Chapter 1
READING DATA
1)Typing data
 x<-c( ,  ,   ,   ,  ) 
2)Reading a file with one data column
 x<-scan('e:datafile.dat') 
3) Reading a file with several columns
 x<-read.table('e:datafile.dat') 
 
CHAPTER 2

1.- For Table 2.1 and Figure 2.3

cells<-c(0,2,2,3,3,4,4,0,0,2,0,1,3,2,2,1,4,2,0,1,2,4,2,0,2,2,
0,4,0,1,1,1,3,0,1,4,1,4,5,3,0,3,0,0,3,2,2,1,2,1)
table(cells)  
## Figure 2.3a Dotplot
stripchart(cells,method="stack", offset=1, at=0, pch=19,cex=2,
main='DOTPLOT')
## Figure 2.3 b Frequency plot 
abnormalcells<-c(0,1,2,3,4,5)
frequencies<-c(12,10,13,7,7,1)
plot(abnormalcells,frequencies,'h',main='FREQUENCIES')

2. STEM-AND-LEAF DISPLAY page 30, HISTOGRAM , BOXPLOT

area<-c(57.78, 57.89, 59.95, 62.68, 71.07, 73.46, 82.25, 65.93,
67.39, 66.32, 62.60, 55.94, 61.57, 59.39, 73.18, 61.04, 63.66, 
59.12, 57.32, 62.36, 59.60, 58.93, 64.93, 64.61, 77.60, 61.47, 
61.21, 59.37, 61.56, 55.61, 59.89, 66.74, 74.64, 62.84)
stem(area)
hist(area)
boxplot(area) 

3. Figure 2.4 HISTOGRAM AND BOXPLOT IN ONE FIGURE

## to read the data
area<-c(57.78, 57.89, 59.95, 62.68, 71.07, 73.46, 82.25, 65.93, 
67.39, 66.32, 62.60, 55.94, 61.57, 59.39, 73.18, 61.04, 63.66, 
59.12, 57.32, 62.36, 59.60, 58.93, 64.93, 64.61, 77.60, 61.47, 
61.21, 59.37, 61.56, 55.61, 59.89, 66.74, 74.64, 62.84)
stem(area)  ## to get the stem-and-leaf display
summary(area) ## calculates five-number summary and mean
par(mfcol=c(1,2))## 1 row and 2 columns of plots
hist(area,col='khaki', main='a. Histogram')  
boxplot(area,col='coral',main='b. Boxplot')  


4. CALCULATING BASIC STATISTICS

x<-c(57.78, 57.89, 59.95, 62.68, 71.07, 73.46, 82.25, 65.93, 
67.39, 66.32, 62.60, 55.94, 61.57, 59.39, 73.18, 61.04, 63.66, 
59.12, 57.32, 62.36, 59.60, 58.93, 64.93, 64.61, 77.60, 61.47, 
61.21, 59.37, 61.56, 55.61, 59.89, 66.74, 74.64, 62.84)
summary(area) ## calculates five-number summary and mean
sd(x)  ## Calculates standard deviation  
var(x)  ## Calculates the variance
sd(x)/mean(x) ## Calculates the coefficient of variation
## Calculates mean absolute deviation with respect to the mean
dev<-abs(x-mean(x))
mean(dev)


5. Change of units. Figure 2.14
 
par(mfcol=c(1,2))  ## puts both histograms in one figure
Celsius<-scan('e:tempsea.dat') ## reads data file in Celsius
Fahrenheit<-(Celsius*9/5)+32    ## transforms to Farenheit
a<-c(14,16,18,20,22,24)        ## endpoints for intervals in C
b<-(a*9/5)+32                  ## endpoints for intervals in F
hist(Celsius,breaks=a,col='palegreen3')   # histogram
hist(Fahrenheit,breaks=b,col='lightcyan3') # histogram
 

 6. Side by side boxplots- Figure 2.22 and statistics by groups

length<-c(11.2,13.0,12.5,10.0,11.3, 7.0,10.0,10.2,10.6,6.7,9.3,
11.0,12.8,9.5,12.2,13.5,13.1,11.3,12.2,14.2,7.6,5.8,7.7, 9.0,
8.1,8.6,6.3,7.5,8.6,8.7,7.8,6.5,6.1,8.0,7.5,8.0,7.0,6.2,7.9,8.2)
type<-c(1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,2,2,2,2,
2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2)
boxplot(length~type,main='Sycamore and Sugar Maple leaves ',
ylab='length (cm)', col='lightgreen')
## Calculating statistics by group
by(length,type,mean); by(length,type,median)
by(length,type,sd)



