Answser keys to practices in R short course R basics

This file shows the code that is run and the result that will be shown in R if there is any, where the
highlighted blue lines are the code and the highlighted black lines are the results shown in R.

Practice 1
#1. What is the dimension of our dataset?
> dim(mydatacsv)
[1] 150 5

#2. Assign the value of the cell [2,3] to the new variable var1
var1=mydatacsv[2,3]

#3. Assign the value of the cell [10,4] to the new variable var2
var2=mydatacsv[10,4]

#4. Output the value of each column separately.

> mydatacsv[,1]
[1] 5.1 4.9 4.7 4.6 5.0 5.4 4.6 5.0 4.4 4.9 5.4 4.8 4.8 4.3 5.8 5.7 5.4 5.1 5.7 5.1 5.4
[22] 5.1 4.6 5.1 4.8 5.0 5.0 5.2 5.2 4.7 4.8 5.4 5.2 5.5 4.9 5.0 5.5 4.9 4.4 5.1 5.0 4.5
[43] 4.4 5.0 5.1 4.8 5.1 4.6 5.3 5.0 7.0 6.4 6.9 5.5 6.5 5.7 6.3 4.9 6.6 5.2 5.0 5.9 6.0
[64] 6.1 5.6 6.7 5.6 5.8 6.2 5.6 5.9 6.1 6.3 6.1 6.4 6.6 6.8 6.7 6.0 5.7 5.5 5.5 5.8 6.0
[85] 5.4 6.0 6.7 6.3 5.6 5.5 5.5 6.1 5.8 5.0 5.6 5.7 5.7 6.2 5.1 5.7 6.3 5.8 7.1 6.3 6.5
[106] 7.6 4.9 7.3 6.7 7.2 6.5 6.4 6.8 5.7 5.8 6.4 6.5 7.7 7.7 6.0 6.9 5.6 7.7 6.3 6.7 7.2
[127] 6.2 6.1 6.4 7.2 7.4 7.9 6.4 6.3 6.1 7.7 6.3 6.4 6.0 6.9 6.7 6.9 5.8 6.8 6.7 6.7 6.3
[148] 6.5 6.2 5.9
> mydatacsv[,2]
[1] 3.5 3.0 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 3.7 3.4 3.0 3.0 4.0 4.4 3.9 3.5 3.8 3.8 3.4
[22] 3.7 3.6 3.3 3.4 3.0 3.4 3.5 3.4 3.2 3.1 3.4 4.1 4.2 3.1 3.2 3.5 3.6 3.0 3.4 3.5 2.3
[43] 3.2 3.5 3.8 3.0 3.8 3.2 3.7 3.3 3.2 3.2 3.1 2.3 2.8 2.8 3.3 2.4 2.9 2.7 2.0 3.0 2.2
[64] 2.9 2.9 3.1 3.0 2.7 2.2 2.5 3.2 2.8 2.5 2.8 2.9 3.0 2.8 3.0 2.9 2.6 2.4 2.4 2.7 2.7
[85] 3.0 3.4 3.1 2.3 3.0 2.5 2.6 3.0 2.6 2.3 2.7 3.0 2.9 2.9 2.5 2.8 3.3 2.7 3.0 2.9 3.0
[106] 3.0 2.5 2.9 2.5 3.6 3.2 2.7 3.0 2.5 2.8 3.2 3.0 3.8 2.6 2.2 3.2 2.8 2.8 2.7 3.3 3.2
[127] 2.8 3.0 2.8 3.0 2.8 3.8 2.8 2.8 2.6 3.0 3.4 3.1 3.0 3.1 3.1 3.1 2.7 3.2 3.3 3.0 2.5
[148] 3.0 3.4 3.0
> mydatacsv[,3]
[1] 1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 1.5 1.6 1.4 1.1 1.2 1.5 1.3 1.4 1.7 1.5 1.7
[22] 1.5 1.0 1.7 1.9 1.6 1.6 1.5 1.4 1.6 1.6 1.5 1.5 1.4 1.5 1.2 1.3 1.4 1.3 1.5 1.3 1.3
[43] 1.3 1.6 1.9 1.4 1.6 1.4 1.5 1.4 4.7 4.5 4.9 4.0 4.6 4.5 4.7 3.3 4.6 3.9 3.5 4.2 4.0
[64] 4.7 3.6 4.4 4.5 4.1 4.5 3.9 4.8 4.0 4.9 4.7 4.3 4.4 4.8 5.0 4.5 3.5 3.8 3.7 3.9 5.1
[85] 4.5 4.5 4.7 4.4 4.1 4.0 4.4 4.6 4.0 3.3 4.2 4.2 4.2 4.3 3.0 4.1 6.0 5.1 5.9 5.6 5.8
[106] 6.6 4.5 6.3 5.8 6.1 5.1 5.3 5.5 5.0 5.1 5.3 5.5 6.7 6.9 5.0 5.7 4.9 6.7 4.9 5.7 6.0
[127] 4.8 4.9 5.6 5.8 6.1 6.4 5.6 5.1 5.6 6.1 5.6 5.5 4.8 5.4 5.6 5.1 5.1 5.9 5.7 5.2 5.0
[148] 5.2 5.4 5.1
> mydatacsv[,4]
[1] 0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 0.2 0.2 0.1 0.1 0.2 0.4 0.4 0.3 0.3 0.3 0.2
[22] 0.4 0.2 0.5 0.2 0.2 0.4 0.2 0.2 0.2 0.2 0.4 0.1 0.2 0.2 0.2 0.2 0.1 0.2 0.2 0.3 0.3
[43] 0.2 0.6 0.4 0.3 0.2 0.2 0.2 0.2 1.4 1.5 1.5 1.3 1.5 1.3 1.6 1.0 1.3 1.4 1.0 1.5 1.0
[64] 1.4 1.3 1.4 1.5 1.0 1.5 1.1 1.8 1.3 1.5 1.2 1.3 1.4 1.4 1.7 1.5 1.0 1.1 1.0 1.2 1.6
[85] 1.5 1.6 1.5 1.3 1.3 1.3 1.2 1.4 1.2 1.0 1.3 1.2 1.3 1.3 1.1 1.3 2.5 1.9 2.1 1.8 2.2
[106] 2.1 1.7 1.8 1.8 2.5 2.0 1.9 2.1 2.0 2.4 2.3 1.8 2.2 2.3 1.5 2.3 2.0 2.0 1.8 2.1 1.8
[127] 1.8 1.8 2.1 1.6 1.9 2.0 2.2 1.5 1.4 2.3 2.4 1.8 1.8 2.1 2.4 2.3 1.9 2.3 2.5 2.3 1.9
[148] 2.0 2.3 1.8
> mydatacsv[,5]
[1] setosa setosa setosa setosa setosa setosa setosa
[8] setosa setosa setosa setosa setosa setosa setosa
[15] setosa setosa setosa setosa setosa setosa setosa
[22] setosa setosa setosa setosa setosa setosa setosa
[29] setosa setosa setosa setosa setosa setosa setosa
[36] setosa setosa setosa setosa setosa setosa setosa
[43] setosa setosa setosa setosa setosa setosa setosa
[50] setosa versicolor versicolor versicolor versicolor versicolor versicolor
[57] versicolor versicolor versicolor versicolor versicolor versicolor versicolor
[64] versicolor versicolor versicolor versicolor versicolor versicolor versicolor
[71] versicolor versicolor versicolor versicolor versicolor versicolor versicolor
[78] versicolor versicolor versicolor versicolor versicolor versicolor versicolor
[85] versicolor versicolor versicolor versicolor versicolor versicolor versicolor
[92] versicolor versicolor versicolor versicolor versicolor versicolor versicolor
[99] versicolor versicolor virginica virginica virginica virginica virginica
[106] virginica virginica virginica virginica virginica virginica virginica
[113] virginica virginica virginica virginica virginica virginica virginica
[120] virginica virginica virginica virginica virginica virginica virginica
[127] virginica virginica virginica virginica virginica virginica virginica
[134] virginica virginica virginica virginica virginica virginica virginica
[141] virginica virginica virginica virginica virginica virginica virginica
[148] virginica virginica virginica
Levels: setosa versicolor virginica

