#
#
############### Graphical Parameters ###############
#

help(par)

colors()

############### Some data ###############

# Need package 'car' for the recode function. 

library(car)

n <- 100
id <- seq(1:n)
sex <- seq(1:2)
sex <- sample(sex, 100, replace = TRUE)
sex <- recode(sex, "1 = 'Female'; 2 = 'Male'")
level <- seq(1:4)
level <- sample(level, 100, replace = TRUE)
level <- recode(level, "1 = 'Freshman'; 2 = 'Sophomore'; 3 = 'Junior'; 4 = 'Senior'")
age <- c(18:25)
age <- sample(age, 100, replace = TRUE)
x1 <- rnorm(n,10,2)
x2 <- rnorm(n,10,1)
x3 <- rnorm(n,12,3)
e <- rnorm(n,0,2)
y <- -1.5 + 1.2*x1 + .8*x2 + 0*x3 + e
df.1 <- data.frame(id, sex, level, age, x1, x2, x3, y)
rm(n, id, sex, level, age, x1, x2, x3, e, y)
summary(df.1)
ls()

cor(df.1[4:8])

mod <- lm(y ~ x1 + x2 + x3, data = df.1)
summary(mod)
attach(df.1)

############### Graphing. ###############

# Basic regression diagnostics. 

oldpar <- par(oma=c(0,0,3,0), mfrow=c(2,2))
plot(mod)
par(oldpar)

# Basic (boring) scatterplot.

plot(x1,y)

# Basic regression diagnostics (again).

mod.x1 <- lm(y ~ x1, data = df.1)
summary(mod.x1)

oldpar <- par(oma=c(0,0,3,0), mfrow=c(2,2))
plot(mod.x1)
par(oldpar)

# A way-too-busy scatterplot; which shows some of the optional arguements and parameters. 

par(bg = "lightgray")
plot(x1, y, pch = 3, cex = 2, col = "blue", xlim = c(6,15), ylim = c(12,25))
abline(reg = mod.x1, col = "green", lwd = 2, lty = "solid")
par(new=T)
plot(lowess(x1,y,f=.2)$x, lowess(x1,y,f=.2)$y, lty = 2, col = "red", xlim = c(6,15), ylim = c(12,25))
box(grid(col="black",lty=2))
par(bg = "white")

# Plotting the lowess function (only) from above. 

plot(x1,y)
lines(lowess(x1,y, f=.2))

# Basic scatterplot matrix.

pairs(df.1[4:8])

## Complex Scatter matrix w/correlations in the upper panel where the font 
## size of each correlation corresponds to the magnitude of the correlation. 
# **Note: all you would need to change to apply this to a new data frame is 
# to change the name of the data frame: listed as 'df.1' (only columns 3 to 7)
# in the 'pairs' function line (last line of code). The 'panel.cor' object is 
# assigned a slightly complex function for setting up our plot design; the 'pairs' 
# function actually completes the plot.

panel.cor <- function(x, y, digits=3, prefix="", cex.cor, ...)
     {
         usr <- par("usr"); on.exit(par(usr))
         par(usr = c(0, 1, 0, 1))
         r <- abs(cor(x,y))
         txt <- format(c(r, 0.123456789), digits=digits)[1]
         txt <- paste(prefix, txt, sep="")
         if(missing(cex.cor)) cex.cor <- 0.8/strwidth(txt)
         text(0.5, 0.5, txt, cex = cex.cor)
     }
pairs(df.1[4:8], lower.panel=panel.smooth, upper.panel=panel.cor)

#####################

n <- 200
z <- 5.0
my.colors <- c("darkgreen", "darkblue")
v <- 1
x <- seq(-5, 5, length.out = n)
y <- plogis(x, location = 0, scale = z)
plot(x,y, col = my.colors[v], xlim = c(-5,5), ylim = c(0,1), xlab = "X", ylab = "Y", pch = ".")

for (i in 1:24){
z <- z - 0.2
v <- sample(my.colors, 1)
x <- seq(-5, 5, length.out = n)
y <- plogis(x, location = 0, scale = z)
par(new=T)
plot(x,y, col = v, xlim = c(-5,5), ylim = c(0,1), xlab = "X", ylab = "Y", pch = ".")
Sys.sleep(.5)
}
rm(i, x, my.colors, v, y, z)

