Curso básico de iniciación a la programación con R

Álvaro Mauricio Bustamante Lozano.

# Atributos, entrada y coerción

> x<-5
> x
[1] 5
> #Vector de números
> x<- 1:100
> x
[1] 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 1
7 18 19 20
[21] 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36
37 38 39 40
[41] 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56
57 58 59 60
[61] 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76
77 78 79 80
[81] 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96
97 98 99 100
> #Vectores de objetos c()
> #Vector numérico
> x<- c(0.3, 0.9)
> x
[1] 0.3 0.9
> x<- c(1, 5, 6 , 8 ,2, 6 , 9, 4,3)
> x
[1] 1 5 6 8 2 6 9 4 3
> #vector lógico
> x<-c(TRUE, FALSE, FALSE, TRUE)
> x
[1] TRUE FALSE FALSE TRUE
> # Caracteres
> x<- c("a", "b", "d", "t")
> x
[1] "a" "b" "d" "t"
> # Vector complejo
> x<- c(1+0i, 2+4i, 3+6i)
> x
[1] 1+0i 2+4i 3+6i
> #Usando la instrucción vector
> x<- vector("numeric", length = 10)
> x
[1] 0 0 0 0 0 0 0 0 0 0
> x<- 1:100
> class(x)
[1] "integer"
> #matrices
> #Función matrix
> m<- matrix(1:6, nrow = 2, ncol = 3)
> m
[,1] [,2] [,3]
[1,] 1 3 5
[2,] 2 4 6
> dim(m)
[1] 2 3
> #Instrucción dim
> m<- 1:10
> m
[1] 1 2 3 4 5 6 7 8 9 10
> dim(m) <- c(2,5)
> m
[,1] [,2] [,3] [,4] [,5]
[1,] 1 3 5 7 9
[2,] 2 4 6 8 10
> d<- 1:20
> dim(d) <- c(4,5)
> d
[,1] [,2] [,3] [,4] [,5]
[1,] 1 5 9 13 17
[2,] 2 6 10 14 18
[3,] 3 7 11 15 19
[4,] 4 8 12 16 20
> #Función cbind y rbind
> x<-5:8
> y<-12:15
> cbind(x,y)
x y
[1,] 5 12
[2,] 6 13
[3,] 7 14
[4,] 8 15
> rbind(x,y)
[,1] [,2] [,3] [,4]
x 5 6 7 8
y 12 13 14 15
> #Operaciones vectoriales y reglas de procedencia
> ?base:sintax
> x<-7:10
> y<-9:12
> x+y
[1] 16 18 20 22
> x>8
[1] FALSE FALSE TRUE TRUE
> y==11
[1] FALSE FALSE TRUE FALSE
> x*y
[1] 63 80 99 120
> x/y
[1] 0.7777778 0.8000000 0.8181818 0.8333333
> x<-matrix(1:16, 4, 4)
> y<-matrix(rep(5,16), 4,4)
> x
[,1] [,2] [,3] [,4]
[1,] 1 5 9 13
[2,] 2 6 10 14
[3,] 3 7 11 15
[4,] 4 8 12 16
> y
[,1] [,2] [,3] [,4]
[1,] 5 5 5 5
[2,] 5 5 5 5
[3,] 5 5 5 5
[4,] 5 5 5 5
> x+y
[,1] [,2] [,3] [,4]
[1,] 6 10 14 18
[2,] 7 11 15 19
[3,] 8 12 16 20
[4,] 9 13 17 21
> x*y
[,1] [,2] [,3] [,4]
[1,] 5 25 45 65
[2,] 10 30 50 70
[3,] 15 35 55 75
[4,] 20 40 60 80
> x%%y
[,1] [,2] [,3] [,4]
[1,] 1 0 4 3
[2,] 2 1 0 4
[3,] 3 2 1 0
[4,] 4 3 2 1
matriz1 <- matrix(0,4,4)
matriz1 <- matrix(c(1:25),5,5,T)
matriz1

