BMAT202P- Probability and statistics lab

Table and Graphical Representations

“
⚫ Importing CSV and Tabular Data Files
We can change the current working directory as follows:
⚫ setwd("<location of the dataset>")

⚫ Example
>setwd("C:\\Users\\admin\\Desktop\\")
>data=read.csv("stud.csv")
⚫ Comma-separated values (CSV) files
⚫ Data files have many formats and accordingly we have
options for loading them.

>data=read.csv(“C:\\Users\\admin\\Desktop\\Mokesh
\\stud.csv”)

Or

>data=read.csv(“C:/Users/admin/Desktop/Mokesh/stud
.csv”)
Graphics on R
⚫ A simple plot plot(X) has each element of a discrete variable X
ploted on the y-axis and the element's index on the x-axis
>v <- c(7,12,28,3,41)
>t <- c(14,7,6,19,3)
> plot(v,type = "o", col = "red", xlab = "Month", ylab =
"Rain fall",main = "Rain fall chart")
>lines(t, type = "o", col = "blue")
R a i n fall c h a r t

40
30
Rainfall

20
10

1 2 3 4 5

M ont h
⚫ Line chart
⚫ A line chart is a simple plot with consecutive plots connected
by lines
 type= p type= l type= o type= b

5
4

4
3

3
y

y
y

y
2

2
1

1
1 3 5 1 3 5 1 3 5 1 3 5

x x x x

type= c type= s type= S type= h

5

5
4

4
3

3
y

y
y

y
2

2
1

1
1 3 5 1 3 5 1 3 5 1 3 5

x x x x
 y y

0 100 300 500 0 100 300 500

1
1

x
3

x
3
type= c
type= p

5
y y

0 100 300 500 0 100 300 500

1

1
x
3

x
3
type= l

type= s

5
5

y y

0 100 300 500 0 100 300 500

1

1
x
3

x
3
type= S
type= o

5
5

y y

0 100 300 500 0 100 300 500

1

1
x
3

x
3
type= h
type= b

5
5
⚫ Scatterplot
A scatterplot plot(X,Y) has each element of a variable Y
ploted on the y-axis and the corresponding element
for variable X on the x-axis

# scatterplot
>attach(mtcars)
>plot(wt, mpg, main="Weight / MPG graph",
xlab="Car Weight (lbs)", ylab="Miles Per Gallon",
pch=19)
 Weight / M P G graph

30
Miles Per Gallon

25
20
15
10

2 3 4 5

C a r W e i g ht (lbs)
⚫ Kernel density plots
⚫ Kernel density plots nicely visualize the shape of a distribution.
They can be better than histograms, even with normal curves
because histograms are strongly affected by the number of bins
used and by outliers.
⚫ # Kernel density plot
⚫ >d <- density(mtcars$mpg) # kernel density estimates
⚫ >plot(d)
⚫ # Filled density plot
⚫ >d <- density(mtcars$mpg)
⚫ >plot(d, main="Kernel Density of Miles Per Gallon")
⚫ >polygon(d, col="red", border="blue")
 Kernel Density of Miles Per Gallon
0.00 0.01 0.02 0.03 0.04 0.05 0.06 0.07
Density

10 20 30 40

N = 32 Bandwidth = 2.477
⚫ boxplot(X) is a plot that, if X is a vector, the vector
elements are the heights of the bars in the plot, if X is a
matrix, the matrix columns are the heights of the bars
in the plot, stacked after the first bar (column)

⚫ If the argument beside=TRUE, then the values in each

column are juxtaposed, not stacked.

