用R中整洁的数据创建Sankey图
用R中整洁的数据创建Sankey图
提问于 2020-08-04 21:52:39
我使用dplyr和tidyr函数“整理”了R中的数据，并创建了如下数据框架：
df <- data.frame(PROD = c("A","A","A","A"), REJECT = c("YES","YES","NO","NO"),ALT_PROD = c("A","B","C","D"), VALUE = c(100,50,400,500))我希望根据上面的值绘制一个3节的sankey图。我发现的大多数示例都使用了2节图(从->到)，但我希望包括中间部分“拒绝”。我还找到了包含多个部分的示例，但由于我在R.
有一个选项可以使用flipPlot包，但是由于包更新问题，我在从GitHub安装软件包时遇到了问题：
Error: Failed to install 'flipPlots' from GitHub:
Failed to install 'flipTransformations' from GitHub:
Failed to install 'flipFormat' from GitHub:
(converted from warning) cannot remove prior installation of package ‘jsonlite’ 我以前使用过networkD3包来创建一个两节图，我真的希望更好地理解如何扩展这个包来构建一个3节图。
Stack Overflow用户
回答已采纳
发布于 2020-08-06 11:36:47
您需要构建符合'source', 'target', ...样式的链接数据框架。在您的示例中，每个连续列(值列除外)都是上一列的目标。您可以通过从每个列的顺序推断每个步骤的顺序来重塑数据.
library(networkD3)
library(dplyr)
library(tidyr)
df <- data.frame(PROD = c("A","A","A","A"),
REJECT = c("YES","YES","NO","NO"),
ALT_PROD = c("A","B","C","D"),
VALUE = c(100,50,400,500))
links <-
df %>%
as_tibble() %>%
mutate(row = row_number()) %>%
pivot_longer(cols = c(-row, -VALUE),
names_to = 'column', values_to = 'source') %>%
mutate(column = match(column, names(df))) %>%
mutate(source = paste0(source, '__', column)) %>%
group_by(row) %>%
mutate(target = lead(source, order_by = column)) %>%
drop_na(target, source) %>%
group_by(source, target) %>%
summarise(value = sum(VALUE), .groups = 'drop')
nodes <- data.frame(name = unique(c(links$source, links$target)))
links$source <- match(links$source, nodes$name) - 1
links$target <- match(links$target, nodes$name) - 1
nodes$name <- sub('__[0-9]+$', '', nodes$name)
sankeyNetwork(Links = links, Nodes = nodes, Source = "source",
Target = "target", Value = "value", NodeID = "name")为了使这个过程更清楚，下面是您需要构建的links数据框架在流程中的每一个重要步骤之后的样子。
df %>%
as_tibble() %>%
mutate(row = row_number())
#> # A tibble: 4 x 5
#> PROD REJECT ALT_PROD VALUE row
#> <chr> <chr> <chr> <dbl> <int>
#> 1 A YES A 100 1
#> 2 A YES B 50 2
#> 3 A NO C 400 3
#> 4 A NO D 500 4
df %>%
as_tibble() %>%
mutate(row = row_number()) %>%
pivot_longer(cols = c(-row, -VALUE),
names_to = 'column', values_to = 'source')
#> # A tibble: 12 x 4
#> VALUE row column source
#> <dbl> <int> <chr> <chr>
#> 1 100 1 PROD A
#> 2 100 1 REJECT YES
#> 3 100 1 ALT_PROD A
#> 4 50 2 PROD A
#> 5 50 2 REJECT YES
#> 6 50 2 ALT_PROD B
#> 7 400 3 PROD A
#> 8 400 3 REJECT NO
#> 9 400 3 ALT_PROD C
#> 10 500 4 PROD A
#> 11 500 4 REJECT NO
#> 12 500 4 ALT_PROD D
df %>%
as_tibble() %>%
mutate(row = row_number()) %>%
pivot_longer(cols = c(-row, -VALUE),
names_to = 'column', values_to = 'source') %>%
mutate(column = match(column, names(df))) %>%
mutate(source = paste0(source, '__', column))
#> # A tibble: 12 x 4
#> VALUE row column source
#> <dbl> <int> <int> <chr>
#> 1 100 1 1 A__1
#> 2 100 1 2 YES__2
#> 3 100 1 3 A__3
#> 4 50 2 1 A__1
#> 5 50 2 2 YES__2
#> 6 50 2 3 B__3
#> 7 400 3 1 A__1
#> 8 400 3 2 NO__2
#> 9 400 3 3 C__3
#> 10 500 4 1 A__1
#> 11 500 4 2 NO__2
#> 12 500 4 3 D__3
df %>%
as_tibble() %>%
mutate(row = row_number()) %>%
pivot_longer(cols = c(-row, -VALUE),
names_to = 'column', values_to = 'source') %>%
mutate(column = match(column, names(df))) %>%
mutate(source = paste0(source, '__', column)) %>%
group_by(row) %>%
mutate(target = lead(source, order_by = column))
#> # A tibble: 12 x 5
#> # Groups: row [4]
#> VALUE row column source target
#> <dbl> <int> <int> <chr> <chr>
#> 1 100 1 1 A__1 YES__2
#> 2 100 1 2 YES__2 A__3
#> 3 100 1 3 A__3 <NA>
#> 4 50 2 1 A__1 YES__2
#> 5 50 2 2 YES__2 B__3
#> 6 50 2 3 B__3 <NA>
#> 7 400 3 1 A__1 NO__2
#> 8 400 3 2 NO__2 C__3
#> 9 400 3 3 C__3 <NA>
#> 10 500 4 1 A__1 NO__2
#> 11 500 4 2 NO__2 D__3
#> 12 500 4 3 D__3 <NA>
df %>%
as_tibble() %>%
mutate(row = row_number()) %>%
pivot_longer(cols = c(-row, -VALUE),
names_to = 'column', values_to = 'source') %>%
mutate(column = match(column, names(df))) %>%
mutate(source = paste0(source, '__', column)) %>%
group_by(row) %>%
mutate(target = lead(source, order_by = column)) %>%
drop_na(target, source)
#> # A tibble: 8 x 5
#> # Groups: row [4]
#> VALUE row column source target
#> <dbl> <int> <int> <chr> <chr>
#> 1 100 1 1 A__1 YES__2
#> 2 100 1 2 YES__2 A__3
#> 3 50 2 1 A__1 YES__2
#> 4 50 2 2 YES__2 B__3
#> 5 400 3 1 A__1 NO__2
#> 6 400 3 2 NO__2 C__3
#> 7 500 4 1 A__1 NO__2
#> 8 500 4 2 NO__2 D__3
df %>%
as_tibble() %>%
mutate(row = row_number()) %>%
pivot_longer(cols = c(-row, -VALUE),
names_to = 'column', values_to = 'source') %>%
mutate(column = match(column, names(df))) %>%
mutate(source = paste0(source, '__', column)) %>%
group_by(row) %>%
mutate(target = lead(source, order_by = column)) %>%
drop_na(target, source) %>%
group_by(source, target) %>%
summarise(value = sum(VALUE), .groups = 'drop')
#> # A tibble: 6 x 3
#> source target value
#> <chr> <chr> <dbl>
#> 1 A__1 NO__2 900
#> 2 A__1 YES__2 150
#> 3 NO__2 C__3 400
#> 4 NO__2 D__3 500
#> 5 YES__2 A__3 100
#> 6 YES__2 B__3 50页面原文内容由Stack Overflow提供。腾讯云小微IT领域专用引擎提供翻译支持
原文链接：
https://stackoverflow.com/questions/63255589
复制相关文章
相似问题
腾讯云开发者
