Galgotias College of Engineering & Technology

Affiliated to Dr. A.P.J. Abdul Kalam Technical University, Lucknow

Department of Computer Science & Engineering

INRODUCTION TO DATA ANALYTICS AND

VISUALIZATION LAB FILE
(KDS-551)

Name HIMANSHU UPADHYAY

Roll No. 2100971549003

Section CS-DS (V SEM)

Batch (D1/D2) D1

Submitted by
PRAMIT KUMAR SAMANT
 INDEX
Experiment Experiment Name Date of Date of Grade Faculty
No. Conduction Submission Signature

PROGRAMMED BY- HIMANSHU UPADHYAY

 PROGRAM-1
OBJECTIVE-To get the input from user and perform numerical operations
(MAX, MIN, AVG, SUM, SQRT, ROUND) using in R.

Program-
#Create a Vector
> data=c(23,4,56,21,34,56,73)
> #Get the maximum value
> print(max(data))
[1] 73
> #Get the minimum value
> print(min(data))
[1] 4
> #Get the SUM-
> sum(data)
[1] 267
> #Get the AVG-
> print(mean(data))
[1] 38.14286
> #Get the SQRT-
> a=5
> print(sqrt(a))
[1] 2.236068
> a=5.2
> #Get the ROUND-
> print(round(a))
[1] 5

PROGRAMMED BY- HIMANSHU UPADHYAY

Sample Output-

MAX & MIN-

SUM & AVG-

SQRT & ROUND-

PROGRAMMED BY- HIMANSHU UPADHYAY

 PROGRAM-2
OBJECTIVE- To perform data import/export (.CSV, .XLS, .TXT) operations using
data frames in R.

Program-
#.CSV
> read.data<-read.csv("C:/Users/sidsh/OneDrive/Desktop/College Work/5th-
Semester/D.A.V Lab/business-financial-data-june-2023-quarter-csv.csv")
> print(read.data)

#.XLS
> install.packages("readxl")
> library(readxl)
> excel_data <-
read_excel("C:/Users/sidsh/Downloads/file_example_XLS_10.xls")
> print(excel_data)

#.TXT
> txt_data <- read.table("C:/Users/sidsh/OneDrive/Desktop/R_Language.txt",
header = TRUE, sep = "\t")
> print(excel_data)

PROGRAMMED BY- HIMANSHU UPADHYAY

Sample Output-
CSV FILE-

XML FILE-

TXT FILE-

PROGRAMMED BY- HIMANSHU UPADHYAY

 PROGRAM-3

OBJECTIVE- To get the input matrix from user and perform Matrix addition,
subtraction, multiplication, inverse transpose and division operations using
vector concept in R.
Program-
#MATRIX CREATION
> {r = readline("Enter the number of rows:")}
> r = as.integer(r)
> {c = readline("Enter the number of columns:")}
> c = as.integer(c)
#MTRIX VALUES:
> A = scan()
> B = scan()
> M1 = matrix(A,nrow = r,ncol = c,byrow = TRUE)
> M2 = matrix(B,nrow = r,ncol = c,byrow = TRUE)
#MATRIX M1:
> print(M1)
#MATRIX M2:
> print(M2)
#1.ADDITION-
> print(M1+M2)
#2.SUBTRACTION-
>print(M1-M2)
#3.MULTIPLICATION-
>print(M1*M2)

PROGRAMMED BY- HIMANSHU UPADHYAY

Sample Output-

PROGRAMMED BY- HIMANSHU UPADHYAY

 PROGRAM-4

OBJECTIVE- To perform statistical operations (Mean, Median, Mode and

Standard deviation) using R.

