Question

我有一个公司的数据，我希望通过树形图可视化。这意味着，我将他们的品牌嵌套在类中，嵌套在子组中，嵌套在分区中（http://www.bayer.com/en/products-from-a-to-z.aspx#B）。

即使stackoverflow上有很多线程如何创建树形图，我也没有找到适用于我的数据的代码片段（例如how to convert a data.frame to tree structure object such as dendrogram）。

修改：如果我是正确的“树状图”在这种情况下不是正确的术语，因为我没有/考虑任何类型的距离测量。这样我使用更通用的术语“树图”

df <- structure(list(Brand = structure(c(73L, 122L, 131L, 44L, 6L, 
7L, 8L, 27L, 52L, 84L, 95L, 101L, 121L, 142L, 17L, 21L, 53L, 
86L, 99L, 112L, 139L, 4L, 97L, 76L, 47L, 113L, 146L, 71L, 109L, 
147L, 148L, 149L, 14L, 80L, 93L, 114L, 3L, 15L, 25L, 26L, 35L, 
36L, 37L, 39L, 42L, 56L, 57L, 59L, 60L, 61L, 62L, 63L, 65L, 66L, 
67L, 68L, 69L, 72L, 90L, 92L, 117L, 28L, 91L, 9L, 16L, 81L, 45L, 
51L, 10L, 130L, 138L, 46L, 74L, 116L, 128L, 137L, 11L, 77L, 82L, 
83L, 94L, 111L, 123L, 124L, 134L, 136L, 141L, 18L, 23L, 48L, 
75L, 79L, 87L, 88L, 100L, 102L, 126L, 129L, 50L, 54L, 115L, 5L, 
22L, 85L, 98L, 118L, 127L, 19L, 38L, 107L, 132L, 58L, 120L, 96L, 
2L, 49L, 55L, 20L, 106L, 135L, 143L, 145L, 1L, 133L, 125L, 108L, 
119L, 12L, 24L, 33L, 78L, 103L, 104L, 105L, 13L, 29L, 30L, 31L, 
32L, 34L, 40L, 41L, 43L, 70L, 89L, 110L, 144L, 64L, 140L), .Label = c("3.0T Prostate eCoil", 
"A1CNow", "Acclaim Polyol", "Adalat", "Admire", "Advantage", 
"Advantix", "Advocate", "Aleve", "Alka-Seltzer", "Antracol", 
"Apec", "Arcol", "Arize", "Artwalk", "Aspirin", "Aspirin Cardio", 
"Atlantis", "Attribut", "Avanta", "Avelox", "Bariton", "Basta", 
"Bayblend", "Baybond", "Baycoll", "Baycox", "Baycusan", "Baydur", 
"Bayfill", "Bayfit", "Bayflex", "Bayfol", "Baygalÿ/Baymidur", 
"Bayhydrol", "Bayhydur", "Bayhytherm", "Bayleton", "Baymer", 
"Baynat", "Baypreg", "Baypren", "Baytec", "Baytril", "Bepanthenÿ/Bepanthol", 
"Berocca", "Betaferonÿ/ Betaseron", "Betanal", "Breezeÿ2", "Calypso", 
"Canesten", "Catosal", "Cipro", "Confidor", "Contourÿ/Contour Linkÿ/Contour TS", 
"CreKat", "Crelan", "Decis", "Desavin", "Desmocap", "Desmocoll", 
"Desmoderm", "Desmodur", "Desmoflex", "Desmolac", "Desmolith", 
"Desmolux", "Desmomelt", "Desmopan", "Desmophen", "Diane", "Dispercoll", 
"Drontal", "Elevit", "Equip", "Eylea", "Fandango", "Fantasia", 
"Fenikan", "FiberMax", "Flanaxÿ/ÿApronax", "Flint", "Folicur", 
"Gadovist", "Gaucho", "Glucobay", "Hoestar", "Husar", "Hyperlite", 
"Imprafix", "Impranil", "Impraperm", "InVigor", "Input", "Iopamiron", 
"K-Othrine", "Kogenate", "Lamardor", "Levitra", "Liberty", "Magnevist", 
"MaisTer", "Makroblend", "Makrofol", "Makrolon", "Mark V ProVis", 
"Maxforce", "Microlet 2", "Mirena", "Multitec", "Nativo", "Nebido", 
"Nexavar", "Nunhems", "Oberon", "One-A-Day", "Pergut", "Poncho", 
"Possis Angio Jet", "Premise", "Primovist", "Profender", "Proline", 
"Prosaro", "Pulsar", "Puma", "Raxil", "Redoxon", "Rely", "Rennie", 
"Rompun", "Ronstar", "Solaris", "Sphere", "Stellant", "Stratego", 
"Supradyn", "Talcid", "Testogel", "Texin", "Twist", "Ultravist", 
"Vistron CT", "Vulkollan", "XDS", "Xarelto", "Yasmin", "Yasminelle", 
"Yaz"), class = "factor"), Class = structure(c(6L, 6L, 6L, 7L, 
8L, 8L, 8L, 13L, 13L, 10L, 11L, 11L, 10L, 11L, 12L, 17L, 17L, 
17L, 18L, 18L, 18L, 20L, 20L, 29L, 33L, 34L, 39L, 43L, 43L, 43L, 