myarray = array(1:12, dim = c(2,3,4))

myarray

matriz1[1,2]

matriz1
matriz2 <- matrix(3,5,5)
matriz2
#Combinar matrices Cbind y rbind

matriz3 <- cbind(matriz1,matriz2)

matriz3

matriz4 <- rbind(matriz1,matriz2)

matriz4

t(matriz1) # transpuesta
diag(matriz1)
det(matriz1)
matriz1*matriz2
matriz1*34

#Resolver sistemas de ecuaciones lineales

# +x -3y +2z = -3
# +5x +6y -z = 13
# +4x -y +3z = 8

A = matrix(c(1,5,4,-3,6,-1,2,-1,3),3,3)
A
B = matrix(c(-3,13,8),3,1)
B
C <- solve(A,B)
C
#Listas, Factores, Valores faltantes
> #Vectores con distintos tipos de datos
> x<-list(1, "a", TRUE, 1+8i)
> x
[[1]]
[1] 1

[[2]]
[1] "a"
[[3]]
[1] TRUE

[[4]]
[1] 1+8i

> #Los factores son untipo especial de vectores, usado para representa
e datos categóricos
> x<-factor(c("yes", "yes", "no"))
> x
[1] yes yes no
Levels: no yes
> x<-(c("Futbol", "ciclismo", "Futbol", "Boxeo", "Futbol", "Boxeo", "c
iclismo"))
>
> x
[1] "Futbol" "ciclismo" "Futbol" "Boxeo" "Futbol" "Boxeo"
"ciclismo"
> table(x)
x
Boxeo ciclismo Futbol
2 2 3
> unclass(x)
[1] "Futbol" "ciclismo" "Futbol" "Boxeo" "Futbol" "Boxeo"
"ciclismo"
> x<-factor(c("si", "no", "no"), levels = c("si","no"))
> x
[1] si no no
Levels: si no
> #Datos faltantes
> x<-c(5, 6, NA, 9, 10)
> is.nan(x)
[1] FALSE FALSE FALSE FALSE FALSE
> is.na(x)
[1] FALSE FALSE TRUE FALSE FALSE
is.na(x)
[1] FALSE FALSE TRUE TRUE FALSE FALSE
> x<-data.frame(columna1 = 1:4, columna2 = c(T, T, T, F))
> x
columna1 columna2
1 1 TRUE
2 2 TRUE
3 3 TRUE
4 4 FALSE
> m<-matrix(1:15, nrow= 5, ncol = 3)
> dimnames <- list(c("a", "b", "c", "d", "e"), c("e", "f", "g"))
> m
[,1] [,2] [,3]
[1,] 1 6 11
[2,] 2 7 12
[3,] 3 8 13
[4,] 4 9 14
[5,] 5 10 15
> dimnames <- list(c("a", "b", "c", "d", "e"), c("f", "g", "h"))
> m
[,1] [,2] [,3]
[1,] 1 6 11
[2,] 2 7 12
[3,] 3 8 13
[4,] 4 9 14
[5,] 5 10 15
> dimnames <- list(c("f", "g", "h"), c("a", "b", "c", "d", "e"))
> m
[,1] [,2] [,3]
[1,] 1 6 11
[2,] 2 7 12
[3,] 3 8 13
[4,] 4 9 14
[5,] 5 10 15
> dimnames <- list(c("f", "g", "h"), c("a", "b", "j", "d", "e"))
> m
[,1] [,2] [,3]
[1,] 1 6 11
[2,] 2 7 12
[3,] 3 8 13
[4,] 4 9 14
[5,] 5 10 15
> dimnames <- list(c("a", "b", "j", "d", "e"), c("f", "g", "h"))
> m
[,1] [,2] [,3]
[1,] 1 6 11
[2,] 2 7 12
[3,] 3 8 13
[4,] 4 9 14
[5,] 5 10 15
> m<-matrix(1:4, nrow = 2, ncol =2)
> dimnames<-list(c("a", "b"), c("h", "i"))
> m
[,1] [,2]
[1,] 1 3
[2,] 2 4
> dimnames<-list(c("a","b"), c("h","i"))
> m
[,1] [,2]
[1,] 1 3
[2,] 2 4
> #Extraer elementos
> x<-c("a", "b", "c", "d", "a")
> x[3]
[1] "c"
> x[1]
[1] "a"
> x[1:5]
