R语言UpSet包实现集合可视化示例详解

#安装及加载R包
#install.packages("UpSetR")
library(UpSetR) 
#载入数据集
data <- read.csv("upSet.csv",header=TRUE)
#先大致浏览一下该数据集,数据集太长，就只看前几列
head(data[,1:6],6)
#View(data) #弹出窗口，可查看数据

upset(data, 
sets = c("Action", "Adventure", "Comedy", "Drama", "Fantasy" , "Children","Crime"),#查看特定的几个集合
 mb.ratio = c(0.55, 0.45),#控制上方条形图以及下方点图的比例
 order.by = "freq", #如何排序，这里freq表示从大到小排序展示
 keep.order = TRUE, #keep.order按照sets参数的顺序排序
 number.angles = 30, #调整柱形图上数字角度
 point.size = 2, line.size = 1, #点和线的大小
 mainbar.y.label = "Genre Intersections", sets.x.label = "Movies Per Genre", #坐标轴名称
 text.scale = c(1.3, 1.3, 1, 1, 1.5, 1)) #六个数字，分别控制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 内置的intersects query
params = list("Drama"), ##指定作用的交集
color = "red", ##设置颜色，未设置会调用默认调色板
active = F,   # TRUE：条形图被颜色覆盖，FALSE：条形图顶端显示三角形
query.name = "Drama"), # 添加query图例
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, #添加属性图
plots = list(
list(plot = scatter_plot, #散点图 
x = "ReleaseDate", y = "AvgRating", #横纵轴的变量
queries = T), #T 则显示出上面queries定义的颜色
list(plot = histogram, x = "ReleaseDate", queries = F)), 
ncols = 2), # 添加的图分两列
query.legend = "top") #query图例在最上方

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

#自定义密度曲线
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))