R Notebook

cargar la libreria para hacer unos graficos

2 + 2 ???

library(ggplot2)
library(dplyr)
glimpse(mpg)

Observations: 234
Variables: 11
$ manufacturer <chr> "audi", "audi", "audi", "audi", "audi", "audi", "audi", "audi", "...
$ model        <chr> "a4", "a4", "a4", "a4", "a4", "a4", "a4", "a4 quattro", "a4 quatt...
$ displ        <dbl> 1.8, 1.8, 2.0, 2.0, 2.8, 2.8, 3.1, 1.8, 1.8, 2.0, 2.0, 2.8, 2.8, ...
$ year         <int> 1999, 1999, 2008, 2008, 1999, 1999, 2008, 1999, 1999, 2008, 2008,...
$ cyl          <int> 4, 4, 4, 4, 6, 6, 6, 4, 4, 4, 4, 6, 6, 6, 6, 6, 6, 8, 8, 8, 8, 8,...
$ trans        <chr> "auto(l5)", "manual(m5)", "manual(m6)", "auto(av)", "auto(l5)", "...
$ drv          <chr> "f", "f", "f", "f", "f", "f", "f", "4", "4", "4", "4", "4", "4", ...
$ cty          <int> 18, 21, 20, 21, 16, 18, 18, 18, 16, 20, 19, 15, 17, 17, 15, 15, 1...
$ hwy          <int> 29, 29, 31, 30, 26, 26, 27, 26, 25, 28, 27, 25, 25, 25, 25, 24, 2...
$ fl           <chr> "p", "p", "p", "p", "p", "p", "p", "p", "p", "p", "p", "p", "p", ...
$ class        <chr> "compact", "compact", "compact", "compact", "compact", "compact",...

Apretando control + shif + enter = se cargan los datos

Con el signo de pregunta antes de “mpg” salen las variables en el cuadro de “help”

Con la palabra “glimpse” se abren los datos con otra dispocision. Entre parentesis “mpg”

“paquete” = app para RStudio

library(skimr)
skim(mpg)

Skim summary statistics
 n obs: 234 
 n variables: 11 

-- Variable type:character -----------------------------------------------------
     variable missing complete   n min max empty n_unique
        class       0      234 234   3  10     0        7
          drv       0      234 234   1   1     0        3
           fl       0      234 234   1   1     0        5
 manufacturer       0      234 234   4  10     0       15
        model       0      234 234   2  22     0       38
        trans       0      234 234   8  10     0       10

-- Variable type:integer -------------------------------------------------------
 variable missing complete   n    mean   sd   p0  p25    p50  p75 p100     hist
      cty       0      234 234   16.86 4.26    9   14   17     19   35 ▅▇▇▇▁▁▁▁
      cyl       0      234 234    5.89 1.61    4    4    6      8    8 ▇▁▁▇▁▁▁▇
      hwy       0      234 234   23.44 5.95   12   18   24     27   44 ▃▇▃▇▅▁▁▁
     year       0      234 234 2003.5  4.51 1999 1999 2003.5 2008 2008 ▇▁▁▁▁▁▁▇

-- Variable type:numeric -------------------------------------------------------
 variable missing complete   n mean   sd  p0 p25 p50 p75 p100     hist
    displ       0      234 234 3.47 1.29 1.6 2.4 3.3 4.6    7 ▇▇▅▅▅▃▂▁

mpg = datos del paquete ggplot2

glimpse y skim son dos formas para conocer los datos

mapeo = como vincular los datos a propiedades visuales

nuestra data en la siguiente ocasion es “mpg”

para agregar propiedades visuales hay que agregar “mapping”

el nombre de la variable la sacamos de data rectangular mpg y lo obtenemos de skim o glimpse

eje x = horizontal; eje y = vertical

geom son las opciones de figuras apra representar en el grafico

en este caso puntos = “geom_point”"

ggplot(data = mpg, mapping = aes(x = displ, y = hwy, color = class, shape = drv )) +
geom_point()

Gráfico de dispersión = puntitos

Clase 2

library(ggplot2)
library(dplyr)
library(skimr)

algunos comandos útiles para explorar la data rectangular o dataframe o tibble

dplyr::glimpse(mpg)

Observations: 234
Variables: 11
$ manufacturer <chr> "audi", "audi", "audi", "audi", "audi", "audi", "audi", "audi", "...
$ model        <chr> "a4", "a4", "a4", "a4", "a4", "a4", "a4", "a4 quattro", "a4 quatt...
$ displ        <dbl> 1.8, 1.8, 2.0, 2.0, 2.8, 2.8, 3.1, 1.8, 1.8, 2.0, 2.0, 2.8, 2.8, ...
$ year         <int> 1999, 1999, 2008, 2008, 1999, 1999, 2008, 1999, 1999, 2008, 2008,...
$ cyl          <int> 4, 4, 4, 4, 6, 6, 6, 4, 4, 4, 4, 6, 6, 6, 6, 6, 6, 8, 8, 8, 8, 8,...
$ trans        <chr> "auto(l5)", "manual(m5)", "manual(m6)", "auto(av)", "auto(l5)", "...
$ drv          <chr> "f", "f", "f", "f", "f", "f", "f", "4", "4", "4", "4", "4", "4", ...
$ cty          <int> 18, 21, 20, 21, 16, 18, 18, 18, 16, 20, 19, 15, 17, 17, 15, 15, 1...
$ hwy          <int> 29, 29, 31, 30, 26, 26, 27, 26, 25, 28, 27, 25, 25, 25, 25, 24, 2...
$ fl           <chr> "p", "p", "p", "p", "p", "p", "p", "p", "p", "p", "p", "p", "p", ...
$ class        <chr> "compact", "compact", "compact", "compact", "compact", "compact",...

