识别连接的子网（R-igraph）

Question

我正在处理网络数据，想要识别连接的子网。我使用
加载了我的数据

graph <- graph_from_data_frame(filtered_df, directed = FALSE)

并绘制了我的网络

plot(graph) 

E(graph)$conflict_period
[1] "72_1"   "72_1"   "72_1"   "72_1"   "72_1"   "72_1"   "72_1"   "72_1"   "72_1"   "72_1"   "72_1"   "372_1"  "372_1"  "372_1" 
[15] "372_1"  "372_1"  "372_1"  "372_1"  "372_1"  "372_1"  "372_1"  "522_0"  "522_0"  "522_0"  "522_0"  "522_0"  "522_0"  "522_0" 
[29] "522_0"  "522_0"  "522_0"  "715_0"  "715_0"  "715_0"  "715_0"  "5390_0"

到目前为止，子组的信息都存储在边中。节点属于它接收边的每个子组，因此节点也可以属于多个子组。例如，马里政府与平民一起属于子组“72_1”，与 FIAA 一起属于子组“372_1”。我想知道子组“72_1”和“372_1”是否已连接，如果属于子组“72_1”的至少两个节点通过边连接到属于子组“372_1”的至少两个节点。我厌倦了网络分析以外的方法来识别这种关系，但失败了。现在我在这里寻求帮助。

这是使用的数据：

structure(list(side_a = c("Government of Mali", "Government of Mali", 
"Government of Mali", "Government of Mali", "Government of Mali", 
"Government of Mali", "Government of Mali", "Government of Mali", 
"Government of Mali", "Government of Mali", "Government of Mali", 
"Government of Mali", "Government of Mali", "Government of Mali", 
"Government of Mali", "Government of Mali", "Government of Mali", 
"Government of Mali", "Government of Mali", "Government of Mali", 
"Government of Mali", "FIAA", "FIAA", "FIAA", "FIAA", "FIAA", 
"FIAA", "FIAA", "FIAA", "FIAA", "FIAA", "MPGK", "MPGK", "MPGK", 
"MPGK", "ARLA, FIAA, FPLA"), side_b = c("Civilians", "Civilians", 
"Civilians", "Civilians", "Civilians", "Civilians", "Civilians", 
"Civilians", "Civilians", "Civilians", "Civilians", "FIAA", "FIAA", 
"FIAA", "FIAA", "FIAA", "FIAA", "FIAA", "FIAA", "FIAA", "FIAA", 
"Civilians", "Civilians", "Civilians", "Civilians", "Civilians", 
"Civilians", "Civilians", "Civilians", "Civilians", "Civilians", 
"Civilians", "Civilians", "Civilians", "Civilians", "MPA"), country = c("Mali", 
"Mali", "Mali", "Mali", "Mali", "Mali", "Mali", "Mali", "Mali", 
"Mali", "Mali", "Mali", "Mali", "Mali", "Mali", "Mali", "Mali", 
"Mali", "Mali", "Mali", "Mali", "Mali", "Mali", "Mali", "Mali", 
"Mali", "Mali", "Mali", "Mali", "Mali", "Mali", "Mali", "Mali", 
"Mali", "Mali", "Mali"), period_start = structure(c(765158400, 
765158400, 765158400, 765158400, 765158400, 765158400, 765158400, 
765158400, 765158400, 765158400, 765158400, 770256000, 770256000, 
770256000, 770256000, 770256000, 770256000, 770256000, 770256000, 
770256000, 770256000, 771552000, 771552000, 771552000, 771552000, 
771552000, 771552000, 771552000, 771552000, 771552000, 771552000, 
769910400, 769910400, 769910400, 769910400, 771206400), tzone = "UTC", class = c("POSIXct", 
"POSIXt")), period_end = structure(c(817862400, 817862400, 817862400, 
817862400, 817862400, 817862400, 817862400, 817862400, 817862400, 
817862400, 817862400, 819158400, 819158400, 819158400, 819158400, 
819158400, 819158400, 819158400, 819158400, 819158400, 819158400, 
816739200, 816739200, 816739200, 816739200, 816739200, 816739200, 
816739200, 816739200, 816739200, 816739200, 814492800, 814492800, 
814492800, 814492800, 802828800), tzone = "UTC", class = c("POSIXct", 
"POSIXt")), conflict_period = c("72_1", "72_1", "72_1", "72_1", 
"72_1", "72_1", "72_1", "72_1", "72_1", "72_1", "72_1", "372_1", 
"372_1", "372_1", "372_1", "372_1", "372_1", "372_1", "372_1", 
"372_1", "372_1", "522_0", "522_0", "522_0", "522_0", "522_0", 
"522_0", "522_0", "522_0", "522_0", "522_0", "715_0", "715_0", 
"715_0", "715_0", "5390_0")), row.names = c(NA, -36L), class = c("tbl_df", 
"tbl", "data.frame"))

