SUBSETTING AND INDEXING

library(MASS)
data("Cars93")
head(Cars93)

Take-out some of the columns

Cars93[,c("Model", "Type", "Price")]

Alternatively, pwede rin Integers specifying the particular columns

Cars93[,c(2,3,5)]

WHICH()

Cars93[,which(colnames(Cars93)=="Model")]

 [1] Integra        Legend         90             100            535i           Century       
 [7] LeSabre        Roadmaster     Riviera        DeVille        Seville        Cavalier      
[13] Corsica        Camaro         Lumina         Lumina_APV     Astro          Caprice       
[19] Corvette       Concorde       LeBaron        Imperial       Colt           Shadow        
[25] Spirit         Caravan        Dynasty        Stealth        Summit         Vision        
[31] Festiva        Escort         Tempo          Mustang        Probe          Aerostar      
[37] Taurus         Crown_Victoria Metro          Storm          Prelude        Civic         
[43] Accord         Excel          Elantra        Scoupe         Sonata         Q45           
[49] ES300          SC300          Continental    Town_Car       323            Protege       
[55] 626            MPV            RX-7           190E           300E           Capri         
[61] Cougar         Mirage         Diamante       Sentra         Altima         Quest         
[67] Maxima         Achieva        Cutlass_Ciera  Silhouette     Eighty-Eight   Laser         
[73] LeMans         Sunbird        Firebird       Grand_Prix     Bonneville     900           
[79] SL             Justy          Loyale         Legacy         Swift          Tercel        
[85] Celica         Camry          Previa         Fox            Eurovan        Passat        
[91] Corrado        240            850           
93 Levels: 100 190E 240 300E 323 535i 626 850 90 900 Accord Achieva Aerostar Altima ... Vision

Find the index number of the column we’re looking for

which(colnames(Cars93)=="Model")

[1] 2

Search for a specific cylinder type

Cars93[which(Cars93$Cylinders=="rotary"),]

attach(Cars93)

Subset rows and columns simultaneously

Cars93[which(Cylinders==8), c("Model","Price")]

Now we can compare the means of those two different groups of cars We take out the “Model” column because we can’t get the mean of that column

mean(Cars93[which(Cars93$Cylinders==6), c("Price")])

[1] 24.38065

mean(Cars93[which(Cars93$Cylinders==8), c("Price")])

[1] 33.78571

We find above that cars with 8 cylinders are a more expensive on average

Create a subset

Ford <- Cars93[which(Cars93$Manufacturer=="Ford"),]

Ford

Forddata <- Cars93[which(Cars93$Manufacturer=="Ford"), c("Weight", "Origin", "Price")]
Forddata

Use “-” or “!” to exclude data.

Ford[-which(Cars93$Cylinders==6),]