EX1.

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

> a=scan()

1: 32

2: 23

3: 34

4: 67

5: 45

> sum(a)

[1] 201

> max(a)

[1] 67

> min(a)

[1] 23

> p=sqrt(a)

> print(p)

[1] 5.656854 4.795832 5.830952 8.185353 6.708204

> round(p)

[1] 6 5 6 8 7

> mean(a)

[1] 40.2
 EX2. To perform data import/export (.CSV, .XLS, .TXT) operations
using data frames in R.

#Data import from .CSV

# R program to read csv file using read.table()
x <- read.csv2("E://Data//myfile.csv", header = TRUE, sep=", ")
# print x
print(x)

Output:

Col1.Col2.Col3
1 100, a1, b1
2 200, a2, b2
3 300, a3, b3

#Data import from .txt

# Simple R program to read txt file
x<-read.table("D://Data//myfile.txt ", header=FALSE)

# print x
print(x)

Output:
V1 V2 V3
1 100 a1 b1
2 200 a2 b2
3 300 a3 b3
#Data import from .xls
# loading the library and other important packages
library("XML")
library("methods")

# the contents of sample.xml are parsed

data <- xmlParse(file = "sample.xml")

print(data)

Output:
1
Alia
620
IT
2
Brijesh
440
Commerce
3
Yash
600
Humanities
4
Mallika
660
IT
5
Zayn
560
IT
#Exporting data from R as .txt
#Creating a data frame
>df=data.frame("name"=c("xxxx","yyyy","zzzz"),
+"language"=c("R","python","java"),"age"=c(21,20,22))
>write.table(df,file="mydata.txt",sep="\t",row.names=TRUE,col.names=NA)

Output:
#Exporting data from R
# Creating a dataframe
df = data.frame( "Name" = c("Amiya", "Raj", "Asish"), "Language" = c("R", "Python",
"Java"), "Age" = c(22, 25, 45) )
# Export a data frame to a text file using write.table()
write.table(df,file = "myDataFrame.csv",sep = "\t",row.names = FALSE,)

Output
EX3. To get the input matrix from user and perform Matrix addition, subtraction,
multiplication, inverse transpose and division operations using vector concept in R.
#To create a matrix in R
>matrix (data, nrow, ncol, byrow, dim_name)
#To create matrix using R programming
>matrix1<-matrix(c(11, 13, 15, 12, 14, 16),nrow =2, ncol =3, byrow = TRUE)
>print(matrix1)
[,1] [,2] [,3]
[1,] 11 13 15
[2,] 12 14 16
#Arranging elements sequentially by row.
P <- matrix(c(5:16), nrow = 4, byrow = TRUE)
print(P)
[,1] [,2] [,3]
[1,] 5 6 7
[2,] 8 9 10
[3,] 11 12 13
[4,] 14 15 16
# Arranging elements sequentially by column.
Q <- matrix(c(3:14), nrow = 4, byrow = FALSE)
print(Q)
[,1] [,2] [,3]
[1,] 3 7 11
[2,] 4 8 12
[3,] 5 9 13
[4,] 6 10 14

# Defining the column and row names.

row_names = c("row1", "row2", "row3", "row4")
col_names = c("col1", "col2", "col3")
R <- matrix(c(3:14), nrow = 4, byrow = TRUE, dimnames = list(row_names, col_names))
print(R)

#To add

>Addition<-P+Q

>print(Addition)

col1 col2 col3

row1 8 10 12
row2 14 16 18
row3 20 22 24
row4 26 28 30
#Tosubtract
>subtraction<- Q-P

>print(subtraction)

[,1] [,2] [,3]

[1,] -2 1 4
[2,] -4 -1 2
[3,] -6 -3 0
[4,] -8 -5 -2
#To multiplication
>mul<-P*Q

>print(mul)

[,1] [,2] [,3]

[1,] 15 42 77
[2,] 32 72 120
[3,] 55 108 169
[4,] 84 150 224
#To Divide
>div<-P/Q
>print(div)
[,1] [,2] [,3]
[1,] 1.666667 0.8571429 0.6363636
[2,] 2.000000 1.1250000 0.8333333
[3,] 2.200000 1.3333333 1.0000000
[4,] 2.333333 1.5000000 1.1428571

#To inverse the matrix

> INV<-matrix(c(11, 13, 15, 12, 14, 16),nrow =2, ncol =2, byrow = TRUE)
>print(INV)
[,1] [,2]
[1,] 11 13
[2,] 15 12
> t<-solve(INV)
>print(t)
[,1] [,2]
[1,] -0.1904762 0.2063492
[2,] 0.2380952 -0.1746032

