stat_density {ggplot2} | R Documentation |
1d kernel density estimate.
stat_density(mapping = NULL, data = NULL, geom = "area", position = "stack", adjust = 1, kernel = "gaussian", trim = FALSE, na.rm = FALSE, ...)
adjust |
see |
kernel |
kernel used for density estimation, see
|
trim |
if |
na.rm |
If |
mapping |
The aesthetic mapping, usually constructed
with |
data |
A layer specific dataset - only needed if you want to override the plot defaults. |
geom |
The geometric object to use display the data |
position |
The position adjustment to use for overlappling points on this layer |
... |
other arguments passed on to
|
data.frame with additional columns:
density |
density estimate |
count |
density * number of points - useful for stacked density plots |
scaled |
density estimate, scaled to maximum of 1 |
stat_density
understands the following aesthetics (required aesthetics are in bold):
x
fill
y
stat_bin
for the histogram
m <- ggplot(movies, aes(x = rating)) m + geom_density() # Adjust parameters m + geom_density(kernel = "rectangular") m + geom_density(kernel = "biweight") m + geom_density(kernel = "epanechnikov") m + geom_density(adjust=1/5) # Very rough m + geom_density(adjust=5) # Very smooth # Adjust aesthetics m + geom_density(aes(fill=factor(Drama)), size=2) # Scale so peaks have same height: m + geom_density(aes(fill=factor(Drama), y = ..scaled..), size=2) m + geom_density(colour="darkgreen", size=2) m + geom_density(colour="darkgreen", size=2, fill=NA) m + geom_density(colour="darkgreen", size=2, fill="green") # Change scales (m <- ggplot(movies, aes(x=votes)) + geom_density(trim = TRUE)) m + scale_x_log10() m + coord_trans(x="log10") m + scale_x_log10() + coord_trans(x="log10") # Also useful with m + stat_bin() # Make a volcano plot ggplot(diamonds, aes(x = price)) + stat_density(aes(ymax = ..density.., ymin = -..density..), fill = "grey50", colour = "grey50", geom = "ribbon", position = "identity") + facet_grid(. ~ cut) + coord_flip() # Stacked density plots # If you want to create a stacked density plot, you need to use # the 'count' (density * n) variable instead of the default density # Loses marginal densities qplot(rating, ..density.., data=movies, geom="density", fill=mpaa, position="stack") # Preserves marginal densities qplot(rating, ..count.., data=movies, geom="density", fill=mpaa, position="stack") # You can use position="fill" to produce a conditional density estimate qplot(rating, ..count.., data=movies, geom="density", fill=mpaa, position="fill") # Need to be careful with weighted data m <- ggplot(movies, aes(x=rating, weight=votes)) m + geom_histogram(aes(y = ..count..)) + geom_density(fill=NA) m <- ggplot(movies, aes(x=rating, weight=votes/sum(votes))) m + geom_histogram(aes(y=..density..)) + geom_density(fill=NA, colour="black") library(plyr) # to access round_any movies$decade <- round_any(movies$year, 10) m <- ggplot(movies, aes(x=rating, colour=decade, group=decade)) m + geom_density(fill=NA) m + geom_density(fill=NA) + aes(y = ..count..) # Use qplot instead qplot(length, data=movies, geom="density", weight=rating) qplot(length, data=movies, geom="density", weight=rating/sum(rating))