10.UpSet集合图绘制
清除当前环境中的变量
rm(list=ls())
设置工作目录
setwd("C:/Users/Dell/Desktop/R_Plots/10upset/")
使用UpSetR包绘制集合图
library(UpSetR)
# 加载UpSetR包的内置数据集
movies <- read.csv(system.file("extdata", "movies.csv", package = "UpSetR"), header = T, sep = ";")
dim(movies)
## [1] 3883 21
head(movies)
## Name ReleaseDate Action Adventure Children
## 1 Toy Story (1995) 1995 0 0 1
## 2 Jumanji (1995) 1995 0 1 1
## 3 Grumpier Old Men (1995) 1995 0 0 0
## 4 Waiting to Exhale (1995) 1995 0 0 0
## 5 Father of the Bride Part II (1995) 1995 0 0 0
## 6 Heat (1995) 1995 1 0 0
## Comedy Crime Documentary Drama Fantasy Noir Horror Musical Mystery
## 1 1 0 0 0 0 0 0 0 0
## 2 0 0 0 0 1 0 0 0 0
## 3 1 0 0 0 0 0 0 0 0
## 4 1 0 0 1 0 0 0 0 0
## 5 1 0 0 0 0 0 0 0 0
## 6 0 1 0 0 0 0 0 0 0
## Romance SciFi Thriller War Western AvgRating Watches
## 1 0 0 0 0 0 4.15 2077
## 2 0 0 0 0 0 3.20 701
## 3 1 0 0 0 0 3.02 478
## 4 0 0 0 0 0 2.73 170
## 5 0 0 0 0 0 3.01 296
## 6 0 0 1 0 0 3.88 940
基础绘图
upset(data = movies,
sets = c("Action", "Adventure", "Comedy", "Drama", "Mystery",
"Thriller", "Romance", "War", "Western"), # 指定所用的集合
number.angles = 30, # 设置相交集合柱状图上方数字的角度
point.size = 3.5, # 设置矩阵中圆圈的大小
line.size = 2, # 设置矩阵中连接圆圈的线的大小
mainbar.y.label = "Genre Intersections", # 设置y轴标签
sets.x.label = "Movies Per Genre", # 设置x轴标签
mb.ratio = c(0.6, 0.4), # 设置bar plot和matrix plot图形高度的占比
order.by = "freq")
image.png
upset(data = movies,
sets = c("Action", "Adventure", "Comedy", "Drama", "Mystery",
"Thriller", "Romance", "War", "Western"), # 指定所用的集合
number.angles = 45, # 设置相交集合柱状图上方数字的角度
point.size = 3, # 设置矩阵中圆圈的大小
line.size = 1.5, # 设置矩阵中连接圆圈的线的大小
mainbar.y.label = "Genre Intersections", # 设置y轴标签
sets.x.label = "Movies Per Genre", # 设置x轴标签
mb.ratio = c(0.7, 0.3), # 设置bar plot和matrix plot图形高度的占比
order.by = "degree", # 更改排序的方式
keep.order = TRUE # 保持集合按输入的顺序排序
)
image.png
# 使用fromList函数输入列表格式的集合数据
# example of list input (list of named vectors)
listInput <- list(one = c(1, 2, 3, 5, 7, 8, 11, 12, 13),
two = c(1, 2, 4, 5, 10),
three = c(1, 5, 6, 7, 8, 9, 10, 12, 13))
listInput
## $one
## [1] 1 2 3 5 7 8 11 12 13
##
## $two
## [1] 1 2 4 5 10
##
## $three
## [1] 1 5 6 7 8 9 10 12 13
upset(fromList(listInput), order.by = "freq")
image.png
# 使用fromExpression函数输入表达式向量格式的集合数据
# example of expression input
expressionInput <- c(one = 2, two = 1, three = 2,
`one&two` = 1, `one&three` = 4,
`two&three` = 1, `one&two&three` = 2)
expressionInput
## one two three one&two one&three
## 2 1 2 1 4
## two&three one&two&three
## 1 2
upset(fromExpression(expressionInput), order.by = "freq",point.size = 2,line.size = 1)
image.png
使用set.metadata参数添加元数据信息
# 构建metadata信息
sets <- names(movies[3:19])
avgRottenTomatoesScore <- round(runif(17, min = 0, max = 90))
metadata <- as.data.frame(cbind(sets, avgRottenTomatoesScore))
names(metadata) <- c("sets", "avgRottenTomatoesScore")
head(metadata)
## sets avgRottenTomatoesScore
## 1 Action 73
## 2 Adventure 76
## 3 Children 30
## 4 Comedy 5
## 5 Crime 44
## 6 Documentary 8
metadata$avgRottenTomatoesScore <- as.numeric(as.character(metadata$avgRottenTomatoesScore))
