#load mtcars dataset
df=read.csv("mtcars-3.csv")
#Displaying the First Few Rows
head(mtcars-3)
#Dimension of Dataset
dim(mtcars-3)
## [1] 32 11
#Data Structure of Variable df
class(df)
## [1] "data.frame"
#Data Types of Columns
class(df$mpg)
## [1] "numeric"
typeof(df$mpg)
## [1] "double"
class(df$hp)
## [1] "integer"
typeof(df$hp)
## [1] "integer"
class(df$am)
## [1] "integer"
typeof(df$am)
## [1] "integer"
#Summary of Dataset
summary(df)
## model mpg cyl disp
## Length:32 Min. :10.40 Min. :4.000 Min. : 71.1
## Class :character 1st Qu.:15.43 1st Qu.:4.000 1st Qu.:120.8
## Mode :character Median :19.20 Median :6.000 Median :196.3
## Mean :20.09 Mean :6.188 Mean :230.7
## 3rd Qu.:22.80 3rd Qu.:8.000 3rd Qu.:326.0
## Max. :33.90 Max. :8.000 Max. :472.0
## hp drat wt qsec
## Min. : 52.0 Min. :2.760 Min. :1.513 Min. :14.50
## 1st Qu.: 96.5 1st Qu.:3.080 1st Qu.:2.581 1st Qu.:16.89
## Median :123.0 Median :3.695 Median :3.325 Median :17.71
## Mean :146.7 Mean :3.597 Mean :3.217 Mean :17.85
## 3rd Qu.:180.0 3rd Qu.:3.920 3rd Qu.:3.610 3rd Qu.:18.90
## Max. :335.0 Max. :4.930 Max. :5.424 Max. :22.90
## vs am gear carb
## Min. :0.0000 Min. :0.0000 Min. :3.000 Min. :1.000
## 1st Qu.:0.0000 1st Qu.:0.0000 1st Qu.:3.000 1st Qu.:2.000
## Median :0.0000 Median :0.0000 Median :4.000 Median :2.000
## Mean :0.4375 Mean :0.4062 Mean :3.688 Mean :2.812
## 3rd Qu.:1.0000 3rd Qu.:1.0000 3rd Qu.:4.000 3rd Qu.:4.000
## Max. :1.0000 Max. :1.0000 Max. :5.000 Max. :8.000
#Change Class of Variable "am"
am=df$am
am=as.logical(am)
class(am)
## [1] "logical"
plot(df$hp, df$mpg,
main="Scatter Plot of MPG and HP",
xlab="hp",
ylab="mpg",
col="purple",
pch=20,
)
Interpretation of Scatter Plot
This graph shows that the lower the horsepower of car, the higher its
mileage. The higher a car’s horsepower is, the worse its mileage is.
library(ggplot2)
count_cyl=data.frame(table(df$cyl))
ggplot(data=count_cyl,aes(x=Var1, y=Freq)) +
geom_bar(stat="identity",fill="darkblue")+
labs(title="Distribution of Cars According to Number of Cylinders", x="Num of Cylinders",y="Count of Cars")+
scale_y_continuous(
breaks=seq(0,20, by=1),
labels=c("0","1","2","3","4","5","6","7","8","9","10","11","12","13","14","15","16","17","18","19","20"),
limits=c(0,14),
expand=c(0.02,0)
)
hist(x=df$mpg,
xlab="MPG",
ylab="Count of Cars",
main="Distribution of Miles Per Gallon",
col="lightgreen")