複雜樹狀網路的視覺化
基於R語言networkD3包實現，可以非常方的畫一般的樹狀圖或者層次聚類數狀圖，很多時候，需要表達關聯關係或者層次關係，樹狀圖是一種非常好的視覺化圖形。下面教大家怎麼構造資料結構並畫出圖形。
一、先看一個官方的例子
Flare <- jsonlite::fromJSON("https://gist.githubusercontent.com/mbostock/4063550/raw/a05a94858375bd0ae023f6950a2b13fac5127637/flare.json",simplifyDataFrame = FALSE)
radialNetwork(List = Flare, fontSize = 10, opacity = 0.9, margin=0,nodeColour = "#00E5EE",linkColour = "#00EEEE")
diagonalNetwork(List = Flare, fontSize = 10, opacity = 0.9, margin=0,nodeColour = "#00E5EE",linkColour = "#00EEEE")
二、看看怎麼畫的
案例1：使用者關聯的裝置，然後關聯新使用者
畫這個圖的難點在於資料結構的構造，需要用到R語言的列表，入門的時候不是很理解，其實列表就是向量的一種變形，下面看個非常簡單的例子：
user-裝置-user1
-user2
-user3
就是通過一個使用者關聯出裝置，然後用裝置關聯出新的人，看看資料結構是怎麼構造的
USER <- list(name = "user", children = list(
list(name = "裝置",
children = list(list(name = "user1"),
list(name = "user2"),
list(name = "user3")
))))
diagonalNetwork(List = USER, fontSize = 10, opacity = 0.9, margin=0,nodeColour = "#00E5EE",linkColour = "#00EEEE")
radialNetwork(List = USER, fontSize = 10, opacity = 0.9, margin=0,nodeColour = "#00E5EE",linkColour = "#00EEEE")
再複雜點，多加兩個裝置
USER <- list(name = "user", children = list(
list(name = "裝置1",
children = list(list(name = "user1"),
list(name = "user2"),
list(name = "user3")
)),
list(name = "裝置2",
children = list(list(name = "user1"),
list(name = "user2"),
list(name = "user3")
)),
list(name = "裝置3",
children = list(list(name = "user1"),
list(name = "user2"),
list(name = "user3")
))))
diagonalNetwork(List = USER, fontSize = 10, opacity = 0.9, margin=0,nodeColour = "#00E5EE",linkColour = "#00EEEE")
radialNetwork(List = USER, fontSize = 10, opacity = 0.9, margin=0,nodeColour = "#00E5EE",linkColour = "#00EEEE")
案例2：一個更復雜點的例子
CanadaPC <- list(name = "Canada", children = list(
list(name = "Newfoundland",
children = list(list(name = "St. John's"))),
list(name = "PEI",
children = list(list(name = "Charlottetown"))),
list(name = "Nova Scotia",
children = list(list(name = "Halifax"))),
list(name = "New Brunswick",
children = list(list(name = "Fredericton"))),
list(name = "Quebec",
children = list(list(name = "Montreal"),
list(name = "Quebec City"))),
list(name = "Ontario",
children = list(list(name = "Toronto"),
list(name = "Ottawa"))),
list(name = "Manitoba",
children = list(list(name = "Winnipeg"))),
list(name = "Saskatchewan",
children = list(list(name = "Regina"))),
list(name = "Nunavuet",
children = list(list(name = "Iqaluit"))),
list(name = "NWT",
children = list(list(name = "Yellowknife"))),
list(name = "Alberta",
children = list(list(name = "Edmonton"))),
list(name = "British Columbia",
children = list(list(name = "Victoria"),
list(name = "Vancouver"))),
list(name = "Yukon",
children = list(list(name = "Whitehorse")))
))
radialNetwork(List = CanadaPC, fontSize = 15, opacity = 0.9, margin=0,nodeColour = "#00E5EE",linkColour = "#00EEEE")
在層次聚類中，每個觀測值自成一類，這些類每次兩兩合併，直到所有的類被聚成一類為止。常用的有單聯動、全聯動、平均聯動、質心以及Ward方法。
使用的資料是，USArrests，結構如下：
#進行聚類
hc <- hclust(dist(USArrests), "ave")
radialNetwork(as.radialNetwork(hc))
diagonalNetwork(as.radialNetwork(hc), height = 700, margin = 50)
dendroNetwork(hc, height = 600)
dendroNetwork(hc, treeOrientation = "vertical")
dendroNetwork(hc, height = 600, linkType = "diagonal")
dendroNetwork(hc, treeOrientation = "vertical", linkType = "diagonal")
dendroNetwork(hc, textColour = c("red", "green", "orange")[cutree(hc, 3)],height = 600)
dendroNetwork(hc, textColour = c("red", "green", "orange")[cutree(hc, 3)], treeOrientation = "vertical")
