R-codes
dim(Pivot_Table_Practice): dimensions (how many rows
and columns)
[1] 149 20
mydata<-Pivot_Table_Practice: rename my dataset
names(mydata): to find the names of columns
rownames(mydata) to find the names of rows
mydata$`Customer Name`
mean(mydata$Profit)
[1] 641.4257
> mean(mydata$Sales)
[1] 3175.091
> mean(mydata$`Shipping Cost`)
[1] 613.1659
median(mydata$Sales)
[1] 2761.2
> median(mydata$Profit)
[1] 527.04
> median(mydata$`Shipping Cost`)
[1] 585.25
sort(mydata$Profit) ascending order
sort(mydata$Sales,decreasing = FALSE): ascending
sort(mydata$Sales,decreasing = TRUE) :descending
summary(mydata$Sales):
Data Set 2
#data set in R
mtcars
?mtcars
help(mtcars)
dim(mtcars)
names(mtcars)
[Link](mtcars)
datanew<-mtcars
dim(datanew)
datanew$vs
datanew$hp
datanew$vs
sort(datanew$hp)
sort(datanew$wt)
sort(datanew$wt,decreasing = TRUE)
sort(datanew$wt,decreasing = FALSE)
mean(datanew$cyl)
median(datanew$cyl)
mode(datanew$cyl)
summary(datanew$cyl)
summary(datanew)
max(datanew$cyl)
head(datanew)
head(datanew)
tail(datanew)
cor(datanew$cyl,datanew$hp)
cor(datanew$mpg,datanew$cyl)
cor(datanew$mpg,datanew$hp)
#scatter plot
plot(datanew$mpg,datanew$hp)
plot(datanew$mpg, datanew$hp,xlab = "miles per
galon",ylab="horse power")
lines([Link](datanew$mpg,datanew$hp))
datasets:: use this code and it will give all
the options of dataset available in R studio.
25-3-2026
Simple linear Regression: One dependent variable
(DV), one independent variable (IDV). Example:
Advertising exp sales
IDV DV
Y=a+bx
Residuals: difference between Actual and predicted
Y=a+bx1+bX2+bx3
Y: DV
X: IDV
a: intercept
b: slope
Multiple linear Regression: One dependent variable (DV), more
than one independent variable (IDV’s)
Correlation and Scatter Plot
Mtcars (dataset)
> cor(mtcars$mpg,mtcars$cyl)
[1] -0.852162
> plot(mtcars$mpg,mtcars$cyl)
> plot(mtcars$mpg,mtcars$hp)
> plot(mtcars$mpg,mtcars$hp,xlab = "mileage per
gallon",ylab = "horse power")
> cor(mtcars$mpg,mtcars$hp)
[1] -0.7761684
> lines([Link](mtcars$mpg,mtcars$hp))
Regression: In R, put DV variable first, then IDV.
> lm(mtcars$mpg~mtcars$cyl)
Call:
lm(formula = mtcars$mpg ~ mtcars$cyl)
Coefficients:
(Intercept) mtcars$cyl
37.885 -2.876
> lm(mtcars$mpg~mtcars$hp)
Call:
lm(formula = mtcars$mpg ~ mtcars$hp)
Coefficients:
(Intercept) mtcars$hp
30.09886 -0.06823
> ml<-lm(formula = mtcars$mpg ~ mtcars$hp)
> ml
Call:
lm(formula = mtcars$mpg ~ mtcars$hp)
Coefficients:
(Intercept) mtcars$hp
30.09886 -0.06823
> summary(ml)
Call:
lm(formula = mtcars$mpg ~ mtcars$hp)
Residuals:
Min 1Q Median 3Q Max
-5.7121 -2.1122 -0.8854 1.5819 8.2360
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 30.09886 1.63392 18.421 < 2e-16 ***
mtcars$hp -0.06823 0.01012 -6.742 1.79e-07 ***
---
Signif. codes:
0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Residual standard error: 3.863 on 30 degrees of freedom
Multiple R-squared: 0.6024, Adjusted R-squared:
0.5892
F-statistic: 45.46 on 1 and 30 DF, p-value: 1.788e-07
> plot(ml)
Hit <Return> to see next plot:
Hit <Return> to see next plot:
Hit <Return> to see next plot:
Hit <Return> to see next plot:
> par(mfrow=c(2,2))
> plot(ml)
Multiple Regression: In R, put DV variable first, then IDV’S.