⚫ The argument horiz=TRUE creates an horizontal

barplot.
⚫ > simple barplot
⚫ > barplot (VADeaths[,"Rural Male"])

60
50
40
30
20
10
0

50-54 55-59 60-64 65-69 70-74

⚫ # stacked barplots
 barplot(VADeaths[,c("Rural Male", "Rural Female")])

150
100
50
0

Rural Male Rural Female

⚫ > # juxtaposed barplots
⚫ > barplot(VADeaths [,c("Rural Male", "Rural
Female")],beside=T)

60
50
40
30
20
10
0

Rural Male Rural Female

>H <- c(7,12,28,3,41)
>M <- c("Mar","Apr","May","Jun","Jul")
>barplot(H,names.arg = M,xlab = "Month",ylab =
"Revenue",col="blue",main = "Revenue chart")
R even u e chart

40
30
Revenue

20
10
0

Mar Apr May Jun Jul

Month
Example :-
>colors <- c("green","orange","brown")
>months <- c("Mar","Apr","May","Jun","Jul")
>regions <- c("East","West","North")
>Values <-
matrix(c(2,9,3,11,9,4,8,7,3,12,5,2,8,10,11),nrow = 3,ncol
= 5,byrow =TRUE)
>barplot(Values,main = "total revenue",names.arg =
months,xlab = "month",ylab = "revenue",col=colors)
>legend("topleft", regions, cex = 1.3, fill = colors)
 total r e v e n u e

30
East
West
25

North
20
revenue

15
10
5
0

Mar A pr May Jun Jul

month
⚫ # Simple Dotplot
>dotchart(mtcars$mpg,labels=row.names(mtcars),cex=.7,
main="Gas Milage for Car Models",xlab="Miles Per
Gallon")
⚫ # Dotplot: Grouped Sorted and Colored
⚫ # Sort by mpg, group and color by cylinder
⚫ >x <- mtcars[order(mtcars$mpg),] # sort by mpg
⚫ >x$cyl <- factor(x$cyl) # it must be a factor
⚫ >x$color[x$cyl==4] <- "red"
⚫ >x$color[x$cyl==6] <- "blue"
⚫ >x$color[x$cyl==8] <- "darkgreen"
⚫ >dotchart(x$mpg,labels=row.names(x),cex=.7,groups=
x$cyl,main="Gas Milage for Car Models\ngrouped by
cylinder",xlab="Miles Per Gallon",gcolor="black",
color=x$color)
 G a s M i l a g e for C a r M o d e l s
g r o u p e d b y c y linde r

4
T o yo t a Corolla
Fiat 128
Lotus E uropa
H o nd a Civic
Fiat X 1 - 9
P o r sc he 9 1 4 - 2
Merc 2 4 0 D
Merc 230
D a t sun 710
T o yo t a C orona
V o l vo 1 4 2 E
6
H ornet 4 D rive
Mazda RX4 W ag
M a z d a RX4
Ferrari Dino
Merc 280
Valiant
Merc 2 8 0 C

8
Pontiac Firebird
H ornet S portabout
Merc 4 5 0 S L
Merc 4 5 0 S E
F o r d P antera L
D o d g e Challenger
A M C Javelin
Merc 4 5 0 S L C
Maserati B ora
C hrysle r Imperial
D uster 360
C am aro Z 2 8
Lincoln Continental
Cadillac Fleetw ood

10 15 20 25 30

Miles Per Gallon

⚫ Pie
⚫ pie(x) draws a circle (pie) cut into segments (slices), each slice
represents a unique value from the elements of x and the sixe of the
slice and the relative frequency of each unique value is represented
by the size of t
# simple pie
>pie(unique(mtcars$cyl), labels = unique(mtcars$cyl), main="Pie Chart of
N. of cylinders") # pie with percentages and colors
>with(mtcars, {
>n.cyl <- unique(cyl)
>percent.cyl <-round(table(cyl)/dim(mtcars)[1]*100,2)
>lbls <- paste(n.cyl," cyl=",percent.cyl,"%", sep="")
>pie(n.cyl, labels = lbls , main="Pie Chart of N. of cylinders",
col=rainbow(length(lbls)))})
 P i e C h a r t o f N. o f c y l i n d e r s

6 cyl=34. 38%

4 cyl=21.88%

8 cyl=43. 75%
>x <- c(21, 62, 10, 53)
>labels <- c("London", "New York", "Singapore",
"Mumbai")
>pie(x,labels)

New York

London

Singapore

Mumbai
>x = c(21, 62, 10, 53)
>labels = c("London", "New York", "Singapore",
"Mumbai")
>pie(x, labels, main = "City pie chart", col =
rainbow(length(x)))
C it y pie c h a r t

