#addition of two numbers

2+3

#square root of 2

sqrt(2)

#natural log of 4

log(4)

#exponential of 2

exp(2)

#value of sin of 20 in radians

sin(20)

#simple division

2/34

#value of pi

pi

#assigning values to variables and then performing operations

a=5

a^2

b<-a

b^2

#listing variables

ls()

#removing a variable/placeholder

rm(a)

ls()

#Example-1 Print every item in a list.

for(x in fruits){

print(x)}

#Example-2 stop the loop at the cheery.

fruits <- list("apple","banana","cheery")

for(x in fruits){

if(x=="cheery"){break}

print(x)}

#Example-3 Skip banana

fruits <- list("apple","banana","cheery")

for(x in fruits){

if(x=="banana"){next}

print(x)}

#Data structure in R

#We use the c() function to enter a vector.

a <- c(2,3,5)

#A vector can contains character strings.

length(a)

length(b)

# Create a vector from 1 to 5.

x <- 1:5

y = c(1,3,5,7,9)

#Two vectors of the same length may be added/subtracted/multiplied/divided.

x+y

x-y

x+10

x-10

x/2

x/y

sqrt(y)

log(x)

x*y

# Extract all elements of y except the third element.

y[-3]

# Extract the third element of y.

y[3]

# Extract the first three elements of y.

y[1:3]
# Extract all except 1st and 5th.

y[-c(1,5)]

# Extract 1st and 5th elements of y.

y[c(1,5)]

# Extract elements of y with value less than 6.

y[y<6]

seq(1,7)

#seq() produces a sequence of numbers.

#Produce a sequence of numbers from 1 to 7 at a distance of 0.5.

seq(from=1,to=7)

#Stepsize 2

seq(from=1,to=7,by=2)

# To find minimum and maximum values of a vector.

a <- c(1,-2,3,-4)

b <- c(-1,2,-3,4)

min(a,b)#minimum values between a&b.

pmin(a,b)# minimum values term by term.

max(a)

min(a)

sum(a)

u <- c(10,20,30)

v <- c(1,2,3,4,5,6,7,8,9)

u+v

#Matrices
# A matrix is created using matrix() function.

matrix(c(1,2,3,4,5,6,7,8,9),nrow=3,byrow=TRUE)

byrow command sequentiatly arranges elements by rowwise.

matrix(c(1,2,3,4,5,6,7,8,9),nrow=3,byrow=FALSE)

A= matrix(c(1,2,3,4,5,6,7,8,9,10),nrow=2,ncol=5,byrow=TRUE)

A[2,3]# Extract the element in row 2 and column 3.

A[2,]# Extract row 2.

A[,4] # Extractcolumn 4.

A[,c(1,3)] #Extract columns 1 and 3.

dimnames(A)=list(c("row1","row2"),c("col1","col2","col3","col4","col5"))

A= matrix(c(1,2,3,4,5,6,7,8,9,10),nrow=2,ncol=5,byrow=TRUE,

A*10

dimnames = list(c("row1","row2"),c("col1","col2","col3","col4","col5")))

# Transpose of A

t(A)

mat <- matrix(c(1,2,3,4),nrow=2,byrow=TRUE)

mat

det(mat)#Determinant of a matrix.

A= matrix(c(1,2,3,4,5),nrow=3,ncol=2,byrow=TRUE)

B= matrix(c(11,12,13,14,15),nrow=3,ncol=2,byrow=TRUE)

A+B

A-B

A*B
A/B

# To create a list use list() function.

list1 <- list("apple","banana","cheery")

list1

list1[1]# 1st element

list[1] <- "blackcurrent"

list1

list1[2:3]

# Add orange to the list1

append(list1,"orange")

append(list1,"orange",after=2) # adds orange after index 2.

# Remove list item.

newlist <- list1[-1]

newlist

# concatenate two list.

list1 <- list("a","b","c")

list2 <- list(1,2,3)

list3 <- c(list1,list2)

list3

#Dataframes

#Data frames are data displayed in a format as a table . It is a list of vectors of equal length.

