Program -4 – VISUALIZATIONS

a.Find the data distributions using box and scatter plot.

Install.packages(“ggplot2”)

Library(ggplot2)

Input <- mtcars[,c('mpg','cyl')]

Input

Boxplot(mpg ~ cyl, data = mtcars, xlab = "number of cylinders", ylab = "miles per gallon", main =
"mileage data")

Dev.off()

Output :- mpg cyl

Mazda rx4

21.0 6

Mazda rx4 wag 21.0 6

Datsun 710

22.8 4

Hornet 4

drive 21.4 6

Hornet

sportabout

18.7 8

Valiant 18.1

6
b. Find the outliers using plot.

v=c(50,75,100,125,150,175,200)

boxplot(v)

c. Plot the histogram, bar chart and pie chart on sample data.

Histogram
library(graphics)

v <- c(9,13,21,8,36,22,12,41,31,33,19)

hist(v,xlab = "Weight",col = "blue",border = "green")

dev.off()

Output:

Bar chart

library(graphics)

H <- c(7,12,28,3,41)

M <- c("Jan","Feb","Mar","Apr","May")

barplot(H,names.arg = M,xlab = "Month",ylab = "Revenue",col = "blue",main = "Revenue chart",border =

"red")

dev.off()

output:
Pie Chart

library(graphics)

x <- c(21, 62, 10, 53)

labels<- c("London", "NewYork", "Singapore", "Mumbai")

pie(x,labels)

dev.off()

output:
Program-2: DESCRIPTIVE STATISTICS IN R
a. Write an R script to find basic descriptive statistics using summary

>mtcars

> summary(mtcars)

>str(mtcars)

>quantile(mtcars$mpg)

>cars

> summary(cars)

> class(cars)

Output:

[1] "data.frame"

>dim(cars)

Output:

[1] 50 2

> str(cars)

>quantile(cars$speed)

b. Write an R script to find subset of dataset by using subset (), aggregate ()

functions on iris dataset.
>aggregate(. ~ Species, data = iris, mean)

>subset(iris,iris$Sepal.Length==5.0)

Program-1:
c.Write Program make a simple calculator that can add, subtract, multiply and
divide using functions.
add <- function(x, y) {

return(x + y) }

subtract <- function(x, y) {

return(x - y) }

multiply <- function(x, y) {

return(x * y) }

divide <- function(x, y) {

return(x / y) }

print("Select operation.")

print("1.Add")

print("2.Subtract")

print("3.Multiply")

print("4.Divide")

choice = as.integer(readline(prompt="Enter choice[1/2/3/4]: "))

num1 = as.integer(readline(prompt="Enter first number: "))

num2 = as.integer(readline(prompt="Enter second number: "))

operator <- switch(choice,"+","-","*","/")

result <- switch(choice, add(num1, num2), subtract(num1, num2), multiply(num1, num2),

divide(num1, num2))

print(paste(num1, operator, num2, "=", result))

Program -3: READING A CSV FILE:

data <- read.csv("input.csv")

print(data)

Analyzing the CSV File:

data <- read.csv("input.csv")

print(is.data.frame(data))

print(ncol(data))

print(nrow(data))

Get the maximum salary:

# Create a data frame.

data <- read.csv("input.csv")

# Get the max salary from data frame.

sal <- max(data$salary)

print(sal)

Get the details of the person with max salary

# Create a data frame.

data <- read.csv("input.csv")

# Get the max salary from data frame.

sal <- max(data$salary)

# Get the person detail having max salary.

retval <- subset(data, salary == max(salary))

print(retval)

Get all the people working in IT department

# Create a data frame.

data <- read.csv("input.csv")

retval <- subset( data, dept == "IT")

print(retval)
Get the persons in IT department whose salary is greater than 600

# Create a data frame.

data <- read.csv("input.csv")

info <- subset(data, salary > 600 & dept == "IT")

print(info)

Get the people who joined on or after 2014

# Create a data frame.

data <- read.csv("input.csv")

retval <- subset(data, as.Date(start_date) > as.Date("2014-01-01"))

print(retval)

Writing into a CSV File

# Create a data frame.

data <- read.csv("input.csv")

retval <- subset(data, as.Date(start_date) > as.Date("2014-01-01"))

# Write filtered data into a new file.

write.csv(retval,"output.csv")

newdata <- read.csv("output.csv")

print(newdata)

Here the column X comes from the data set newper. This can be dropped using

additional parameters while writing the file.

# Create a data frame.

data <- read.csv("input.csv")

retval <- subset(data, as.Date(start_date) > as.Date("2014-01-01"))

# Write filtered data into a new file.

write.csv(retval,"output.csv", row.names = FALSE)

newdata <- read.csv("output.csv")

print(newdata)
b. Reading Excel data sheet in R.

Verify and Load the "xlsx" Package

# Verify the package is installed.

any(grepl("xlsx",installed.packages()))

# Load the library into R workspace.

library("xlsx")

Input as xlsx File

Reading the Excel File

# Read the first worksheet in the file input.xlsx.

Data <- read.xlsx(“input.xlsx”, sheetIndex = 1)

Print(data)

Or

Install.packages(“xlsx”)

Library(“xlsx”)

Data<- read.xlsx(“input.xlsx”, sheetIndex = 1)

Data

c. Reading XML dataset in R.

install.packages(“XML”)

Input Data

<RECORDS>

<EMPLOYEE>

<ID>1</ID>

<NAME>Rick</NAME>

<SALARY>623.3</SALARY>

<STARTDATE>1/1/2012</STARTDATE>

<DEPT>IT</DEPT>
</EMPLOYEE>

<EMPLOYEE>

<ID>2</ID>

<NAME>Dan</NAME>

<SALARY>515.2</SALARY>

<STARTDATE>9/23/2013</STARTDATE>

<DEPT>Operations</DEPT>

</EMPLOYEE>

<EMPLOYEE>

<ID>3</ID>

<NAME>Michelle</NAME>

<SALARY>611</SALARY>

<STARTDATE>11/15/2014</STARTDATE>

<DEPT>IT</DEPT>

</EMPLOYEE>

<EMPLOYEE>

<ID>4</ID>

<NAME>Ryan</NAME>

<SALARY>729</SALARY>

<STARTDATE>5/11/2014</STARTDATE>

<DEPT>HR</DEPT>

</EMPLOYEE>

<EMPLOYEE>

<ID>5</ID>

<NAME>Gary</NAME>

<SALARY>843.25</SALARY>

<STARTDATE>3/27/2015</STARTDATE>

<DEPT>Finance</DEPT>

</EMPLOYEE>
<EMPLOYEE>

<ID>6</ID>

<NAME>Nina</NAME>

<SALARY>578</SALARY>

<STARTDATE>5/21/2013</STARTDATE>

<DEPT>IT</DEPT>

</EMPLOYEE>

<EMPLOYEE>

<ID>7</ID>

<NAME>Simon</NAME>

<SALARY>632.8</SALARY>

<STARTDATE>7/30/2013</STARTDATE>

<DEPT>Operations</DEPT>

</EMPLOYEE>

<EMPLOYEE>

<ID>8</ID>

<NAME>Guru</NAME>

<SALARY>722.5</SALARY>

<STARTDATE>6/17/2014</STARTDATE>

<DEPT>Finance</DEPT>

</EMPLOYEE>

</RECORDS>
Reading XML File

# Load the package required to read XML files.

Library(“XML”)

# Also load the other required package.

Library(“methods”)

# Give the input file name to the function.

Result <- xmlParse(file = “input.xml”)

# Print the result.

Print(result)