######################

x <- seq(-5, 5, length.out = n)
y0 <- plogis(x, location = 0, scale = 1.5)
y1 <- plogis(x, location = 0, scale = 1.25)
y2 <- plogis(x, location = 0, scale = 1)
y3 <- plogis(x, location = 0, scale = .75)
y4 <- plogis(x, location = 0, scale = .5)
y5 <- plogis(x, location = 0, scale = .25)

plot(x,y0, col = "yellow", xlim = c(-5,5), ylim = c(0,1))
par(new=T)
plot(x,y1, col = "orange", xlim = c(-5,5), ylim = c(0,1))
par(new=T)
plot(x,y2, col = "red", xlim = c(-5,5), ylim = c(0,1))
par(new=T)
plot(x,y3, col = "darkgreen", xlim = c(-5,5), ylim = c(0,1))
par(new=T)
plot(x,y4, col = "blue", xlim = c(-5,5), ylim = c(0,1))
par(new=T)
plot(x,y5, col = "purple", xlim = c(-5,5), ylim = c(0,1))
lines(x = c(-5,5), y = c(0,1.0), lwd = 2) 
rm(n, x, y0, y1, y2, y3, y4, y5)

######################

# Basic boxplot (changing the background to lightgray).

par(bg = "lightgray")
boxplot(y ~ sex, ylab = "y", col = "lightgreen")

boxplot(y ~ level, ylab = "y", col = "green")

# Basic histogram. 

hist(y, col = "lightblue1", main = "Histogram of y")

# Basic kernal density function (kdf) plotted.

plot(density(y), col = "blue")

# Combining the histogram and kdf. 

hist(y, col = "lightblue1", main = "Histogram of y", xlim = range(y), prob = T)
lines(density(y), col = "blue")

# Combining histogram, and normal curve (black); with a proxi for the density function. 

h <- hist(x1, breaks = 10, col = "lightblue1")
xfit <- seq(min(x1), max(x1), length = 40)
yfit <- dnorm(xfit, mean = mean(x1), sd = sd(x1))
yfit <- yfit * diff(h$mids[1:2]) * length(x1)
lines(xfit, yfit, col = "black", lwd = 2)
bob <- density(x1)
lines(bob$x, bob$y * 100, col = "blue", lwd = 2)

# Another way to achieve a similar overlay; here, a standard normal curve is 
# overlaid on the accurate densities:

hist(x3, prob = T, breaks = 8, col = "lightblue1")
lines(density(x3), lwd = 2, col = "blue")
par(new = T)
temp <- seq(-5, 5, length = 100)
dtemp <- dnorm(temp)
plot(temp, dtemp, type = "l", col = "black", lwd = 1, xlab = "", ylab = "", axes = FALSE)

# Restore the background to white:

par(bg = "white")

### The 'car' package contains the 'scatterplot' function.

# The scatterplot function (& scatterplotMatrix function) has some amazing flexibility. 

help(scatterplot)

# Smoother lines and lowess lines are good for checking for non-linearity.

scatterplot(x1, y)

# Ellipses are good for checking correlation (i.e. thin ellipse = high correlation). 

scatterplot(x1, y, ellipse=TRUE, span =.5)

# Multiple variable matrices can quickly become difficult to interpret.

scatterplotMatrix(df.1[4:8], smooth=TRUE, ellipse=TRUE, span =.5)

scatterplotMatrix(df.1[c(5,6,8)], ellipse=TRUE, span =.5)

cor(df.1[c(5,6,8)])

## The 'lattice' package contain a variety of choices for 
## producing plots & graphs specialized for multivariate data. 

# See the book: 
# Deepayan, S. (2008). Lattice: Multivariate Data Visualization with R. New York: Springer 
#      Science+Business Media, LLC.

library(lattice)

histogram(~ x1 | sex)

histogram(~ x1 | level, col = "lightblue1")

# Multiple group's Density plots overlayed. 

densityplot(~ x1, data = df.1, groups = level, plot.points = FALSE, ref = TRUE, 
            auto.key = list(columns = 2))

# Multiple group's bivariate scatterplots. 

xyplot(y ~ x1 | sex + level, data = df.1)

# Q-Q plots.

qqmath(~ y | factor(level), data = df.1, f.value = ppoints(100))

qq(sex ~ y | factor(level), data = df.1, f.value = ppoints(100), aspect = 1)

# Boxplots (i.e. Box-and-Whisker plots).

bwplot(y ~ sex, data = df.1, xlab = "y")

bwplot(y ~ sex | level, data = df.1, xlab = "Gender", layout = c(4,1))

# Violin plots (compared with the normal boxplot). 

bwplot(y ~ level, data = df.1, ylim = c(10,30))

bwplot(y ~ level, data = df.1, panel = panel.violin, ylim = c(10,30), col = "lightblue2")

# There is a great deal more one can do with the lattice package, see the book mentioned above. 
# As I come across interesting / useful ways for plotting data I'll add them here. 


# Originally posted: Jan. 2011
# Last updated: Feb 25, 2011