In questo documento vediamo alcune funzioni personalizzate che possono essere utili durante il corso. Per poterle utilizzare potete copiare e incollare direttamente la funzione per poi salvarla come oggetto.
put_random_na()put_random_na <- function(data, n){
pos <- list(rows = 1:nrow(data),
cols = 1:ncol(data))
pos <- expand.grid(pos)
na_pos <- sample(1:nrow(pos), n)
for (i in 1:length(na_pos)) {
na_pos_i <- pos[na_pos[i], ]
data[na_pos_i[[1]], na_pos_i[[2]]] <- NA
}
return(data)
}Utilizzo:
put_random_na(mtcars, 30)## mpg cyl disp hp drat wt qsec vs am gear carb
## Mazda RX4 21.0 6 160.0 110 3.90 2.620 16.46 0 1 NA NA
## Mazda RX4 Wag 21.0 6 160.0 110 3.90 2.875 17.02 NA 1 4 4
## Datsun 710 22.8 4 108.0 93 3.85 2.320 18.61 1 1 4 1
## Hornet 4 Drive 21.4 6 258.0 110 NA 3.215 19.44 1 0 3 1
## Hornet Sportabout 18.7 8 360.0 175 3.15 3.440 17.02 0 0 3 2
## Valiant 18.1 6 225.0 105 2.76 3.460 20.22 1 0 3 1
## Duster 360 NA 8 360.0 245 3.21 3.570 15.84 0 0 3 4
## Merc 240D 24.4 4 NA 62 3.69 3.190 20.00 1 0 4 2
## Merc 230 22.8 4 140.8 95 3.92 NA 22.90 1 0 4 NA
## Merc 280 19.2 6 167.6 123 3.92 3.440 18.30 1 0 4 4
## Merc 280C 17.8 6 167.6 123 3.92 3.440 18.90 1 NA 4 4
## Merc 450SE 16.4 8 275.8 180 3.07 4.070 17.40 NA 0 3 3
## Merc 450SL 17.3 8 275.8 180 NA 3.730 17.60 0 0 3 3
## Merc 450SLC 15.2 8 275.8 180 NA 3.780 18.00 0 0 3 3
## Cadillac Fleetwood 10.4 8 NA 205 2.93 5.250 17.98 0 0 NA 4
## Lincoln Continental 10.4 8 460.0 215 3.00 5.424 17.82 NA 0 3 4
## Chrysler Imperial 14.7 NA 440.0 230 3.23 5.345 17.42 0 0 3 4
## Fiat 128 32.4 4 78.7 66 4.08 2.200 19.47 1 1 4 1
## Honda Civic 30.4 4 75.7 52 4.93 1.615 18.52 NA 1 4 2
## Toyota Corolla 33.9 4 71.1 65 4.22 1.835 19.90 1 1 4 1
## Toyota Corona 21.5 4 120.1 97 3.70 2.465 20.01 1 0 3 1
## Dodge Challenger NA 8 318.0 150 2.76 3.520 16.87 0 0 NA 2
## AMC Javelin NA 8 304.0 150 3.15 NA 17.30 0 0 3 2
## Camaro Z28 NA 8 350.0 245 3.73 3.840 15.41 0 0 3 4
## Pontiac Firebird 19.2 8 400.0 175 3.08 3.845 17.05 0 0 NA 2
## Fiat X1-9 27.3 4 79.0 66 4.08 1.935 18.90 1 1 4 NA
## Porsche 914-2 26.0 4 120.3 NA 4.43 2.140 NA 0 1 5 2
## Lotus Europa 30.4 4 95.1 113 3.77 1.513 16.90 1 1 5 2
## Ford Pantera L 15.8 8 351.0 264 4.22 3.170 14.50 NA 1 5 4
## Ferrari Dino NA 6 145.0 NA 3.62 2.770 15.50 0 1 5 6
## Maserati Bora 15.0 8 301.0 335 3.54 3.570 14.60 0 NA 5 8
## Volvo 142E 21.4 4 121.0 109 4.11 2.780 18.60 1 1 4 2randomize_case()randomize_case <- function(x, nletters = 15, n_prob = 0.30){
new_x <- tolower(x)
to_randomize <- sample(LETTERS, nletters)
names(to_randomize) <- tolower(to_randomize)
n_to_randomize <- floor(length(x) * n_prob)
id_to_randomize <- sample(1:length(x), n_to_randomize)
new_x[id_to_randomize] <- stringr::str_replace_all(new_x[id_to_randomize], to_randomize)
return(new_x)
}Utilizzo:
randomize_case(iris$Species)## [1] "setosa" "setosa" "setosa" "setosa" "setosa" "setosa"
## [7] "SEToSa" "SEToSa" "setosa" "setosa" "SEToSa" "setosa"
## [13] "setosa" "SEToSa" "SEToSa" "setosa" "setosa" "SEToSa"
## [19] "setosa" "setosa" "setosa" "setosa" "SEToSa" "SEToSa"
## [25] "setosa" "setosa" "setosa" "SEToSa" "setosa" "SEToSa"
## [31] "setosa" "setosa" "setosa" "SEToSa" "SEToSa" "setosa"
## [37] "setosa" "SEToSa" "setosa" "SEToSa" "setosa" "setosa"
## [43] "setosa" "setosa" "setosa" "setosa" "setosa" "setosa"
## [49] "SEToSa" "setosa" "versicolor" "versicolor" "versicolor" "versicolor"
## [55] "VERSICoLoR" "versicolor" "VERSICoLoR" "VERSICoLoR" "versicolor" "versicolor"
## [61] "versicolor" "versicolor" "VERSICoLoR" "versicolor" "VERSICoLoR" "versicolor"
## [67] "versicolor" "versicolor" "versicolor" "versicolor" "versicolor" "VERSICoLoR"
## [73] "VERSICoLoR" "VERSICoLoR" "versicolor" "versicolor" "versicolor" "VERSICoLoR"
## [79] "VERSICoLoR" "versicolor" "versicolor" "versicolor" "VERSICoLoR" "VERSICoLoR"
## [85] "versicolor" "versicolor" "versicolor" "versicolor" "versicolor" "versicolor"
## [91] "versicolor" "versicolor" "VERSICoLoR" "VERSICoLoR" "versicolor" "versicolor"
## [97] "versicolor" "versicolor" "versicolor" "versicolor" "VIRgINICa" "VIRgINICa"
## [103] "virginica" "VIRgINICa" "virginica" "VIRgINICa" "virginica" "virginica"
## [109] "VIRgINICa" "VIRgINICa" "virginica" "virginica" "virginica" "virginica"
## [115] "virginica" "virginica" "virginica" "VIRgINICa" "VIRgINICa" "virginica"
## [121] "VIRgINICa" "VIRgINICa" "VIRgINICa" "virginica" "virginica" "virginica"
## [127] "virginica" "virginica" "virginica" "virginica" "VIRgINICa" "virginica"
## [133] "virginica" "virginica" "virginica" "virginica" "virginica" "virginica"
## [139] "virginica" "virginica" "virginica" "VIRgINICa" "virginica" "virginica"
## [145] "VIRgINICa" "VIRgINICa" "VIRgINICa" "virginica" "virginica" "virginica"