# For the first few lab sessions, you will type things in on your own.
# Later, you'll be able to cut and paste bits of R code that you will be given.
# Even when you type things in, note that the up/down arrow keys scroll thru
# all the commands you may have typed in already. So, you don't have to
# type-in things that you've already typed-in.

# First, here are some R basics:

(57/276)^2+4.3*.001          # = 0.04695123 . Basic algebraic operations.

## Lines starting with "#" are comments.

##Create variables and assign them value

## Variable names, function names, etc., should contain only alphanumeric 
## characters (A-Z, a-z, 0-9) and the period ".". Take note, a name cannot 
## start with a digit and ".". R is case-sensitive, i.e., "a" and "A" are
## different.  Here are some more basic operations:

x <- 3         ## assignment can be done using either "=" or "<-"
x
y = 1 + 1
y
log10(y); log2(y)  ## Commands are separated by semicolons (;) or by a newline.
sqrt(y)

# Variables can be either number, vector, matrix, dataframe, character, or 
# logical expression. No need for serious definitions here, for we will come 
# across these gradually.

x <- 1:5                   # A few ways of entering data in R:
x
y <- c (34, 30, 41, 35, 21)   
y

mean(y)    ## sample average of y -- measures "location."
median(y)  ## sample median of y -- another measure of "location."
sd(y)      ## sample standard deviation of y -- measures "spread."

                         # For the following, use your up-arrow key.
range(y)                 # Gives two numbers, min and max. 
range(y)[1]              # First component of range(y), i.e., min
range(y)[2]              # Second ..., i.e., max.
min(y)
max(y)

sort(y)

###################################################################

## To get help and examples on any function, say median:

?median           # Explains and gives examples at end, usually.
                  # q will get you out of the help page.
###################################################################

# R comes with a bunch of data sets. This is how you see what they are:

data()              # Now you know where to get data, if you want some!

# This is how you read-in the R data sets:

data(USArrests)     ## Make the dataset available; q quits.

?USArrests          # Gives info on data set; q quits.
USArrests           # Simply prints all the data onto the screen.
names(USArrests)    # Tells you the name of the variables.          Use up-arrow.
dim(USArrests)      # Tells the (row X column) dimensions.          Use up-arrow.  
USArrests$Murder    # $ selects a given column/variable, by name.  Use up-arrow.
USArrests[,1]       # Same as above, but selects by column number. Use up-arrow.

murder = USArrests[,1] # Selects and assigns to some variable.
murder                 # Shows arrest.
mean(murder)           # Use up-arrow.
sd(murder)             # standard deviation of arrest.

####################################################################

# This is how you read-in data from a text file. (At the bottom of this file,
# below, you can see how to read-in data from CD of your textbook, etc.)

dat = read.table("http://www.stat.washington.edu/marzban/390/hist_dat.txt", header=F)
dat

## Now, let's do some histograms on this data.

# A histogram is simply a count (or frequency) plot of different values of a 
# variable. It answers the questions, for example, "How many x=1's occur in the 
# data?", "How many x=2's occur in the data?" Etc. That's easy when the variable 
# (x) is discrete. But what if it's continuous? Then, the answer to all of the
# above questions is "zero." The only reasonable questions are of the type 
# "How many cases in the data are within 0.1 of x=1?" Etc. The 0.1 is called
# the class interval, or the bin size. What you will see here is the effect
# of this bin size on the histogram. In R, instead of specifying the bin size,
# it's more convenient to simply specify the number of bins, specified by
# "breaks=" or "nclass=". Here are some examples.

x = dat[,1]      # Selects the first column/variable in the file.
x

# Let's turn the "knob" on binsize and see what happens:

                    # For the following, USE YOUR UP-ARROW.
par(mfrow=c(3,3))   # This puts the 9 following histograms on 1 page.
hist(x, breaks = 2) # looks useless
hist(x, breaks = 3)
hist(x, breaks = 4) # looks unimodal and bell-shaped.
hist(x, breaks = 5)
hist(x, breaks = 10) # looks bimodal.
hist(x, breaks = 20)
hist(x, breaks = 30)
hist(x, breaks = 100) # looks bimodal + outlier
hist(x, breaks = 10000) # looks useless

# The above suggests that the data/variable x is probably made-up of
# two different groups. For example, x could be "height", in which case
# the two "humps" (at around breaks = 30 or 100 may be identified as the 
# heights of boys and girls, respectively. This type of analysis is a
# simple form of data-mining, i.e. trying to figure out what's in the data.

# Take qz1. TAs, scroll up and display on the screen the read.table line.

q()           # This will get you out of R altogether.  

####################################################################

# Extras:  TAs, give this to students, but do not cover in class, 
# unless there is time.

is.vector(x)       # Checking to see if something is a vector.

                   # To make a sequence of numbers, use c() or seq():
y <- seq (from = 0, to = 1, by = 0.1)  # Or simply,  y <- seq (0, 1, 0.1)

help.search("poisson")  # Searches for "possion" in all of R.

                        # If you want the breaks in specfic places:
hist(murder, breaks=seq(0, 20, by=3)) 
hist(murder, breaks=c(0,1,5,10,20))

# This is how you read-in data from CD of your textbook:

read.table(file.choose(),header=T)

# For reading excel files, save the file as .csv, and then read it as

read.csv(file.choose(),header=F)

# This is how you read-in data from a file (e.g. hist_dat.txt) in some
# directory:

setwd("G://Documents/2008AU/STAT 390/Lab")  # This is an example!!!
dat <- read.table("hist_dat.txt", header=F)

# OR from the web

dat <- read.table("http://www.stat.washington.edu/marzban/390/hist_dat.txt",
header=F)

###########################################################################