7. Figure 2.23
## read a data file with 2 or more columns using read.table
## columns have no names thus header=FALSE
gene<-read.table('e:onegene.dat',header=FALSE)
## objects are formed with each column
intensity<-gene[,1]  ## all rows of column 1
subtype<-gene[,2]    ## all rows of column 2
## produce side by side boxplots for the gene expression example
boxplot(intensity~subtype, main='Intensity of expression of one gene',
xlab='Subtype of tumor', ylab='Intensity' ,col='cadetblue2')
 

8. Dotplots by group- Figure 2.24

treatment<-c(2,2,2.4,1.8,1.9,1.8,2,1.5,1.9,2.1)
control<-c(0.1,0,0.1,0.1,0,0.2,0.2,0.1,0.1,0.1)
a<-c(0,2.5) ## entering the endpoints of the x axis
par(mfcol=c(2,1)) ## 2 plots in the same figure
## cex controls the size of symbols 
## offset controls the vertical space between symbols
## pch=19 indicates dots instead of squares
## xlim controls the endpoints of the x axis
## stripchart prepares the dotplot
stripchart(treatment,method='stack',offset=0.5,at=0,cex=1,
pch=19,xlim=a, main='a. Treatment',xlab='difference=after-before' ) 
stripchart(control,method='stack',offset=0.5,at=0,cex=1,
pch=19,xlim=a,  main='b. Control', xlab='difference=after-before')   
 
9. Plotting time series- Figure 2.26

activity<-scan('e:onebeesu.dat') ## reads the data
ts.plot(activity)    ## plots the time series
## commands for Figure 2.25
temp<-scan('e:tempsea.dat')    ## reads data
temperature<- ts(temp, start = c(1956, 1), frequency = 12) ##dates 
t<-rep(seq(1,12,by=1),30)   ## creates labels for months
par(mfrow=c(2,1))   ## to plot two figures together
ts.plot(temperature, main='a. timeplot') 
boxplot(temperature~t, main='b. boxplots by month')  


10. Survival plot in Figure 2.28


nindi<-200   ## how many flies we start with
## we type in the data of number of dead flies each day
x<-c(0,1,2,0,2,1,5,1,4,2,5,4,3,7,6,
     6,18,11,18,31,21,17,0,23,6,1,3,0,0,0)
## NO MORE INPUT IS NEEDED
n=length(x)  ## calculates the number of days
day<-seq(1,n,by=1)       ## creates the values for 'day'
cum<-cumsum(x)           ## accumulates the values
surv<-nindi-cum          ## calculates the number of survivors
propsurv<-surv/nindi     ## calculates proportion of survivors
plot(day,propsurv,'s',col='red',ylim=c(0,1))
abline(0.5,0)            ## adds the horizontal line
## END HERE if there is only one group
 

11. SCATTERPLOTS Figure 2.29

Altitude<-c(0,1840,2200,2200,5000,5200,5750,7400,8650,10740,12000,
12200,12300,14200,14800,14900,17500)
RBC<-c(4.93,4.75,5.40,4.65,5.42,6.55,5.99,5.39,5.44,5.82,7.50,5.67,  
6.31,7.05,6.46,6.66,7.37)
plot(Altitude,RBC) ## gets scatterplot
cor(Altitude,RBC)## calculates Pearson's correlation r


12. Matrix of scatter plots and stars plots (Figures 2.32 and 2.33)

## reads the data file with several columns
birdswn<-read.table('e:/DATdatafiles/birds20wn2.dat')
birds<-birdswn[,2:6] ## creates object birds with numerical values
stars(birds,labels=birdswn[,1]) ## makes stars, puts labels  
pairs(birds) ## produces matrix of scatterplots

13. BAR CHART AND PIE CHART Figure 2.34
 
par(mfcol=c(1,2))    ## 1 row and 2 columns of plots
g<-c(60,100)    ## enter frequencies
names(g)<-c("Round ", "Sickle ")
barplot(g, main= "Erythrocytes by shape ", col= "bisque")
pie(g,c("round","sickle"))
 
14. CLUSTERED BAR CHARTS  Figure 2.35

## clustered bars charts
## next we enter the rows  of data
A<-matrix(c(77,49,45,39,45,36,43,101,75,51),nrow=5,ncol=2)
## enter the names of the categories
rnames<-c('0-20 ', '20-40 ','40-60 ', '60-80', '80-100')
## this command prepares the plot
barplot(A,beside=TRUE, names=c('Random sites','Habitat sites'),
xlab='% cover',main='Understory vegetation',legend=rnames)
 