Program-
# DEFINING VECTOR
> a=c(23,84,16,95,23,6,41,29,6,4,6)
#1.MEAN-
> print(mean(a))
#2.MEDIAN-
> print(median(a))
#3.MODE-
> getmode <- function(a) {
uniqv <- unique(a)
uniqv[which.max(tabulate(match(a, uniqv)))]
}
> print(getmode(a))
#4.STANDARD DEVIATION-
> print(sd(a))

PROGRAMMED BY- HIMANSHU UPADHYAY

Sample Output-

PROGRAM-5
PROGRAMMED BY- HIMANSHU UPADHYAY
OBJECTIVE- To perform data pre-processing operation (1) Handle mining data
(2) Min-Max normalization

Program-
#Handle Mining Data-
x = c(NA,3,4,NA,NA,NA)
is.na(x)
x = c(NA,3 4,NA,NA,0/0,0/0)
is. nan (x)

#Min-Max Normlization-
install.packages("caret")
library(caret)
data = data.frame(Var1 = c(120, 345, 145, 522, 596, 285, 21), Var2 = c(10,
15, 45, 22, 53, 28, 12), Var3 = c(-34, 0.05, 0-15, 0-12, -6, 0·85, 0.11))

#Creating Function To Implement Min-Max Scaling-

MinMax = function (x) {(x-min(x))/(max(x)-min(x))}

#Normalize Data Using Custom Function-

Normalized_My_Data = as.data.frame(apply(data, 1, MinMax))
head(Normalized_My_Data)

#Checking Summary After Normalization-

>summary (Normalized_My_Data)

Sample Output-

PROGRAMMED BY- HIMANSHU UPADHYAY

PROGRAMMED BY- HIMANSHU UPADHYAY
 PROGRAM-6
OBJECTIVE- To perform dimensionality reduction operation using PCA for
houses data set in R.

Program-
> data("USArrests")
> rawdf <- na.omit(USArrests)
> names(rawdf)=c("Murder","Assault", "Assasination”, "UrbanPop")
> head(rawdf)
> arrests.pca <- prcomp(scale(USArrests),center = TRUE)

#Checking output of pca. prcomp function returns standard deviation

(sdev), rotation and loadings-

> names(arrests.pca)
> print(arrests.pca)
> summary(arrests.pca)
> pcaCharts(arrests.pca)
> biplot(arrests.pca,scale=0, cex=.7)
> pca.out <- arrests.pca
> pca.out$rotation <- -pca.out$rotation
> pca.out$x <- -pca.out$x
> biplot(pca.out,scale=0, cex=.7)
> pca.out$rotation[,1:2]

Sample Output-

PROGRAMMED BY- HIMANSHU UPADHYAY

PROGRAMMED BY- HIMANSHU UPADHYAY
 PROGRAM-7
OBJECTIVE- To perform single linear regression with R.

Program-
#Create the predictor and response variable:

PROGRAMMED BY- HIMANSHU UPADHYAY

> x <- c(151, 174, 138, 186, 128, 136, 179, 163, 152, 131)
> y <- c(63, 81, 56, 91, 47, 57, 76, 72, 62, 48)
> relation <- lm(y~x)

#Give the chart file a name:

> png(file = "linearregression.png")

#Plot the chart:

> plot(y,x,col = "blue",main = "Height & Weight Regression",
abline(lm(x~y)),cex = 1.3,pch = 16,xlab = "Weight in Kg",ylab = "Height in
cm")

#Save the file:

> dev.off()

Sample Output-

PROGRAMMED BY- HIMANSHU UPADHYAY

PROGRAMMED BY- HIMANSHU UPADHYAY
 PROGRAM – 8

OBJECTIVE – To perform market basket analysis / Apriori algorithm on given

data set.
Program –
library(arules)

library(arulesViz)

library(RColorBrewer)

data("Groceries")

rules <- apriori(Groceries, parameter = list(supp = 0.01, conf = 0.2))

inspect(rules[1:10])

arules::itemFrequencyPlot(Groceries, topN = 20,

col = brewer.pal(8, 'Pastel2'),

main = 'Relative Item Frequency Plot',

type = "relative",

ylab = "Item Frequency (Relative)")

Output –

PROGRAMMED BY- HIMANSHU UPADHYAY

 Galgotias College of Engineering & Technology
Affiliated to Dr. A.P.J. Abdul Kalam Technical University, Lucknow

Department of Computer Science & Engineering

INRODUCTION TO DATA ANALYTICS AND

VISUALIZATION LAB FILE
(KDS-551)

Name SIDDHARTH SHARMA

Roll No. 2100971540058

Section CS-DS (V SEM)

Batch (D1/D2) D2

PROGRAMMED BY- HIMANSHU UPADHYAY

 INDEX
Experiment Experiment Name Date of Date of Grade Faculty
No. Conduction Submission Signature

PROGRAMMED BY- HIMANSHU UPADHYAY

 PROGRAM-1
OBJECTIVE-To get the input from user and perform numerical operations (MAX, MIN, AVG,
SUM, SQRT, ROUND) using in R.