#To Transpose matrix

> A12<-t(INV)
>print(A12)
[,1] [,2]
[1,] 11 15
[2,] 13 12
EX4. To perform Association Rule Mining and Clustering using R.
a)Association rule mining
#loading required packages
> install.packages("arules")
> install.packages("arulesViz")
>library(arules)
>library(arulesViz)
>library(RColorBrewer)
#loading dataset
>a=data(Groceries)
>head(Groceries)
> itemFrequencyPlot(Groceries,topN=10,type='absolute')
> rule=apriori(Groceries,parameter = list(supp=0.001,conf=0.9))
Apriori
Parameter specification:
confidence minval smax arem aval originalSupport maxtime support minlen maxlen target
ext
0.9 0.1 1 none FALSE TRUE 5 0.001 1 10 rules TRUE

Algorithmic control:
filter tree heap memopt load sort verbose
0.1 TRUE TRUE FALSE TRUE 2 TRUE
Absolute minimum support count: 9
set item appearances ...[0 item(s)] done [0.00s].
set transactions ...[169 item(s), 9835 transaction(s)] done [0.00s].
sorting and recoding items ... [157 item(s)] done [0.00s].
creating transaction tree ... done [0.00s].
checking subsets of size 1 2 3 4 5 6 done [0.01s].
writing ... [129 rule(s)] done [0.00s].
creating S4 object ... done [0.00s]
> rule
set of 129 rule
> inspect (rule)
 lhs rhs support confidence coverage lift count
[1] {liquor, red/blush wine} => {bottled beer} 0.001931876 0.9047619 0.002135231 11.235269 19
[2] {curd, cereals} => {whole milk} 0.001016777 0.9090909 0.001118454 3.557863 10
[3] {soups, bottled beer} => {whole milk} 0.001118454 0.9166667 0.001220132 3.587512 11
[4] {whipped/sour cream, house keeping products} => {whole milk} 0.001220132 0.9230769 0.001321810 3.612599
12
[5] {pastry, sweet spreads} => {whole milk} 0.001016777 0.9090909 0.001118454 3.557863 10
[6] {rice, sugar} => {whole milk} 0.001220132 1.0000000 0.001220132 3.913649 12
[7] {rice, bottled water} => {whole milk} 0.001220132 0.9230769 0.001321810 3.612599 12
[8] {canned fish, hygiene articles} => {whole milk} 0.001118454 1.0000000 0.001118454 3.913649 11
[9] {grapes, onions} => {other vegetables} 0.001118454 0.9166667 0.001220132 4.737476 11
[10] {hard cheese, oil} => {other vegetables} 0.001118454 0.9166667 0.001220132 4.737476 11
[11] {root vegetables, butter, rice} => {whole milk} 0.001016777 1.0000000 0.001016777 3.913649 10
[12] {herbs, whole milk, fruit/vegetable juice} => {other vegetables} 0.001016777 0.9090909 0.001118454 4.698323 10
[13] {citrus fruit, tropical fruit, herbs} => {whole milk} 0.001118454 0.9166667 0.001220132 3.587512 11
[14] {root vegetables, whipped/sour cream, flour} => {whole milk} 0.001728521 1.0000000 0.001728521 3.913649 17
[15] {butter, soft cheese, domestic eggs} => {whole milk} 0.001016777 1.0000000 0.001016777 3.913649 10
[16] {tropical fruit, whipped/sour cream, soft cheese} => {other vegetables} 0.001220132 0.9230769 0.001321810 4.770605
12
[17] {root vegetables, whipped/sour cream, soft cheese} => {whole milk} 0.001220132 0.9230769 0.001321810 3.612599
12
[18] {citrus fruit, root vegetables, soft cheese} => {other vegetables} 0.001016777 1.0000000 0.001016777 5.168156 10
[19] {frankfurter, tropical fruit, frozen meals} => {other vegetables} 0.001016777 0.9090909 0.001118454 4.698323 10
[20] {frankfurter, tropical fruit, frozen meals} => {whole milk} 0.001016777 0.9090909 0.001118454 3.557863 10
[21] {tropical fruit, butter, frozen meals} => {whole milk} 0.001016777 0.9090909 0.001118454 3.557863 10
[22] {tropical fruit, whipped/sour cream, hard cheese} => {other vegetables} 0.001016777 0.9090909 0.001118454 4.698323
10
[23] {pork, whole milk, butter milk} => {other vegetables} 0.001016777 0.9090909 0.001118454 4.698323 10
[24] {pip fruit, butter milk, fruit/vegetable juice} => {other vegetables} 0.001016777 0.9090909 0.001118454 4.698323 10
[25] {frankfurter, root vegetables, sliced cheese} => {whole milk} 0.001016777 0.9090909 0.001118454 3.557863 10
[26] {butter, whipped/sour cream, sliced cheese} => {whole milk} 0.001220132 0.9230769 0.001321810 3.612599 12
[27] {yogurt, oil, coffee} => {other vegetables} 0.001016777 0.9090909 0.001118454 4.698323 10
[28] {root vegetables, onions, napkins} => {other vegetables} 0.001016777 0.9090909 0.001118454 4.698323 10
[29] {sausage, berries, butter} => {whole milk} 0.001016777 0.9090909 0.001118454 3.557863 10
…………
……….
[126] {tropical fruit, other vegetables, whole milk, yogurt, oil} => {root vegetables} 0.001016777 0.9090909 0.001118454 8.340400
10
[127] {tropical fruit, other vegetables, butter, yogurt, domestic eggs} => {whole milk} 0.001016777 0.9090909 0.001118454
3.557863 10
[128] {citrus fruit, root vegetables, whole milk, yogurt, whipped/sour cream} => {other vegetables} 0.001016777 0.9090909 0.001118454
4.698323 10
[129] {citrus fruit, tropical fruit, root vegetables, whole milk, yogurt} => {other vegetables} 0.001423488 0.9333333 0.001525165
4.823612 14
b) clustering
> data("iris")
> head(iris)
Sepal.Length Sepal.Width Petal.Length Petal.Width Species
1 5.1 3.5 1.4 0.2 setosa
2 4.9 3.0 1.4 0.2 setosa
3 4.7 3.2 1.3 0.2 setosa
4 4.6 3.1 1.5 0.2 setosa
5 5.0 3.6 1.4 0.2 setosa
6 5.4 3.9 1.7 0.4 setosa
> x=iris[,3:4]
> model=kmeans(x,3)
> library(cluster)
> clusplot(x,model$cluster)
> clusplot(x,model$cluster,color=T,shade=T)
EX5. To perform data pre-processing operations i) Handling Missing data ii) MinMax
normalization
i) Handling Missing data
# Create a data frame
> dataframe <- data.frame( Name = c("Banu", "Anil", "Varshini", "Veena"),Physics = c(98, 87,
+ 91, 94), Chemistry = c(NA, 84, 93, 87), Mathematics = c(91, 86, NA, NA) )

