Caret - Assingment 2

install.packages(“caret”) install.packages(“ISLR”) install.packages(“ISLR2”) install.packages(“lattice”)

Step 1

library(ISLR2)
library(caret)

## Loading required package: ggplot2

## Warning: package 'ggplot2' was built under R version 4.3.2

## Loading required package: lattice

## Warning: package 'lattice' was built under R version 4.3.2

library(ggplot2)
library(lattice)
summary(Carseats)

##      Sales          CompPrice       Income        Advertising    
##  Min.   : 0.000   Min.   : 77   Min.   : 21.00   Min.   : 0.000  
##  1st Qu.: 5.390   1st Qu.:115   1st Qu.: 42.75   1st Qu.: 0.000  
##  Median : 7.490   Median :125   Median : 69.00   Median : 5.000  
##  Mean   : 7.496   Mean   :125   Mean   : 68.66   Mean   : 6.635  
##  3rd Qu.: 9.320   3rd Qu.:135   3rd Qu.: 91.00   3rd Qu.:12.000  
##  Max.   :16.270   Max.   :175   Max.   :120.00   Max.   :29.000  
##    Population        Price        ShelveLoc        Age          Education   
##  Min.   : 10.0   Min.   : 24.0   Bad   : 96   Min.   :25.00   Min.   :10.0  
##  1st Qu.:139.0   1st Qu.:100.0   Good  : 85   1st Qu.:39.75   1st Qu.:12.0  
##  Median :272.0   Median :117.0   Medium:219   Median :54.50   Median :14.0  
##  Mean   :264.8   Mean   :115.8                Mean   :53.32   Mean   :13.9  
##  3rd Qu.:398.5   3rd Qu.:131.0                3rd Qu.:66.00   3rd Qu.:16.0  
##  Max.   :509.0   Max.   :191.0                Max.   :80.00   Max.   :18.0  
##  Urban       US     
##  No :118   No :142  
##  Yes:282   Yes:258  
##                     
##                     
##                     
## 

Train_Index=createDataPartition(Carseats$Sales, p=0.75, list = FALSE)

Train_Data=Carseats[Train_Index,]
Test_Data=Carseats[-Train_Index,]

summary(Train_Data$Sales)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   0.000   5.420   7.490   7.537   9.320  16.270

summary(Test_Data$Sales)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   0.160   5.350   7.440   7.374   9.230  15.630

Step 2

Temp_Index = createDataPartition(Train_Data$Sales, p=300/nrow(Train_Data), list = FALSE)

Temp_Data = Train_Data[Temp_Index,]
Test_Data = Train_Data[-Temp_Index,]

Train_Index_2 = createDataPartition(Temp_Data$Sales, p=200/nrow(Temp_Data), list = FALSE)

Training_Data = Temp_Data[Train_Index_2,]
Validation_Data = Temp_Data[-Train_Index_2,]