Program-
#Create a Vector

> data=c(23,4,56,21,34,56,73)

> #Get the maximum value

> print(max(data))

[1] 73

> #Get the minimum value

> print(min(data))

[1] 4

> #Get the SUM-

> sum(data)

[1] 267

> #Get the AVG-

> print(mean(data))

[1] 38.14286

> #Get the SQRT-

> a=5

> print(sqrt(a))

[1] 2.236068

> a=5.2

> #Get the ROUND-

> print(round(a))

[1] 5

PROGRAMMED BY- HIMANSHU UPADHYAY

Sample Output-

MAX & MIN-

SUM & AVG-

SQRT & ROUND-

PROGRAMMED BY- HIMANSHU UPADHYAY

 PROGRAM-2
OBJECTIVE- To perform data import/export (.CSV, .XLS, .TXT) operations using data frames in
R.

Program-
#.CSV
> read.data<-read.csv("C:/Users/sidsh/OneDrive/Desktop/College Work/5th-
Semester/D.A.V Lab/business-financial-data-june-2023-quarter-csv.csv")
> print(read.data)

#.XLS
> install.packages("readxl")
> library(readxl)
> excel_data <-
read_excel("C:/Users/sidsh/Downloads/file_example_XLS_10.xls")
> print(excel_data)

#.TXT
> txt_data <- read.table("C:/Users/sidsh/OneDrive/Desktop/R_Language.txt",
header = TRUE, sep = "\t")
> print(excel_data)

PROGRAMMED BY- HIMANSHU UPADHYAY

Sample Output-

PROGRAMMED BY- HIMANSHU UPADHYAY

CSV FILE-

XML FILE-

TXT FILE-

PROGRAMMED BY- HIMANSHU UPADHYAY

 PROGRAM-3
OBJECTIVE- To get the input matrix from user and perform Matrix addition, subtraction,
multiplication, inverse transpose and division operations using vector concept in R.

Program-
#MATRIX CREATION
> {r = readline("Enter the number of rows:")}
> r = as.integer(r)
> {c = readline("Enter the number of columns:")}
> c = as.integer(c)
#MTRIX VALUES:
> A = scan()
> B = scan()
> M1 = matrix(A,nrow = r,ncol = c,byrow = TRUE)
> M2 = matrix(B,nrow = r,ncol = c,byrow = TRUE)
#MATRIX M1:
> print(M1)
#MATRIX M2:
> print(M2)
#1.ADDITION-
> print(M1+M2)
#2.SUBTRACTION-
>print(M1-M2)
#3.MULTIPLICATION-
>print(M1*M2)

PROGRAMMED BY- HIMANSHU UPADHYAY

Sample Output-

PROGRAMMED BY- HIMANSHU UPADHYAY

 PROGRAM-4
OBJECTIVE- To perform statistical operations (Mean, Median, Mode and Standard deviation)
using R.

Program-
# DEFINING VECTOR
> a=c(23,84,16,95,23,6,41,29,6,4,6)
#1.MEAN-
> print(mean(a))
#2.MEDIAN-
> print(median(a))
#3.MODE-
> getmode <- function(a) {
uniqv <- unique(a)
uniqv[which.max(tabulate(match(a, uniqv)))]
}
> print(getmode(a))
#4.STANDARD DEVIATION-
> print(sd(a))

Sample Output-

PROGRAMMED BY- HIMANSHU UPADHYAY

 PROGRAM-5
OBJECTIVE- To perform data pre-processing operation (1) Handle mining data (2) Min-Max
normalization

Program-
#Handle Mining Data-
x = c(NA,3,4,NA,NA,NA)
is.na(x)
x = c(NA,3 4,NA,NA,0/0,0/0)
is. nan (x)

#Min-Max Normlization-
install.packages("caret")
library(caret)
data = data.frame(Var1 = c(120, 345, 145, 522, 596, 285, 21), Var2 = c(10,
15, 45, 22, 53, 28, 12), Var3 = c(-34, 0.05, 0-15, 0-12, -6, 0·85, 0.11))