[1] "a" "b" "c" "d" "a"
> x[x>"b"]
[1] "c" "d"
index<-x>"a"
> index
[1] FALSE TRUE TRUE TRUE FALSE
> x[index]
[1] "b" "c" "d"
> #con matrices
> x<.matrix(1:10, 2, 5)
Error in .matrix(1:10, 2, 5) : could not find function ".matrix"
> x<- matrix(1:10, 2, 5)
> x
[,1] [,2] [,3] [,4] [,5]
[1,] 1 3 5 7 9
[2,] 2 4 6 8 10
> x[1,]
[1] 1 3 5 7 9
> x[,4]
[1] 7 8
> x[1,3]
[1] 5
> x
[,1] [,2] [,3] [,4] [,5]
[1,] 1 3 5 7 9
[2,] 2 4 6 8 10
> x<-matrix(1:20, 5, 4)
> x[3,4]
[1] 18
> x[3, 4, drop = FALSE]
[,1]
[1,] 18
> x[1,]
class(x[1,])
[1] "integer"
> x
[,1] [,2] [,3] [,4]
[1,] 1 6 11 16
[2,] 2 7 12 17
[3,] 3 8 13 18
[4,] 4 9 14 19
[5,] 5 10 15 20
> airquality[1:7,]
Ozone Solar.R Wind Temp Month Day
1 41 190 7.4 67 5 1
2 36 118 8.0 72 5 2
3 12 149 12.6 74 5 3
4 18 313 11.5 62 5 4
5 NA NA 14.3 56 5 5
6 28 NA 14.9 66 5 6
7 23 299 8.6 65 5 7
no_faltantes<-complete.cases(airquality)
> no_faltantes
[1] TRUE TRUE TRUE TRUE FALSE FALSE TRUE TRUE TRUE FALSE FALS
E TRUE TRUE
[14] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRU
E FALSE FALSE
[27] FALSE TRUE TRUE TRUE TRUE FALSE FALSE FALSE FALSE FALSE FALS
E TRUE FALSE
[40] TRUE TRUE FALSE FALSE TRUE FALSE FALSE TRUE TRUE TRUE TRU
E TRUE FALSE
[53] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE TRUE TRU
E TRUE FALSE
[66] TRUE TRUE TRUE TRUE TRUE TRUE FALSE TRUE TRUE FALSE TRU
E TRUE TRUE
[79] TRUE TRUE TRUE TRUE FALSE FALSE TRUE TRUE TRUE TRUE TRU
E TRUE TRUE
[92] TRUE TRUE TRUE TRUE FALSE FALSE FALSE TRUE TRUE TRUE FALS
E FALSE TRUE
[105] TRUE TRUE FALSE TRUE TRUE TRUE TRUE TRUE TRUE TRUE FALS
E TRUE TRUE
[118] TRUE FALSE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRU
E TRUE TRUE
[131] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRU
E TRUE TRUE
[144] TRUE TRUE TRUE TRUE TRUE TRUE FALSE TRUE TRUE TRUE
airquality[no_faltantes,][1:5]
Ozone Solar.R Wind Temp Month
1 41 190 7.4 67 5
2 36 118 8.0 72 5
3 12 149
#Función plot
> plot(c(1, 2, 3), c(4, 5, 5))
> plot(c(1, 2, 3), c(4, 5, 5), pch="x")
> plot(c(1, 2, 3), c(4, 5, 5), pch="m")
> plot(c(1, 3), c(1, 8), type = "n", xlab = "Valores de x", ylab = "Va
lores de y")
> #la anterior es una gráfica vacía
> #c(1, 3), c(1, 8) informa sobre el rotulado de los ejes
> #type = "n"Informa que es una gráfica sin puntos
> #xlab = "Valores de x", ylab = "Valores de y" Etiqueta de los ejes
> #Podemos agregar algunos puntos
> x<-c(1, 2, 3)
> y<-c(2, 4, 8)
> points(x, y)
> #Queremos agregar una línea (Ajuste lineal)
> mi_linea<-lm(y~x)
> abline(mi_linea)
> class(mi_linea)
[1] "lm"
> mi_linea

