# exlporing data

# entering data
hs0 <- read.table("http://www.ats.ucla.edu/stat/R/notes/hs0.csv", header=T, sep=",")

# listing the first 20 observations, noticing missing values of variable science
hs0[1:20, ]

# listing the names of all the objects in hs0, in this case, listing all the variable names
names(hs0)

# creating a subset containing fewer variables, in this case, read-science
read.sci <- hs0[ , 7:10]

# checking the type of object 
class(read.sci)
 
# listing the first 10 observations
head(read.sci, n=10)

# the descriptive statistics 

# displaying the dimension 
dim(read.sci)
length(read.sci)
length(read.sci$read)

summary(read.sci)


# range function
range(read.sci$write)
range(read.sci$science)
range(read.sci$science, na.rm=T)
# the minimum and the maximum among all the variables
range(read.sci, na.rm=T)

# looking at the mean and standard deviation of each variable in read.sci
mean(read.sci)
mean(read.sci, na.rm=T)
sd(read.sci, na.rm=T)

# looking at the entire data set, the means and standard deviations of all 
# the variables by program type (prgtype)
table(hs0$prgtype)
by(hs0, hs0$prgtype, mean)
by(hs0, hs0$prgtype, sd)

# now it is time to put hs0 on the search path 
# so its variables will be searchable by R
attach(hs0)

# changing the default number of digits = 7 to 2
getOption("digits")
options(digits=2)
by(hs0, prgtype, mean, na.rm=T)
by(hs0, prgtype, sd, na.rm=T)

# displaying the stats in a nicer way
# ragged array: http://www.encyclopedia.com/doc/1O11-raggedarray.html

m   <- tapply(write, prgtype, mean)
v   <- tapply(write, prgtype, var)
med <- tapply(write, prgtype, median)
n   <- tapply(write, prgtype, length)
sd  <- tapply(write, prgtype, sd)
cbind(mean=m, var=v, std.dev=sd, median=med, n=n)

# set the number of digits to 7
options(digits=7)
# now graphics...

# histogram 
hist(write)

# load trellis graphics
library(lattice)  

# trellis graphs 
histogram(~write, hs0, type="count")

# histogram of write by gender
histogram(~write | gender, hs0, type="count")  

# change the number of bins to 15
hist(write, breaks=15)


# boxplot function in the graphics package
boxplot(write)

#trellis graphs
bwplot(ses~ write, hs0)

# boxplot by gender
bwplot(ses~ write| gender, hs0)

# bar chart with default options
barplot(table(ses, gender))

# side by side bar chart with legend  
barplot(table(ses, gender), beside=T, legend.text=c("low", "medium", "high"))

# changing the default color
barplot(table(ses, gender), beside=T, legend.text=c("low", "medium", "high"), ylim=c(0, 50), 
col=c("lightblue", "blue", "dark blue"))

# labeling gender variable
barplot(table(ses, gender), beside=T, legend.text=c("low", "medium", "high"), ylim=c(0, 50), 
col=c("lightblue", "blue", "dark blue"), names.arg=c("male", "female"))

# spacing
barplot(table(ses, gender), beside=T, legend.text=c("low", "medium", "high"), ylim=c(0, 50), 
col=c("lightblue", "blue", "dark blue"), names.arg=c("male", "female"), space=c(.1, 2))

# changing the location of legend and adding a title
barplot(table(ses, gender), beside=T, legend.text=c("low", "medium", "high"), ylim=c(0, 50), space=c(.1, 1),
col=c("lightblue", "blue", "dark blue"), names.arg=c("male", "female"),
main="Distribution of SES by gender", args.legend=list(x =9, y=45, cex=.6))


# correlations and scatter plots

# correlation of a pair of variables
cor(write, math)
cor(write, science)
cor(write, science, use="complete.obs")

# correlation matrix
cor(read.sci, use="complete.obs")
cor(read.sci, use="pairwise.complete.obs")

plot(math, write)

# scatter plot matrix
plot(read.sci)

detach(hs0)