# 4110/7110 Lecture 28 -- UNIVATIATE DATA

# R functions used in this lecture

#par(mfrow=c(2,2))
#windows()
#x11()

table	 	# frequency table
factor 	# to encode a vector as a factor
as.factor  	# to coerce its argument to a factor.
barplot 	# bar plot
boxplot     # box plot
bwplot	# trellis box plot(s)
pie		# pie plot
dotchart	# dot plot
stem		# stem and leaf plot
hist	 	# histogram plot
histogram	# trellis histogram plot(s)
plot	 	# generic plot function
rnorm		# random number from standard normal
mean	 	# calculate the mean
median 	# calculate the median
range	 	# calculate the minimum and maximum
sd	 	# calculate the standard deviation
var	 	# calculate the variance
length	# calculates the count
quantile 	# compute the quantiles
IQR		# compute the Interquartile range
cor	 	# compute correlations
summary	# generic function provides a summary results of an object
fivenum     # min, lower hinge, Median, upper hinge, max
apropos 	# returns a character vector giving the names of 
		# all objects in the search list matching what.
scan()	# read data
data()      # list all available data sets
attach	# attaching a data frame (or list) to the search path
detach	# detaching a data frame (or list) to the search path

########################################################
# Categorical Data

x=c("Yes","No","No","Yes","Yes")
table(x)
x 
factor(x)
as.factor(x)

# Factors
1:5
mean(1:5)
factor(1:5)
mean(factor(1:5))
letters[1:5]
factor(letters[1:5])
factor(LETTERS[1:5])

# Bar Charts
beer = scan()
 3 4 1 1 3 4 3 3 1 3 2 1 2 1 2 3 2 3 1 1 1 1 4 3 1

barplot(beer)                 # this isn't correct
barplot(table(beer))          # Yes, call with summarized data
barplot(table(beer)/length(beer)) # divide by n for proportion

par(mfrow=c(3,1))
barplot(beer)                 
barplot(table(beer))          
barplot(table(beer)/length(beer)) 

plot(1:10)
?abline
abline(a=0,b=1)# Add a Straight Line to a Plot through the 1:10 points
abline(a=1,b=1, col="red")

windows()  # or x11()
plot(rnorm(10))
abline(-1.5,1)# Add a Straight Line to a Plot through the 1:10 points
abline(h=0, col="green")# for the residual plot

# Pie Charts
# par(mfrow=c(2,2))
?pie
?pie
beer.counts = table(beer)     # store the table result
pie(beer.counts)              # first pie -- kind of dull
names(beer.counts) = c("domestic\n can","Domestic\n bottle", "Microbrew","Import")
pie(beer.counts)              # prints out names
pie(beer.counts,col=c("red","green","yellow","white"))  # now with colors


# Dot Charts
?dotchart # plot of either a vector or matrix of numeric values 

VADeaths # we are going to use dataset VADeaths: Death rates per 1000 in Virginia in 1940.
is.vector(VADeaths)
is.matrix(VADeaths)

dotchart(VADeaths, main = "Death Rates in Virginia - 1940")
dotchart(t(VADeaths), xlim = c(0,100), main = "Death Rates in Virginia - 1940") 
          # t: matrix transpose
t(VADeaths)
 
#################################################################
# Numerical Data

sals = scan()            # read in with scan
 12  0.4   5   2   50   8   3   1   4   0.25

mean(sals)               # the average
var(sals)                # the variance
sd(sals)                 # the standard deviation 
median(sals)             # the median
summary(sals)

data=c(10, 17, 18, 25, 28, 28)
summary(data)
quantile(data,.25)
quantile(data,c(.25,.75))     # two values of p at once

mean(sals,trim=1/10)          # trim 1/10 off top and bottom
mean(sals,trim=2/10)
IQR(sals)

# Stem-and-leaf plots
scores = scan()
2 3 16 23 14 12 4 13 2 0 0 0 6 28 31 14 4 8 2 5

stem(scores)

sals = c(12, .4, 5, 2, 50, 8, 3, 1, 4, .25) # enter data
cats = cut(sals,breaks=c(0,1,5,max(sals)))  # specify the breaks
cats                          # view the values
table(cats) # organize
levels(cats) = c("poor","rich","rolling in it") # change labels
table(cats)

# Histograms
x=scan()
29.6 28.2 19.6 13.7 13.0  7.8  3.4  2.0  1.9  1.0  0.7  0.4  0.4  0.3
0.3 0.3  0.3  0.3  0.2  0.2  0.2  0.1  0.1  0.1  0.1  0.1

par(mfrow=c(2,2))
hist(x)                       # frequencies
hist(x,probability=TRUE)      # proportions (or probabilities)
rug(jitter(x))                # add tick marks

hist(x,breaks=10)             # 10 breaks, or just hist(x,10) 
hist(x,breaks=c(0,1,2,3,4,5,10,20,max(x))) # specify break points

# Boxplots
data()                        # list all available data setsAirPassengers   
women                         # data 'women' will be used 
names(women)
mean(height)
mean(women$height)
attach(women)                # to access the names above
mean(height)
boxplot(height,main="Average Height of \n American Women",horizontal=TRUE)
boxplot(weight,main="Average Weight of \n American Women",horizontal=TRUE)
plot(women, xlab = "Height (in)", ylab = "Weight (lb)", main = "women data: American women aged 30-39")
detach(women)


#Density Functions
data(faithful)
par(mfrow=c(1,1))
attach(faithful)             # make eruptions visible
hist(eruptions,15,prob=T)    # proportions, not frequencies
lines(density(eruptions))    # lines makes a curve, default bandwidth
lines(density(eruptions,bw="SJ"),col='red')# Use SJ bandwidth, in red
detach(faithful)