R Notebook

ggplo2 como paquete –> aplicación de gráficos

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

todos los paquetes se escriben: library (blah) para cargarlos –> aplicaciones extras de mi celular

dplyr::glimpse(mpg)

Observations: 234
Variables: 11
$ manufacturer <chr> "audi", "audi", "audi", "audi", "audi", "audi", "audi", "audi", "audi", "...
$ model        <chr> "a4", "a4", "a4", "a4", "a4", "a4", "a4", "a4 quattro", "a4 quattro", "a4...
$ 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, 3.1, 3.1...
$ year         <int> 1999, 1999, 2008, 2008, 1999, 1999, 2008, 1999, 1999, 2008, 2008, 1999, 1...
$ cyl          <int> 4, 4, 4, 4, 6, 6, 6, 4, 4, 4, 4, 6, 6, 6, 6, 6, 6, 8, 8, 8, 8, 8, 8, 8, 8...
$ trans        <chr> "auto(l5)", "manual(m5)", "manual(m6)", "auto(av)", "auto(l5)", "manual(m...
$ drv          <chr> "f", "f", "f", "f", "f", "f", "f", "4", "4", "4", "4", "4", "4", "4", "4"...
$ cty          <int> 18, 21, 20, 21, 16, 18, 18, 18, 16, 20, 19, 15, 17, 17, 15, 15, 17, 16, 1...
$ hwy          <int> 29, 29, 31, 30, 26, 26, 27, 26, 25, 28, 27, 25, 25, 25, 25, 24, 25, 23, 2...
$ fl           <chr> "p", "p", "p", "p", "p", "p", "p", "p", "p", "p", "p", "p", "p", "p", "p"...
$ class        <chr> "compact", "compact", "compact", "compact", "compact", "compact", "compac...

glimpse es para explorar datos: nos da un resumen de lo que tenemos.

int: entero dbl: mayor precisión. decimales chr: palabras, texto

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 <U+2585><U+2587><U+2587><U+2587><U+2581><U+2581><U+2581><U+2581>
      cyl       0      234 234    5.89 1.61    4    4    6      8    8 <U+2587><U+2581><U+2581><U+2587><U+2581><U+2581><U+2581><U+2587>
      hwy       0      234 234   23.44 5.95   12   18   24     27   44 <U+2583><U+2587><U+2583><U+2587><U+2585><U+2581><U+2581><U+2581>
     year       0      234 234 2003.5  4.51 1999 1999 2003.5 2008 2008 <U+2587><U+2581><U+2581><U+2581><U+2581><U+2581><U+2581><U+2587>

-- 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 <U+2587><U+2587><U+2585><U+2585><U+2585><U+2583><U+2582><U+2581>

skim: nos da un resumen estadístico. nos da mas info compactab que glimpse

datos: sacados de mpg variables representadas: en puntos

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

drv: variable que nos dice si la traccion del auto está adelante, atrás o en las 4 ruedas

4 = 4 x 4 f = frontal r = atrás

split (mpg, mpg$drv)

$`4`

$f

$r

NA

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

aes: atributo estético (english)

este gráfico de líneo no tiene sentido visual para los datos que hemos recabado. }

grafico de barras

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

formas de crear gráficos ejemplificadores

data_autos_resumida <- tribble(
    ~ tipo_traccion, ~ num_obs,
  "4"  ,  104, 
  "f"  ,  102, 
  "r"  ,  25
  )
data_autos_resumida

Gráfico de barras en relacion anuestros datos ya hechos. (gráfico anterior)

capa: representacion geométrica, por ejemplo geom_point

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

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

constante: por ejemplo el color, se escribe fuera de aes.

grafico de burbujas: gráfico de dispersión con tamaños diferentes de puntos (size)

library(dplyr)
data_americas <- filter(gapminder, continent == "Americas")

data_americas

dplyr::glimpse(data_americas)

Observations: 300
Variables: 6
$ country   <fct> Argentina, Argentina, Argentina, Argentina, Argentina, Argent...
$ continent <fct> Americas, Americas, Americas, Americas, Americas, Americas, A...
$ year      <int> 1952, 1957, 1962, 1967, 1972, 1977, 1982, 1987, 1992, 1997, 2...
$ lifeExp   <dbl> 62.485, 64.399, 65.142, 65.634, 67.065, 68.481, 69.942, 70.77...
$ pop       <int> 17876956, 19610538, 21283783, 22934225, 24779799, 26983828, 2...
$ gdpPercap <dbl> 5911.315, 6856.856, 7133.166, 8052.953, 9443.039, 10079.027, ...

ggplot (data_americas)+
geom_point(mapping= aes ( x = gdpPercap , y = lifeExp, size = pop))

NA

Este gráfico representa que a mayor PIB es mayor la expectativa de vida.

10-4