Practical 1

#1.Create Vector
fruits<-c("apple","banana","mango","pineapple");
print(fruits)
#class of vector
print(class(fruits))
num<-c(1,4,5,7,8,9);
print(num)
#class of vetor
print(class(num))

#2.List
list1<-list(c(1:3),fruits)
print(list1)

#3.Matrices
M=matrix(c(1:9),nrow=3,byrow=TRUE)
print(M)
K=matrix(c(1:12),nrow=4,ncol=3,byrow=TRUE)
print(K)

#4.Array
A<-array(c("yes","no","true","false"),dim=c(4))
print(A)
B<-array(c("yes","no","true","false"),dim=c(3,4))
print(B)
C<-array(c("yes","no","true","false"),dim=c(3,4,2))
print(C)

#5.Factor
apple_colors<-c("red","blue","green")
factor_apple<-factor(apple_colors)
#convert in sequence order
print(factor_apple)
print(nlevels(factor_apple))

#6.Data frames
my<-data.frame(
name=c("veer","nilesh","pooja","habat"),
gender=c("male","male","female","male"),
height=c(6.8,6.7,6,5.7),
weight=c(75,80,50,64),
age=c(21,19,18,20)
)
print(my)
data.frame(my$name,my$gender)
Output:-

Practical 3

#1.find mean of 12,7,3,4,2,1,18,2,54,-21,8,-5

x<-c(12,7,3,4,2,1,18,2,54,-21,8,-5)
result.mean<-mean(x)
print(result.mean)

#2.find median of 12,7,3,4,2,1,18,2,54,-21,8,-5

x<-c(12,7,3,4,2,1,18,2,54,-21,8,-5)
result.median<-median(x)
print(result.median)

#3.find mode of 2,1,2,3,12,3,4,1,5,5,3,2,2

getmode=function(v)
{
uniqv=unique(v)
uniqv[which.max(tabulate(match(v,uniqv)))]
}
v<-c(2,1,2,3,12,3,4,1,5,5,3,2,2)
result.mode<-getmode(v)
print(result.mode)

#find range of the eruption duration in the data set faithful

duration=faithful$eruption
min(duration)
max(duration)
result.range=max(duration)-min(duration)
print(result.range)

#find standard deviation of the eruption duration in the data set faithful
duration=faithful$eruption
result.sd=sd(duration)
print(result.sd)

#find variance of the eruption duration in the data set faithful

duration=faithful$eruption
result.var=var(duration)
print(result.var)

#find summary of the data set faithful

result.summary=summary(faithful)
print(result.summary)

Output:-
Practical No: 4

salarydata<-data.frame(
salaries_low=c(25000,26000,27000,28000,29000,30000,31000),
salaries_high=c(25999,26999,27999,28999,29999,30999,32999),
Numbers=c(8,10,16,14,10,5,2)
)
print(salarydata)
#salarydata<-salarydata[,cumNumbers:=cumsum(Numbers)]
salarydata

mediangroup<-salarydata
{
((cumNumbers-Numbers)<=(max(cumNumbers)/2 &
(cumNumbers)>=(max(cumNumbers)/2))
{
l1=mediangroup(,salaries_low)
l2=mediangroup(,salaries_high)
f=mediangroup(,Numbers)
pcf=mediangroup(,cumNumbers-Numbers)
n=salarydata(,sum(Numbers))
}
}
median<-l1+(((n/2)-pcf)/f*(l2-l1))

median

Output:-
Practical No: 5

salarydata<-data.frame(
salaries_low=c(25000,26000,27000,28000,29000,30000,31000),
salaries_high=c(25999,26999,27999,28999,29999,30999,32999),
Numbers=c(8,10,16,14,10,5,2)
)
print(salarydata)
salarydata[ , prevNumbers := shift(Numbers,1)]

salarydata[ , nextNumbers := shift(Numbers,-1)]

salarydata

#identifying mode group

modegroup <- salarydata[Numbers == max(Numbers)]
modegroup

#creating the variables needed to calculate mode

l1 = modegroup[,salaries_low]
l2 = modegroup[,salaries_high]
f1 = modegroup[,Numbers]
f0 = modegroup[,prevNumbers]
f2 = modegroup[,nextNumbers]

#calculating mode
groupmode <- l1 + ((f1-f0)/(f1-f0+f1-f2)*(l2-l1))
groupmode

Output:-
Practical No: 6

# a) 12, 6, 7, 3, 15, 10, 18, 5

# b) 9, 3, 8, 8, 9, 8, 9, 18.

input<-data.frame(
X1=c(12, 6, 7, 3, 15, 10, 18, 5),
X2=c(9, 3, 8, 8, 9, 8, 9, 18)
)
print("Standard Deviaton of X1 and X2 are : ")
sd(input$X1)
sd(input$X2)

print("Variance of X1 and X2 are : ")

var(input$X1)
var(input$X2)