添加元数据条形图
upset(movies,
sets = c("Action", "Adventure", "Comedy", "Drama", "Mystery", "Thriller", "Romance", "War", "Western"),
set.metadata = list(data = metadata,
plots = list(list(type = "hist", column = "avgRottenTomatoesScore", assign = 20))))
image.png
添加元数据热图
Cities <- sample(c("Boston", "NYC", "LA"), 17, replace = T)
metadata <- cbind(metadata, Cities)
metadata$Cities <- as.character(metadata$Cities)
metadata[which(metadata$sets %in% c("Drama", "Comedy", "Action", "Thriller", "Romance")), ]
## sets avgRottenTomatoesScore Cities
## 1 Action 73 LA
## 4 Comedy 5 LA
## 7 Drama 55 NYC
## 13 Romance 43 Boston
## 15 Thriller 51 LA
head(metadata)
## sets avgRottenTomatoesScore Cities
## 1 Action 73 LA
## 2 Adventure 76 LA
## 3 Children 30 NYC
## 4 Comedy 5 LA
## 5 Crime 44 NYC
## 6 Documentary 8 LA
upset(movies,
sets = c("Drama", "Comedy", "Action", "Thriller", "Romance"),
set.metadata = list(data = metadata,
plots = list(list(type = "heat", column = "Cities", assign = 10, colors = c(Boston = "green", NYC = "navy", LA = "purple")))))
image.png
upset(movies,
sets = c("Drama", "Comedy", "Action", "Thriller", "Romance"),
set.metadata = list(data = metadata,
plots = list(list(type = "heat", column = "Cities", assign = 10, colors = c(Boston = "green", NYC = "navy", LA = "purple")),
list(type = "heat", column = "avgRottenTomatoesScore", assign = 10))))
image.png
添加元数据文本
upset(movies,
sets = c("Drama", "Comedy", "Action", "Thriller", "Romance"),
set.metadata = list(data = metadata,
plots = list(list(type = "text", column = "Cities", assign = 10, colors = c(Boston = "green", NYC = "navy", LA = "purple")))))
image.png
添加元数据矩阵条形图
upset(movies,
sets = c("Drama", "Comedy", "Action", "Thriller", "Romance"),
set.metadata = list(data = metadata,
plots = list(list(type = "hist", column = "avgRottenTomatoesScore", assign = 20),
list(type = "matrix_rows", column = "Cities", colors = c(Boston = "green", NYC = "navy", LA = "purple"), alpha = 0.5))))
image.png
使用queries参数查询数据
head(movies)
## Name ReleaseDate Action Adventure Children
## 1 Toy Story (1995) 1995 0 0 1
## 2 Jumanji (1995) 1995 0 1 1
## 3 Grumpier Old Men (1995) 1995 0 0 0
## 4 Waiting to Exhale (1995) 1995 0 0 0
## 5 Father of the Bride Part II (1995) 1995 0 0 0
## 6 Heat (1995) 1995 1 0 0
## Comedy Crime Documentary Drama Fantasy Noir Horror Musical Mystery
## 1 1 0 0 0 0 0 0 0 0
## 2 0 0 0 0 1 0 0 0 0
## 3 1 0 0 0 0 0 0 0 0
## 4 1 0 0 1 0 0 0 0 0
## 5 1 0 0 0 0 0 0 0 0
## 6 0 1 0 0 0 0 0 0 0
## Romance SciFi Thriller War Western AvgRating Watches
## 1 0 0 0 0 0 4.15 2077
## 2 0 0 0 0 0 3.20 701
## 3 1 0 0 0 0 3.02 478
## 4 0 0 0 0 0 2.73 170
## 5 0 0 0 0 0 3.01 296
## 6 0 0 1 0 0 3.88 940
# 使用内置的相交查询intersects来查找或显示特定相交处的元素。
upset(movies,
queries = list(list(query = intersects, params = list("Drama", "Comedy", "Action"), color = "orange", active = T),
list(query = intersects, params = list("Drama"), color = "red", active = F),
list(query = intersects, params = list("Action", "Drama"), active = T)))
image.png
