Nuage de points et tendance

/ Johanie Fournier, agr.

Pour le #Tidytuesday de cette semaine, j’ai créer un nuage de point et dégager une tendance dans les données des comics et animations qui sont catalogués sur le site MyAnimeList.net.

CONTEXTE

Ce site offre à ses utilisateurs un système de type liste pour organiser et marquer des comics et des animations selon le gout de l’utilisateur et fournit une grande base de données sur les animations et les comics. Le site prétend avoir 4,4 millions d’animations et 775 000 comics. En 2015, le site a reçu 120 millions de visiteurs par mois.

OBJECTIFS

1) Visualiser la relation entre la popularité des animations et leur score.


IMPORTER

tidy_anime <- readr::read_csv("https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2019/2019-04-23/tidy_anime.csv")
FALSE Parsed with column specification:  
FALSE cols(  
FALSE   .default = col_character(),  
FALSE   animeID = col_double(),  
FALSE   episodes = col_double(),  
FALSE   airing = col_logical(),  
FALSE   start_date = col_date(format = ""),  
FALSE   end_date = col_date(format = ""),  
FALSE   score = col_double(),  
FALSE   scored_by = col_double(),  
FALSE   rank = col_double(),  
FALSE   popularity = col_double(),  
FALSE   members = col_double(),  
FALSE   favorites = col_double()  
FALSE )
FALSE See spec(...) for full column specifications.



EXPLORER

glimpse(tidy_anime)
## Observations: 77,911  
## Variables: 28  
## $ animeID        <dbl> 1, 1, 1, 1, 1, 1, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 6…  
## $ name           <chr> "Cowboy Bebop", "Cowboy Bebop", "Cowboy Bebop", "…  
## $ title_english  <chr> "Cowboy Bebop", "Cowboy Bebop", "Cowboy Bebop", "…  
## $ title_japanese <chr> "カウボーイビバップ", "カウボーイビバップ", "カウボーイビバップ", "カウボーイビバップ…  
## $ title_synonyms <chr> "[]", "[]", "[]", "[]", "[]", "[]", "[\"Cowboy Be…  
## $ type           <chr> "TV", "TV", "TV", "TV", "TV", "TV", "Movie", "Mov…  
## $ source         <chr> "Original", "Original", "Original", "Original", "…  
## $ producers      <chr> "Bandai Visual", "Bandai Visual", "Bandai Visual"…  
## $ genre          <chr> "Action", "Adventure", "Comedy", "Drama", "Sci-Fi…  
## $ studio         <chr> "Sunrise", "Sunrise", "Sunrise", "Sunrise", "Sunr…  
## $ episodes       <dbl> 26, 26, 26, 26, 26, 26, 1, 1, 1, 1, 1, 1, 1, 1, 1…  
## $ status         <chr> "Finished Airing", "Finished Airing", "Finished A…  
## $ airing         <lgl> FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, …  
## $ start_date     <date> 1998-04-03, 1998-04-03, 1998-04-03, 1998-04-03, …  
## $ end_date       <date> 1999-04-02, 1999-04-02, 1999-04-02, 1999-04-02, …  
## $ duration       <chr> "24 min per ep", "24 min per ep", "24 min per ep"…  
## $ rating         <chr> "R - 17+ (violence & profanity)", "R - 17+ (viole…  
## $ score          <dbl> 8.81, 8.81, 8.81, 8.81, 8.81, 8.81, 8.41, 8.41, 8…  
## $ scored_by      <dbl> 405664, 405664, 405664, 405664, 405664, 405664, 1…  
## $ rank           <dbl> 26, 26, 26, 26, 26, 26, 164, 164, 164, 164, 164, …  
## $ popularity     <dbl> 39, 39, 39, 39, 39, 39, 449, 449, 449, 449, 449, …  
## $ members        <dbl> 795733, 795733, 795733, 795733, 795733, 795733, 1…  
## $ favorites      <dbl> 43460, 43460, 43460, 43460, 43460, 43460, 776, 77…  
## $ synopsis       <chr> "In the year 2071, humanity has colonized several…  
## $ background     <chr> "When Cowboy Bebop first aired in spring of 1998 …  
## $ premiered      <chr> "Spring 1998", "Spring 1998", "Spring 1998", "Spr…  
## $ broadcast      <chr> "Saturdays at 01:00 (JST)", "Saturdays at 01:00 (…  
## $ related        <chr> "{'Adaptation': [{'mal_id': 173, 'type': 'manga',…
summary(tidy_anime)
##     animeID          name           title_english      title_japanese      
##  Min.   :    1   Length:77911       Length:77911       Length:77911        
##  1st Qu.: 3052   Class :character   Class :character   Class :character    
##  Median :13667   Mode  :character   Mode  :character   Mode  :character    
##  Mean   :16863                                                             
##  3rd Qu.:31452                                                             
##  Max.   :39197                                                             
##                                                                            
##  title_synonyms         type              source           
##  Length:77911       Length:77911       Length:77911        
##  Class :character   Class :character   Class :character    
##  Mode  :character   Mode  :character   Mode  :character    
##                                                            
##                                                            
##                                                            
##                                                            
##   producers            genre              studio             episodes       
##  Length:77911       Length:77911       Length:77911       Min.   :   1.0    
##  Class :character   Class :character   Class :character   1st Qu.:   1.0    
##  Mode  :character   Mode  :character   Mode  :character   Median :  12.0    
##                                                           Mean   :  15.8    
##                                                           3rd Qu.:  13.0    
##                                                           Max.   :3057.0    
##                                                           NA's   :987       
##     status            airing          start_date          
##  Length:77911       Mode :logical   Min.   :1917-01-01    
##  Class :character   FALSE:76528     1st Qu.:2002-09-01    
##  Mode  :character   TRUE :1383      Median :2011-01-22    
##                                     Mean   :2007-03-14    
##                                     3rd Qu.:2015-09-18    
##                                     Max.   :2019-02-03    
##                                     NA's   :238           
##     end_date            duration            rating           
##  Min.   :1962-02-02   Length:77911       Length:77911        
##  1st Qu.:2005-06-02   Class :character   Class :character    
##  Median :2012-06-02   Mode  :character   Mode  :character    
##  Mean   :2009-03-29                                          
##  3rd Qu.:2016-03-02                                          
##  Max.   :2019-09-02                                          
##  NA's   :33824                                               
##      score          scored_by            rank         popularity     
##  Min.   : 1.000   Min.   :      0   Min.   :    1   Min.   :    1    
##  1st Qu.: 6.360   1st Qu.:    597   1st Qu.: 1530   1st Qu.: 1064    
##  Median : 7.020   Median :   7130   Median : 3685   Median : 3033    
##  Mean   : 6.894   Mean   :  43495   Mean   : 4557   Mean   : 4567    
##  3rd Qu.: 7.550   3rd Qu.:  39876   3rd Qu.: 6724   3rd Qu.: 7394    
##  Max.   :10.000   Max.   :1107955   Max.   :13838   Max.   :15474    
##  NA's   :174                                                         
##     members          favorites        synopsis          background         
##  Min.   :      6   Min.   :     0   Length:77911       Length:77911        
##  1st Qu.:   1968   1st Qu.:     2   Class :character   Class :character    
##  Median :  18214   Median :    40   Mode  :character   Mode  :character    
##  Mean   :  85051   Mean   :  1468                                          
##  3rd Qu.:  88560   3rd Qu.:   413                                          
##  Max.   :1610561   Max.   :120331                                          
##                                                                            
##   premiered          broadcast           related           
##  Length:77911       Length:77911       Length:77911        
##  Class :character   Class :character   Class :character    
##  Mode  :character   Mode  :character   Mode  :character    
##                                                            
##                                                            
##                                                            
##

