Cars Data Analysis

Load packages

library(ggplot2)
library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

read the dataset cars.csv

cars<-read.csv("cars.csv")

Data structure for ‘cars’

str(cars)

## 'data.frame':    428 obs. of  19 variables:
##  $ name       : chr  "Chevrolet Aveo 4dr" "Chevrolet Aveo LS 4dr hatch" "Chevrolet Cavalier 2dr" "Chevrolet Cavalier 4dr" ...
##  $ sports_car : logi  FALSE FALSE FALSE FALSE FALSE FALSE ...
##  $ suv        : logi  FALSE FALSE FALSE FALSE FALSE FALSE ...
##  $ wagon      : logi  FALSE FALSE FALSE FALSE FALSE FALSE ...
##  $ minivan    : logi  FALSE FALSE FALSE FALSE FALSE FALSE ...
##  $ pickup     : logi  FALSE FALSE FALSE FALSE FALSE FALSE ...
##  $ all_wheel  : logi  FALSE FALSE FALSE FALSE FALSE FALSE ...
##  $ rear_wheel : logi  FALSE FALSE FALSE FALSE FALSE FALSE ...
##  $ msrp       : int  11690 12585 14610 14810 16385 13670 15040 13270 13730 15460 ...
##  $ dealer_cost: int  10965 11802 13697 13884 15357 12849 14086 12482 12906 14496 ...
##  $ eng_size   : num  1.6 1.6 2.2 2.2 2.2 2 2 2 2 2 ...
##  $ ncyl       : int  4 4 4 4 4 4 4 4 4 4 ...
##  $ horsepwr   : int  103 103 140 140 140 132 132 130 110 130 ...
##  $ city_mpg   : int  28 28 26 26 26 29 29 26 27 26 ...
##  $ hwy_mpg    : int  34 34 37 37 37 36 36 33 36 33 ...
##  $ weight     : int  2370 2348 2617 2676 2617 2581 2626 2612 2606 2606 ...
##  $ wheel_base : int  98 98 104 104 104 105 105 103 103 103 ...
##  $ length     : int  167 153 183 183 183 174 174 168 168 168 ...
##  $ width      : int  66 66 69 68 69 67 67 67 67 67 ...

Visualize histogram for city_mpg and sub-graph wrt Sport Utility Vehicle

ggplot(cars,aes(x=city_mpg))+geom_histogram()+facet_wrap(~ suv)

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

## Warning: Removed 14 rows containing non-finite values (stat_bin).

Filter cars with 4, 6, 8 cylinders

car<-cars %>%
  filter(ncyl==c(4,6,8))

## Warning in ncyl == c(4, 6, 8): longer object length is not a multiple of shorter
## object length

Create box plots of city mpg by ncyl

car%>%
  ggplot(aes(x=city_mpg,y=as.factor(ncyl)))+geom_boxplot()+coord_flip()

## Warning: Removed 3 rows containing non-finite values (stat_boxplot).

Create overlaid density plots for same data

ggplot(car, aes(x = city_mpg, fill = as.factor(ncyl))) + geom_density(alpha =.4)

## Warning: Removed 3 rows containing non-finite values (stat_density).

Create hist of horsepwr

ggplot(car,aes(horsepwr))+geom_histogram()

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

Create hist of horsepwr with binwidth of 3

car %>%
  ggplot(aes(horsepwr))+geom_histogram(binwidth = 3)

Construct box plot of msrp

car%>%
  ggplot(aes(msrp))+geom_boxplot()+coord_flip()

Exclude outliers from data more than 100000

car %>%
  filter(msrp < 100000)%>%
  ggplot(aes(x = 1, y = msrp)) +geom_boxplot()