Call:
lm(formula = y ~ x)

Coefficients:
(Intercept) x
-1.333 3.000

> #superponer otra linea

> lines(c(1,4), c(4,7))
> #para diferenciarla podemos cambiarle el color
> lines(c(1,4), c(4,7), col = "green")
> #para guardar la gráfica en R: Export
> #También se puede guardar con las instrucciones pdf("Archivo.pdf") p
ng("Archivo.png")
> #Jpeg("Archivo.jpeg) postscript("Archivo.ps") se debe dar la cadena
de ruta
> #Funciones gráficas de alto nivel
> iris
Sepal.Length Sepal.Width Petal.Length Petal.Width Species
1 5.1 3.5 1.4 0.2 setosa
2 4.9 3.0 1.4 0.2 setosa
3 4.7 3.2 1.3 0.2 setosa
4 4.6
hist(iris$Sepal.Length, freq = FALSE)
> hist(iris$Sepal.Length)
> #Se puede agregar freq = FALSE para que en el eje y pinte la probabi
lidad y no la frecuencia

hist(iris$Sepal.Length, breaks = 10, col = "red")

> datos<-iris$Sepal.Width
> h<-hist(datos, breaks = 10, col = "green")
> xfit<-seq(min(datos), max(datos), length = 40)
> yfit<-dnorm(xfit, mean = mean(datos), sd = sd(datos))
> yfit<-yfit*diff(h$mids[1:2])*length(datos)
> lines(xfit, yfit, col = "blue", lwd = 2)
> density(datos)

Call:
density.default(x = datos)

