R和统计 3：ggplot2

 1. qplot

library(ggplot2)

dsmall <- diamonds[sample(nrow(diamonds), 100), ]
# relationship
qplot(carat, price, data = diamonds)
qplot(carat,x*y*z,data = diamonds)
# colour, shape
qplot(carat, price, data = dsmall, colour = color)
qplot(carat, price, data = dsmall, shape = cut)
# opaque
qplot(carat, price, data = diamonds, alpha = I(1/10))
qplot(carat, price, data = diamonds, alpha = I(1/100))
qplot(carat, price, data = diamonds, alpha = I(1/200))

# swig 1 not  
qplot(carat, price, data = dsmall, geom = c("point", "smooth"),    span = 1)

library(mgcv)
qplot(carat, price, data = dsmall, geom = c("point", "smooth"),
        method = "gam", formula= y ~ s(x, bs = "cs"))

library(splines)
qplot(carat, price, data = dsmall, geom = c("point", "smooth"),
        method = "lm")
qplot(carat, price, data = dsmall, geom = c("point", "smooth"),
        method = "lm", formula= y ~ ns(x,5))

# jitter
qplot(color, price / carat, data = diamonds, geom = "jitter",
        alpha = I(1 / 200))

# histogram
qplot(carat, data = diamonds, geom = "histogram")
qplot(carat, data = diamonds, geom = "density")
qplot(carat, data = diamonds, geom = "histogram", binwidth = 1,
        xlim = c(0,3))
qplot(carat, data = diamonds, geom = "histogram", binwidth = 0.1,
        xlim = c(0,3))
qplot(carat, data = diamonds, geom = "histogram", binwidth = 0.01,
        xlim = c(0,3))

qplot(carat, data = diamonds, geom = "density", colour = color)
qplot(carat, data = diamonds, geom = "histogram", fill = color) #important

qplot(color, data = diamonds, geom = "bar")
qplot(color, data = diamonds, geom = "bar", weight = carat) +
        scale_y_continuous("carat")

# time series
qplot(date, unemploy / pop, data = economics, geom = "line")  # important
qplot(date, uempmed, data = economics, geom = "line")

year <- function(x) as.POSIXlt(x)$year + 1900
qplot(unemploy / pop, uempmed, data = economics,
        geom = c("point", "path"))
qplot(unemploy / pop, uempmed, data = economics,
                geom = "path", colour = year(date)) + scale_area()
# facet
qplot(carat, data = diamonds, facets = color ~ .,
        geom = "histogram", binwidth = 0.1, xlim = c(0, 3))
qplot(carat, ..density.., data = diamonds, facets = color ~ .,
        geom = "histogram", binwidth = 0.1, xlim = c(0, 3))

data(mpg)
qplot(displ, hwy, data = mpg, colour = factor(cyl))

qplot(displ, hwy, data=mpg, facets=.~year) + geom_smooth()

 

 

2. 了解qplot的强大以后，可以开始了解ggplot了

A plot object is a list with components data, mapping(the default aesthetic mappings),layers, scales, coordinates and facet.

 

# ggplot
ggplot(msleep, aes(sleep_rem / sleep_total, awake)) +
        geom_point() + geom_smooth()
bestfit <- geom_smooth(method = "lm", se = F,
        colour = alpha("steelblue", 0.5), size = 2)
qplot(sleep_rem, sleep_total, data = msleep) + bestfit
qplot(awake, brainwt, data = msleep, log = "y") + bestfit
qplot(bodywt, brainwt, data = msleep, log = "xy") + bestfit

p <- ggplot(mtcars, aes(mpg, wt, colour = cyl)) + geom_point()
p
mtcars <- transform(mtcars, mpg = mpg ^ 2)
p %+% mtcars

aes(x = weight,y=height, colour = age)
layer(geom, geom_params, stat, stat_params, data, mapping,
        position)

# forward
p <- ggplot(Oxboys, aes(age, height, group = Subject)) +
        geom_line()

p + geom_smooth(aes(group = Subject), method="lm", se = F)
p + geom_smooth(aes(group = 1), method="lm", size = 2, se = F)

d <- ggplot(diamonds, aes(carat)) + xlim(0, 3)
d + stat_bin(aes(ymax = ..count..), binwidth = 0.1, geom = "area")
d + stat_bin(
        aes(size = ..density..), binwidth = 0.1,
        geom = "point", position="identity")
d + stat_bin(
        aes(y = 1, fill = ..count..), binwidth = 0.1,
        geom = "tile", position="identity"
)