#Creating Function To Implement Min-Max Scaling-

MinMax = function (x) {(x-min(x))/(max(x)-min(x))}

PROGRAMMED BY- HIMANSHU UPADHYAY

#Normalize Data Using Custom Function-
Normalized_My_Data = as.data.frame(apply(data, 1, MinMax))
head(Normalized_My_Data)

#Checking Summary After Normalization-

>summary (Normalized_My_Data)

Sample Output-

PROGRAMMED BY- HIMANSHU UPADHYAY

 PROGRAM-6
OBJECTIVE- To perform dimensionality reduction operation using PCA for houses data set in
R.

Program-
> data("USArrests")

PROGRAMMED BY- HIMANSHU UPADHYAY

> rawdf <- na.omit(USArrests)
> names(rawdf)=c("Murder","Assault", "Assasination”, "UrbanPop")
> head(rawdf)
> arrests.pca <- prcomp(scale(USArrests),center = TRUE)

#Checking output of pca. prcomp function returns standard deviation

(sdev), rotation and loadings-

> names(arrests.pca)
> print(arrests.pca)
> summary(arrests.pca)
> pcaCharts(arrests.pca)
> biplot(arrests.pca,scale=0, cex=.7)
> pca.out <- arrests.pca
> pca.out$rotation <- -pca.out$rotation
> pca.out$x <- -pca.out$x
> biplot(pca.out,scale=0, cex=.7)
> pca.out$rotation[,1:2]

Sample Output-

PROGRAMMED BY- HIMANSHU UPADHYAY

PROGRAMMED BY- HIMANSHU UPADHYAY
 PROGRAM-7
OBJECTIVE- To perform single linear regression with R.

Program-
#Create the predictor and response variable:
> x <- c(151, 174, 138, 186, 128, 136, 179, 163, 152, 131)
> y <- c(63, 81, 56, 91, 47, 57, 76, 72, 62, 48)
> relation <- lm(y~x)
#Give the chart file a name:
> png(file = "linearregression.png")
#Plot the chart:
> plot(y,x,col = "blue",main = "Height & Weight Regression",
abline(lm(x~y)),cex = 1.3,pch = 16,xlab = "Weight in Kg",ylab = "Height in
cm")
#Save the file:
> dev.off()

Sample Output-

PROGRAMMED BY- HIMANSHU UPADHYAY

 PROGRAM – 8

OBJECTIVE – To perform market basket analysis / Apriori algorithm on given

data set.
Program –
library(arules)

library(arulesViz)

library(RColorBrewer)

data("Groceries")

rules <- apriori(Groceries, parameter = list(supp = 0.01, conf = 0.2))

inspect(rules[1:10])

arules::itemFrequencyPlot(Groceries, topN = 20,

col = brewer.pal(8, 'Pastel2'),

main = 'Relative Item Frequency Plot',

type = "relative",

ylab = "Item Frequency (Relative)")

Output –

PROGRAMMED BY- HIMANSHU UPADHYAY

PROGRAMMED BY- HIMANSHU UPADHYAY
 PROGRAM-9
OBJECTIVE- To perform K-means clustering operation and visualize for iris data
set.

Program-
>install.packages(“stats”)

>install.packages(“cluster”)

>install.packages(“ClusterR”)

>library(stats)

>library(cluster)

>library(ClusterR)

> # Removing initial label of

> # Species from original dataset

> iris_1 <- iris[, -5]

> # Fitting K-Means clustering Model

> # to training dataset

> set.seed(240) # Setting seed

> kmeans.re <- kmeans(iris_1, centers = 3, nstart = 20)

> kmeans.re

> # Cluster identification for

> # each observation

> kmeans.re$cluster

> # Confusion Matrix

> cm <- table(iris$Species, kmeans.re$cluster)

> cm

> # Model Evaluation and visualization

> plot(iris_1[c("Sepal.Length", "Sepal.Width")])

> plot(iris_1[c("Sepal.Length", "Sepal.Width")],

+ col = kmeans.re$cluster)