43L, 43L, 1L, 2L, 2L, 41L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 
5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 
31L, 37L, 3L, 3L, 3L, 9L, 14L, 16L, 16L, 16L, 42L, 42L, 42L, 
42L, 42L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 
21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 26L, 26L, 
26L, 27L, 32L, 32L, 32L, 32L, 32L, 21L, 15L, 19L, 21L, 26L, 36L, 
40L, 4L, 4L, 4L, 22L, 22L, 23L, 23L, 23L, 24L, 24L, 25L, 28L, 
38L, 30L, 30L, 30L, 30L, 30L, 30L, 30L, 31L, 31L, 31L, 31L, 31L, 
31L, 31L, 31L, 31L, 31L, 31L, 31L, 31L, 35L, 35L), .Label = c("Agricultural Seed", 
"Agricultural seed", "Analgesics", "Blood Glucose Monitoring Systems", 
"Coatings, adhesives, specialties", "Companion Animal", "Companion Animal / Food Animal Product", 
"Companion animals", "Dermatologicals", "Diagnostic Imaging", 
"Diagnostic imaging", "Drug product for protection against heart attack", 
"Food Animal Product", "Fungal infections", "Fungicides", "Gastrointestinals", 
"General Medicine", "General Medicine / Mens HealthCare", "General insect control", 
"Hematology/cardiology", "Herbicides", "Injection Systems / Cardiology", 
"Injection Systems / Computer Tomography", "Injection Systems / Magnetic Resonance Tomography", 
"Injections Systems Ultrasound", "Insecticides", "Insecticides/seed treatment", 
"Lancing Devices", "Ophthalmology", "Polycarbonates", "Polyurethanes", 
"Seed treatment", "Specialty Medicine", "Specialty Medicine / Onkology", 
"TPU granules", "Termiticides", "Textile coating", "Thrombectomy", 
"Thromboembolic diseases", "Vector and locust control", "Vegetable seed", 
"Vitamins", "Women's healthcare"), class = "factor"), Subgroup = structure(c(2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 
1L, 1L, 1L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 
3L, 3L, 3L, 3L), .Label = c("Bayer CropScience", "Bayer HealthCare", 
"Bayer MaterialScience"), class = "factor"), Division = structure(c(1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 
3L, 3L, 3L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 5L, 5L, 
5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 6L, 6L, 6L, 6L, 6L, 
6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 
6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 7L, 8L, 8L, 8L, 8L, 8L, 
8L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 10L, 
10L, 10L, 10L, 10L, 10L, 10L, 11L, 11L, 11L, 11L, 11L, 11L, 11L, 
11L, 11L, 11L, 11L, 11L, 11L, 12L, 12L), .Label = c("Animal Health", 
"Bayer HealthCare Pharmaceuticals, Germany", "BioScience", "Coatings, Adhesives, Specialties", 
"Consumer Care", "Crop Protection", "Crop Protection/Environmental Science", 
"Environmental Science", "Medical Care", "Polycarbonates", "Polyurethanes", 
"Thermoplastic Polyurethanes"), class = "factor")), .Names = c("Brand", 
"Class", "Subgroup", "Division"), class = "data.frame", row.names = c(NA, 
-149L))

我感谢任何帮助。

Answer 1

使用包ape，并假设您的数据为olddat：

library(ape)
newdata <- as.phylo(x=~Division/Subgroup/Class/Brand,data=olddat)
plot.phylo(x=newdata,show.tip.label=TRUE,show.node.label=TRUE,no.margin=TRUE)

你需要玩各种情节选项，但我认为这会让你朝着正确的方向前进。如果我能让情节看起来不错，我会看到更新答案。

创建树形图

1 个答案: