stat_summary allows for tremendous flexibilty in the specification
of summary functions. The summary function can either supply individual
summary functions for each of y, ymin and ymax (with fun.y,
fun.ymax, fun.ymin), or return a data frame containing any
number of aesthetiics with with fun.data. All summary functions
are called with a single vector of values, x.stat_summary(mapping = NULL, data = NULL, geom = "pointrange",
position = "identity", ...)aes or aes_string. Only needs to be set
at the layer level if you are overriding the plot defaults.p <- qplot(cyl, mpg, data = mtcars, stat="summary", fun.y = "mean") p # Don't use ylim to zoom into a summary plot - this throws the # data away p + ylim(15, 30) # Instead use coord_cartesian p + coord_cartesian(ylim = c(15, 30))
# You can supply individual functions to summarise the value at # each x:
stat_sum_single <- function(fun, geom="point", ...) { stat_summary(fun.y=fun, colour="red", geom=geom, size = 3, ...) }
d + stat_sum_single(mean) d + stat_sum_single(mean, geom="line") d + stat_sum_single(median) d + stat_sum_single(sd)
d + stat_summary(fun.y = mean, fun.ymin = min, fun.ymax = max, colour = "red")
d + aes(colour = factor(vs)) + stat_summary(fun.y = mean, geom="line")
# Alternatively, you can supply a function that operates on a data.frame. # A set of useful summary functions is provided from the Hmisc package:
stat_sum_df <- function(fun, geom="crossbar", ...) { stat_summary(fun.data=fun, colour="red", geom=geom, width=0.2, ...) }
# The crossbar geom needs grouping to be specified when used with # a continuous x axis. d + stat_sum_df("mean_cl_boot", mapping = aes(group = cyl)) d + stat_sum_df("mean_sdl", mapping = aes(group = cyl)) d + stat_sum_df("mean_sdl", mult = 1, mapping = aes(group = cyl)) d + stat_sum_df("median_hilow", mapping = aes(group = cyl))
# There are lots of different geoms you can use to display the summaries
d + stat_sum_df("mean_cl_normal", mapping = aes(group = cyl)) d + stat_sum_df("mean_cl_normal", geom = "errorbar") d + stat_sum_df("mean_cl_normal", geom = "pointrange") d + stat_sum_df("mean_cl_normal", geom = "smooth")
# Summaries are more useful with a bigger data set: mpg2 <- subset(mpg, cyl != 5L) m <- ggplot(mpg2, aes(x=cyl, y=hwy)) + geom_point() + stat_summary(fun.data = "mean_sdl", geom = "linerange", colour = "red", size = 2, mult = 1) + xlab("cyl") m # An example with highly skewed distributions: set.seed(596) mov <- movies[sample(nrow(movies), 1000), ] m2 <- ggplot(mov, aes(x= factor(round(rating)), y=votes)) + geom_point() m2 <- m2 + stat_summary(fun.data = "mean_cl_boot", geom = "crossbar", colour = "red", width = 0.3) + xlab("rating") m2 # Notice how the overplotting skews off visual perception of the mean # supplementing the raw data with summary statistics is _very_ important
# Next, we'll look at votes on a log scale.
# Transforming the scale means the data are transformed # first, after which statistics are computed: m2 + scale_y_log10() # Transforming the coordinate system occurs after the # statistic has been computed. This means we're calculating the summary on the raw data # and stretching the geoms onto the log scale. Compare the widths of the # standard errors. m2 + coord_trans(y="log10")
geom_errorbar, geom_pointrange,
geom_linerange, geom_crossbar for geoms to
display summarised data