> plot(iris_1[c("Sepal.Length", "Sepal.Width")],

+ col = kmeans.re$cluster,

PROGRAMMED BY- HIMANSHU UPADHYAY

+ main = "K-means with 3 clusters")

> ## Plotiing cluster centers

> kmeans.re$centers

> kmeans.re$centers[, c("Sepal.Length", "Sepal.Width")]

> # cex is font size, pch is symbol

> points(kmeans.re$centers[, c("Sepal.Length", "Sepal.Width")],

+ col = 1:3, pch = 8, cex = 3)

> ## Visualizing clusters

> y_kmeans <- kmeans.re$cluster

> clusplot(iris_1[, c("Sepal.Length", "Sepal.Width")],

+ y_kmeans,

+ lines = 0,

+ shade = TRUE,

+ color = TRUE,

+ labels = 2,

+ plotchar = FALSE,

+ span = TRUE,

+ main = paste("Cluster iris"),

+ xlab = 'Sepal.Length',

+ ylab = 'Sepal.Width')

Sample Output-

PROGRAMMED BY- HIMANSHU UPADHYAY

PROGRAMMED BY- HIMANSHU UPADHYAY
 PROGRAM-10
OBJECTIVE- Write R script to diagnose any disease using KNN classification and
plot the results.

Program-
>install.packages("class")

>install.packages("ggplot2")

>library(class)

>library(ggplot2)

>features <- iris[, c("Sepal.Length", "Sepal.Width")]

>diagnosis <- rep(c("Healthy", "Diseased"), each = 75)

>train_indices <- sample(1:nrow(diagnosis_data), 0.7 * >nrow(diagnosis_data))

>train_data <- diagnosis_data[train_indices, ]

>test_data <- diagnosis_data[-train_indices, ]

>k <- 3

>predicted_labels <- knn(train = train_data[, 1:2], test = test_data[, 1:2], cl = train_data$Diagnosis, k

= k)

>results <- data.frame(Actual = test_data$Diagnosis, Predicted = predicted_labels)

>print("Actual vs. Predicted:")

>print(results)

>ggplot(results, aes(x = Actual, fill = Predicted)) +

geom_bar(position = "dodge", color = "black", stat = "count") +

labs(title = "Disease Diagnosis Results",

x = "Actual Diagnosis",

y = "Count",

fill = "Predicted Diagnosis") +

theme_minimal()

PROGRAMMED BY- HIMANSHU UPADHYAY

Sample Output-

PROGRAMMED BY- HIMANSHU UPADHYAY

 PROGRAM-11
OBJECTIVE- : To convert the following dataset into bar.

Program-
> library(ggplot2)

> feature1 <- c(1,2,2,5,8,8,9,11)

> feature2 <- c(1,3,4,3,6,7,2,12) class <- c(1,1,1,1,2,2,2,3)

> circle <- data.frame(feature1,feature2,class)

> barplot(as.matrix(circle), main="Bar Plots", ylab="Serial_no", beside=TRUE)

Sample Output-

PROGRAMMED BY- HIMANSHU UPADHYAY

 PROGRAM-12
OBJECTIVE- : WAP to print Decision tree in R for the data set Reading Skills.

Program-
> install packages(“party”)

> library(party)

> print(head(readingSkill))

> inpu.dat <- readingSkill[c(1:105)]

> png(file= “ecision_tree.png”)

> output.tree <- ctree(nativeSpeaker ~ age + shoeSize + score, data=input.dat)

>plot(output.tree)

>dev.off()

Sample Output-

PROGRAMMED BY- HIMANSHU UPADHYAY

PROGRAMMED BY- HIMANSHU UPADHYAY
PROGRAMMED BY- HIMANSHU UPADHYAY
 PROGRAM-12
OBJECTIVE- : WAP to print Decision tree in R for the data set Reading Skills.

Program-
> install packages(“party”)

> library(party)

> print(head(readingSkill))

> inpu.dat <- readingSkill[c(1:105)]

> png(file= “ecision_tree.png”)

> output.tree <- ctree(nativeSpeaker ~ age + shoeSize + score, data=input.dat)

>plot(output.tree)

>dev.off()

Sample Output-

PROGRAMMED BY- HIMANSHU UPADHYAY

PROGRAMMED BY- HIMANSHU UPADHYAY