Answer 1

使用

igraph::groups()

查找连接的集群/子网：

filtered_df <- structure(list(side_a = c(
  "Government of Mali", "Government of Mali",
  "Government of Mali", "Government of Mali", "Government of Mali",
  "Government of Mali", "Government of Mali", "Government of Mali",
  "Government of Mali", "Government of Mali", "Government of Mali",
  "Government of Mali", "Government of Mali", "Government of Mali",
  "Government of Mali", "Government of Mali", "Government of Mali",
  "Government of Mali", "Government of Mali", "Government of Mali",
  "Government of Mali", "FIAA", "FIAA", "FIAA", "FIAA", "FIAA",
  "FIAA", "FIAA", "FIAA", "FIAA", "FIAA", "MPGK", "MPGK", "MPGK",
  "MPGK", "ARLA, FIAA, FPLA"
), side_b = c(
  "Civilians", "Civilians",
  "Civilians", "Civilians", "Civilians", "Civilians", "Civilians",
  "Civilians", "Civilians", "Civilians", "Civilians", "FIAA", "FIAA",
  "FIAA", "FIAA", "FIAA", "FIAA", "FIAA", "FIAA", "FIAA", "FIAA",
  "Civilians", "Civilians", "Civilians", "Civilians", "Civilians",
  "Civilians", "Civilians", "Civilians", "Civilians", "Civilians",
  "Civilians", "Civilians", "Civilians", "Civilians", "MPA"
), country = c(
  "Mali",
  "Mali", "Mali", "Mali", "Mali", "Mali", "Mali", "Mali", "Mali",
  "Mali", "Mali", "Mali", "Mali", "Mali", "Mali", "Mali", "Mali",
  "Mali", "Mali", "Mali", "Mali", "Mali", "Mali", "Mali", "Mali",
  "Mali", "Mali", "Mali", "Mali", "Mali", "Mali", "Mali", "Mali",
  "Mali", "Mali", "Mali"
), period_start = structure(c(
  765158400,
  765158400, 765158400, 765158400, 765158400, 765158400, 765158400,
  765158400, 765158400, 765158400, 765158400, 770256000, 770256000,
  770256000, 770256000, 770256000, 770256000, 770256000, 770256000,
  770256000, 770256000, 771552000, 771552000, 771552000, 771552000,
  771552000, 771552000, 771552000, 771552000, 771552000, 771552000,
  769910400, 769910400, 769910400, 769910400, 771206400
), tzone = "UTC", class = c(
  "POSIXct",
  "POSIXt"
)), period_end = structure(c(
  817862400, 817862400, 817862400,
  817862400, 817862400, 817862400, 817862400, 817862400, 817862400,
  817862400, 817862400, 819158400, 819158400, 819158400, 819158400,
  819158400, 819158400, 819158400, 819158400, 819158400, 819158400,
  816739200, 816739200, 816739200, 816739200, 816739200, 816739200,
  816739200, 816739200, 816739200, 816739200, 814492800, 814492800,
  814492800, 814492800, 802828800
), tzone = "UTC", class = c(
  "POSIXct",
  "POSIXt"
)), conflict_period = c(
  "72_1", "72_1", "72_1", "72_1",
  "72_1", "72_1", "72_1", "72_1", "72_1", "72_1", "72_1", "372_1",
  "372_1", "372_1", "372_1", "372_1", "372_1", "372_1", "372_1",
  "372_1", "372_1", "522_0", "522_0", "522_0", "522_0", "522_0",
  "522_0", "522_0", "522_0", "522_0", "522_0", "715_0", "715_0",
  "715_0", "715_0", "5390_0"
)), row.names = c(NA, -36L), class = c(
  "tbl_df",
  "tbl", "data.frame"
))

graph <- igraph::graph_from_data_frame(filtered_df, directed = FALSE)

plot(graph)

graph |>
  igraph::cluster_optimal() |>
  igraph::groups()
#> $`1`
#> [1] "Government of Mali" "FIAA"               "MPGK"              
#> [4] "Civilians"         
#> 
#> $`2`
#> [1] "ARLA, FIAA, FPLA" "MPA"

^{创建于 2024-02-29，使用 reprex v2.1.0}

Answer 2

也许您应该使用

decompose

来分隔子图，然后检索边中的“子组”信息，例如，

df %>%
    graph_from_data_frame(directed = FALSE) %>%
    decompose() %>%
    map(\(x) unique(E(x)$conflict_period))

输出

[[1]]
[1] "72_1"  "372_1" "522_0" "715_0"

[[2]]
[1] "5390_0"