smokes = c("Y","N","N","Y","N","Y","Y","Y","N","Y")
amount = c(1,2,2,3,3,1,2,1,3,2)
table(smokes,amount)
barplot(table(smokes,amount))

data1<-read.csv(url("http://stat.columbia.edu/~rachel/datasets/nyt1.csv"))
head(data1)
data1$agecat<-cut(data1$Age,c(-Inf,0,18,24,34,44,54,64,Inf))
summary(data1)

install.packages("doBy")
library("doBy")
siterange<-function(x){c(length(x),min(x),mean(x),max(x))}
summaryBy(Age~agecat, data=data1,FUN=siterange)
install.packages("ggplot2")
library(ggplot2)
ggplot(data1,aes(x=agecat,y=Impressions,fill=agecat))+geom_boxplot()
ggplot(subset(data1,Clicks>0),aes(x=Clicks/Impressions,colour=agecat))+geom_density()
ggplot(data1,aes(x=Impressions,fill=agecat))+geom_histogram(binwidth=1)
data1$scode[data1$Impressions==0]<-"NoImps"
data1$scode[data1$Impressions>0]<-"Imps"
data1$scode[data1$Clicks>0]<-"Clicks"
data1$scode<-factor(data1$scode)
head(data1)
data3<-subset(data1,scode=="NoImps")
head(data3)
clen<-function(x){c(length(x))}
etable<-summaryBy(Impressions~scode+Gender+agecat,data=data1,FUN=clen)