#
#
# Sources include:
#    http://www.r-bloggers.com/ggplot2-version-of-figures-in-%E2%80%9C25-recipes-for-getting-started-with-r%E2%80%9D/?utm_source=feedburner&utm_medium=feed&utm_campaign=Feed%3A+RBloggers+%28R+bloggers%29
# Generally used without permission but withthe hope of futrher sharing the examples.

plot(cars)

library(ggplot2)
ggplot(cars,aes(speed,dist))+geom_point()

# 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)")


library(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)


# Box Plot

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


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


# 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)


# 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)

par(mfrow=c(1,1))

########################################################################
# Star and Network Plot

require(network) # network
require(sna) # plot.network
require(Hmisc) # largest.empty
  
# Create some data.

con <- textConnection("name,age,jobyrs,inc,saved,int,chld,addryrs
Adam,21,1,46,110,3.9,2.62,16.46
Ben,32,6,82,110,3.9,2.875,17.02
Chris,22,2,38,93,3.85,2.32,18.61
David,46,16,158,110,3.08,3.215,19.44
Elvin,58,4,110,175,3.15,3.44,17.02
Fred,18,1,25,105,2.76,3.46,20.22
Greg,23,1,60,245,3.21,3.57,15.84
Henry,44,12,46,62,3.69,3.19,20
Ivan,32,2,40,95,3.92,3.15,22.9
James,29,5,67,123,3.92,3.44,18.3
Kevin,27,10,67,123,3.92,3.44,18.9
Luke,46,18,75,180,3.07,4.07,17.4")
nodelist <-read.csv(con)
close( con ) 

con <- textConnection("from,to
Adam,Ben
Adam,Chris
Chris,David
Chris,Elvin
David,Fred
Fred,Greg
Greg,Henry
Henry,James
Henry,Ivan
James,Kevin
Ivan,Kevin
Kevin,Luke")

edgelist <- read.csv(con)
close( con )

nodes <- levels(as.factor(nodelist[[1]]))

# Create a matrix to represent the network.

m <- matrix(data = 0, nrow=length(nodes), ncol=length(nodes))
rownames(m) <- colnames(m) <- nodes

apply(edgelist, 1, function(x) m[x[[1]], x[[2]]] <<- 1)

graph <- network(m, matrix.type="adjacency")

# Now plot the network, without the nodes.

par(xpd=TRUE)
xy <- plot(graph, vertex.cex=5, vertex.col="white", vertex.border=0)

# Get the some other data from the nodes and generate a plot for
# each node and place them onto the network. Include a Key at some
# empty space.

kl <- largest.empty(xy[,1], xy[,2], 2, 2)

stars(nodelist[-1], labels=nodelist[[1]], locations=xy, draw.segments=TRUE,
      key.loc=c(kl$x, kl$y), add=TRUE)

#------------------------------------------------------------------------
# Now plot the network but with a hist at each node.

par(xpd=TRUE)
xy <- plot(graph, vertex.cex=5, vertex.col="white", vertex.border=0)

for (i in 1:nrow(xy)) 
{
  subplot(hist(rnorm(100), col=rainbow(10), 
               main="", axes=FALSE, xlab="", ylab=""), 
          xy[i, 1], xy[i, 2], size=c(0.4,0.4))
  text(xy[i, 1]+0.8, xy[i, 2]+0.8, nodelist[[1]][i])
}