dados = read_csv(
    here::here("data/participation-per-country.csv"),
    col_types = cols(
        .default = col_double(),
        site = col_character(),
        country = col_character(),
        geo = col_character(),
        four_regions = col_character(),
        eight_regions = col_character(),
        six_regions = col_character(),
        `World bank income group 2017` = col_character()
    )
) %>% 
    filter(usuarios > 200)
glimpse(dados)

## Observations: 121
## Variables: 21
## $ site                           <chr> "StackOverflow", "StackOverflow",…
## $ country                        <chr> "Argentina", "Australia", "Austri…
## $ PDI                            <dbl> 49, 36, 11, 80, 65, 69, 70, 39, 6…
## $ IDV                            <dbl> 46, 90, 55, 20, 75, 38, 30, 80, 2…
## $ MAS                            <dbl> 56, 61, 79, 55, 54, 49, 40, 52, 2…
## $ UAI                            <dbl> 86, 51, 70, 60, 94, 76, 85, 48, 8…
## $ usuarios                       <dbl> 2798, 12313, 2518, 2558, 4275, 10…
## $ responderam_prop               <dbl> 0.5357398, 0.6133355, 0.6310564, …
## $ perguntaram_prop               <dbl> 0.5210865, 0.5897832, 0.5933280, …
## $ editaram_prop                  <dbl> 0.09256612, 0.14699911, 0.1493248…
## $ comentaram_prop                <dbl> 0.25339528, 0.33395598, 0.3502780…
## $ GNI                            <dbl> NA, 59570, 48160, 840, 44990, 116…
## $ Internet                       <dbl> 51.0, 79.5, 79.8, 5.0, 78.0, 45.0…
## $ EPI                            <dbl> 59.02, NA, 63.21, NA, 61.21, 49.9…
## $ geo                            <chr> "arg", "aus", "aut", "bgd", "bel"…
## $ four_regions                   <chr> "americas", "asia", "europe", "as…
## $ eight_regions                  <chr> "america_south", "east_asia_pacif…
## $ six_regions                    <chr> "america", "east_asia_pacific", "…
## $ Latitude                       <dbl> -34.00000, -25.00000, 47.33333, 2…
## $ Longitude                      <dbl> -64.00000, 135.00000, 13.33333, 9…
## $ `World bank income group 2017` <chr> "Upper middle income", "High inco…

dados %>% 
    ggplot(aes(x = IDV, y = responderam_prop)) + 
    geom_point()

dados %>% 
    ggplot(aes(x = IDV, y = responderam_prop, color = site)) + 
    geom_point()

dados %>%
    ggplot(aes(
        x = IDV,
        y = responderam_prop,
        color = site,
        size = log10(usuarios)
    )) +
    geom_point(alpha = .6)

dados %>%
    ggplot(aes(
        size = IDV,
        y = responderam_prop,
        color = site,
        x = log10(usuarios)
    )) +
    geom_point(alpha = .6)

dados %>%
    ggplot(aes(
        x = IDV,
        y = responderam_prop,
        color = Internet,
        size = log10(usuarios)
    )) +
    geom_point(alpha = .6) + 
    facet_grid(site ~ ., scales = "free_y")

dados %>%
    ggplot(aes(
        x = IDV,
        y = responderam_prop,
        size = Internet,
        color = log10(usuarios)
    )) +
    geom_point(alpha = .6) + 
    facet_grid(site ~ ., scales = "free_y")

## Warning: Removed 3 rows containing missing values (geom_point).

so = dados %>% 
    filter(site == "StackOverflow") %>% 
    sample_n(20)

so %>%
    ggplot(aes(
        x = country,
        color = responderam_prop,
        y = ""
    )) +
    geom_point(size = 4) + 
    coord_flip()

so %>%
    ggplot(aes(
        x = country,
        size = responderam_prop,
        y = ""
    )) +
    geom_point(alpha = .3) + 
    coord_flip()

so %>%
    ggplot(aes(
        x = country,
        y = "",
        size = responderam_prop,
        color = six_regions
    )) +
    geom_point() + 
    coord_flip()

so %>%
    ggplot(aes(
        x = country,
        y = responderam_prop,
        color = six_regions
    )) +
    geom_point(size = 3) + 
    coord_flip()