# 使用内置的元素查询elements来可视化某些元素在相交之间的分布方式
upset(movies,
queries = list(list(query = elements, params = list("AvgRating", 3.5, 4.1), color = "blue", active = T),
list(query = elements, params = list("ReleaseDate", 1980, 1990, 2000), color = "red", active = F)))
image.png
# 添加查询图例
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")))
image.png
使用attribute.plots参数添加属性图
head(movies)
## Name ReleaseDate Action Adventure Children
## 1 Toy Story (1995) 1995 0 0 1
## 2 Jumanji (1995) 1995 0 1 1
## 3 Grumpier Old Men (1995) 1995 0 0 0
## 4 Waiting to Exhale (1995) 1995 0 0 0
## 5 Father of the Bride Part II (1995) 1995 0 0 0
## 6 Heat (1995) 1995 1 0 0
## Comedy Crime Documentary Drama Fantasy Noir Horror Musical Mystery
## 1 1 0 0 0 0 0 0 0 0
## 2 0 0 0 0 1 0 0 0 0
## 3 1 0 0 0 0 0 0 0 0
## 4 1 0 0 1 0 0 0 0 0
## 5 1 0 0 0 0 0 0 0 0
## 6 0 1 0 0 0 0 0 0 0
## Romance SciFi Thriller War Western AvgRating Watches
## 1 0 0 0 0 0 4.15 2077
## 2 0 0 0 0 0 3.20 701
## 3 1 0 0 0 0 3.02 478
## 4 0 0 0 0 0 2.73 170
## 5 0 0 0 0 0 3.01 296
## 6 0 0 1 0 0 3.88 940
添加内置属性直方图
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))
image.png
添加内置属性散点图
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 = scatter_plot, x = "ReleaseDate", y = "AvgRating", queries = T),
list(plot = scatter_plot, x = "AvgRating", y = "Watches", queries = F)), ncols = 2), query.legend = "bottom")
image.png
添加属性箱线图
upset(movies, boxplot.summary = c("AvgRating", "ReleaseDate"))
image.png
一次性添加元数据，查询和属性图
upset(movies,
set.metadata = list(data = metadata,
plots = list(list(type = "hist", column = "avgRottenTomatoesScore", assign = 20),
list(type = "text", column = "Cities", assign = 5, colors = c(Boston = "green", NYC = "navy", LA = "purple")),
list(type = "matrix_rows", column = "Cities", colors = c(Boston = "green", NYC = "navy", LA = "purple"), alpha = 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 = 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")
image.png
sessionInfo()
## R version 3.6.0 (2019-04-26)
## Platform: x86_64-w64-mingw32/x64 (64-bit)
## Running under: Windows 10 x64 (build 18363)
##
## Matrix products: default
##
## locale:
## [1] LC_COLLATE=Chinese (Simplified)_China.936
## [2] LC_CTYPE=Chinese (Simplified)_China.936
## [3] LC_MONETARY=Chinese (Simplified)_China.936
## [4] LC_NUMERIC=C
## [5] LC_TIME=Chinese (Simplified)_China.936
##
## attached base packages:
## [1] stats graphics grDevices utils datasets methods base
##
## other attached packages:
## [1] UpSetR_1.4.0
##
## loaded via a namespace (and not attached):
## [1] Rcpp_1.0.5 knitr_1.23 magrittr_1.5 tidyselect_0.2.5
## [5] munsell_0.5.0 colorspace_1.4-1 R6_2.4.0 rlang_0.4.7
## [9] plyr_1.8.4 stringr_1.4.0 dplyr_0.8.3 tools_3.6.0
## [13] grid_3.6.0 gtable_0.3.0 xfun_0.8 withr_2.1.2
## [17] htmltools_0.3.6 assertthat_0.2.1 yaml_2.2.0 lazyeval_0.2.2
## [21] digest_0.6.20 tibble_2.1.3 crayon_1.3.4 gridExtra_2.3
## [25] purrr_0.3.2 ggplot2_3.2.0 glue_1.3.1 evaluate_0.14
## [29] rmarkdown_1.13 labeling_0.3 stringi_1.4.3 compiler_3.6.0
## [33] pillar_1.4.2 scales_1.0.0 pkgconfig_2.0.2