Playing with dplyr.
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
data(mtcars)
filter(mtcars, mpg>20, cyl == 6)
## mpg cyl disp hp drat wt qsec vs am gear carb
## 1 21.0 6 160 110 3.90 2.620 16.46 0 1 4 4
## 2 21.0 6 160 110 3.90 2.875 17.02 0 1 4 4
## 3 21.4 6 258 110 3.08 3.215 19.44 1 0 3 1
arrange operator same as ‘sort’.
arrange(mtcars, cyl, desc(wt))
## mpg cyl disp hp drat wt qsec vs am gear carb
## 1 24.4 4 146.7 62 3.69 3.190 20.00 1 0 4 2
## 2 22.8 4 140.8 95 3.92 3.150 22.90 1 0 4 2
## 3 21.4 4 121.0 109 4.11 2.780 18.60 1 1 4 2
## 4 21.5 4 120.1 97 3.70 2.465 20.01 1 0 3 1
## 5 22.8 4 108.0 93 3.85 2.320 18.61 1 1 4 1
## 6 32.4 4 78.7 66 4.08 2.200 19.47 1 1 4 1
## 7 26.0 4 120.3 91 4.43 2.140 16.70 0 1 5 2
## 8 27.3 4 79.0 66 4.08 1.935 18.90 1 1 4 1
## 9 33.9 4 71.1 65 4.22 1.835 19.90 1 1 4 1
## 10 30.4 4 75.7 52 4.93 1.615 18.52 1 1 4 2
## 11 30.4 4 95.1 113 3.77 1.513 16.90 1 1 5 2
## 12 18.1 6 225.0 105 2.76 3.460 20.22 1 0 3 1
## 13 19.2 6 167.6 123 3.92 3.440 18.30 1 0 4 4
## 14 17.8 6 167.6 123 3.92 3.440 18.90 1 0 4 4
## 15 21.4 6 258.0 110 3.08 3.215 19.44 1 0 3 1
## 16 21.0 6 160.0 110 3.90 2.875 17.02 0 1 4 4
## 17 19.7 6 145.0 175 3.62 2.770 15.50 0 1 5 6
## 18 21.0 6 160.0 110 3.90 2.620 16.46 0 1 4 4
## 19 10.4 8 460.0 215 3.00 5.424 17.82 0 0 3 4
## 20 14.7 8 440.0 230 3.23 5.345 17.42 0 0 3 4
## 21 10.4 8 472.0 205 2.93 5.250 17.98 0 0 3 4
## 22 16.4 8 275.8 180 3.07 4.070 17.40 0 0 3 3
## 23 19.2 8 400.0 175 3.08 3.845 17.05 0 0 3 2
## 24 13.3 8 350.0 245 3.73 3.840 15.41 0 0 3 4
## 25 15.2 8 275.8 180 3.07 3.780 18.00 0 0 3 3
## 26 17.3 8 275.8 180 3.07 3.730 17.60 0 0 3 3
## 27 14.3 8 360.0 245 3.21 3.570 15.84 0 0 3 4
## 28 15.0 8 301.0 335 3.54 3.570 14.60 0 1 5 8
## 29 15.5 8 318.0 150 2.76 3.520 16.87 0 0 3 2
## 30 18.7 8 360.0 175 3.15 3.440 17.02 0 0 3 2
## 31 15.2 8 304.0 150 3.15 3.435 17.30 0 0 3 2
## 32 15.8 8 351.0 264 4.22 3.170 14.50 0 1 5 4
select - to focus on some important columns only.
select(mtcars, mpg, hp)
## mpg hp
## Mazda RX4 21.0 110
## Mazda RX4 Wag 21.0 110
## Datsun 710 22.8 93
## Hornet 4 Drive 21.4 110
## Hornet Sportabout 18.7 175
## Valiant 18.1 105
## Duster 360 14.3 245
## Merc 240D 24.4 62
## Merc 230 22.8 95
## Merc 280 19.2 123
## Merc 280C 17.8 123
## Merc 450SE 16.4 180
## Merc 450SL 17.3 180
## Merc 450SLC 15.2 180
## Cadillac Fleetwood 10.4 205
## Lincoln Continental 10.4 215
## Chrysler Imperial 14.7 230
## Fiat 128 32.4 66
## Honda Civic 30.4 52
## Toyota Corolla 33.9 65
## Toyota Corona 21.5 97
## Dodge Challenger 15.5 150
## AMC Javelin 15.2 150
## Camaro Z28 13.3 245
## Pontiac Firebird 19.2 175
## Fiat X1-9 27.3 66
## Porsche 914-2 26.0 91
## Lotus Europa 30.4 113
## Ford Pantera L 15.8 264
## Ferrari Dino 19.7 175
## Maserati Bora 15.0 335
## Volvo 142E 21.4 109
To get unique values of a certain column.