15. STACKED BAR CHARTS Figure 2.36
 
## clustered and stacked bars charts
par(mfcol=c(1,2))    ## 2 plots appear side by side
## next we enter the 2 columns of data or percentages
A<-matrix(c(35.7,7.3,2.5,54.5,41.03,10.15,2.5,46.32),nrow=4,ncol=2)
rnames<-c('A ', 'B ','AB ', '0')
## the only difference is in the BESIDE option of the barplot
barplot(A,beside=TRUE, names=c('ulcers ', 'no ulcers '),
main='Blood type',ylab='percent',legend=rnames)
barplot(A,beside=FALSE,names=c('ulcers ', 'no ulcers '),
main='Blood type',ylab='percent')

16. Exercise 7 in chapter 2 (page 93)
cell<-c(6.2,6.0,6.7,7.4,6.0,6.4 ,5.9,5.9,6.1,6.2,6.5,6.1,6.2, 
6.6,7.2,7.5,5.3,6.0,5.9,6.3,7.0,6.9,5.1,6.1)
nucleus<-c(2.2,2.1,2.7,3.2,2.1,2.1,2.3,2.4,2.3,2.2,2.7,2.4
,2.4,2.4,3.0,2.9,2.0,2.3,2.2,2.4,2.3,2.4,2.1,2.1)
plot(cell,nucleus) 
n<-length(cell)  ## to count the number of observations
((n-1)/n)*cor(cell,nucleus)

17. Exercise 8 in Chapter 2 (page 94)
height<-c(63, 66, 67, 61.5, 65, 67, 64, 64.8, 66.5, 64.5, 67, 68, 67, 63, 65, 63, 66.5, 66, 65.5, 63, 65, 68, 62)
foot <-c(8, 8, 9.5, 8, 7.1, 8.5, 8.35, 8, 10.1, 8.5, 9.5, 7.5, 8.1, 8, 9.5, 7, 9.50, 9.50, 9.50, 8.5, 8, 9, 7)
handspan<-c( 8, 7.5, 7.5, 6.2, 6.2, 8, 6.40, 7, 8.4, 8.5, 8.25, 7.4, 6.9, 7.5, 8.5, 6, 8.5, 7, 7.25, 7.5, 7, 8, 7.5)
cor(height,foot)
cor(foot,handspan)
cor(height,foot)

18. Exercise 9 
petiole<-c(6.2, 3.6, 5.3, 5.6, 5.2, 6, 4.2, 6.1, 5.3,
6.9, 4.3, 4.8, 5.5, 5, 5.2, 4.9, 5.5, 4.6, 5.9, 6.4)
leaf<-c(0.587,0.235,0.480,0.738,0.587,0.793,0.401,0.611,0.617,
0.578,0.373,0.327,0.281,0.528,0.399,0.543,0.413,0.323,0.544,0.577)

19. Project 1 , page 95
## reads the data file
hens<-read.table('e:/DATdatafiles/hens.dat',header=FALSE)
## creates objects with each variable
species<-hens[,1]; mass<-hens[,2]; wing<-hens[,3]; 
tarsus<-hens[,4]; tail<-hens[,5]; clutch<-hens[,6];
eggmass<-hens[,7]
## create a data frame with some variables for later use.
body<-data.frame(mass,wing,tarsus,tail)
stars(body)

20. Project 2, page 96
## reads the data file
birds<-read.table('e:/DATdatafiles/LybiidaeMales.dat',
header=FALSE)
## creates objects with each variable
species<-birds[,1]; mass<-birds[,2]; tarsus<-birds[,3]
bill<-birds[,4]; wing<-birds[,5]; tail<-birds[,6]
## forms a data frame that does not include the species number
body<-data.frame(mass,tarsus,bill,wing,tail)
stars(body)
pairs(body)

21. Project 4 , page 97
mydata<-read.table('e:/DATdatafiles/fiveleaves.dat',
header=FALSE)
species<-mydata[,1]; length<-mydata[,2]
width<-mydata[,3] ; petiole<-mydata[,4]
mass<-mydata[,5]

22. Project 5, page 98
bones<-read.table('e:/DATdatafiles/BMD.dat',
header=FALSE)
age<-bones[,1]
lumbar1<-bones[,2];  lumbar2<-bones[,3]
lumbar3<-bones[,4];  lumbar4<-bones[,5]
LFNeck<-bones[,6];   LTotHip<-bones[,7]
RFNeck<-bones[,8];   RTotHip<-bones[,9]