TALLER 14 - USO DE APPLY, TAPPLY, SAPPLY
Erazo Gabriela, Espinosa Ricardo, Gavilanes Mayra, Guamán Jennifer
2022-08-16
UNIVERSIDAD CENTRAL DEL ECUADOR
FACULTAD DE CIENCIAS ECONÓMICAS
INGENIERIA EN ESTADÍSTICA
APLICANDO CONOCIMIENTOS ADQUIRIDOS ACERCA DE LA FUNCIÓN APPLY, SAPPLY, TAPPLY
En este documento se presentan 4 ejercicios de aprendizaje sobre funciones como apply, sapply, tapply, para la comunidad de RStudio.
AUTORES
- Erazo Gabriela A.
- Espinosa Ricardo O.
- Gavilanes Mayra A.
- Guamán Jennifer G.
COLABORACIÓN
- Profesor: Francisco Valverde (PhD en informática)
EJERCICIOS
EJERCICIO 1 - APPLY
# Data frame
df <- data.frame(x = 1:4, y = 5:8, z = 10:13)
df## x y z
## 1 1 5 10
## 2 2 6 11
## 3 3 7 12
## 4 4 8 13apply(X = df, MARGIN = 1, FUN = sum)## [1] 16 19 22 25apply(df, 1, sum)## [1] 16 19 22 25apply(df[c(1, 2), ], 1, sum)## 1 2
## 16 19apply(df, 2, sum)## x y z
## 10 26 46apply(df[, c(1, 3)], 2, sum)## x z
## 10 46apply(df, c(1, 2), sum)## x y z
## [1,] 1 5 10
## [2,] 2 6 11
## [3,] 3 7 12
## [4,] 4 8 13apply(df, c(2, 1), sum)## [,1] [,2] [,3] [,4]
## x 1 2 3 4
## y 5 6 7 8
## z 10 11 12 13apply(df, 1, mean, na.rm = TRUE)## [1] 5.333333 6.333333 7.333333 8.333333# FUNCION
fun <- function(x, character = FALSE) {
if (character == FALSE) {
x ^ 2
} else {
as.character(x ^2)
}
}
apply(df, 1, fun)## [,1] [,2] [,3] [,4]
## x 1 4 9 16
## y 25 36 49 64
## z 100 121 144 169apply(df, 1, fun, character = TRUE)## [,1] [,2] [,3] [,4]
## [1,] "1" "4" "9" "16"
## [2,] "25" "36" "49" "64"
## [3,] "100" "121" "144" "169"apply(df, 2, fun)## x y z
## [1,] 1 25 100
## [2,] 4 36 121
## [3,] 9 49 144
## [4,] 16 64 169apply(df, c(1, 2), fun)## x y z
## [1,] 1 25 100
## [2,] 4 36 121
## [3,] 9 49 144
## [4,] 16 64 169f <- function(x) sum(exp(x))
apply(df, 1, f)## [1] 22177.60 60284.96 163871.51 445448.95apply(df, 2, f)## x y z
## 84.79102 4629.43310 687068.79094apply(df, 1:2, f)## x y z
## [1,] 2.718282 148.4132 22026.47
## [2,] 7.389056 403.4288 59874.14
## [3,] 20.085537 1096.6332 162754.79
## [4,] 54.598150 2980.9580 442413.39apply(df, 2, min)## x y z
## 1 5 10apply(df, 2, range)## x y z
## [1,] 1 5 10
## [2,] 4 8 13apply(df, 1, summary)## [,1] [,2] [,3] [,4]
## Min. 1.000000 2.000000 3.000000 4.000000
## 1st Qu. 3.000000 4.000000 5.000000 6.000000
## Median 5.000000 6.000000 7.000000 8.000000
## Mean 5.333333 6.333333 7.333333 8.333333
## 3rd Qu. 7.500000 8.500000 9.500000 10.500000
## Max. 10.000000 11.000000 12.000000 13.000000apply(df, 2, summary)## x y z
## Min. 1.00 5.00 10.00
## 1st Qu. 1.75 5.75 10.75
## Median 2.50 6.50 11.50
## Mean 2.50 6.50 11.50
## 3rd Qu. 3.25 7.25 12.25
## Max. 4.00 8.00 13.00ar <- array(data = 1:18, dim = c(3, 2, 3))
apply(ar, 3, sum)## [1] 21 57 93EJERCICIO 2 - TAPPLY