distinct(select(mtcars, gear))
## gear
## 1 4
## 2 3
## 3 5
To make new column by operating some old ones.
mutate(mtcars, performance=hp/wt)
## mpg cyl disp hp drat wt qsec vs am gear carb performance
## 1 21.0 6 160.0 110 3.90 2.620 16.46 0 1 4 4 41.98473
## 2 21.0 6 160.0 110 3.90 2.875 17.02 0 1 4 4 38.26087
## 3 22.8 4 108.0 93 3.85 2.320 18.61 1 1 4 1 40.08621
## 4 21.4 6 258.0 110 3.08 3.215 19.44 1 0 3 1 34.21462
## 5 18.7 8 360.0 175 3.15 3.440 17.02 0 0 3 2 50.87209
## 6 18.1 6 225.0 105 2.76 3.460 20.22 1 0 3 1 30.34682
## 7 14.3 8 360.0 245 3.21 3.570 15.84 0 0 3 4 68.62745
## 8 24.4 4 146.7 62 3.69 3.190 20.00 1 0 4 2 19.43574
## 9 22.8 4 140.8 95 3.92 3.150 22.90 1 0 4 2 30.15873
## 10 19.2 6 167.6 123 3.92 3.440 18.30 1 0 4 4 35.75581
## 11 17.8 6 167.6 123 3.92 3.440 18.90 1 0 4 4 35.75581
## 12 16.4 8 275.8 180 3.07 4.070 17.40 0 0 3 3 44.22604
## 13 17.3 8 275.8 180 3.07 3.730 17.60 0 0 3 3 48.25737
## 14 15.2 8 275.8 180 3.07 3.780 18.00 0 0 3 3 47.61905
## 15 10.4 8 472.0 205 2.93 5.250 17.98 0 0 3 4 39.04762
## 16 10.4 8 460.0 215 3.00 5.424 17.82 0 0 3 4 39.63864
## 17 14.7 8 440.0 230 3.23 5.345 17.42 0 0 3 4 43.03087
## 18 32.4 4 78.7 66 4.08 2.200 19.47 1 1 4 1 30.00000
## 19 30.4 4 75.7 52 4.93 1.615 18.52 1 1 4 2 32.19814
## 20 33.9 4 71.1 65 4.22 1.835 19.90 1 1 4 1 35.42234
## 21 21.5 4 120.1 97 3.70 2.465 20.01 1 0 3 1 39.35091
## 22 15.5 8 318.0 150 2.76 3.520 16.87 0 0 3 2 42.61364
## 23 15.2 8 304.0 150 3.15 3.435 17.30 0 0 3 2 43.66812
## 24 13.3 8 350.0 245 3.73 3.840 15.41 0 0 3 4 63.80208
## 25 19.2 8 400.0 175 3.08 3.845 17.05 0 0 3 2 45.51365
## 26 27.3 4 79.0 66 4.08 1.935 18.90 1 1 4 1 34.10853
## 27 26.0 4 120.3 91 4.43 2.140 16.70 0 1 5 2 42.52336
## 28 30.4 4 95.1 113 3.77 1.513 16.90 1 1 5 2 74.68605
## 29 15.8 8 351.0 264 4.22 3.170 14.50 0 1 5 4 83.28076
## 30 19.7 6 145.0 175 3.62 2.770 15.50 0 1 5 6 63.17690
## 31 15.0 8 301.0 335 3.54 3.570 14.60 0 1 5 8 93.83754
## 32 21.4 4 121.0 109 4.11 2.780 18.60 1 1 4 2 39.20863
Calculating mean using dplyr. We can also use Psych, Pastecs, DoBy for more info..
summarise(mtcars, avg_mpg = mean(mpg, na.rm = T))
## avg_mpg
## 1 20.09062
Using pipe operator.
mtcars %>% filter(cyl==6) %>% summarise(mean(hp))
## mean(hp)
## 1 122.2857