# managing data
options(digits=7)
rm(list=ls())
hs1 <- read.table("http://www.ats.ucla.edu/stat/R/notes/hs1.csv", header=T, sep=",")

# attach hs1 to the search path
attach(hs1)
# keep observations if condition is met
hs1.read.well <- hs1[read >= 60, ]
dim(hs1.read.well)
mean(hs1.read.well$read)
mean(hs1$read)

# another example 
hs1.female.readwell<-hs1[female==1 & read>=60, ]
dim(hs1.female.readwell)

# one more example
hs1.female.read.or.write<-hs1[female==1 & (read>=60 | write>=60) , ]
dim(hs1.female.read.or.write)


# keeping variables, read and write
hs2<-hs1[, c("read", "write")]
names(hs2)
# another way of doing the same thing
hs2<-hs1[, c(7, 8)]
names(hs2)

# dropping variables, read and write

hs2.drop<-hs1[, -c(7, 8)]
names(hs2.drop)

# append 
# creating a subset containg only females
hsfemale<-hs1[female==1, ]

# creating a subset containg only males
hsmale<-hs1[female==0, ]

dim(hsfemale)
dim(hsmale)

hs.all<-rbind(hsfemale, hsmale)
dim(hs.all)


# 1-1 merge
hs.demo<-hs1[, c("id", "ses", "female", "race")]
hs.scores<-hs1[, c("id", "read", "write", "math", "science")]
dim(hs.demo)
dim(hs.scores)

hs.merge <- merge(hs.demo, hs.scores, by="id", all=T)
head(hs.merge)
dim(hs.merge)

# if the linking variable has different name in the two data sets
hs.merge1 <- merge(hs.demo, hs.scores, by.x="id", by.y="id", all=T)

#sort using the order function
sort(hs1$write)

hs.ordered<-hs1[order(female),]
head(hs.ordered, n=20)

hs.ordered<-hs1[order(female, ses),]
head(hs.ordered, n=20)