# Use data.frame() to create a data frame

n=c(2,3,5)

s=c("english","economics","hindi")

b=c(TRUE,FALSE,TRUE)
df=data.frame(n,s,b)

df

#Example-2

Data_frame <- data.frame(training=c("strength","stamina","other"),

Data_frame

pulse= c(100,50,120),duration=c(60,30,45))

Data_frame[1] # access the col1

Data_frame[["training"]]

Data_frame $ training

# Add row

Data_frame1 <- rbind(Data_frame,c("strength",110,110))

Data_frame1

Add column using cbind()

Data_frame2 <- cbind(Data_frame,steps= c(100,200,300))

Data_frame2

# Remove rows and columns

Data_frame3 <- Data_frame[-c(1),-c(2)]

Data_frame3

dim(Data_frame)

ncol(Data_frame)

nrow(Data_frame)

# Factors are used to categorize data

#Example

music <- factor(c("jazz","rock", "classic","classic","pop"))

levels(music)

length(music)

music[3]

music[3] <- "pop"

music[3]

#Data types in R

# 1) logical 2) numeric 3) integer 4) complex 5) character

a1=TRUE

class(a1)

a2=FALSE

class(a2)

a3 <- 2.45

class(a3)

a4 <- 12

class(a4)

a5 <- 2+3i

class(a5)

a6="hi"

class(a6)

a7=hi

country<-c("China","India","US","Indonesia","Pakistan")

population_2022<-c("142764786","1352642280","327096265","267670543","212228286")

population_2023<-c("1433783686","1366417754","320064917","270625568","216565318")

change_in_percentage<-c("+0.43%","+1.02%","+0.60%","+1.10%","2.04%")
data<-data.frame(country,population_2022,population_2023,change_in_percentage)

print(data)

install.packages("readxl")

library("readxl")

#Reading data from an excell file

getwd()

setwd("C:/Users/MATHS LAB/Documents/vikas")

getwd()

data<-read_excel("stats.xlsx",sheet=1) -/

print(data)

# A tibble: 5 ×4

df<-read.table("data.txt",header=TRUE)

#to view data from

print(df)

dim(df)

#write table

df<-data.frame(var1=c(1,2,3,4,5),var2=c(2,3,4,5,6),var3=c(5,6,7,8,9))

df

#export data to desktop(your folder)

write.table(df,"C:/Users/MATHS LAB/Documents/vikas/data2.txt")

#Data visualization is the technique to deliver insights in data using visuals such as graphs charts

# The plot() function is used to draw points (markers) in the diagram

plot(0.5,0.5)

plot(c(1,2,3,4),c(1,4,9,16))
x=seq(-pi,pi,0.1)

y=sin(x)

plot(x,y)

plot(1:10,type="l")

plot(1:10,type="l",col="blue")

# Scatter plot

# a scatter plot is a type of plot used to display the relationship between two numerical variables and
plot on dot for each

observation.

#the basic syntax for scatterplot is:

#plot(x,y,main,x|ab,y|ab,xlim,ylim,axes)

table(mtcars$wt)

plot(x=mtcars$wt,y=mtcars$mg,main="Weight vs Milage",xlab="Weight",ylab="Milage",col="blue")

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

M<-c("Mar","Apr","May","Jun","Jul")

#To give chart file a name

#Plot bar chart

barplot(H,names.arg=M)

#pie chart

#use the pie() function to draw a pie chart

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

labels <- c("London","New York","Singapore","Mumbai")

colors <- rainbow(length(slices))

# Create the pie chart

pie(x,labels)

#Histogram
value=c(10,15,17,20,24,26,30)

hist(value)

#box Plot

boxplot(value)

scores=scan()

1: 81 81 96 77

5: 95 98 73 83

9: 80 86 89 60

13: 79 62

15:

Read 14 items

range(scores)

median(scores)

mean(scores)

sd(scores)

hist(scores)

#ggplot is an R package which is designed especially for data visualization and providing exploratotry
data analysis.

#Use the function ggplot() to generate the plots.

