AffiliatedtoDr.A.P.J.

AbdulKalamTechnicalUniversity,Lucknow,UttarPradesh

PRACTICAL FILE

PROGRAM:- MBA(BUSINESS ANALYTICS)

SEMESTER-1

ACADEMIC YEAR:- 2022-2023

SUBJECT:- BASICS OFDATA MANAGEMENT WITH “R”

SUBJECT CODE:- KMBA152

SUBMITTED BY:- SUBMITTED TO:-

AKANKSHA KUMARI MS.NEETU SINGH
 INDEX

Sr. No. TOPICS T SIGN COMMENTS

1 Learn the basics of R Syntax

1.1 R Script for Arithmetic Operators

1.2 R Script for Logical Operators

1.3 R Script for Relational Operators.

1.4 R Script for Conditional Statements.

1.5 R Scripts for Looping.

1.6 R Scripts for User-Defined Functions.

1.7 R Scripts for Data Frames

2 Learn how to organize and modify data in R using data

frames and dplyr

2.1 R Script for Data Manipulation with the help of

dplyr(filter,distinct,arrange,select,rename,mutate,trans
mutate,summarize) functions

2.2 R Script for Data Manipulation with the help of tidyr

package(gather,separate,unite,spread) functions

3 Learn how to prepare data for analysis in R using dplyr

and tidyr
 INDEX

Sr. No. TOPICS T SIGN COMMENTS

4 Learn the basics of how to create visualizations using

the popular R package ggplot2

4.1 R Script for Summary of Data Set

4.2 R Script for Data Layers

4.3 R Script for Aesthetic Layer

4.4 R Script for Geometric Layer

4.5 R Script for Adding Size,Colour and Shape

4.6 R Script for Histogram Plot

4.7 R Script for Facet Layer

4.8 R Script for Statistics Layer

4.9 R Script for Coordinates Layer

4.10 R Script for Coord_cartesian()

4.11 R Script for Theme Layer

5 Learn the basics of aggregate functions in R with dplyr,

which let us calculate quantities that describe groups of
data

5.1 R script to create with 4 columns and group with

subjects and get the aggregates like minimum, sum, and
maximum.

5.2 R Script to create with 4 columns and group with

 subjects and get the average (mean)

Sr. No. TOPICS T SIGN COMMENTS

6 Learn the basics of joining tables together in R with

dplyr

6.1 R Script for Inner Join

6.2 R Script for Left Join

6.3 R Script for Right Join

6.4 R Script for Full Join

6.5 R Script for Semi Join

6.6 R Script for Anti Join

7 Learn to use R or manually calculate the mean, median,

and mode of real-world datasets

7.1 R Script for importing data using read.csv and find

mean,median and mode value.

8 Learn how to quantify the spread of the dataset

by calculating the variance and standard
deviation in R
# R Arithmetic Operators Example for integers

INPUT:
a <- 7.5
b <- 2

print ( a+b ) #addition

print ( a-b ) #subtraction
print ( a*b ) #multiplication
print ( a/b ) #Division
print ( a%%b ) #Reminder
print ( a%/%b ) #Quotient
print ( a^b ) #Power of

OUTPUT:

INPUT:

# R Operators - R Logical Operators Example for basic logical elements

a <- 0 # logical FALSE

b <- 2 # logical TRUE

print ( a & b ) # logical AND element wise

print ( a | b ) # logical OR element wise
print ( !a ) # logical NOT element wise
print ( a && b ) # logical AND consolidated for all elementsprint( a || b ) #
logical OR consolidated for all elements

OUTPUT:

INPUT:

# R Operators - R Relational Operators Example for Numbers

a <- c(7.5, 3, 5)

b <- c(2, 7, 0)
print ( a<b ) # less than

print ( a>b ) # greater than

print ( a==b ) # equal to

print ( a<=b ) # less than or equal to

print ( a>=b ) # greater than or equal to

OUTPUT:

print ( a!=b ) # not equal to

INPUT:

# R scripts for conditional Statements

x <- -3
if (x < 0) {
print("x is a negative number")
}
OUTPUT:
INPUT:

R Scripts For Looping:

