R語言UpSet包實現集合可視化示例詳解

#安裝及加載R包
#install.packages("UpSetR")
library(UpSetR) 
#載入數據集
data <- read.csv("upSet.csv",header=TRUE)
#先大致瀏覽一下該數據集,數據集太長，就隻看前幾列
head(data[,1:6],6)
#View(data) #彈出窗口，可查看數據

upset(data, 
sets = c("Action", "Adventure", "Comedy", "Drama", "Fantasy" , "Children","Crime"),#查看特定的幾個集合
 mb.ratio = c(0.55, 0.45),#控制上方條形圖以及下方點圖的比例
 order.by = "freq", #如何排序，這裡freq表示從大到小排序展示
 keep.order = TRUE, #keep.order按照sets參數的順序排序
 number.angles = 30, #調整柱形圖上數字角度
 point.size = 2, line.size = 1, #點和線的大小
 mainbar.y.label = "Genre Intersections", sets.x.label = "Movies Per Genre", #坐標軸名稱
 text.scale = c(1.3, 1.3, 1, 1, 1.5, 1)) #六個數字，分別控制c(intersection size title, intersection size tick labels, set size title, set size tick labels, set names, numbers above bars)

upset(data, main.bar.color = "black", 
queries = list(list(query = intersects,   #UpSetR 內置的intersects query
params = list("Drama"), ##指定作用的交集
color = "red", ##設置顏色，未設置會調用默認調色板
active = F,   # TRUE：條形圖被顏色覆蓋，FALSE：條形圖頂端顯示三角形
query.name = "Drama"), # 添加query圖例
list(query = intersects,  params = list("Action", "Drama"), active = T,query.name = "Emotional action"), 
list(query = intersects,  params = list("Drama", "Comedy", "Action"), color = "orange", active = T)),query.legend = "top")

upset(data, main.bar.color = "black", 
queries = list(list(query = intersects, params = list("Drama"), color = "red", 
active = F,  query.name = "Drama"),
list(query = intersects,  params = list("Action", "Drama"), active = T,query.name = "Emotional action"), 
list(query = intersects,  params = list("Drama", "Comedy", "Action"), color = "orange", active = T)),  
attribute.plots = list(gridrows = 45, #添加屬性圖
plots = list(
list(plot = scatter_plot, #散點圖 
x = "ReleaseDate", y = "AvgRating", #橫縱軸的變量
queries = T), #T 則顯示出上面queries定義的顏色
list(plot = histogram, x = "ReleaseDate", queries = F)), 
ncols = 2), # 添加的圖分兩列
query.legend = "top") #query圖例在最上方

upset(movies, boxplot.summary = c("AvgRating", "ReleaseDate")) 

#自定義密度曲線
another.plot <- function(data, x, y) {
    data$decades <- round_any(as.integer(unlist(data[y])), 10, ceiling)
    data <- data[which(data$decades >= 1970), ]
    myplot <- (ggplot(data, aes_string(x = x)) + geom_density(aes(fill = factor(decades)), 
        alpha = 0.4) + theme(plot.margin = unit(c(0, 0, 0, 0), "cm"), legend.key.size = unit(0.4, "cm")))
}

upset(data, main.bar.color = "black", mb.ratio = c(0.5, 0.5), queries = list(list(query = intersects, 
    params = list("Drama"), color = "red", active = F), list(query = intersects, 
    params = list("Action", "Drama"), active = T), list(query = intersects, 
    params = list("Drama", "Comedy", "Action"), color = "orange", active = T)), 
    attribute.plots = list(gridrows = 50, plots = list(list(plot = histogram, 
        x = "ReleaseDate", queries = F), list(plot = scatter_plot, x = "ReleaseDate", 
        y = "AvgRating", queries = T), list(plot = another.plot, x = "AvgRating", 
        y = "ReleaseDate", queries = F)), ncols = 3))