> #Print dataframe

> print(dataframe)
Name Physics Chemistry Mathematics
1 Banu 98 NA 91
2 Anil 87 84 86
3 Varshini 91 93 NA
4 Veena 94 87 NA
> listMissingColumns <- colnames(dataframe)[ apply(dataframe, 2, anyNA)]
> print(listMissingColumns)
[1] "Chemistry" "Mathematics"
> meanMissing <- apply(dataframe[,colnames(dataframe) %in% listMissingColumns],
+ 2, mean, na.rm = TRUE)
> print(meanMissing)
Chemistry Mathematics
88.0 88.5
> medianMissing <- apply(dataframe[,colnames(dataframe) %in% listMissingColumns],
+ 2, median, na.rm = TRUE)
> print(medianMissing)
Chemistry Mathematics
87.0 88.5
> # Importing library
> library(dplyr)
> # Create a data frame
> dataframe <- data.frame( Name = c("Banu", "Anil", "Varshini", "Veena"),Physics = c(98, 87,
+ 91, 94),Chemistry = c(NA, 84, 93, 87), Mathematics = c(91, 86, NA, NA) )

> listMissingColumns <- colnames(dataframe)[ apply(dataframe, 2, anyNA)]

> meanMissing <- apply(dataframe[,colnames(dataframe) %in% listMissingColumns],
+ 2, mean, na.rm = TRUE)
> medianMissing <- apply(dataframe[,colnames(dataframe) %in% listMissingColumns],
+ 2, median, na.rm = TRUE)
> newDataFrameMedian <- dataframe %>% mutate(
+ Chemistry = ifelse(is.na(Chemistry), medianMissing[1], Chemistry),
+ Mathematics = ifelse(is.na(Mathematics), medianMissing[2],Mathematics))
> print(newDataFrameMedian)
Name Physics Chemistry Mathematics
1 Banu 98 87 91.0
2 Anil 87 84 86.0
3 Jai 91 93 88.5
4 Naveen 94 87 88.5
ii) MinMax normalization
> min_max_norm<-function(x){(x-min(x)/(max(x)-min(x))}
> min_max_norm<-function(x){(x-min(x))/(max(x)-min(x))}
> iris_norm<-as.data.frame(lapply(iris[1:4],min_max_norm))
> head(iris_norm)