# R program to demonstrate the use of for loop

# using for loop

for (valin1: 5)
{
# statement
print(val)
}

OUTPUT:

INPUT:

# R program to illustrate
# application of for loop

# assigning strings to the vector

week < - c('Sunday',
'Monday',
 'Tuesday',
'Wednesday',
'Thursday',
'Friday',
'Saturday')

# using for loop to iterate

# over each string in the vector
for (day inweek)
{

# displaying each string in the vector

print(day)
}

OUTPUT:

INPUT:
# R program to demonstrate the use of while loop

val = 1

# using while loop

while (val<= 5)
{
# statements
print(val)
val = val + 1
}

OUTPUT:

INPUT:
# R Scripts For User-Defined Functions

vec1 <- c(28,64,63,43,56,46,87,34,73)

vec2 <- c(53,37,29,45,68,33,76,49,30)

vec3 <- c(12,44,36,75,36,93,34,64,18)

vec1 <- ((vec1-min(vec1))/(max(vec1)-min(vec1)))

vec2 <- ((vec2-min(vec2))/(max(vec2)-min(vec2)))

vec3 <- ((vec3-min(vec3))/(max(vec3)-min(vec3)))

vec1

OUTPUT:

# R Scripts for Data Frames

# R program to create dataframe

# creating a data frame

friend.data<- data.frame(
friend_id = c(1:5),
friend_name = c("Sachin", "Sourav",
"Dravid", "Sehwag",
"Dhoni"),
stringsAsFactors = FALSE
)
# print the data frame
print(friend.data)

OUTPUT:
Learn how to organize and modify data in R using data frames and dplyr

.R Script for Data Manipulation With the help of dplyr package

(filter,distinct ,arrange, select, rename, mutate,trans mutate, summarize)functions

# import dplyr package

library(dplyr)

# create a data frame

stats <- data.frame(player=c('A', 'B', 'C', 'D'),
runs=c(100, 200, 408, 19),
wickets=c(17, 20, NA, 5))

# fetch players who scored more

# than 100 runs
filter(stats, runs>100)

OUTPUT:

# import dplyr package

library(dplyr)
# create a data frame
stats <- data.frame(player=c('A', 'B', 'C', 'D', 'A', 'A'),
runs=c(100, 200, 408, 19, 56, 100),
wickets=c(17, 20, NA, 5, 2, 17))

# removes duplicate rows

distinct(stats)
#remove duplicates based on a column
distinct(stats, player, .keep_all = TRUE)

OUTPUT:

# import dplyr package

library(dplyr)

# create a data frame

stats <- data.frame(player=c('A', 'B', 'C', 'D'),
runs=c(100, 200, 408, 19),
wickets=c(17, 20, NA, 5))

# ordered data based on runs

arrange(stats, runs)

OUTPUT:

# import dplyr package

library(dplyr)

# create a data frame

stats <- data.frame(player=c('A', 'B', 'C', 'D'),
runs=c(100, 200, 408, 19),
wickets=c(17, 20, NA, 5))

# fetch required column data

select(stats, player,wickets)

OUTPUT:

# import dplyr package

library(dplyr)

# create a data frame

stats <- data.frame(player=c('A', 'B', 'C', 'D'),
runs=c(100, 200, 408, 19),
wickets=c(17, 20, NA, 5))

# renaming the column

rename(stats, runs_scored=runs)
OUTPUT:

# import dplyr package

library(dplyr)

# create a data frame

stats <- data.frame(player=c('A', 'B', 'C', 'D'),
runs=c(100, 200, 408, 19),
wickets=c(17, 20, 7, 5))

# add new column avg

mutate(stats, avg=runs/4)

# drop all and create a new column

transmute(stats, avg=runs/4)

OUTPUT:

INPUT:
# import dplyr package
 library(dplyr)

# create a data frame

stats <- data.frame(player=c('A', 'B', 'C', 'D'),
runs=c(100, 200, 408, 19),
wickets=c(17, 20, 7, 5))

# summarize method
summarize(stats, sum(runs), mean(runs))

Output:

R Script for Data Manipulation With the help of tidyr Package

(Seprate, Unite, Spread) functions

INPUT:

