Tercera Clase

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

algunos comandos utiles para explorar la data rectangular o dataframe

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...

nombre + () = función glimpse nos da un resumen de las variables que tenemos

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>

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

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

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

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

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_smooth(mapping = aes(x = displ, y = hwy))

ggplot(data = mpg) +
  geom_point(mapping = aes(x = displ, y = hwy), colour = "turquoise") +
  geom_point(mapping = aes(x = displ, y = hwy),
             data = data.frame(displ = 4, hwy = 40),
             colour = "pink",
             size = 4)

library(gapminder)
gapminder

library(dplyr)
filter(gapminder, continent == "Oceania")

datos_oceania <- filter(gapminder, continent == "Oceania")
datos_oceania

glimpse(datos_oceania)

Observations: 24
Variables: 6
$ country   <fct> Australia, Australia, Australia, Australia, Australia, Australia, Australi...
$ continent <fct> Oceania, Oceania, Oceania, Oceania, Oceania, Oceania, Oceania, Oceania, Oc...
$ year      <int> 1952, 1957, 1962, 1967, 1972, 1977, 1982, 1987, 1992, 1997, 2002, 2007, 19...
$ lifeExp   <dbl> 69.120, 70.330, 70.930, 71.100, 71.930, 73.490, 74.740, 76.320, 77.560, 78...
$ pop       <int> 8691212, 9712569, 10794968, 11872264, 13177000, 14074100, 15184200, 162572...
$ gdpPercap <dbl> 10039.60, 10949.65, 12217.23, 14526.12, 16788.63, 18334.20, 19477.01, 2188...

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