" or "quantile", see description of univariate_grid().

na.rm

Should missing values be dropped from the grid? Default is TRUE.

Value

A vector or factor of evaluation points.

See also

multivariate_grid()

Examples

univariate_grid(iris$Species)
#> [1] setosa     versicolor virginica 
#> Levels: setosa versicolor virginica
univariate_grid(rev(iris$Species))                       # Same
#> [1] setosa     versicolor virginica 
#> Levels: setosa versicolor virginica

x <- iris$Sepal.Width
univariate_grid(x, grid_size = 5)                        # Uniform binning
#> [1] 2.2 2.7 3.2 3.7 4.2
univariate_grid(x, grid_size = 5, strategy = "quantile")  # Quantile
#> [1] 2.2 2.8 3.0 3.3 4.2