# The examples I am working with are from an introductory for R called 
# “Verzani-SimpleR”   
# found at the R Cran website 
# https://cran.r-project.org/doc/contrib/Verzani-SimpleR.pdf

# Keeping track of typos of various drafts.

typos.draft1=c(2,3,0,3,1,0,0,1)
typos.draft2=c(0,3,0,3,1,0,0,1)

# We can apply commands (functions) to these vectors:

mean(typos.draft1)
mean(typos.draft2)

median(typos.draft1)
median(typos.draft2)

var(typos.draft1)
var(typos.draft2)

sd(typos.draft1)
sd(typos.draft2)

typos.draft2=typos.draft1     	# make a copy with a new name
typos.draft2[1]=0		# assigns the first page with 0 typos
typos.draft2
typos.draft2[2]			# prints the 2nd pages’ value
typos.draft2[4]			# prints the 4th pages’ value
typos.draft2[-4]		# prints all but the 4th page
typos.draft2[c(1,3,5)]		# prints only the 1st, 3rd and 5th pages
max(typos.draft2)		# most number of typos
min(typos.draft2)		# least number of typos
typos.draft2 == 3		# what pages have 3 typos? 

# The usage of the double equals sign (==) tests all values 
# to see if they are equal to 3. 
# The 2nd and 4th answer yes (TRUE) and the others no (FALSE). 
# How can we get the page numbers rather than a TRUE or FALSE?

which(typos.draft2==3)  # Now the answer tells us which page(s) have 3 typos.
sum(typos.draft2)		# total number of typos
sum(typos.draft2>0)		# how many pages with typos
typos.draft2-typos.draft2	# difference between the two sets of drafts

# reading in data with scan(), read.table() and read.csv()

# scan() one column, input by hand:
x=scan() # hit enter to start scan()
1	# hit enter after every entry 
2
3
4	# hit enter twice after the last value to stop scan()

# scan() pasting in one column
x=scan()
1 2 3 
4	# hit enter twice after pasting last value to stop scan()

# scan() with matrix() to paste in more than 1 column of data
data <- matrix(scan(),ncol=3,byrow=TRUE)
1 1 7.75   
1 1 8.25
1 2 8.25   
1 2 8.75
1 3 7.75   
1 3 8.25
2 1 6.75   
2 1 7.25
2 2 7.25   
2 2 7.75
2 3 6.75  
2 3 7.25
3 1 6.25   
3 1 6.75
3 2 8.25   
3 2 7.75
3 3 8.75   
3 3 9.25

data

HotDogs1 <- data.frame(data)
colnames(HotDogs1) <- c("meat","salt","y")
y <- HotDogs1$y

# to make sure that meat is a factor, not numeric
meat <- as.factor(HotDogs1$meat) 

# to make sure that salt is a factor, not numeric
salt <- as.factor(HotDogs1$salt) 

# names for the 3 levels of meat  
levels(meat) <- c("beef","pork","chic")     

rm(data) 
# this removes the original dataset called data and leaves us with the new one 
# with row and column labels

HotDogs1



# read.table()
x=read.table('S:/Courses/stat-renaes/Data/hotdogs.csv',header=T,sep=‘,’)
x

# read.csv()
y=read.csv('S:/Courses/stat-renaes/Data/hotdogs.csv',header=T)
y

# accessing variables in a dataset:
# all variable names have a 2-level name.
# an example with the Hot Dogs dataset
# the variable names are meat, salt and y (y is the response -- taste rating)
# the variable names (with the 2-level names) have to include the dataset name 
# the default way to "call" a variable of a dataset is: datasetname$variablename
# the $ is necessary to extract "objects" from a dataset
# so the names from the Hot Dog dataset:

HotDogs1$meat
HotDogs1$salt
HotDogs1$y

# but who wants to always type that much? attach() will help!
# General form: attach(datasetname)
# attach will "attach" the variable names to the variables and negates the need 
# for a 2-level name

attach(HotDogs1)
meat
salt
y

# when you are finished with your R session, use detach() 
# General form: detach(datasetname)

detach(HotDogs1)
meat
salt
y

HotDogs1$meat
HotDogs1$salt
HotDogs1$y