#5. Assign the values of Petal.Width to a new variable PW.

PW=mydatacsv[,4]

#6. Output the value of row 15.

mydatacsv[15,]
Sepal.Length Sepal.Width Petal.Length Petal.Width Species
15 5.8 4 1.2 0.2 setosa

Practice 2a.
#1. Read into R the dataset pubfileb.csv.
public<- read.table('pubfileb.csv', sep=',', header=T)

#2. Determine the dimensions of the dataset.

dim(public)
[1] 988346 38

#3. Extract the variable povpct, income as percent of poverty level (column 35) as a new variable.
povpct=public[,35]

#4. Extract the variable ms, marital status (column 5) as a new variable.
ms= public[,5]

#5. Obtain the minimum, maximum, mean, variance, median for the variable povpct and store them in
separate variables.
m=mean(povpct)
var=var(povpct)
min=min(povpct)
max=max(povpct)
med=median(povpct)

#6. Create a vector with the stored values from 5.

sumvec=c(m,var,min,max,med)
summary(povpct)
Min. 1st Qu. Median Mean 3rd Qu. Max.
1.00 5.00 10.00 10.27 16.00 21.00

#7. Create a histogram of povpct of a different color with 20 breaks.

hist(povpct, main="Histogram of povpct", col="tomato", breaks=20)
Practice 2b.
#1. Create a boxplot of povpct of a different color.
boxplot(povpct, main="Boxplot of povpct", col="limegreen", ylab="povpct")
#2. Create a boxplot of povpct by ms with the same color for all boxes.
boxplot(povpct~ms,col="blue", main="Boxplot of povpct by Marital Status")
#3. Create a boxplot of povpct by ms with the same color for the first three boxes and another color for
the remaining three boxes.
boxplot(povpct~ms,col=c("blue", "blue", "blue", "yellow", "yellow", "yellow"),
main="Boxplot of povpct by Marital Status")
#4. Create a normal Q-Q plot for povpct.
qqnorm(povpct, main="Normal QQ Plot povpct")
#5. Using for loops count how many observations are there in a metropolitan area (smsast=1) (col 20)
with an age lower than 15 (col 2).
count=0
for(i in 1:dim(public)[1]){
if (public[i,20]==1){
if(public[i,2]<15) count=count+1
}
}
count
[1] 53671

#6. Export your extracted variables as a .csv file and the dataset as a tab delimited .txt file.
write.csv(povpct,file="povpct.csv")
write.table(public,file="public.txt", sep="\t")