第四單元(4B)：互動視覺化與資料探索

---

(4A)單元摘要： 使用漫畫人物資料集來

• 複習資料處理套件
  • dplyr
• 練習繪圖套件
  • ggplot2
  • plotly
• 利用互動式圖表做資料探索

載入套件

pacman::p_load(dplyr,ggplot2,plotly,stringr)

【A】漫畫人物資料集

a = read.csv("data/comics.csv")
summary(a)

     name                id               align               eye           
 Length:23272       Length:23272       Length:23272       Length:23272      
 Class :character   Class :character   Class :character   Class :character  
 Mode  :character   Mode  :character   Mode  :character   Mode  :character  
                                                                            
                                                                            
                                                                            
                                                                            
     hair              gender              gsm               alive          
 Length:23272       Length:23272       Length:23272       Length:23272      
 Class :character   Class :character   Class :character   Class :character  
 Mode  :character   Mode  :character   Mode  :character   Mode  :character  
                                                                            
                                                                            
                                                                            
                                                                            
  appearances   first_appear        publisher        
 Min.   :   1   Length:23272       Length:23272      
 1st Qu.:   1   Class :character   Class :character  
 Median :   4   Mode  :character   Mode  :character  
 Mean   :  19                                        
 3rd Qu.:  10                                        
 Max.   :4043                                        
 NA's   :1451                                        

is.na(a) %>% colSums()

        name           id        align          eye         hair       gender 
           0         5783         3413        13395         6538          979 
         gsm        alive  appearances first_appear    publisher 
       23118            6         1451          884            0 

str_extract(a$first_appear, "\\d+") %>% as.numeric %>% unique %>% sort

  [1]    0    1    2    3    4    5    6    7    8    9   10   11   12   13   39
 [16]   40   41   42   43   44   45   46   47   48   49   50   51   52   53   54
 [31]   55   56   57   58   59   60   61   62   63   64   65   66   67   68   69
 [46]   70   71   72   73   74   75   76   77   78   79   80   81   82   83   84
 [61]   85   86   87   88   89   90   91   92   93   94   95   96   97   98   99
 [76] 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949
 [91] 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964
[106] 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979
[121] 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994
[136] 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009
[151] 2010 2011 2012 2013

a = a %>% mutate(
  year = as.numeric(str_extract(first_appear,"\\d+")) %>% {case_when(
    . < 20  ~ . + 2000,
    . < 100 ~ . + 1900,
    TRUE ~ .
    ) } ) 

a %>% top_n(50, appearances) %>% 
  ggplot(aes(x=year,y=appearances,color=publisher,shape=gender,label=name)) + 
  geom_point(size=3,alpha=0.5) -> p
ggplotly(p)