OUTPUT:-

Practical No: 7

input<-data.frame(
X=c(0,1,2,3,4),
F1=c(10,5,2,2,1),
F2=c(1,2,14,2,1),
F3=c(1,2,5,5,10)
)
getmode <- function(v) {
uniqv <- unique(v)
uniqv[which.max(tabulate(match(v, uniqv)))]
}

mean1<-mean(rep(input$X,input$F1))
median1<-median(rep(input$X,input$F1))
mode1<-getmode(rep(input$X,input$F1))
sd1<-sd(rep(input$X,input$F1))
Pearsonfirst<-((mean1-mode1)/sd1)
Pearsonsecond<-(3*(mean1-median1)/sd1)
print("Pearson's first coefficients of skewness with x and f1 is : ")
print(Pearsonfirst)
print("Pearson's second coefficients of skewness with x and f1 is : ")
print(Pearsonsecond)

mean1<-mean(rep(input$X,input$F2))
median1<-median(rep(input$X,input$F2))
mode1<-getmode(rep(input$X,input$F2))
sd1<-sd(rep(input$X,input$F2))
Pearsonfirst<-((mean1-mode1)/sd1)
Pearsonsecond<-(3*(mean1-median1)/sd1)
print("Pearson's first coefficients of skewness with x and f2 is : ")
print(Pearsonfirst)
print("Pearson's second coefficients of skewness with x and f2 is : ")
print(Pearsonsecond)

mean1<-mean(rep(input$X,input$F3))
median1<-median(rep(input$X,input$F3))
mode1<-getmode(rep(input$X,input$F3))
sd1<-sd(rep(input$X,input$F3))
Pearsonfirst<-((mean1-mode1)/sd1)
Pearsonsecond<-(3*(mean1-median1)/sd1)
print("Pearson's first coefficients of skewness with x and f3 is : ")
print(Pearsonfirst)
print("Pearson's second coefficients of skewness with x and f3 is : ")
print(Pearsonsecond)

OUTPUT:-

Practical No: 8

Me<-data.frame(
Spades=402, Diamonds=358,Clubs=273, Hearts=467
)
attach(Me)
result<-chisq.test(Me)
print(result)
if(result$p.value>=0.05){
print("Null Hypothesis is Accepted")
}else{
print("Null Hypothesis is Rejected")
}

OUTPUT:-

Practical No: 9

input<-data.frame(
Finance = c(12,7),
Sales = c(38,19),
HR= c(5,3),Technology= c(8,1))
attach(input)
result<-chisq.test(input)
print(result)
if(result$p.value>=0.05){
print("Null Hypothesis is Accepted")
}else{
print("Null Hypothesis is Rejected")
}
OUTPUT:-
Practical No: 10

# (a) What percentage play in fewer than 750 games?

# (b) What percentage play in more than 2000 games?
# (c) Find the 90th percentile for the number of games played during a career.

print("What percentage play in fewer than 750 games")

pa<-pnorm(750, mean = 1500, sd = 350)
Percenta <- pa*100
print(Percenta)

print("What percentage play in more than 2000 games")

pb<-pnorm(2000, mean = 1500, sd = 350, lower.tail = FALSE)
Percentb <- pb*100
print(Percentb)

print("the 90th percentile for the number of games played during a career")
p05<-round(qnorm(0.05,mean = 1500, sd = 350),0)
p95<-round(qnorm(0.95,mean = 1500, sd = 350),0)
cat("Range for 90 Percentile is : ",p05,"-",p95)

Output:-

Practical No: 11

prac<-data.frame(
H=c(70,63,72,60,66,70,74,65,62,67,65,68),
W=c(155,150,180,135,156,168,178,160,132,145,139,152)
)

print("a) H as the independent variable")

reg<-lm(W ~ H,data = prac)
print(reg)

print("b) H as the dependent variable")

reg<-lm(H ~ W,data = prac)
print(reg)

OUTPUT:-

Practical No: 12

a) Graph the data and show the least-squares regression line.

# (b) Find and plot the trend line for the data.
# (c) Estimate the value of total agricultural exports in the
# year 2006.

input<-data.frame(
YEAR=c(2000,2001,2002,2003,2004,2005),
TOTAL=c(51246,53659,53115,59364,61383,62958)
)
reg<-lm(TOTAL ~ YEAR,data = input)
print(reg)

plot(input$YEAR,input$TOTAL,type = "p", col = "blue", pch = 16, cex = 1.3,xlab = "Year",ylab

= "Total Value",main = "total agricultural exports")
abline(reg,col = "red")

print("Estimate the value of total agricultural exports in the year 2006.")

newdata = data.frame(YEAR=2006)
predict(reg, newdata)

OUTPUT:-