Data: datos (150 obs.); Bandwidth 'bw' = 0.1233

x y
 Min. :1.630 Min. :0.0002431
1st Qu.:2.415 1st Qu.:0.0353665
Median :3.200 Median :0.2170174
Mean :3.200 Mean :0.3181879
3rd Qu.:3.985 3rd Qu.:0.5372552
Max. :4.770 Max. :1.0623691
> plot(density(datos))
mtcars
mpg cyl disp hp drat wt qsec vs am gear car
b
Mazda RX4 21.0 6 160.0 110 3.90 2.620 16.46 0 1 4
4
Mazda RX4 Wag 21.0 6 160.0 110 3.90 2.875 17.02 0 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
mtcars$mpg
[1] 21.0 21.0 22.8 21.4 18.7 18.1 14.3 24.4 22.8 19.2 17.8 16.4 17.3
15.2 10.4 10.4
[17] 14.7 32.4 30.4 33.9 21.5 15.5 15.2 13.3 19.2 27.3 26.0 30.4 15.8
19.7 15.0 21.4
> row.names(mtcars)
[1] "Mazda RX4" "Mazda RX4 Wag" "Datsun 710"
[4] "Hornet 4 Drive" "Hornet Sportabout" "Valiant"
[7] "Duster 360" "Merc 240D" "Merc 230"
[10] "Merc 280" "Merc 280C" "Merc 450SE"
[13] "Merc 450SL" "Merc 450SLC" "Cadillac Fleetwood"
[16] "Lincoln Continental" "Chrysler Imperial" "Fiat 128"
[19] "Honda Civic" "Toyota Corolla" "Toyota Corona"
[22] "Dodge Challenger" "AMC Javelin" "Camaro Z28"
[25] "Pontiac Firebird" "Fiat X1-9" "Porsche 914-2"
[28] "Lotus Europa" "Ford Pantera L" "Ferrari Dino"
[31] "Maserati Bora" "Volvo 142E"
> dotchart(mtcars$mpg, labels = row.names(mtcars))
> tail(mtcars)
mpg cyl disp hp drat wt qsec vs am gear carb
Porsche 914-2 26.0 4 120.3 91 4.43 2.140 16.7 0 1 5 2
Lotus Europa 30.4 4 95.1 113 3.77 1.513 16.9 1 1 5 2
Ford Pantera L 15.8 8 351.0 264 4.22 3.170 14.5 0 1 5 4
Ferrari Dino 19.7 6 145.0 175 3.62 2.770 15.5 0 1 5 6
Maserati Bora 15.0 8 301.0 335 3.54 3.570 14.6 0 1 5 8
Volvo 142E 21.4 4 121.0 109 4.11 2.780 18.6 1 1 4 2
> boxplot(mpg~cyl, data = mtcars)
hist(datos, main = "Histograma de Frecuencias", sub = "Millas por galó
n", xlab = "Límite de clase para los Datos", ylab = "Frecuencia absolu
ta", breaks = 9, col = "blue" )
h<-hist(datos, main = "Histograma de Frecuencias", sub = "Millas por g
alón", xlab = "Límite de clase para los Datos", ylab = "Frecuencia abs
oluta", breaks = 9, col = "blue")
> xfit<-seq(min(datos), max(datos), length = 40)
> yfit<-dnorm(xfit, mean = mean(datos), sd = sd(datos))
yfit<-yfit*diff(h$mids[1:2])*length(datos)
> lines(xfit, yfit, col = "red", lwd = 2)
boxplot(mpg~cyl, data = mtcars, col = 2:4)
pie(c(50, 50, 50), labels = levels(iris$Species))
install.packages("rgl")
x<-sort(rnorm(1000))
> y<-rnorm(1000)
> z<-rnorm(1000) +atan2(x,y)
> open3d()
wgl
1
plot3d(x, y, z, col = rainbow(1000), type = "p")
x<-iris$Sepal.Length
> y<-iris$Petal.Length
> z<-iris$Sepal.Width
plot3d(iris$Sepal.Length, iris$Petal.Length, iris$Sepal.Width, type =
"s", col = rainbow(150))
plot3d(iris$Sepal.Length, iris$Petal.Length, iris$Sepal.Width, type =
"s", col = rainbow(150), main = "Flores", xlab = "Longitus S", ylab =
"Longitud P", zlab = "Grosor S.")
install.packages("ggplot2")
also installing the dependency ‘isoband’

trying URL 'https://cran.rstudio.com/bin/windows/contrib/3.6/isoband_0.2.1.zip'

Content type 'application/zip' length 3304390 bytes (3.2 MB)
downloaded 3.2 MB
trying URL 'https://cran.rstudio.com/bin/windows/contrib/3.6/ggplot2_3.3.1.zip'
Content type 'application/zip' length 4023199 bytes (3.8 MB)
downloaded 3.8 MB
package ‘isoband’ successfully unpacked and MD5 sums checked
package ‘ggplot2’ successfully unpacked and MD5 sums checked
The downloaded binary packages are in
C:\Users\mauricio\AppData\Local\Temp\RtmpkbnHsl\downloaded_packages

>
library(ggplot2)
Warning message:
package ‘ggplot2’ was built under R version 3.6.3
> qplot(carat, price, data = diamonds)
qplot(color, data=diamonds)
qplot(color,price/carat, data=diamonds,geom="boxplot")
> qplot(carat,price,data=dchico,alpha=I(1/10))
qplot(color, data=diamonds, geom="density")