# modifying data
# cleaning up 
rm(list=ls())

# reading in data
hs0 <- read.table("http://www.ats.ucla.edu/stat/R/notes/hs0.csv", header=T, sep=",")
# adding comment
comment(hs0)<-"High school and beyond data"
# checking
comment(hs0)

# variable labels using comment
comment(hs0$write)<-"writing score"
comment(hs0$read) <-"reading score"

# more checking
save(hs0,file="hs0.rda") 
rm(list=ls())
load(file="hs0.rda")
comment(hs0)
comment(hs0$write)

# checking that hs0 is on the search path
search()
attach(hs0)
search()

#checking what variables are factor variables
sapply(hs0, is.factor)

# creating a factor, ie. a categorical variable
schtyp.f <- factor(schtyp, levels=c(1, 2), labels=c("public", "private"))
female <- factor(gender, levels=c(0, 1), labels=c("male", "female")) 

# schtyp.f or female is a factor variable, mean function does not apply
mean(schtyp.f)

# but table function makes perfect sense
table(schtyp.f)
table(female)

# plotting using variable label
plot(write, read, xlab=comment(write))

# recoding

# looking at race variable
table(hs0$race)
hs0$race[hs0$race==5] <-NA
table(hs0$race)

# displaying the missings as well
table(hs0$race, useNA="ifany")

total<-read+write+math+science
# noticing the missing values generated
summary(total)

# initializing a variable
grade<-0
grade[total <=140]<-0
grade[total > 140 & total <= 180] <-1
grade[total > 180 & total <= 210] <-2
grade[total > 210 & total <= 234] <-3
grade[total > 234] <-4

comment(grade)<-"combined grades of read, write, math, science"
grade<-factor(grade, levels=c(0, 1, 2, 3, 4), labels=c("F", "D", "C", "B", "A"))
table(grade)

# difference between the mean function and manually computing the mean
m1<-(read+write+math+science)/4
m2<-rowMeans(cbind(read, write, math, science))
m2<-rowMeans(cbind(read, write, math, science), na.rm=T)


# adding the newly-created variables to the original data set
hs1<-cbind(hs0, cbind(schtyp.f, female, total, grade))
table(hs1$race)
is.data.frame(hs1)