> lm(mtcars$mpg~mtcars$cyl+mtcars$hp)
Call:
lm(formula = mtcars$mpg ~ mtcars$cyl + mtcars$hp)
Coefficients:
(Intercept) mtcars$cyl mtcars$hp
36.90833 -2.26469 -0.01912
> mml<-lm(formula = mtcars$mpg ~ mtcars$cyl +
mtcars$hp)
> mml
Call:
lm(formula = mtcars$mpg ~ mtcars$cyl + mtcars$hp)
Coefficients:
(Intercept) mtcars$cyl mtcars$hp
36.90833 -2.26469 -0.01912
> summary(mml)
Call:
lm(formula = mtcars$mpg ~ mtcars$cyl + mtcars$hp)
Residuals:
Min 1Q Median 3Q Max
-4.4948 -2.4901 -0.1828 1.9777 7.2934
Coefficients:
Estimate Std. Error t value
(Intercept) 36.90833 2.19080 16.847
mtcars$cyl -2.26469 0.57589 -3.933
mtcars$hp -0.01912 0.01500 -1.275
Pr(>|t|)
(Intercept) < 2e-16 ***
mtcars$cyl 0.00048 ***
mtcars$hp 0.21253
---
Signif. codes:
0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’
0.1 ‘ ’ 1
Residual standard error: 3.173 on 29 degrees of freedom
Multiple R-squared: 0.7407, Adjusted R-squared:
0.7228
F-statistic: 41.42 on 2 and 29 DF, p-value: 3.162e-09
> plot(mml)
> par(mfrow=c(2,2))
> plot(mml)
> par(mfrow=c(1,1))
> plot(mml)
Hit <Return> to see next plot:
Hit <Return> to see next plot:
Hit <Return> to see next plot:
Hit <Return> to see next plot:
10-4-2026
> #vector
> city1<-c("delhi","mumbai")
> city1
[1] "delhi" "mumbai"
> View(city1)
> print(class(city1))
[1] "character"
> class(city1)
[1] "character"
> age2<-c(10,20,30)
> age2
[1] 10 20 30
> class(age2)
[1] "numeric"
#list
> city2<-list("delhi","mumbai","HP")
> city2
[[1]]
[1] "delhi"
[[2]]
[1] "mumbai"
[[3]]
[1] "HP"
> AGE3<-list(20,25,42)
> AGE3
[[1]]
[1] 20
[[2]]
[1] 25
[[3]]
[1] 42
> a<-list(20,c(20.1,23,25))
>a
[[1]]
[1] 20
[[2]]
[1] 20.1 23.0 25.0
> a1<-c(20.1,list(20.2,20.4,26))
> a1
[[1]]
[1] 20.1
[[2]]
[1] 20.2
[[3]]
[1] 20.4
[[4]]
[1] 26
> #Dataframe
First example:
>companyx=c(20000,30000,40000)
>companyy=c(30000,50000,60000)
>companyz=c(50000,80000,40000)
>datanew=[Link](companyx,companyy,companyz)
>datanew
>View(datanew)
Second example:
>data123=[Link](companyx=c(20000,30000,40000),companyy=c(30000,500
00,60000),companyz=c(50000,80000,40000))
>data123
Third example:
> companyA<-
[Link](days=c("monday","tuesday","wednesday"),sal
es=c(12000,15000,20000),profit=c(15000,25000,35000))
> print(companyA)
days sales profit
1 monday 12000 15000
2 tuesday 15000 25000
3 wednesday 20000 35000
> View(companyA)
> companyA
days sales profit
1 monday 12000 15000
2 tuesday 15000 25000
3 wednesday 20000 35000
Data summary
> mean(companyb$sales)
[1] 15666.67
> mean(companyA$profit)
[1] 25000
> summary(companyA$sales)
Min. 1st Qu. Median Mean 3rd Qu. Max.
12000 13500 15000 15667 17500 20000
> summary(companyA)
days sales profit
Length:3 Min. :12000 Min. :15000
Class :character 1st Qu.:13500 1st Qu.:20000
Mode :character Median :15000 Median :25000
Mean :15667 Mean :25000
3rd Qu.:17500 3rd Qu.:30000
Max. :20000 Max. :35000
> cor(companyA$sales,companyA$profit)
[1] 0.9897433
> plot(companyA$sales,companyA$profit)
> plot(companyA$sales,companyA$profit,xlab =
"sales",ylab = "profit")
>lm(companyA$profit~companyA$sales)
17-4-2026
#creation of dataset in r
x=[Link](Name=c("Amit","Radhika"),Age=c(22,24),gender=c("Male","Female"))
x
print(x)
View(x)
#ACCESSING THE ITEMS OF DATA FRAME
x$Age
x$gender
x[1]
x[2]
x[3]
#STRUCTURAL SIZE OF A DATA FRAME
dim(x)
size=dim(x)
size
ncol(x)
nrow(x)
#COMBINING DATA FRAMES
#Combining row wise
y=[Link](Name=c("Megha","Arun"),Age=c(25,27),gender=c("Female","Male"))
y
z=rbind(x,y)
z
#Combining coloumn wise
k=[Link](Salary=c(20000,30000),city=c("mumbai","delhi"))
k
xk=cbind(x,k)
xk
print(xk)
#Accessing the element of data frame
x[2,2]
x[3,2]
x[2,3]
#ADDING ROWS IN A DATA FRAME
x=[Link](Name=c("Amit","Radhika"),Age=c(22,24),gender=c("Male","Female"))
x
x1=rbind(x,c("Ram",28,"Male"))
x1
#ADDING COLOUMN IN A DATA FRAME
x2=cbind(x,city=c("East","West"))
x2
city=c("East","West")
city
x3=cbind(x,city)
x3
x4=c("Ram",28,"Male")
x4
x5=rbind(x,x4)
x5
17-4-2026
#1) Create data 2) Calculate mean and median 3) Calculate total and total percentage for each student 4)
create data of name, total, and percentage’.
#1
marks_1 <- [Link]( name = c("Anu","Dhruv","Vaibhav","Chirag"), maths = c(78,89,65,75), science =
c(77,88,55,99), english = c(98,95,96,94))
print(marks_1)
#2
mean(marks_1$maths)
mean(marks_1$science)
mean(marks_1$english)
median(marks_1$maths)
median(marks_1$science)
median(marks_1$english)
summary (marks_1$maths)
summary(marks_1)
#3
total <- (marks_1$maths+marks_1$science+marks_1$english)
print(total)
percentage <- (total/300)*100
print(percentage)
#4
name <- marks_1$name
output <- [Link](name,total,percentage)