geom_density_: More general smoothed density estimates

Description

Computes and draws kernel density estimate. Compared with geom_density(), it provides more general cases that accepting `x` and `y`. The `x` (or `y`) is a group variable and `y` (or `x`) is the target variable to be plotted. The result is a different density of `y` (`x`) for each value of `x` (`y`). If only one of `x` or `y` is provided, it will be the target variable (no grouping) and the standard geom_density() will be executed.

Usage

geom_density_(
  mapping = NULL,
  data = NULL,
  stat = "density_",
  position = "identity_",
  ...,
  scale.x = NULL,
  scale.y = c("data", "variable"),
  as.mix = FALSE,
  positive = TRUE,
  adjust = 0.9,
  na.rm = FALSE,
  orientation = NA,
  show.legend = NA,
  inherit.aes = TRUE
)
stat_density_(
  mapping = NULL,
  data = NULL,
  geom = "density_",
  position = "stack_",
  ...,
  bw = "nrd0",
  adjust = 1,
  kernel = "gaussian",
  n = 512,
  trim = FALSE,
  na.rm = FALSE,
  orientation = NA,
  show.legend = NA,
  inherit.aes = TRUE
)

Arguments

mapping

Set of aesthetic mappings created by aes() or aes_(). If specified and inherit.aes = TRUE (the default), it is combined with the default mapping at the top level of the plot. You must supply mapping if there is no plot mapping.

data

The data to be displayed in this layer. There are three options:

If NULL, the default, the data is inherited from the plot data as specified in the call to ggplot().

A data.frame, or other object, will override the plot data. All objects will be fortified to produce a data frame. See fortify() for which variables will be created.

A function will be called with a single argument, the plot data. The return value must be a data.frame, and will be used as the layer data. A function can be created from a formula (e.g. ~ head(.x, 10)).

stat

Use to override the default connection between geom_density and stat_density.

position

Position adjustment, either as a string, or the result of a call to a position adjustment function.

...

Other arguments passed on to layer(). These are often aesthetics, used to set an aesthetic to a fixed value, like colour = "red" or size = 3. They may also be parameters to the paired geom/stat.

scale.x

A length 2 numerical vector. Scale the n coordinates of the points where the density is estimated.

scale.y

one of 'data', 'variable' to specify.

Type	Description
data (default)	The density estimates are scaled by the whole data set

If the scale.y is "data", it is meaningful to compare the density (shape and area) across all groups; else it is only meaningful to compare the density under each variable.

as.mix

Logical. Under each variable, if as.mix = TRUE, the sum of the density estimate area is mixed and scaled to maximum 1. The area of each group is proportional to its own count; if as.mix = FALSE the area of each group is the same, with maximum 1.

positive

If `y` is set as the density estimate, where the smoothed curved is faced to, right (`positive`) or left (`negative`) as vertical layout; up (`positive`) or down (`negative`) as horizontal layout?

adjust

adjust the proportional maximum height of the estimate (density, histogram, ...).

na.rm

If FALSE, the default, missing values are removed with a warning. If TRUE, missing values are silently removed.

orientation

The orientation of the layer. The default (NA) automatically determines the orientation from the aesthetic mapping. In the rare event that this fails it can be given explicitly by setting orientation to either "x" or "y". See the Orientation section for more detail.

show.legend

logical. Should this layer be included in the legends? NA, the default, includes if any aesthetics are mapped. FALSE never includes, and TRUE always includes. It can also be a named logical vector to finely select the aesthetics to display.

inherit.aes

If FALSE, overrides the default aesthetics, rather than combining with them. This is most useful for helper functions that define both data and aesthetics and shouldn't inherit behaviour from the default plot specification, e.g. borders().

geom

Use to override the default connection between geom_density and stat_density.

The smoothing bandwidth to be used. If numeric, the standard deviation of the smoothing kernel. If character, a rule to choose the bandwidth, as listed in stats::bw.nrd().

kernel

Kernel. See list of available kernels in density().

number of equally spaced points at which the density is to be estimated, should be a power of two, see density() for details

trim

If FALSE, the default, each density is computed on the full range of the data. If TRUE, each density is computed over the range of that group: this typically means the estimated x values will not line-up, and hence you won't be able to stack density values. This parameter only matters if you are displaying multiple densities in one plot or if you are manually adjusting the scale limits.

Orientation

This geom treats each axis differently and, thus, can thus have two orientations. Often the orientation is easy to deduce from a combination of the given mappings and the types of positional scales in use. Thus, ggplot2 will by default try to guess which orientation the layer should have. Under rare circumstances, the orientation is ambiguous and guessing may fail. In that case the orientation can be specified directly using the orientation parameter, which can be either "x" or "y". The value gives the axis that the geom should run along, "x" being the default orientation you would expect for the geom.

Details

There are four combinations of scale.y and as.mix

scale.y = "variable" and as.mix = FALSE: The density estimates area of each group under the same variable is the same and scaled to maximum of 1.
scale.y = "variable" and as.mix = TRUE: The density estimates area of each group under the same variable is proportional to its own counts (over this variable).
scale.y = "data" and as.mix = FALSE: The sum of density estimates area of all group is scaled to maximum of 1. The sum of the density area for each variable is proportional to the its counts (over the whole dataset). Under each variable, the area of each group is the same.
scale.y = "data" and as.mix = TRUE: The sum of density estimates area of all group is scaled to maximum of 1 and the area of each group is proportional to its own count.

Examples

Run this code

# NOT RUN {
if(require(dplyr)) {
  mpg %>%
    dplyr::filter(drv != "f") %>%
    ggplot(mapping = aes(x = drv, y = cty, fill = factor(cyl))) +
    geom_density_(alpha = 0.1)

  # only `x` or `y` is provided
  # that would be equivalent to call function `geom_density()`
  diamonds %>%
    dplyr::sample_n(500) %>%
    ggplot(mapping = aes(x = price)) +
    geom_density_()

  # density and boxplot
  # set the density estimate on the left
  mpg %>%
    dplyr::filter(drv != "f") %>%
    ggplot(mapping = aes(x = drv, y = cty, fill = factor(cyl))) +
    geom_density_(alpha = 0.1, scale.y = "data", positive = FALSE) +
    geom_boxplot()

  # x as density
  set.seed(12345)
  suppressWarnings(
    diamonds %>%
      dplyr::sample_n(500) %>%
      ggplot(mapping = aes(x = price, y = cut, fill = color)) +
      geom_density_(orientation = "x", adjust = 0.25,
                    position = "stack_",
                    scale.y = "variable")
  )
}
# settings of `scale.y` and `as.mix`
# }
# NOT RUN {
ggplots <- lapply(list(
                      list(scale.y = "data", as.mix = TRUE),
                      list(scale.y = "data", as.mix = FALSE),
                      list(scale.y = "variable", as.mix = TRUE),
                      list(scale.y = "variable", as.mix = FALSE)
                    ),
                   function(vars) {
                     scale.y <- vars[["scale.y"]]
                     as.mix <- vars[["as.mix"]]
                     ggplot(mpg,
                            mapping = aes(x = drv, y = cty, fill = factor(cyl))) +
                       geom_density_(alpha = 0.1, scale.y = scale.y, as.mix = as.mix) +
                       labs(title = paste("scale.y =", scale.y),
                            subtitle = paste("as.mix =", as.mix))
                   })
suppressWarnings(
  gridExtra::grid.arrange(grobs = ggplots)
)
# }
# NOT RUN {
# }