###############################################
## Author: Joshua M. Tebbs
## Date: 27 July 2016
## Update: 15 March 2024
## STAT 110 course notes: R Code Chapter 10
###############################################

# Figure 10.1
# Page 78
# Find data web site
# Cut and paste data set into a notepad file
# Save this file (e.g., nutrition.txt) to a folder on your laptop or desktop
# Import the data from the folder 

# This creates a table (with each row corresponding to one infant)
nutrition.type = read.table("C:\\Users\\tebbs\\OneDrive - University of South Carolina\\Documents\\texfiles\\Classes\\USC\\stat110\\s24\\data\\nutrition.txt",header=TRUE)

# This creates a univariate data set (ignoring infant case number)
nutrition.type = nutrition.type[,1]

# This creates a table of the data
# There are 605 data values for the nutrition type variable (10 values were missing)
count = table(nutrition.type) 
count
# Create table but use proportions instead of counts
proportion = count/605
round(proportion,2)

# Create labels for the categories of nutrition type
labels = c("Breastmilk","Fluids","TPN","Formula")
# Barplot of counts (left)
barplot(count, main="",xlab="Nutrition Type",ylab="Count",names.arg=labels,ylim=c(0,300),col="lightblue")
# Barplot of proportions (right)
barplot(proportion,main="",xlab="Nutrition Type",ylab="Proportion",names.arg=labels,ylim=c(0,0.5),col="lightblue")


# Figure 10.2
# Page 79
# Create pie chart of proportions
proportion = c(0.39,0.10,0.44,0.07)
labels = c("Breastmilk","Fluids","TPN","Formula")
pie(proportion,labels = proportion,main = "",col=c("lightblue","khaki","lightcoral","lightgreen"))
legend("topright",labels,cex = 1,fill=c("lightblue","khaki","lightcoral","lightgreen"))


# Figure 10.3
# Page 80
# Construct bar graph of states (percentage of residents with a bachelor's degree)
percents = c(27.4,25.3,33.2,34.6,26.5,34.9,24.8,31.5,30.5,41.8)
labels = c("AL","AR","FL","GA","LA","NC","MS","SC","TN","VA")
# Figure 10.3 (left)
barplot(percents,main="Percentage of Residents with Bachelor's Degree",xlab="State",ylab="Percent",ylim = c(0,50.0),names.arg=labels,col="lightblue")

# Plot in descending order
# Figure 10.3 (right)
labels.sort = c("VA","NC","GA","FL","SC","TN","AL","LA","AR","MS")
barplot(sort(percents,decreasing=TRUE),main="Percentage of Residents with Bachelor's Degree",xlab="State",ylab="Percent",ylim = c(0,50.0),names.arg=labels.sort,col="lightblue")


# Figure 10.4
# Page 82
enrollment = ts(read.table(file = "C:\\Users\\tebbs\\OneDrive - University of South Carolina\\Documents\\texfiles\\Classes\\USC\\stat110\\s24\\data\\enrollment.txt",header=TRUE),start=1954)
plot(enrollment,ylab="Number of students",xlab="Year",type="o",ylim=c(0,40000),pch=19,cex=0.75)


# Figure 10.5
# Page 84 # Email me if you would like either data set
# Airmiles data (top)
data(airmiles) # TSA package; need to install (see me)
plot(airmiles/1000,ylab="Number of airline miles (in 1000s)",xlab="Year",type="o",pch=19,cex=0.75)
# Home run data (bottom)
homeruns = ts(read.table(file = "C:\\Users\\tebbs\\OneDrive - University of South Carolina\\Documents\\texfiles\\Classes\\USC\\stat520\\f13\\data\\homeruns.txt",header=TRUE),start=1909)
plot(homeruns,ylab="Number of home runs",xlab="Year",type="o",pch=19,cex=0.75)


# Figure 10.6
# Page 85 # Email me if you would like either data set
# Earthquake data (top)
earthquake = ts(read.table(file = "C:\\Users\\tebbs\\OneDrive - University of South Carolina\\Documents\\texfiles\\Classes\\USC\\stat520\\f13\\data\\earthquake.txt",header=TRUE),start=1900)
plot(earthquake,ylab="Number of earthquakes",xlab="Year",type="o",pch=19,cex=0.75)
# Supreme Court data (bottom)
homeruns = ts(read.table(file = "C:\\Users\\tebbs\\OneDrive - University of South Carolina\\Documents\\texfiles\\Classes\\USC\\stat520\\f13\\data\\homeruns.txt",header=TRUE),start=1909)
plot(homeruns,ylab="Number of home runs",xlab="Year",type="o",pch=19,cex=0.75)


# Figure 10.7
# Page 86
# Yearly case count (left)
yearly.tb.cases = ts(read.table(file = 
	"C:\\Users\\tebbs\\OneDrive - University of South Carolina\\Documents\\texfiles\\Classes\\USC\\stat110\\s24\\data\\yearly.tb.cases.txt",header=TRUE),start=1953)
plot(yearly.tb.cases,ylab="Number of TB cases",xlab="Year",type="o",pch=19,cex=0.75))
# Monthly case count (right)
monthly.tb.cases = ts(read.table(file = 
	"C:\\Users\\tebbs\\OneDrive - University of South Carolina\\Documents\\texfiles\\Classes\\USC\\stat110\\s24\\data\\monthly.tb.cases.txt",header=TRUE),start=2000,freq=12)
plot(monthly.tb.cases,ylab="Number of TB cases",xlab="Year",type="o",pch=19,cex=0.75)


# Figure 10.8
# Page 89
# Create labels for the categories of nutrition type
labels = c("Trump","Reagan","Bush","Clinton","Bush Jr","Obama")
count = c(24,19,18,18,16,15)
# Create barplot of counts
barplot(count,main="",xlab="President",ylab="Number of appellate judgeships confirmed",names.arg=labels,ylim=c(0,25),col="lightblue")


# Figure 10.9
# Page 90
temperature = ts(read.table(file = "C:\\Users\\tebbs\\OneDrive - University of South Carolina\\Documents\\texfiles\\Classes\\USC\\stat110\\s24\\data\\temperature.txt",header=TRUE),start=1875)
# Compressed vertical axis (top)
plot(temperature,ylab="Average global surface temperature (deg F)",xlab="Year",type="o",pch=19,cex=0.75,ylim=c(35,70))
# Better vertical axis (bottom)
plot(temperature,ylab="Average global surface temperature (deg F)",xlab="Year",type="o",pch=19,cex=0.75,ylim=c(48,57))