skim(mpg)

Skim summary statistics
 n obs: 234 
 n variables: 11 

-- Variable type:character -----------------------------------------------------
     variable missing complete   n min max empty n_unique
        class       0      234 234   3  10     0        7
          drv       0      234 234   1   1     0        3
           fl       0      234 234   1   1     0        5
 manufacturer       0      234 234   4  10     0       15
        model       0      234 234   2  22     0       38
        trans       0      234 234   8  10     0       10

-- Variable type:integer -------------------------------------------------------
 variable missing complete   n    mean   sd   p0  p25    p50  p75 p100     hist
      cty       0      234 234   16.86 4.26    9   14   17     19   35 ▅▇▇▇▁▁▁▁
      cyl       0      234 234    5.89 1.61    4    4    6      8    8 ▇▁▁▇▁▁▁▇
      hwy       0      234 234   23.44 5.95   12   18   24     27   44 ▃▇▃▇▅▁▁▁
     year       0      234 234 2003.5  4.51 1999 1999 2003.5 2008 2008 ▇▁▁▁▁▁▁▇

-- Variable type:numeric -------------------------------------------------------
 variable missing complete   n mean   sd  p0 p25 p50 p75 p100     hist
    displ       0      234 234 3.47 1.29 1.6 2.4 3.3 4.6    7 ▇▇▅▅▅▃▂▁

ggplot() +
  geom_point(data = mpg, mapping = aes(x = displ, y = hwy, color = class, shape = ))

en el gráfico anterior se ordenaron los puntos con la ecuación de arriba, la x es igual a la capacidad del estanque, y es igual a los kilometros que puede recorrer con el estanque lleno

con “mpg” en la consola salen los valores

poco a poco se pueden omitir datos, por ejemplo en este caso nos saltamos “data” y vamos directo a “mpg”

cola de chancho alt + 126

ggplot(mpg) +
  geom_point(aes(x = displ, y = hwy, color = class)) +
facet_wrap(~ drv)

ggplot(data = mpg) +
  geom_line(mapping = aes(x = displ, y = hwy )
)

ggplot (mpg) +
  geom_bar (mapping = aes(x = drv ))

data = data_autos_resumida = tribble (
  ~ tipo_traccion, ~num_obs,
  "4" , 104,
  "f" , 102,
  "r" , 25
) 
data_autos_resumida

ggplot(data = data_autos_resumida) +
  geom_bar(mapping = aes(x = tipo_traccion, y = num_obs), 
           stat = "identity")

ggplot(mpg) + 
  geom_point(mapping = aes(x = displ, y = hwy, color = class)) +
  geom_smooth(mapping = aes(x = displ, y = hwy))

Ahora sacaremos el atributo Smooth (linea) y cambiaremos el color de los puntos en el segundo parentesis

ggplot(mpg) + 
  geom_point(mapping = aes(x = displ, y = hwy, color = class), color = "green")

Ahora agregaremos otra data agrandando el tamaño de un nuevo punto y cambiando color

ggplot(mpg) + 
  geom_point(mapping = aes(x = displ, y = hwy), color = blue) +
  geom_ponit(mapping = aes(x = displ, y = hwy),
             data = data.frame(displ = 4, hwy = 40),
             colour = "red",
             size = 4)

Error in layer(data = data, mapping = mapping, stat = stat, geom = GeomPoint,  : 
  object 'blue' not found

actividad

library(dplyr)
filter(mtcars, cyl == 6)

library(gapminder)
gapminder

Africa_continente = filter(gapminder,continent == "Africa")

dplyr::glimpse(gapminder)

Observations: 1,704
Variables: 6
$ country   <fct> Afghanistan, Afghanistan, Afghanistan, Afghanistan, Afghanistan, Afg...
$ continent <fct> Asia, Asia, Asia, Asia, Asia, Asia, Asia, Asia, Asia, Asia, Asia, As...
$ year      <int> 1952, 1957, 1962, 1967, 1972, 1977, 1982, 1987, 1992, 1997, 2002, 20...
$ lifeExp   <dbl> 28.801, 30.332, 31.997, 34.020, 36.088, 38.438, 39.854, 40.822, 41.6...
$ pop       <int> 8425333, 9240934, 10267083, 11537966, 13079460, 14880372, 12881816, ...
$ gdpPercap <dbl> 779.4453, 820.8530, 853.1007, 836.1971, 739.9811, 786.1134, 978.0114...

ggplot(data = Africa_continente) +
 geom_point(mapping = aes(x = gdpPercap, y = lifeExp, size = pop, color = year))