Les données ont déjà été travaillées et tout est déjà sous un format prêt à travailler. Faire attention aux NA’s ici.



PRÉPARER:

data<-tidy_anime%>%
    select(name, start_date, score, rating, popularity)%>%
    filter(!is.na(start_date) & !is.na(score))%>%
    filter(!rating=="None")%>%
    distinct()



VISUALISER

#Graphique  
gg<-ggplot(data=data, aes(x=popularity, y=score))  
gg<-gg + geom_point(size=2, color=alpha("#80FF72", 0.1))  
gg<-gg + geom_smooth(size=2.5, color="#E8EBE4")  
#ajuster les axes   #gg<-gg + scale_y_continuous(breaks=seq(1,7,1), limits = c(1, 7))  
gg<-gg + scale_x_continuous(breaks=seq(0, 18000, 2000),limits = c(0, 16000))   
#modifier la légende  
gg<-gg + theme(legend.position="none")  
#modifier le thème  
gg<-gg +theme(panel.border = element_blank(),
                panel.background = element_rect(fill = "#292E1E", colour = "#292E1E"),
                plot.background = element_rect(fill = "#292E1E", colour = "#292E1E"),
                panel.grid.major.y= element_blank(),
                panel.grid.major.x= element_blank(),
                panel.grid.minor = element_blank(),
                axis.line = element_line(size=1, color="#E8EBE4", linetype="solid"),
                axis.ticks= element_line(size=0.5, color="#E8EBE4", linetype="solid"))  
#ajouter les titres  
gg<-gg + labs(title="Existe-t-il une relation entre la popularité et le score des animations et des comics?",
                subtitle="Il semblerait que plus les animations sont populaires, c'est-à-dire plus il y a de personnes qui les ont dans leurs listes\npersonnelles, plus le score de l'animation diminue.",
                y="Score",
                 x="Popularité")  
gg<-gg + theme(plot.title    = element_text(hjust=0,size=17, color="#E8EBE4"),
                 plot.subtitle = element_text(hjust=0,size=12, color="#E8EBE4"),
                 axis.title.y  = element_text(hjust=1, size=12, color="#E8EBE4"),
                 axis.title.x  = element_text(hjust=0, size=12, color="#E8EBE4"),
                 axis.text.y   = element_text(hjust=0.5, size=10, color="#E8EBE4"),
                 axis.text.x   = element_text(hjust=0.5, size=10, color="#E8EBE4"))

Voici ce que

Voici ce que ça donne:

Tu veux en savoir plus sur ma démarche? Va écouter l’épisode de podcast dans lequel j’explique mes réflexions pour arriver à ce résultat.

Une réflexion sur “Nuage de points et tendance”

  1. Pingback: Podcast ADV #7: Qu’est-ce qu’on fait quand ce qu’on pensait visualiser dans les données ne donne rien de bon? | Johanie Fournier, agr.

Laisser un commentaire

Ce site utilise Akismet pour réduire les indésirables. En savoir plus sur comment les données de vos commentaires sont utilisées.