1+1
(4+8)*4
4^2
sqrt(9)

x <- 1+1
x
x = c(1,1)
x
sum(x)

(x <- matrix(0, 2, 2))
x <- matrix(runif(25), 5, 5)
det(x)
x[1,]
x[,1]
x[1,1]

mtcars
?mtcars
 
str(mtcars)
?str
 
hist(mtcars$mpg)
hist(mtcars$mpg, main="My first plot in R!")
?hist
 
hist(mtcars$mpg, main="My first histogram in R!", col="green", density=20)
abline(2,0, col="red", lty=2, lwd=2)
 
summary(mtcars$mpg)
summary(mtcars)
 
table(mtcars$gear)
pie(table(mtcars$gear))
 
t <- table(iris$Species)
pie(t)
str(iris)
iris$Species
class(iris$Species)
levels(iris$Species)
 
cor(iris[, 1:4])
pairs(iris[, 1:4])
?pairs
 
panel.cor <- function(x, y, digits=2, 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 * r)
     }
pairs(iris[, 1:4], upper.panel=panel.cor)
pairs(iris[1:4], main="Edgar Anderson's Iris Data", pch=21,
		bg = c("red", "green3", "blue")[unclass(iris$Species)])

mean(mtcars)
max(mean(mtcars))
which.max(mean(mtcars))
mtcars[, which.max(mean(mtcars))]
 
table(mtcars$gear)
prop.table(table(mtcars$gear))
table(mtcars$gear, mtcars$am)
prop.table(table(mtcars$gear, mtcars$am))
library(gmodels)
install.packages('gmodels')
CrossTable(mtcars$gear, mtcars$am)
 
mosaicplot(table(mtcars$gear, mtcars$am))
mosaicplot(table(mtcars$gear, mtcars$am), shade=TRUE, color=TRUE)
t <- chisq.test(table(mtcars$gear, mtcars$am))
t
str(t)
t$expected
 
V <- function(x) sqrt(x$statistic^2/(sum(x$observed)*x$parameter))
V(t)
 
V <- function(x) as.numeric(sqrt(x$statistic^2/(sum(x$observed)*x$parameter)))
V(t)
 
bickel <- data.frame(gender=c(rep("Male", 8442), rep("Female", 4321)),
	admit=c(rep("Admitted", 3738), rep("Deny", 4704),
	rep("Admitted", 1494), rep("Deny", 2827)))
mosaicplot(table(bickel), shade=T)
 
library(XML)
theurl <- "http://en.wikipedia.org/wiki/Simpson's_paradox"
tables <- readHTMLTable(theurl)
xtable(tables[[6]])

hist(rnorm(100, 0.5, 0.1))
hist(rnorm(100, 0.5, 0.1))
curve(dnorm(x,0.5,0.1), add=TRUE, col="red")
 
curve(pnorm(x,0.5,0.1))
?rnorm
?rbeta

fit <- lm(mpg~disp+hp+wt+drat, data=mtcars)
 
library(car) # John Fox
outlierTest(fit)
qqPlot(fit, main="QQ Plot")
leveragePlots(fit)
 
predict(fit)
cbind(mtcars$mpg, predict(fit))
plot(cbind(mtcars$mpg, predict(fit)))

fit <- princomp(mtcars, cor=TRUE)
fit
summary(fit)
loadings(fit)
plot(fit,type="lines")
fit$scores
biplot(fit)
 
prcomp(mtcars, cor=TRUE)
prcomp(mtcars, cor=TRUE, scale=TRUE)
 
fit <- factanal(mtcars, 3)
fit <- factanal(mtcars, 3, rotation="none")
print(fit, digits=1, cutoff=.3, sort=TRUE)
 
load <- fit$loadings[, 1:2] 
plot(load, type="n")
text(load,labels=names(mtcars),cex=.7)
 
library(FactoMineR)
result <- PCA(mtcars) 
library(GPArotation)

library(ggplot2)
?diamonds
str(diamonds)
 
ggplot(diamonds, aes(clarity)) + geom_bar()
ggplot(diamonds, aes(clarity)) + geom_bar() + ylab("N")
ggplot(diamonds, aes(clarity)) + geom_bar() + ylab("N") + facet_wrap(~ cut)
ggplot(diamonds, aes(clarity)) + geom_bar() + ylab("N") + facet_wrap(~ cut) + theme_bw() + opts(title="53.940 diamonds")
 
ggplot(diamonds, aes(carat, price)) + geom_point() + geom_smooth() + ylab('') + 
		scale_y_continuous(formatter="dollar") + theme_bw() + opts(title="53.940 diamonds")
 
ggplot(diamonds, aes(cut, price)) + geom_boxplot() + xlab('') + ylab('') + 
		scale_y_continuous(formatter="dollar") + theme_bw() + opts(title="53.940 diamonds")

library(foreign)
df <- read.spss('http://ppke.snowl.net/files/2010/08/ESS_HUN_4_media1.sav', to.data.frame=TRUE)
str(df)
attr(df, "variable.labels")
boxplot(f7 ~ f2_1, df)
 
df <- read.csv2('http://ppke.snowl.net/files/2010/08/mds_telepulesek.csv', fileEncoding='cp1252')
row.names(df) <- df[,1]
df[,1] <- NULL
df <- as.dist(df)
mds <- cmdscale(df)
mds
plot(mds)
text(mds[,1], mds[,2], row.names(mds))