# import tidyr package

library(tidyr)
long <- tidy_dataframe %>%
gather(Group, Frequency,
Group.1:Group.3)

# use separate() function to make data wider

separate_data<- long %>%
separate(Group, c("Allotment",
"Number"))

# print the wider format

separate_data

OUTPUT:

INPUT:

long <- tidy_dataframe %>%

gather(Group, Frequency,
Group.1:Group.3)
# use separate() function to make data wider
separate_data<- long %>%
separate(Group, c("Allotment",
"Number"))

# use unite() function to glue

# Allotment and Number columns
unite_data<- separate_data %>%
unite(Group, Allotment,
Number, sep = ".")

# print the new data frame

unite_data
OUTPUT:
INPUT:
# use unite() function to make data wider
back_to_wide<- unite_data %>%
spread(Group, Frequency)

# print the new data frame

back_to_wide
OUTPUT:
Learn the basics of how to create visualization using the popular R
package ggplot2
.R script for summary of data set

INPUT:

# Installing the package

install.packages("dplyr")

# Loading package
library(dplyr)

# Summary of dataset in package

summary(mtcars)

OUTPUT:
INPUT:
# Data Layer
ggplot(data = mtcars)
OUTPUT:
INPUT:
# Aesthetic Layer
ggplot(data = mtcars, aes(x = hp, y = mpg, col = disp))
OUTPUT:
INPUT:
# Geometric layer
ggplot(data = mtcars,
aes(x = hp, y = mpg, col = disp)) + geom_point()
INPUT:
# Facet Layer
p <- ggplot(data = mtcars,
aes(x = hp, y = mpg,
shape = factor(cyl))) + geom_point()

# Separate rows according to transmission type

p + facet_grid(am ~ .)

# Separate columns according to cylinders

p + facet_grid(. ~ cyl)
OUTPUT:
INPUT:

# Statistics layer
ggplot(data = mtcars, aes(x = hp, y = mpg)) +
geom_point() +
stat_smooth(method = lm, col = "red")

OUTPUT:
INPUT:
# Coordinates layer: Control plot dimensions
ggplot(data = mtcars, aes(x = wt, y = mpg)) +
geom_point() +
stat_smooth(method = lm, col = "red") +
scale_y_continuous("mpg", limits = c(2, 35),
expand = c(0, 0)) +
scale_x_continuous("wt", limits = c(0, 25),
expand = c(0, 0)) + coord_equal()
OUTPUT:
INPUT:
# Add coord_cartesian() to proper zoom in
ggplot(data = mtcars, aes(x = wt, y = hp, col = am)) +
geom_point() + geom_smooth() +
coord_cartesian(xlim = c(3, 6))

OUTPUT:
INPUT:
# Theme layer
ggplot(data = mtcars, aes(x = hp, y = mpg)) +
geom_point() + facet_grid(. ~ cyl) +
theme(plot.background = element_rect(
fill = "black", colour = "gray"))
OUTPUT:
Learn the basics of aggregate functions in R with dplyr, Which let us
calculate quantities that describe groups of data
.R Script Using aggregate function to summarize in one variable and
Group by one variable.

INPUT:
# create the dataframe with 4 columns
data = data.frame(subjects=c("java", "python", "java",
"java", "php", "php"),
id=c(1, 2, 3, 4, 5, 6),
names=c("manoj", "sai", "mounika",
"durga", "deepika", "roshan"),
marks=c(89, 89, 76, 89, 90, 67))

# get sum of marks by grouping with subjects

aggregate(marks~ subjects, data, FUN=sum)

OUTPUT:
INPUT: Multiple Value
# create the dataframe with 4 columns
data = data.frame(subjects=c("java", "python", "java",
"java", "php", "php"),
id=c(1, 2, 3, 4, 5, 6),
names=c("manoj", "sai", "mounika",
"durga", "deepika", "roshan"),
marks=c(89, 89, 76, 89, 90, 67))

# get sum of marks by grouping with subjects and names

aggregate(marks~ subjects+names, data, FUN=sum)