set.seed(2)
data_set <- data.frame(precio = round(rnorm(25, sd = 10, mean = 30)),
tipo = sample(1:4, size = 25, replace = TRUE),
tienda = sample(paste("Tienda", 1:4),
size = 25, replace = TRUE))
head(data_set)## precio tipo tienda
## 1 21 2 Tienda 2
## 2 32 3 Tienda 3
## 3 46 4 Tienda 4
## 4 19 3 Tienda 4
## 5 29 1 Tienda 4
## 6 31 3 Tienda 4precio <- data_set$precio
tienda<- data_set$tienda
tipo <- factor(data_set$tipo,
labels = c("Juguetes", "Comida", "Electrónica", "Bebidas"))
precios_medios <- tapply(precio, tipo, mean)
precios_medios## Juguetes Comida Electrónica Bebidas
## 39.50000 30.33333 32.20000 29.33333class(precios_medios)## [1] "array"precios_medios[2]## Comida
## 30.33333lista_precios_medios <- tapply(precio, tipo, mean, simplify = FALSE)
lista_precios_medios## $Juguetes
## [1] 39.5
##
## $Comida
## [1] 30.33333
##
## $Electrónica
## [1] 32.2
##
## $Bebidas
## [1] 29.33333lista_precios_medios$Juguetes## [1] 39.5data_set[1, 1] <- NA
data_set[2, 3] <- NA
tapply(data_set$precio, data_set$tienda, mean)## Tienda 1 Tienda 2 Tienda 3 Tienda 4
## 32.00000 NA 39.25000 33.14286tapply(data_set$precio, data_set$tienda, mean, na.rm = TRUE)## Tienda 1 Tienda 2 Tienda 3 Tienda 4
## 32.00000 33.50000 39.25000 33.14286f <- function(x) mean(x, na.rm = TRUE)
tapply(data_set$precio, data_set$tienda, f)## Tienda 1 Tienda 2 Tienda 3 Tienda 4
## 32.00000 33.50000 39.25000 33.14286tapply(precio, list(tipo, tienda), mean)## Tienda 1 Tienda 2 Tienda 3 Tienda 4
## Juguetes 46 31.00000 49 36.66667
## Comida 26 30.33333 39 NA
## Electrónica 50 29.00000 32 25.00000
## Bebidas 22 40.00000 20 36.00000tapply(precio, list(tipo, tienda), mean, default = 0)## Tienda 1 Tienda 2 Tienda 3 Tienda 4
## Juguetes 46 31.00000 49 36.66667
## Comida 26 30.33333 39 0.00000
## Electrónica 50 29.00000 32 25.00000
## Bebidas 22 40.00000 20 36.00000EJERCICIO 3 - SAPPLY
sapply(1:4, sqrt)## [1] 1.000000 1.414214 1.732051 2.000000sapply(1:4, function(i) sqrt(i))## [1] 1.000000 1.414214 1.732051 2.000000mi_fun <- function(i) {
sqrt(i)
}
sapply(1:4, mi_fun)## [1] 1.000000 1.414214 1.732051 2.000000out <- numeric(10)
for (i in 1:10) {
out[i] <- i ^ 2
}
out## [1] 1 4 9 16 25 36 49 64 81 100sapply(1:10, function(i) i ^ 2)## [1] 1 4 9 16 25 36 49 64 81 100Lista <- list(A = 1:5, B = 6:20, C = 1)
sapply(Lista, length)## A B C
## 5 15 1EJERCICIO 4 - SAPPLY VS LAPPLY
sapply(c(3, 5, 7), exp)## [1] 20.08554 148.41316 1096.63316lapply(c(3, 5, 7), exp)## [[1]]
