#	This Document covers data import
#	You must have file1 - file7 in your working directory
#	They can be found at the link to the right of this document.

#	Before importing to R, you should get and idea of the data
#	format.  For small data sets, any text editor should work,
#	for large data sets, use the unix program "less"

# ----------------------------------------------------------------- #
# -------------------------- read.table --------------------------- #

#	OPEN file1 -- Note: there is a header and entries are separated by ,
#	OPEN file2 -- Note: it is just like file 1 but there is no header

#	The approapriate commands are

x1 = read.table("file1", header=T, sep=",")
x2 = read.table("file2", header=F, sep=",")

# or

x2 = read.table("file2", sep=",")

# since "header=F" is the default, as can be seen by typing ?read.table

x1; x2; class(x1); class(x2)

# note that x1 has named columns corresponding to the header, 
# whereas x2 has default column names V1 and V2.
# also note that read.table returns a data frame

# ----------------------------------------------------------------- #

#	OPEN file3 -- Note: there is a header entries are separated by a space
#	OPEN file4 -- Note: it is just like file 1 but one entry has ***

#	The approapriate commands are

x3 = read.table("file3", header=T)
x4 = read.table("file4", header=T, sep=",", na.strings="***")

x4

# note that the *** has become NA

# Every system has its conventions for dealing with missing values; for R
# the convention is NA, and there are many statistical functions that will 
# work with data containing NAs. For example,

summary(x4)
mean(x4[,2], na.rm=T)

# ----------------------------------------------------------------- #
# ----------------------------- scan ------------------------------ #

# Scan is good for simple data structures, such as a long vector or a matrix.
# It can only handle 1 type (plus missing values), and the default is "double".
# For large data sets, scan is much faster than read.table 

# Open file5-file7, type "?scan", and try the following:

x5 = scan("file5")
x6 = scan("file6", what="character")
x7 = scan("file7", sep = ",")

x5; x6; x7
summary(x7)