Output:
Sepal.Length Sepal.Width Petal.Length Petal.Width
1 0.22222222 0.6250000 0.06779661 0.04166667
2 0.16666667 0.4166667 0.06779661 0.04166667
3 0.11111111 0.5000000 0.05084746 0.04166667
4 0.08333333 0.4583333 0.08474576 0.04166667
5 0.19444444 0.6666667 0.06779661 0.04166667
6 0.30555556 0.7916667 0.11864407 0.12500000
EX6. To perform Simple Linear Regression with R.
> 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)
> print(relation)

Output:
Call:
lm(formula = y ~ x)
Coefficients:
(Intercept) x
-38.4551 0.6746
EX7. To perform market basket analysis using Association Rules (Apriori).
# Loading Libraries
library(arules)
library(arulesViz)
library(RColorBrewer)

# import dataset
data("Groceries")

# using apriori() function

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

Parameter specification:
confidence minval smax arem aval originalSupport maxtime support minlen
0.2 0.1 1 none FALSE TRUE 5 0.01 1
maxlen target ext
10 rules TRUE

Algorithmic control:
filter tree heap memopt load sort verbose
0.1 TRUE TRUE FALSE TRUE 2 TRUE

Absolute minimum support count: 98

set item appearances ...[0 item(s)] done [0.00s].

set transactions ...[169 item(s), 9835 transaction(s)] done [0.00s].
sorting and recoding items ... [88 item(s)] done [0.00s].
creating transaction tree ... done [0.00s].
checking subsets of size 1 2 3 4 done [0.00s].
writing ... [232 rule(s)] done [0.00s].
creating S4 object ... done [0.00s].
# using inspect() function
inspect(rules[1:10])
lhs rhs support confidence coverage
[1] {} => {whole milk} 0.25551601 0.2555160 1.00000000
[2] {hard cheese} => {whole milk} 0.01006609 0.4107884 0.02450432
[3] {butter milk} => {other vegetables} 0.01037112 0.3709091 0.02796136
[4] {butter milk} => {whole milk} 0.01159126 0.4145455 0.02796136
[5] {ham} => {whole milk} 0.01148958 0.4414062 0.02602949
[6] {sliced cheese} => {whole milk} 0.01077783 0.4398340 0.02450432
[7] {oil} => {whole milk} 0.01128622 0.4021739 0.02806304
[8] {onions} => {other vegetables} 0.01423488 0.4590164 0.03101169
[9] {onions} => {whole milk} 0.01209964 0.3901639 0.03101169
[10] {berries} => {yogurt} 0.01057448 0.3180428 0.03324860
lift count
[1] 1.000000 2513
[2] 1.607682 99
[3] 1.916916 102
[4] 1.622385 114
[5] 1.727509 113
[6] 1.721356 106
[7] 1.573968 111
[8] 2.372268 140
[9] 1.526965 119
[10] 2.279848 104

# using itemFrequencyPlot() function

arules::itemFrequencyPlot(Groceries, topN = 20,
col = brewer.pal(8, 'Pastel2'),
main = 'Relative Item Frequency Plot',
type = "relative",
ylab = "Item Frequency (Relative)")
EX8. Using R perform the Time-series analysis with respect to stock market data
# Install the library
install.packages("prophet")
# Load the library
library(prophet)
# Dataset
ap <- read.csv("example_air_passengers.csv")
m <- prophet(ap)
# Predictions
future <- make_future_dataframe(m,periods = 365)

# Print predictions
cat("\nPredictions:\n")
tail(future)

Output:
Predictions:
ds
504 1961-11-26
505 1961-11-27
506 1961-11-28
507 1961-11-29
508 1961-11-30
509 1961-12-01

# Forecast
forecast <- predict(m, future)
tail(forecast[c('ds', 'yhat',
'yhat_lower', 'yhat_upper')])
# Output to be present
# As PNG file
png(file = "facebookprophetGFG.png")
# Plot
plot(m, forecast)

# Saving the file

dev.off()

# Output to be present
# As PNG file
png(file = "facebookprophettrendGFG.png")

# Plot
prophet_plot_components(m, forecast)

# Saving the file

dev.off()