我们在可视化集合之间关系的时候,常常会绘制韦恩图。但随着集合的增多,韦恩图显示的关系会越来越复杂,很难一眼看出其中的信息。这种情况下我们需要使用 UpSetR 包来反映集合间的关系。
把你需要展示的集合做成一个list即可,我这里是需要展示的集合存在各个Rdata中,故用下述代码导入该文件夹中所有的Rdata数据。
rm(list=ls())
#install.packages("UpSetR")
library(UpSetR)
## 数据导入
#设置文件路径
file_path <- "../Rdata/"
#列出所有以 .Rdata 结尾的文件
rdata_files <- list.files(file_path, pattern = "\\.Rdata$")
#依次加载每个文件
for (file in rdata_files) {
load(file.path(file_path, file))
}
##需要展示的向量形成一个集合
input_list <- list(
DC_HAO_pro_dif_all = DC_HAO_pro_dif_all,
FE_HAO_pro_dif_all = FE_HAO_pro_dif_all,
DC_HAO_trans_dif_all = DC_HAO_trans_dif_all,
FE_HAO_trans_dif_all = FE_HAO_trans_dif_all,
DC_exo_dif_all = DC_exo_dif_all,
FE_exo_dif_all = FE_exo_dif_all
)采用三段法进行图片的保存与绘制
#绘图
# 保存
png("../Table+figure/upset_plot.png", width = 1000, height = 800, res = 150)
UpSetR::upset(
fromList(input_list),
order.by = "freq",
nsets = length(input_list), # 显示所有集合
nintersects = NA #显示所有交集
)
dev.off() # 关闭 PDF 设备
参考链接https://zhuanlan.zhihu.com/p/370210775
例如,使用 number.angles 来设置柱状图柱子上方数字的倾斜角度;使用 point.size 和 line.size 来设置矩阵点图中点和线的大小;mainbar.y.label和 sets.x.label 可以设置柱状图和条形图的轴标签;text.scale 包含6 个值,用于指定图上所有文本标签的大小。
text.scale 参数值的顺序为:
- 柱状图的轴标签和刻度
- 条形图的轴标签和刻度
- 集合名称
- 柱子上方表示交集大小的数值upset(fromList(input_list),
sets = c("DC_HAO_pro_dif_all", "FE_HAO_pro_dif_all", "DC_HAO_trans_dif_all"),
#mb.ratio 用于控制上下图形所占比例
mb.ratio = c(0.55, 0.45)
)
通过置 order.by 参数,来对交集进行排序
freq默认是升序,可以使用 decreasing = TRUE 让其降序排列
upset(fromList(input_list),
sets = c("DC_HAO_pro_dif_all", "FE_HAO_pro_dif_all", "DC_HAO_trans_dif_all"),
mb.ratio = c(0.55, 0.45),
order.by = "freq",
decreasing = FALSE
)
使用order.by = "degree",参数,degree 默认为降序排序,设置 decreasing = FALSE 使其升序排列
upset(fromList(input_list),
sets = c("DC_HAO_pro_dif_all", "FE_HAO_pro_dif_all", "DC_HAO_trans_dif_all"),
mb.ratio = c(0.55, 0.45),
order.by = "degree",
decreasing = FALSE
)
3.3 同时指定freq,degree顺序
upset(fromList(input_list),
sets = c("DC_HAO_pro_dif_all", "FE_HAO_pro_dif_all", "DC_HAO_trans_dif_all"),
mb.ratio = c(0.55, 0.45),
order.by = c("degree", "freq"),
decreasing = c(TRUE, FALSE)
)通过设置keep.order = TRUE参数
如果想要显示交集为空的组合,可以设置 empty.intersections = “on” 参数
upset(fromList(input_list),
sets = c("DC_HAO_pro_dif_all", "DC_HAO_trans_dif_all","FE_HAO_pro_dif_all"),
mb.ratio = c(0.55, 0.45),
keep.order = TRUE
)
查询通过 queries 参数来执行,接受一个嵌套的 list 来表示多个查询条件,每个查询条件包含四个字段:
query:需要执行的查询
params:查询参数列表
color:设置满足查询条件的元素在图中的颜色
active:如果为 TRUE,柱状图颜色将会被覆盖,为 FALSE 则会在柱子上添加带有随机扰动的点我们使用内置的交集查询:intersects,用来寻找或显示特定的交集,并将找到的交集进行上色
upset(fromList(input_list), queries = list(
list(
query = intersects,
params = list("DC_HAO_trans_dif_all", "FE_HAO_trans_dif_all"),
color = "orange",
active = T),
list(
query = intersects,
params = list("FE_HAO_trans_dif_all", "DC_exo_dif_all"),
color = "red",
active = T)#list最后一个元素后不能有逗号
)
)
upset图,不仅可以传入一个向量列表,还可以传入一个数据框,接下来的演示使用upset包自带的数据进行演示
movies <- read.csv(system.file("extdata", "movies.csv", package = "UpSetR"),
header = T, sep = ";")
> colnames(movies)
[1] "Name" "ReleaseDate" "Action" "Adventure" "Children" "Comedy"
[7] "Crime" "Documentary" "Drama" "Fantasy" "Noir" "Horror"
[13] "Musical" "Mystery" "Romance" "SciFi" "Thriller" "War"
[19] "Western" "AvgRating" "Watches" 使用 elements 来进行元素查询,来展示元素在交集中的分布情况
upset(movies,
queries = list(
list(
query = elements,
#这里检查 movies 数据集的 AvgRating 列,选出评分在 3.5 和 4.1 之间的电影。
params = list("AvgRating", 3.5, 4.1),
color = "blue",