OUTPUT:
INPUT: Multiple Value and Group by one variable
# create the dataframe with 4 columns
data = data.frame(subjects=c("java", "python", "java",
"java", "php", "php"),
id=c(1, 2, 3, 4, 5, 6),
names=c("manoj", "sai", "mounika",
"durga", "deepika", "roshan"),
marks=c(89, 89, 76, 89, 90, 67))

# get sum of marks and id by grouping with subjects

aggregate(cbind(marks, id)~ subjects, data, FUN=sum)

OUTPUT:
INPUT: Multiple value and Group by multiple variable
# create the dataframe with 4 columns
data = data.frame(subjects=c("java", "python", "java",
"java", "php", "php"),
id=c(1, 2, 3, 4, 5, 6),
names=c("manoj", "sai", "mounika",
"durga", "deepika", "roshan"),
marks=c(89, 89, 76, 89, 90, 67))

# get sum of marks and id by grouping

# with subjects and names
aggregate(cbind(marks, id)~ subjects+names, data, FUN=sum)

OUTPUT:
Learn the basics of joining tables together in R with dplyr
R script for Inner Join
INPUT: R Script for inner join
# load the library
library("dplyr")

# create dataframe with 1 to 5 integers

gfg1 < -data.frame(ID=c(1: 5))

# create dataframe with 4 to 8 integers

gfg2 < -data.frame(ID=c(4: 8))

# perform inner join

inner_join(gfg1, gfg2, by="ID")

OUTPUT:
INPUT: R Script for Left Join
# load the library
library("dplyr")

# create the dataframes

gfg1<-data.frame(ID=c(1:5))

gfg2<-data.frame(ID=c(4:8))

# perform left join

left_join(gfg1,gfg2, by = "ID")

OUTPUT:
INPUT: Right Join
# load the library
library("dplyr")

# create dataframes
gfg1<-data.frame(ID=c(1:5))

gfg2<-data.frame(ID=c(4:8))

# perform right join

right_join(gfg1,gfg2, by = "ID")

OUTPUT:
INPUT: Full Join
# load library
library("dplyr")

# create dataframe
gfg1<-data.frame(ID=c(1:5))
gfg2<-data.frame(ID=c(4:8))

# perform full join

full_join(gfg1,gfg2, by = "ID")

OUTPUT:
INPUT: Semi Join
# load the library
library("dplyr")

# create the dataframes

gfg1<-data.frame(ID=c(1:5))
gfg2<-data.frame(ID=c(4:8))

# perform semijoin
semi_join(gfg1,gfg2, by = "ID")

OUTPUT:
INPUT: Anti Join
# load the library
library("dplyr")

# create the dataframes

gfg1<-data.frame(ID=c(1:5))
gfg2<-data.frame(ID=c(4:8))

# perform anti join

anti_join(gfg1,gfg2, by = "ID")

OUTPUT:
Learn to Use R Or manually Calculate the Mean, median, and mode of
real-world datasets
.R Script for importing data using read.CSV

INPUT:

# import and store the dataset in data1

data1 <- read.csv(file.choose(), header=T)

# display the data

data1

OUTPUT:
INPUT:R Script for importing data using read.csv and find mean,
median, and mode value

# R program to import data into R

# Import the data using read.csv()

myData = read.csv("CardioGoodFitness.csv",
stringsAsFactors=F)
# Print the first 6 rows
print(head(myData))

OUTPUT:
INPUT:
# R program to illustrate

# Descriptive Analysis

# Import the data using read.csv()

myData = read.csv("CardioGoodFitness.csv",
stringsAsFactors=F)

# Compute the mean value

mean = mean(myData$Age)
print(mean)

OUTPUT:
INPUT:
# Import the data using read.csv()
myData = read.csv("CardioGoodFitness.csv",
stringsAsFactors=F)

mode = function(){
return(sort(-table(myData$Age))[1])
}

mode()

OUTPUT:

INPUT:

# R program to illustrate
# Descriptive Analysis

# Import the library

library(modeest)

# Import the data using read.csv()

myData = read.csv("CardioGoodFitness.csv",
stringsAsFactors=F)

# Compute the mode value

mode = mfv(myData$Age)
print(mode)

OUTPUT: