GoT: Analise da série e aula de GGPLOT

#importa a biblioteca
library(tidyverse)

## ── Attaching packages ──────────────── tidyverse 1.3.0 ──

## ✓ ggplot2 3.3.0     ✓ purrr   0.3.3
## ✓ tibble  2.1.3     ✓ dplyr   0.8.5
## ✓ tidyr   1.0.2     ✓ stringr 1.4.0
## ✓ readr   1.3.1     ✓ forcats 0.5.0

## ── Conflicts ─────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

library(ggbeeswarm)

series = read_csv("data/series_from_imdb.csv.zip")

## Parsed with column specification:
## cols(
##   series_name = col_character(),
##   Episode = col_character(),
##   series_ep = col_double(),
##   season = col_double(),
##   season_ep = col_double(),
##   url = col_character(),
##   UserRating = col_double(),
##   UserVotes = col_double(),
##   r1 = col_double(),
##   r2 = col_double(),
##   r3 = col_double(),
##   r4 = col_double(),
##   r5 = col_double(),
##   r6 = col_double(),
##   r7 = col_double(),
##   r8 = col_double(),
##   r9 = col_double(),
##   r10 = col_double()
## )

# Nunca usar read.csv()

glimpse(series)

## Observations: 63,956
## Variables: 18
## $ series_name <chr> "Altered Carbon", "Altered Carbon", "Altered Carbon", "Al…
## $ Episode     <chr> "Out of the Past", "Fallen Angel", "In a Lonely Place", "…
## $ series_ep   <dbl> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 1, 2, 3, 4, 5, 6, 7, 8, 9,…
## $ season      <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, …
## $ season_ep   <dbl> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 1, 2, 3, 4, 5, 6, 7, 8, 9,…
## $ url         <chr> "http://www.imdb.com/title/tt5989942/?ref_=ttep_ep1", "ht…
## $ UserRating  <dbl> 7.9, 7.9, 8.1, 8.6, 8.4, 8.4, 8.3, 8.3, 8.5, 8.5, 8.1, 8.…
## $ UserVotes   <dbl> 3673, 2868, 2621, 2841, 2417, 2345, 2515, 2203, 2274, 249…
## $ r1          <dbl> 0.011979308, 0.011157601, 0.011064479, 0.011967617, 0.012…
## $ r2          <dbl> 0.004900626, 0.004184100, 0.003052270, 0.003167899, 0.003…
## $ r3          <dbl> 0.005445140, 0.004881450, 0.004959939, 0.003167899, 0.003…
## $ r4          <dbl> 0.013340594, 0.012552301, 0.009156810, 0.010207673, 0.007…
## $ r5          <dbl> 0.029403757, 0.029986053, 0.019458222, 0.018655403, 0.019…
## $ r6          <dbl> 0.07187585, 0.07147838, 0.06486074, 0.03871876, 0.0496483…
## $ r7          <dbl> 0.16662129, 0.18654114, 0.14650897, 0.08658923, 0.1092263…
## $ r8          <dbl> 0.3283420, 0.3518131, 0.3410912, 0.1964097, 0.2581713, 0.…
## $ r9          <dbl> 0.18812959, 0.15062762, 0.20030523, 0.30095037, 0.2767894…
## $ r10         <dbl> 0.1799619, 0.1767782, 0.1995422, 0.3301654, 0.2602400, 0.…

Filtrar os dados pelo nome da serie:

got = series %>% 
    filter(series_name == "Game of Thrones")
#View(got)

got %>% 
    ggplot(mapping = aes(x = "GoT", y = UserRating)) +
    geom_point(alpha = 0.25)

got %>% 
    ggplot(mapping = aes(x = "GoT", y = UserRating)) +
    geom_jitter(height = 0, width = .1, alpha = .4)

got %>% 
    ggplot(mapping = aes(x = "GoT", y = UserRating)) +
    geom_quasirandom(width = .15)

library(ggbeeswarm)
got %>% 
    ggplot(mapping = aes(x = "GoT", y = UserVotes)) +
    geom_quasirandom(width = .15, color = "red")

Por temporada:

got %>% 
    ggplot(mapping = aes(y = UserRating, x = season)) +
    geom_quasirandom(width = .1, color = "black", alpha = .5)

got %>% 
    ggplot(mapping = aes(y = UserVotes, x = season)) +
    geom_quasirandom(width = .1, color = "black", alpha = .6)

got %>% 
    ggplot(mapping = aes(y = UserRating, x = season_ep)) +
    geom_quasirandom(width = .1, color = "blue", alpha = .6)

got %>% 
    ggplot(mapping = aes(y = UserRating, x = season_ep, group = season)) +
    geom_line()

got %>% 
    ggplot(mapping = aes(y = UserRating, x = series_ep, group = season, color = season)) +
    geom_line(alpha = 0.7) +
    geom_point()