#表示该查询条件是激活的,会在图形中显示
active = T),
list(
query = elements,
#查询 ReleaseDate 列,选出发行年份在 1980、1990 或 2000 年的电影
params = list("ReleaseDate", 1980, 1990, 2000),
color = "red",
#该查询条件不激活,因此不会在图形中显示
active = F)
)
)
可以为 expression 参数设置过滤表达式来提取查询结果的子集
upset(movies,
queries = list(
#第一个查询条件(用于筛选 Action 和 Drama 电影的交集)
list(
query = intersects,
params = list("Action", "Drama"),
active = T),
#第二个查询条件(用于筛选 ReleaseDate)指定查询 ReleaseDate 列,
#选择发行年份在 1980、1990 或 2000 年的电影
list(
query = elements,
params = list("ReleaseDate", 1980, 1990, 2000),
color = "red",
active = F)),
expression = "AvgRating > 3 & Watches > 100"
)
#查询函数会应用于数据的每一行中,我们可以定义如下查询函数
#筛选发行日期在 release 内,且平均评分大于某个值的电影
Myfunc <- function(row, release, rating) {
data <- (row["ReleaseDate"] %in% release) & (row["AvgRating"] > rating)
}
upset(movies,
queries = list(
list(
query = Myfunc,
params = list(c(1970, 1980, 1990, 1999, 2000), 2.5),
color = "blue",
active = T)
)
)
使用 query.legend 参数来指定查询图例的位置,top 或bottom
在查询条件中,使用 query.name 来设置查询的名称,如果没设置,会自动生成
upset(movies,
query.legend = "top",
queries = list(
list(
query = intersects,
params = list("Drama", "Comedy", "Action"),
color = "orange", active = T,
query.name = "Funny action"),
list(
query = intersects,
params = list("Drama"),
color = "red", active = F),
list(
query = intersects,
params = list("Action", "Drama"),
active = T,
query.name = "Emotional action")
)
)
属性图
attribute.plots 参数用于执行属性图的绘制,包含 3 个字段:
gridrows:设置属性图的空间大小,UpSet plot 默认为 100 X 100,如果设置为 50,则整个图形变成 150 X 100
plots:图形列表,每个元素包含 4 个参数:
plot:返回 ggplot 对象的函数
x:图形的 x 轴变量
y:图形的 y 轴变量
queries:是否使用已经存在的查询来覆盖绘图数据upset(movies,
main.bar.color = "black",
queries = list(
list(
query = intersects,
params = list("Drama"),
active = T)
),
attribute.plots = list(
gridrows = 50,
plots = list(
list(
plot = histogram,
x = "ReleaseDate",
queries = F),
list(
plot = histogram,
x = "AvgRating",
queries = T)
), ncols = 2
)
)
upset(movies,
main.bar.color = "black",
queries = list(
list(
query = intersects,
params = list("Drama"),
color = "red",
active = F),
list(
query = intersects,
params = list("Drama", "Comedy", "Action"),
color = "orange",
active = T)
), attribute.plots = list(
gridrows = 45,
plots = list(
list(
plot = scatter_plot,
x = "ReleaseDate",
y = "AvgRating",
queries = T),
list(plot = scatter_plot,
x = "AvgRating",
y = "Watches",
queries = F)
),
ncols = 2),
query.legend = "bottom"
)
我们先定义两个基于 ggplot2 的函数,用于绘制散点图和密度图
my_scatter <- function(data, x, y) {
p <- ggplot(data, aes_string(x, y, colour = "color")) +
geom_point() +
scale_colour_identity() +
theme(
plot.margin = unit(c(0, 0, 0, 0), "cm")
)
p
}
my_density <- function(data, x, y) {
data$decades <- data[, y] %/% 10 * 10
data <- data[which(data$decades >= 1970), ]
p <- ggplot(data, aes_string(x)) +
geom_density(aes(fill = factor(decades)), alpha = 0.3) +
theme(
plot.margin = unit(c(0, 0, 0, 0), "cm"),
legend.key.size = unit(0.4, "cm")
)
p
}然后应用在属性图中
upset(movies,
main.bar.color = "black",
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 = 45,
plots = list(
list(
plot = my_scatter,
x = "ReleaseDate",
y = "AvgRating",
queries = T),
list(
plot = my_density,
x = "AvgRating",
y = "ReleaseDate",
queries = F)
),
ncols = 2)
)
想要绘制箱线图,可以使用 boxplot.summary 参数,最多只能同时绘制两个变量的箱线图。
upset(movies, boxplot.summary = c("AvgRating", "ReleaseDate"))
原创声明:本文系作者授权腾讯云开发者社区发表,未经许可,不得转载。
如有侵权,请联系 cloudcommunity@tencent.com 删除。