## 1. Starting Up
## 1.1	Getting started under Windows
## 1.2	Use of an Editor Script Window

## 1.3 	A Short R Session
austpop <- read.table("d:/austpop.txt", header=TRUE)
austpop
names(austpop)
## 1.3.1	Entry of Data at the Command Line
elasticband <- data.frame(stretch=c(46,54,48,50,44,42,52),
                          distance=c(148,182,173,166,109,141,166))
## 1.3.2 Entry and/or editing of data in an editor window
elasticband <- edit(elasticband)
## 1.3.3 Options for read.table()
## 1.3.4 Options for plot() and allied functions

## 1.4 	Further Notational Details
## 1.5 	On-line Help
help()
help(plot)
help.search("matrix")
apropos("matrix")

## 1.6 	The Loading or Attaching of Datasets
attach("usingR.RData")
## 1.7 	Exercises

2. An Overview of R
## 2.1 The Uses of R
## 2.1.1 R may be used as a calculator. 
2+2
sqrt(10)
2*3*4*5
1000*(1+0.075)^5 - 1000 # Interest on $1000, compounded annually 
                        # at 7.5% p.a. for five years
pi  # R knows about pi
2*pi*6378 #Circumference of Earth at Equator, in km; radius is 6378 km
sin(c(30,60,90)*pi/180) # Convert angles to radians, then take sin()
## 2.1.2 R will provide numerical or graphical summaries of data
load("hills.Rdata")   # Assumes hills.Rdata is in the working directory
summary(hills)
2.1.3 R has extensive graphical abilities
pairs(hills)
## 2.1.4 R will handle a variety of specific analyses
options(digits=3)
cor(hills)
cor(log(hills))
plot(distance ~ stretch,data=elasticband, pch=16)
elastic.lm <- lm(distance~stretch,data=elasticband)
lm(distance ~stretch,data=elasticband)
summary(lm(distance~stretch,data=elasticband))
## 2.1.5 R is an Interactive Programming Language
celsius <- 25:30
fahrenheit <- 9/5*celsius+32
conversion <- data.frame(Celsius=celsius, Fahrenheit=fahrenheit)
print(conversion)

## 2.2 R Objects
save.image()		   # Save contents of workspace, into the file .RData
save.image(file="archive.RData")      # Save into the file archive.RData
save(celsius, fahrenheit, file="tempscales.RData")
attach("tempscales.RData")
ls(pos=2)	# Check the contents of the file that has been attached

## *2.3 Looping
for (i in 1:10) print(i)
# Celsius to Fahrenheit
for (celsius in 25:30)
+     print(c(celsius, 9/5*celsius + 32))
## 2.3.1 More on looping
answer <- 0
for (j in c(31,51,91)){answer <- j+answer}
answer
sum(c(31,51,91))

## 2.4 Vectors
c(2,3,5,2,7,1)
3:10   # The numbers 3, 4, .., 10
c(TRUE,FALSE,FALSE,FALSE,TRUE,TRUE,FALSE)
c("Canberra","Sydney","Newcastle","Darwin")
## 2.4.1 Joining (concatenating) vectors
x <- c(2,3,5,2,7,1)
x
y <- c(10,15,12)
y
z <- c(x, y)
z
## 2.4.2 Subsets of Vectors
x <- c(3,11,8,15,12)  # Assign to x the values 3, 11, 8, 15, 12
x[c(2,4)]   # Extract elements (rows) 2 and 4
x <- c(3,11,8,15,12)
x[-c(2,3)]
x>10  # This generates a vector of logical (T or F)
x[x>10]
## 2.4.3 The Use of NA in Vector Subscripts
y <- c(1, NA, 3, 0, NA)
y[is.na(y)] <- 0
## 2.4.4 Factors
gender <- c(rep("female",691), rep("male",692))
gender <- factor(gender):
levels(gender)  # Assumes gender is a factor, created as above
gender <- relevel(gender, ref="male")
gender <- factor(gender, levels=c("male", "female"))
gender <- factor(c(rep("female",691), rep("male",692)))
table(gender)
gender <- factor(gender, levels=c("male", "female"))
table(gender)
gender <- factor(gender, levels=c("Male", "female"))  
     		# Erroneous - "male" rows now hold missing values
table(gender)
rm(gender)  	# Remove gender

## 2.5 Data Frames
Cars93.summary
type <- Cars93.summary$abbrev
type <- Cars93.summary[,4]
type <- Cars93.summary[,"abbrev"]
type <- Cars93.summary[[4]] 	# Take the object that is stored
# in the fourth list element.
## 2.5.1 Data frames as lists
## 2.5.2 Inclusion of character string vectors in data frames
## 2.5.3 Built-in data sets
summary(trees)

## 2.6 Common Useful Functions
print()   	# Prints a single R object
cat()     	# Prints multiple objects, one after the other
length()  	# Number of elements in a vector or of a list
mean()
median()
range()
unique()  	# Gives the vector of distinct values
diff()    	# Replace a vector by the vector of first differences
	         # N. B. diff(x) has one less element than x
sort()    	# Sort elements into order, but omitting NAs
order()	# x[order(x)] orders elements of x, with NAs last
cumsum()
cumprod()
rev()     	# reverse the order of vector elements

x <- c(1, 20,  2, NA, 22)
order(x)
x[order(x)]
sort(x)
## 2.6.1 Applying a function to all columns of a data frame
sapply(rainforest, is.factor)
sapply(rainforest[,-7], range)   # The final column (7) is a factor
range(rainforest$branch, na.rm=TRUE)  # Omit NAs, then determine the range
sapply(rainforest[,-7], range, na.rm=TRUE)

## 2.7 Making Tables
library(lattice) 	# The data frame barley accompanies lattice
table(barley$year, barley$site)
x <- c(1,5,NA,8)
x <- factor(x)
x
factor(x,exclude=NULL)
## 2.7.1 Numbers of NAs in subgroups of the data
table(rainforest$species, !is.na(rainforest$branch))

## 2.8 The Search List
search()
library(MASS)
search()
names(primates)
Bodywt
attach(primates)     # R will now know where to find Bodywt
Bodywt
av <- with(primates, mean(Bodywt))

## 2.9 Functions in R
## 2.9.1 An Approximate Miles to Kilometers Conversion
miles.to.km <- function(miles)miles*8/5
miles.to.km(175)  # Approximate distance to Sydney, in miles
miles.to.km(c(100,200,300))
## 2.9.2 A Plotting function
attach(florida)
plot(BUSH, BUCHANAN, xlab="Bush", ylab="Buchanan")
detach(florida)   # In S-PLUS, specify detach("florida")
plot.florida <- function(xvar="BUSH", yvar="BUCHANAN"){
	x <- florida[,xvar]
	y <- florida[,yvar]
	plot(x, y, xlab=xvar,ylab=yvar)
	mtext(side=3, line=1.75, 
	"Votes in Florida, by county, in \nthe 2000 US Presidential election")
}
plot.florida(yvar="NADER")  # yvar="NADER" over-rides the default
plot.florida(xvar="GORE", yvar="NADER")
## 2.10 More Detailed Information

## 2.11 Exercises
## ex1. 
## a)  
answer <- 0
for (j in 3:5){ answer <- j+answer }
## b)  
answer<- 10
for (j in 3:5){ answer <- j+answer }
## c)  
answer <- 10
for (j in 3:5){ answer <- j*answer }