## [1] 20.08554
##
## [[2]]
## [1] 148.4132
##
## [[3]]
## [1] 1096.633sapply(c(3, 5, 7), exp, simplify = FALSE)## [[1]]
## [1] 20.08554
##
## [[2]]
## [1] 148.4132
##
## [[3]]
## [1] 1096.633as.list(sapply(c(3, 5, 7), exp))## [[1]]
## [1] 20.08554
##
## [[2]]
## [1] 148.4132
##
## [[3]]
## [1] 1096.633simplify2array(lapply(c(3, 5, 7), exp))## [1] 20.08554 148.41316 1096.63316unlist(lapply(c(3, 5, 7), exp))## [1] 20.08554 148.41316 1096.63316mi_lista <- list(A = c(1, 4, 6), B = c(8, NA, 9 , 5))
sapply(mi_lista, sum)## A B
## 11 NAsapply(mi_lista, sum, na.rm = TRUE)## A B
## 11 22matrix(1, ncol = 3, nrow = 3)## [,1] [,2] [,3]
## [1,] 1 1 1
## [2,] 1 1 1
## [3,] 1 1 1sapply(1:3, function(i) matrix(i, ncol = 3, nrow = 3))## [,1] [,2] [,3]
## [1,] 1 2 3
## [2,] 1 2 3
## [3,] 1 2 3
## [4,] 1 2 3
## [5,] 1 2 3
## [6,] 1 2 3
## [7,] 1 2 3
## [8,] 1 2 3
## [9,] 1 2 3sapply(1:3, function(i) matrix(i, ncol = 3, nrow = 3), simplify = "array")## , , 1
##
## [,1] [,2] [,3]
## [1,] 1 1 1
## [2,] 1 1 1
## [3,] 1 1 1
##
## , , 2
##
## [,1] [,2] [,3]
## [1,] 2 2 2
## [2,] 2 2 2
## [3,] 2 2 2
##
## , , 3
##
## [,1] [,2] [,3]
## [1,] 3 3 3
## [2,] 3 3 3
## [3,] 3 3 3sapply(1:3, function(i) matrix(i, ncol = 3, nrow = 3), simplify = FALSE)## [[1]]
## [,1] [,2] [,3]
## [1,] 1 1 1
## [2,] 1 1 1
## [3,] 1 1 1
##
## [[2]]
## [,1] [,2] [,3]
## [1,] 2 2 2
## [2,] 2 2 2
## [3,] 2 2 2
##
## [[3]]
## [,1] [,2] [,3]
## [1,] 3 3 3
## [2,] 3 3 3
## [3,] 3 3 3df <- trees
res <- data.frame()
for(i in 1:ncol(df)) {
for (j in 1:nrow(df)) {
res[j, i] <- df[j, i] * 2
}
}
sapply(1:ncol(df), function(i) {
sapply(1:nrow(df), function(j) {
df[j, i] * 2
})
})## [,1] [,2] [,3]
## [1,] 16.6 140 20.6
## [2,] 17.2 130 20.6
## [3,] 17.6 126 20.4
## [4,] 21.0 144 32.8
## [5,] 21.4 162 37.6
## [6,] 21.6 166 39.4
## [7,] 22.0 132 31.2
## [8,] 22.0 150 36.4
## [9,] 22.2 160 45.2
## [10,] 22.4 150 39.8
## [11,] 22.6 158 48.4
## [12,] 22.8 152 42.0
## [13,] 22.8 152 42.8
## [14,] 23.4 138 42.6
## [15,] 24.0 150 38.2
## [16,] 25.8 148 44.4
## [17,] 25.8 170 67.6
## [18,] 26.6 172 54.8
## [19,] 27.4 142 51.4
## [20,] 27.6 128 49.8
## [21,] 28.0 156 69.0
## [22,] 28.4 160 63.4
## [23,] 29.0 148 72.6
## [24,] 32.0 144 76.6
## [25,] 32.6 154 85.2
## [26,] 34.6 162 110.8
## [27,] 35.0 164 111.4
## [28,] 35.8 160 116.6
## [29,] 36.0 160 103.0
## [30,] 36.0 160 102.0
## [31,] 41.2 174 154.0plot(rnorm(10), ylim = c(-6, 6))
nlines <- 5
for (i in 1:nlines) {
lines(-i:i, col = i, lwd = 3)
}
plot(rnorm(10), ylim = c(-6, 6))
nlines <- 5
invisible(sapply(1:nlines, function(i) lines(-i:i, col = i, lwd = 3)))
EL CONOCIMIENTO ES LA GUÍA PARA FORJAR UN FUTURO MEJOR