In order to provide an option to compare graphs produced by basic internal plot function and ggplot2, I recreated the figures in the book, 25 Recipes for Getting Started with R, with ggplot2.

The code used to create the images is in separate paragraphs, allowing easy comparison.

1.16 Creating a Scatter Plot

plot(cars)

ggplot(cars,aes(speed,dist))+geom_point()

1.17 Creating a Bar Chart

heights <- tapply(airquality$Temp, airquality$Month, mean)
par(mfrow=c(1,2))
barplot(heights)
barplot(heights,
        main="Mean Temp. by Month",
        names.arg=c("May", "Jun", "Jul", "Aug", "Sep"),
        ylab="Temp (deg. F)")

require(gridExtra)
heights=ddply(airquality,.(Month), mean)
heights$Month=as.character(heights$Month)
p1 <- ggplot(heights, aes(x=Month,weight=Temp))+
    geom_bar()
p2 <- ggplot(heights, aes(x=factor(heights$Month,
                          labels=c("May", "Jun", "Jul", "Aug", "Sep")),
                          weight=Temp))+
    geom_bar()+
    opts(title="Mean Temp. By Month") +
    xlab("") +
    ylab("Temp (deg. F)")

grid.arrange(p1,p2, ncol=2)

1.18 Creating a Box Plot

y <- c(-5, rnorm(100), 5)
boxplot(y)

ggplot()+geom_boxplot(aes(x=factor(1),y=y))+xlab("")+ylab("")

1.19 Creating a Histogram

data(Cars93, package="MASS")
par(mfrow=c(1,2))
hist(Cars93$MPG.city)
hist(Cars93$MPG.city, 20)

p <- ggplot(Cars93, aes(MPG.city))
p1 <- p + geom_histogram(binwidth=diff(range(Cars93$MPG.city))/5)
p2 <- p + geom_histogram(binwidth=diff(range(Cars93$MPG.city))/20)
grid.arrange(p1,p2, ncol=2)

1.23 Diagnosing a Linear Regression

data(iris)
m = lm( Sepal.Length ~ Sepal.Width, data=iris)
par(mfrow=c(2,2))
plot(m)

r <- residuals(m)
yh <- predict(m)
scatterplot <- function(x,y, title="", xlab="", ylab="") {
	d <- data.frame(x=x,y=y)
	p <- ggplot(d, aes(x=x,y=y)) + geom_point() + opts(title=title) + xlab(xlab) + ylab(ylab)
	return(p)
}

p1 <- scatterplot(yh,r,
                  title="Residuals vs Fitted",
                  xlab="Fitted values",
                  ylab="Residuals")
p1 <- p1 +geom_hline(yintercept=0)+geom_smooth()

s <- sqrt(deviance(m)/df.residual(m))
rs <- r/s

qqplot <- function(y,
                   distribution=qnorm,
                   title="Normal Q-Q",
                   xlab="Theretical Quantiles",
                   ylab="Sample Quantiles") {
    require(ggplot2)
    x <- distribution(ppoints(y))
    d <- data.frame(x=x, y=sort(y))
    p <- ggplot(d, aes(x=x, y=y)) +
        geom_point() +
            geom_line(aes(x=x, y=x)) +
                opts(title=title) +
                    xlab(xlab) +
                        ylab(ylab)
    return(p)
}

p2 <- qqplot(rs, ylab="Standardized residuals")

sqrt.rs <- sqrt(abs(rs))
p3 <- scatterplot(yh,sqrt.rs,
                  title="Scale-Location",
                  xlab="Fitted values",
                  ylab=expression(sqrt("Standardized residuals")))
p3 <- p3 + geom_smooth()

hii <- lm.influence(m, do.coef = FALSE)$hat
p4 <- scatterplot(hii,rs)
p4 <- p4+
    geom_hline(yintercept=0)+
    geom_smooth() +
    geom_text(aes(x=min(hii)+diff(range(hii))*0.3,
                  y=min(rs)+diff(range(rs))*0.04,
                  label="--   Cook's distance", size=3))+
    opts(legend.position="none")

grid.arrange(p1,p2,p3,p4, ncol=2)

Related Posts

• August 14, 2011 -- the batman equation (3)
• August 2, 2011 -- Q-Q Plot (0)
• June 15, 2011 -- mzDelta plot (0)
• March 29, 2011 -- Machine Learning Ex3 – Multivariate Linear Regression (0)
• March 27, 2011 -- clusterProfiler in Bioconductor 2.8 (1)
• March 22, 2011 -- Machine Learning Ex2 – Linear Regression (2)
• December 1, 2010 -- bubble chart by using ggplot2 (0)
• December 1, 2010 -- The avalanche of publications mentioning GO (0)
• October 12, 2010 -- ClusterProfiles (0)
• June 24, 2011 -- 关于统计-生物学家需要知道的五件事 (4)