N e w York

L o nd o n

S i ng a p o r e

M um b a i
>x <- c(21, 62, 10,53)
>labels <- c("London","New York“ ,"Singapore“ ,"Mumbai" )
>piepercent<- round(100*x/sum(x), 1)
>pie(x, labels = piepercent, main = "City pie chart",col =
rainbow(length(x)))
>legend("topright", c("London","New York","Singapore",
"Mumbai"), cex = 0.8,fill = rainbow(length(x)))
C it y pie c h a r t

London
N ew York
Singap ore
42.5 Mumb ai

14.4

6.8

36.3
⚫ histogram
⚫ hist(X) is an histogram, a bar plot with the frequencies of the values
in X on the y-axis and the ranges of values on the x-axis
⚫ A cumulative distribution curve is the proportion of X on the y-
axis, up to the current position on the x-axis

⚫ > # simple histogram

⚫ > hist(faithful$waiting)
 H i s t o g r a m o f faithful$waiting

50
40
Frequency

30
20
10
0

40 50 60 70 80 90 100

faithful$waiting
# draw the histogram
>hist(faithful$waiting, prob =TRUE, xlim=range(xx) , border =
"gray" , col="gray90")
# adds the frequency polygon
>lines(xx, yy, lwd=2, col = "royalblue")
⚫ boxplot
boxplot(X) is a box-and-whisker plot with the values of variable X,
this is an effective way to summarize larger datasets.

# Boxplot of MPG by Car Cylinders

> boxplot(mpg~cyl,data=mtcars, main="Car Milage
Data",xlab="Number of Cylinders", ylab="Miles Per
Gallon")
 Car Milage Data

30
Miles Per Gallon

25
20
15
10

4 6 8

Number of Cylinders
⚫ Pairs
⚫ pairs() shows a matrix with all the scatterplots for the columns of
variable X

⚫ pairs(~mpg+disp+drat+wt,data=mtcars,
main="Scatterplot Matrix MPG, Displacement,Rear
axle ratio,Weight")
Scatterplot M atri x M P G , Di sp l acem en t, Rear axle ratio, W ei g h
100 300 2 3 4 5

30
mpg

20
10
300

disp
100

5.0
4.0
d ra t

3.0
5
4

wt
3
2

10 20 30 3.0 4.0 5.0

⚫ Contour
⚫ contour(X,Y,Z) draws a contour plot, with vector X for the rows,
vectorY for the columns and matrix X for the data
>x <- 10*(1:nrow(volcano)); x.at <- seq(100, 800, by=100)
>y <- 10*(1:ncol(volcano)); y.at <- seq(100, 600, by=100)
# Using Terrain Colors
>image(x, y, volcano, col=terrain.colors(100),axes=FALSE)
>contour(x, y, volcano, levels=seq(90, 200, by=5), add=TRUE,
col="brown")
>axis(1, at=x.at)
>axis(2, at=y.at)
>box()
>title(main="Maunga Whau Volcano", sub =
"col=terrain.colors(100)", font.main=4)
 Mau n g a Whau Volcano

600
500 110

155
400
300
y

200

180

140
100

135
125
120

100 200 300 400 500 600 700 800

x
c o l= t e r r a i n . c o lo r s ( 1 0 0 )
⚫ Persp
persp(X,Y,Z) draws a 3d graph, with vector X for the rows, vectorY
for the columns and matrix X for the data

# # (2) Visualizing a simple DEM model

>z <- 2 * volcano # Exaggerate the relief
>x <- 10 * (1:nrow(z)) # 10 meter spacing (S to N)
>y <- 10 * (1:ncol(z)) # 10 meter spacing (E to W)
>persp(x, y, z, theta = 120, phi = 15, scale = FALSE, axes =
FALSE)
⚫ Tables
Example:
> library(MASS)
>ships
> table(ships$type)

>table(ships$type,ships$year)
Example :-
>library(MASS)
>USArrests
>table(USArrests[,3])
>table(cut(USArrests[,3],pretty(USArrests[,3])))

Example :-
> airquality
> table(airquality[,4],airquality[,5])
>table(cut(airquality[,4],pretty(airquality[,4])),
airquality[,5])
Example :-

> library(MASS)
> cars