getwd()

?read.table
sample1 <- read.table("~/Downloads/Book1.txt",head=TRUE,sep=" ")
sample2 <- read.table("Book1.txt",head=TRUE,sep=" ")
identical(sample1,sample2)
sample2

sample1 <- read.table("Book1.txt",sep=" ")
sample1
sample1 <- read.table("Book1.txt")
sample1
sample1 <- read.table("Book1.csv")
sample1
sample1 <- read.table("Book1.csv",sep=" ")
sample1
sample1 <- read.table("Book1.csv",sep=",")
sample1

data <- read.csv("Book1.csv")
data
data <- read.csv("Book1.csv", header = FALSE)
data
data <- read.xls("Book1.xlsx", sheet = 1, header = TRUE)

rm(list=ls(all=TRUE))     # removes ALL your Data!!!!!!!!!!!
                          # NOTE:  ALL values are ERASED!!!!  

?openintro
??openintro  # Click on openintro::openintro-package 
             # Scroll to bottom
             # Click on "Index" for list of data sets
             # and supplemental functions
install.packages("openintro-package")

data(cars)
assign("cars", openintro::cars, envir=globalenv())
assign("mpg.midsize", cars[cars$type=="midsize","mpgCity"], envir=globalenv())
cars
plot(cars$weight, cars$mpgCity)
boxplot(price ~ type, data=cars, xlab="Type", ylab="Price")

path2csv <- file.path('~/Downloads/2014-07-08.csv')
mydf <- read.csv(path2csv, stringsAsFactors = FALSE)
getwd()     # To determine your working directory
path2csv <- file.path('../../Downloads/2014-07-08.csv')
mydf <- read.csv(path2csv, stringsAsFactors = FALSE)
mydf2 <- read.csv('../../Downloads/2014-07-08.csv', stringsAsFactors = FALSE)
mydf3 <- read.csv('/Users/YOURusername/Downloads/2014-07-08.csv', 
stringsAsFactors = FALSE)   # Replace YOURusername with your user name
identical(mydf, mydf2)
rm("mydf2")     # remove mydf2
rm("mydf3")     # remove mydf3


dim(mydf)
head(mydf)


##################################################################
##    Manipulating data with dplyr - Getting and Cleaning Data ###
##################################################################

install.packages("dplyr")
library(dplyr)
packageVersion("dplyr")

cran <- tbl_df(mydf)
?tbl_df
rm("mydf")     # remove mydf
cran

?select
select(cran, ip_id, package, country)
select(cran, r_arch:country)
select(cran, country:r_arch)
cran
select(cran, -time)
-5:20
-(5:20)
select(cran, -(X:size))
?filter
filter(cran, package == "swirl")
filter(cran, r_version == "3.1.1", country == "US")

?Comparison

filter(cran, r_version <= "3.0.2", country == "IN")
filter(cran, country == "US" | country == "IN")
filter(cran, size > 100500, r_os == "linux-gnu")

is.na(c(3, 5, NA, 10))

"!is.na(c(3, 5, NA, 10))"

filter(cran, !is.na(r_version))

cran2 <- select(cran, size:ip_id)

?arrange
arrange(cran2, ip_id)
arrange(cran2, desc(ip_id))
arrange(cran2, package, ip_id)
arrange(cran2, country, desc(r_version), ip_id)

cran3 <- select(cran, ip_id, package, size)
cran3
?mutate
mutate(cran3, size_mb = size / 2^20)
mutate(cran3, size_mb = size / 2^20, size_gb = size_mb / 2^10)
mutate(cran3, correct_size = size + 1000)

summarize(cran, avg_bytes = mean(size))