#Syntax

#ggplot(data=<DATA>,mapping=aes(<MAPPINGS>))+<geom_function>()

# to load ggplot2

library(ggplot2)

#read in dataset

data(iris)

iris
ggplot(data=iris)

ggplot(data=iris,aes(y=Sepal.Length,x=Petal.Length,col=Species))+geom_point()

#Bar Plot and Histograms

# A bar count plot for "cyl" in mpg data

p<-ggplot(mpg,aes(x=factor(cyl)))+geom_bar(stat='count')

# A histogram count plot for "hwy" in mpg data

ggplot(data=mpg,aes(x=hwy))+geom_histogram(col="red",fill="green",alpha=0.2,bindwidth=5)

`stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

# PieChart

df<-as.data.frame(table(mpg$class))

colnames(df)<-c("class","freq")

df

ggplot(df,aes(x="",y=freq,fill=factor(class)))+geom_bar(width=1,stat="Identity")+coord_polar(theta="y",
start=0)

#MEAN mean(x,trim=0,na.rm=FALSE,...)

#Create a vector

x <- c(12,7,3,4.2,18,2,54,-21,8,-5)

xmean<-mean(x)

xmean

x <- c(12,7,3,4.2,18,2,54,-21,8,-5)

xmean<-mean(x,trim=0.3) #When trim = 0.3, 3 values from each end will be dropped from the
calculations to find mean.

xmean
x<-c(-1,-3,1,0,2,5,4,7,6,3,8,-2,9,NA)

xmean<-mean(x)

xmean

xmean<-mean(x,na.rm=TRUE)

xmean

x<-c(-1,-3,1,0,2,5,4,7,6,3,8,-2,9,NA)

xmedian<-median(x)

xmedian

x<-c(-1,-3,1,0,2,5,4,7,6,3,8,-2,9,ΕΑ )

xmedian<-median(x,na.rm=TRUE)

xmedian

install.packages("readxl")

library("readxl")

getwd()

setwd("C:/Users/hp/Downloads")

getwd()

data <-read_excel('BPData.xlsx',sheet=1)

View(data)

data

# A tibble: 10 ×3

str(data) #gives summary of data

tibble [10 ×3] (S3: tbl_df/tbl/data.frame)

$ AGE : num [1:10] 25 30 33 35 37 40 41 43 44 48

$ WEIGHT : num [1:10] 82 142 66 113 123 147 115 178 115 116

$ BLOOD PRESSURE: num [1:10] 89 151 37 127 65 96 103 194 176 74

# A tibble: 6 ×3

tail(data) #last six rows

# A tibble: 6 ×3

mean(data$WEIGHT)

median(data$WEIGHT)

range(data$WEIGHT)

IQR(data$WEIGHT)

sd(data$WEIGHT)

summary(data$WEIGHT)

Min. 1st Qu. Median Mean 3rd Qu. Max.

66.0 113.5 115.5 119.7 137.2 178.0

summary(data)

hist(data$WEIGHT,col="steelblue")

hist(data$'BLOOD PRESSURE')

qqnorm(data$'BLOOD PRESSURE')

library(moments)

#calculate skewness

skewness(data$WEIGHT)

x<-c(40,41,42,43,50)

hist(x)

print(skewness(x))

x<-c(10,11,21,22,23,25)

hist(x)

print(skewness(x))
#Regression analysis in R

#linear Regression

#Syntax:lm(formula data)

#Example predicting weight of a person when height is known

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)# gives relation between x and y

print(relation)

Call:

lm(formula = y ~ x)

#prediction finding syntax

#predict(object,newdata)

#find weight of a person with height 170

a=data.frame(x=170)

result=predict(relation,a)

print(result)

cor.test(x,y) # to find pearson's product-moment correlation

pearson's product-moment correlation

data: x and y

t = 12.997, df = 8, p-value = 1.164e-06

alternative hypothesis: true correlation is not equal to 0

95 percent confidence interval:

0.9031373 0.9947558

sample estimates:

cor
0.9771296

# time series analysis in R

#it is used to see how an object behaves over a period of time

#Syntax: object name=ts(data,start,end,frequency)

#converting to time series

sales=c(79,11,74,86,65,23,45,49,99,24,40,48,51)

T1=ts(sales)

T1

time Series:

Start = 1

End = 13

Frequency = 1

plot(T1)

sales.ts=ts(sales,start=2018,frequency=12)

sales.ts

stockrate=c(480,968,274,492,771,968,961,236,208,381,927,140,197)

#example: stock rate over a year

stockrate=c(480,968,274,492,771,968,961,236,208,381,927,140,197)

stockrate.ts=ts(stockrate,start=2019,frequency=12)

print(stockrate.ts)

plot(stockrate.ts)