Question

我有一个包含交易数据的大型数据框。每个事务指的是对工件做出贡献的人（例如，开发人员修改了文件）。

我努力将此数据转换为双边networkDynamic图，其中人和工件是节点，事务表示为边，仅在事务的时间点处于活动状态。显然，在两个节点之间可以存在多个事务，这意味着我们有多次激活一条边。

到目前为止一切顺利。在一天结束时，我需要计算有关此网络演变的统计数据，例如：测量统计数据，如网络在多个时间点的连通性。

出于某种原因，我经常遇到问题。例如，在下面的可重现代码示例中，函数tSnaStats的最后一次调用会抱怨多个属性值。这通常应该没问题，因为我们在查询法术中有一个多次激活的边缘。然而，尽管我将规则指定为最新值，但它使用最早的值是奇怪的。最后一次调用（使用gtrans）甚至失败并显示错误。

所以我的第一个问题是我的网络构造代码是否有效（也许我误解了一些东西）。如果是，问题是这是否是tsna包中的错误......

if (!require("pacman")) install.packages("pacman")
library("pacman")
pacman::p_load(network, networkDynamic, tsna)
dfTransactions <-
    structure(
        list(
            weight = c(1, 2, 2),
            contributorweight = c(1, 2, 2),
            artifactweight = c(1, 2, 2),
            contributorId = c("u1", "u1", "u2"),
            instantId =
                c(1000, 2000, 3000) ,
            artifactId = c("a1", "a1", "a2")
        ),
        .Names = c(
            "weight",
            "contributorweight",
            "artifactweight",
            "contributorId",
            "instantId",
            "artifactId"
        ),
        row.names = c(1L, 2L, 3L),
        class = "data.frame"
    )

dfEdges <- unique(dfTransactions[, c("contributorId", "artifactId")])

veUniqueContributors   <- unique(dfEdges[[1]])
veUniqueArtifacts      <- unique(dfEdges[[2]])
veUniqueVertices       <- c(veUniqueContributors, veUniqueArtifacts)
nuNrUniqueContributors <- length(veUniqueContributors)
nuNrUniqueArtifacts    <- length(veUniqueArtifacts)
nuNrUniqueVertices     <- length(veUniqueVertices)

dfEdgeSpells <-
    dfTransactions[c("instantId",
                     "instantId",
                     "contributorId",
                     "artifactId",
                     "weight")]
dfContributorSpells <-
    dfTransactions[c("instantId",
                     "instantId",
                     "contributorId",
                     "contributorweight")]
dfArtifactSpells <-
    dfTransactions[c("instantId", "instantId", "artifactId", "artifactweight")]

names(dfContributorSpells) <-
    c("onset", "terminus", "vertex.id", "weight")
names(dfArtifactSpells) <-
    c("onset", "terminus", "vertex.id", "weight")

dfVertexSpells <- data.frame(
    onset = numeric(),
    terminus = numeric(),
    vertex.id = character(),
    weight = numeric()
)

dfVertexSpells <- rbind(dfContributorSpells, dfArtifactSpells)

# Convert vertex names to vertex ids
dfEdgeSpells[["contributorId"]] <-
    match(dfEdgeSpells[["contributorId"]], veUniqueVertices)
dfEdgeSpells[["artifactId"]]    <-
    match(dfEdgeSpells[["artifactId"]], veUniqueVertices)
dfVertexSpells$vertex.id            <-
    match(dfVertexSpells$vertex.id, veUniqueVertices)

net <- network.initialize(
    nuNrUniqueVertices,
    directed = TRUE,
    hyper = FALSE,
    loops = FALSE,
    multiple = FALSE,
    bipartite = nuNrUniqueContributors
)

net %v% "vertex.names" <- veUniqueVertices
net %v% "vertex.type"  <-
    c(rep("contributor", nuNrUniqueContributors),
      rep("artifact", nuNrUniqueArtifacts))

net <- networkDynamic(
    net,
    create.TEAs = TRUE,
    edge.spells = dfEdgeSpells,
    edge.TEA.names = c("weight"),
    vertex.spells = dfVertexSpells,
    vertex.TEA.names = c("weight")
)

reconcile.vertex.activity(net = net,
                          mode = "encompass.edges",
                          edge.active.default = TRUE)


# Returns Warning
tSnaStats(
    net,
    "connectedness",
    time.interval = 1001,
    aggregate.dur = 1001,
    rule = "latest"
)

# Returns Error
tSnaStats(
    net,
    "gtrans",
    time.interval = 100,
    aggregate.dur = 100,
    rule = "latest"
)

如何使用networkDynamic和tsna在多个时间点（切片）测量图形统计数据？

0 个答案: