A rolling kernel moves along one of the axes and assigns weights to datapoints depending on the distance to the kernel's location. It then calculates a weighted average on the y-values of the datapoints, creating a trendline. In contrast to (weighted) rolling averages, the interval between datapoints do not need to be constant.
stat_rollingkernel( mapping = NULL, data = NULL, geom = "line", position = "identity", ..., bw = "nrd", kernel = "gaussian", n = 256, expand = 0.1, na.rm = FALSE, orientation = "x", show.legend = NA, inherit.aes = TRUE )
Set of aesthetic mappings created by
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
mappingif there is no plot mapping.
The data to be displayed in this layer. There are three options:
NULL, the default, the data is inherited from the plot data as specified in the call to
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.
functionwill 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
functioncan be created from a
~ head(.x, 10)).
Use to override the default geom (
Position adjustment, either as a string naming the adjustment (e.g.
position_jitter), or the result of a call to a position adjustment function. Use the latter if you need to change the settings of the adjustment.
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.
A bandwidth, which can be one of the following:
One of the following:
functionthat takes a vector of distances as first argument, a numeric bandwidth as second argument and returns relative weights.
characterof length one that can take one of the following values:
A kernel that follows a normal distribution with 0 mean and bandwidth as standard deviation.
A kernel that follows a uniform distribution with \(bandwidth * -0.5\) and \(bandwidth * 0.5\) as minimum and maximum. This is similar to a simple, unweighted moving average.
A kernel that follows a Cauchy distribution with 0 as location and bandwidth as scale parameters. The Cauchy distribution has fatter tails than the normal distribution.
integerof length one: how many points to return per group.
numericof length one: how much to expand the range for which the rolling kernel is calculated beyond the most extreme datapoints.
FALSE, the default, missing values are removed with a warning. If
TRUE, missing values are silently removed.
characterof length one, either
"y", setting the axis along which the rolling should occur.
logical. Should this layer be included in the legends?
NA, the default, includes if any aesthetics are mapped.
FALSEnever includes, and
TRUEalways includes. It can also be a named logical vector to finely select the aesthetics to display.
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.
stat_rollingkernel() understands the following
aesthetics (required aesthetics are in bold)
A sequence of ordered x positions.
The weighted value of the rolling kernel.
The sum of weight strengths at a position.
The fraction of weight strengths at a position. This is the same as
weight / sum(weight)by group.
ggplot(mpg, aes(displ, hwy, colour = class)) + geom_point() + stat_rollingkernel() # The (scaled) weights can be used to emphasise data-dense areas ggplot(mpg, aes(displ, hwy, colour = class)) + geom_point() + stat_rollingkernel(aes(alpha = after_stat(scaled)))