plot method for ale objects

#' @description For the 2D plots, n_y_quant is the number of quantiles into which to divide the predicted variable (y). The middle quantiles are grouped specially:

• The middle quantile is the first confidence interval of median_band_pct (median_band_pct[1]) around the median. This middle quantile is special because it generally represents no meaningful interaction.

• The quantiles above and below the middle are extended from the borders of the middle quantile to the regular borders of the other quantiles.

Usage

# S3 method for class 'ale'
plot(
  x,
  type = "ale",
  ...,
  relative_y = "median",
  p_alpha = c(0.01, 0.05),
  median_band_pct = c(0.05, 0.5),
  rug_sample_size = obj$params$sample_size,
  min_rug_per_interval = 1,
  n_x1_bins = NULL,
  n_x2_bins = NULL,
  n_y_quant = 10,
  seed = 0,
  silent = FALSE
)

Arguments

x

ale object. The object of class ale containing data to be plotted.

type

character(1). 'ale' for regular ALE plots; 'effects' for an ALE statistic effects plot.

...

not used. Inserted to require explicit naming of subsequent arguments.

relative_y

character(1) in c('median', 'mean', 'zero'). The ALE y values in the plots will be adjusted relative to this value. 'median' is the default. 'zero' will maintain the actual ALE values, which are relative to zero.

p_alpha

numeric length 2 from 0 to 1. Alpha for "confidence interval" ranges for printing bands around the median for single-variable plots. These are the default values used if p_values are provided. If p_values are not provided, then median_band_pct is used instead. The inner band range will be the median value of y ± p_alpha[2] of the relevant ALE statistic (usually ALE range or normalized ALE range). For plots with a second outer band, its range will be the median ± p_alpha[1]. For example, in the ALE plots, for the default p_alpha = c(0.01, 0.05), the inner band will be the median ± ALE minimum or maximum at p = 0.05 and the outer band will be the median ± ALE minimum or maximum at p = 0.01.

median_band_pct

numeric length 2 from 0 to 1. Alpha for "confidence interval" ranges for printing bands around the median for single-variable plots. These are the default values used if p_values are not provided. If p_values are provided, then median_band_pct is ignored. The inner band range will be the median value of y ± median_band_pct[1]/2. For plots with a second outer band, its range will be the median ± median_band_pct[2]/2. For example, for the default median_band_pct = c(0.05, 0.5), the inner band will be the median ± 2.5% and the outer band will be the median ± 25%.

rug_sample_size, min_rug_per_interval

non-negative integer(1). Rug plots are down-sampled to rug_sample_size rows otherwise they can be very slow for large datasets. By default, their size is the sample_size size from the ale_obj parameters. They maintain representativeness of the data by guaranteeing that each of the ALE bins will retain at least min_rug_per_interval elements; usually set to just 1 (default) or 2. To prevent this down-sampling, set rug_sample_size to Inf.

n_x1_bins, n_x2_bins

positive integer(1). Number of bins for the x1 or x2 axes respectively for interaction plot. These values are ignored if x1 or x2 are not numeric (i.e, if they are logical or factors).

n_y_quant

positive integer(1). Number of intervals over which the range of y values is divided for the colour bands of the interaction plot. See details.

seed

See documentation for ale()

silent

See documentation for ale()

Details

There will always be an odd number of quantiles: the special middle quantile plus an equal number of quantiles on each side of it. If n_y_quant is even, then a middle quantile will be added to it. If n_y_quant is odd, then the number specified will be used, including the middle quantile.