CarsPreprocessingReport20220730

Preprocessing in R

here we are trying to some preprocessing

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

##      Sl..No         mpg          cylinders     cubicinches          hp       
##  Min.   :  1   Min.   :10.00   Min.   :3.00   Min.   : 68.0   Min.   : 46.0  
##  1st Qu.: 66   1st Qu.:16.90   1st Qu.:4.00   1st Qu.:101.0   1st Qu.: 75.0  
##  Median :131   Median :22.00   Median :6.00   Median :156.0   Median : 95.0  
##  Mean   :131   Mean   :23.14   Mean   :5.59   Mean   :201.1   Mean   :106.4  
##  3rd Qu.:196   3rd Qu.:28.80   3rd Qu.:8.00   3rd Qu.:302.0   3rd Qu.:138.0  
##  Max.   :261   Max.   :46.60   Max.   :8.00   Max.   :455.0   Max.   :230.0  
##    weightlbs      time.to.60         year         brand          
##  Min.   :1613   Min.   : 8.00   Min.   :1971   Length:261        
##  1st Qu.:2246   1st Qu.:14.00   1st Qu.:1974   Class :character  
##  Median :2835   Median :16.00   Median :1977   Mode  :character  
##  Mean   :3005   Mean   :15.55   Mean   :1977                     
##  3rd Qu.:3664   3rd Qu.:17.00   3rd Qu.:1980                     
##  Max.   :4997   Max.   :25.00   Max.   :1983

GRAPHICAL METHODS FOR IDENTIFYING OUTLIERS

Set up the plot area

Here we are trying to examine the outlierby using Histogram

par(mfrow = c(1,3))

summary(cars$weightlbs)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##    1613    2246    2835    3005    3664    4997

hist(cars$weightlbs,
     breaks = 30,
     xlim = c(1500, 5000),
     col = "blue",
     border = "black",
     ylim = c(0, 20),
     xlab = "Weight",
     ylab = "Counts",
     main = "Histogram
of Car Weights")

scatterplot

Here we are examining the outlierby using the scatter plot

plot(cars$weightlbs,
     cars$mpg,
     xlim = c(1500, 5000),
     ylim = c(0, 50),
     xlab = "Weight",
     ylab = "MPG",
     main = "Scatterplot of MPG by Weight",
     type = "p",
     pch = 20,
     col = "blue")

results from scatter plot

from the scatter plot,wehave observed that majority of data lineswith in the range and not outlier

We are examining theoutlier by using Boxplot

boxplot(mpg ~ cylinders, data = cars, xlab = "Number of Cylinders",
        ylab = "Miles Per Gallon", main = "Mileage Data")

box <- boxplot(mpg ~ brand, data = cars, xlab = "brand",
        ylab = "Miles Per Gallon", main = "Mileage Data")

box <- boxplot(cars$mpg,  xlab = "box",
               ylab = "Miles Per Gallon", main = "Mileage Data")$out

##Creating a data with outlier

cars1 <- edit(cars)
cars1 <- cars1

boxplot(cars1$mpg,  xlab = "box",
               ylab = "Miles Per Gallon", main = "Mileage Data")

box1 <- boxplot(cars1$mpg,  xlab = "box",
               ylab = "Miles Per Gallon", main = "Mileage Data")$out

outliers_data<- cars1[which(cars1$mpg %in% box1),]
outliers_data

##    Sl..No mpg cylinders cubicinches  hp weightlbs time.to.60 year   brand
## 8       8  86         8         440 215      4312          9 1971     US.
## 19     19  76         4         113  95      2278         16 1973  Japan.

cars2 <- cars1[-which(cars1$mpg %in% box1),]