如何使用 reshape2 包中的 melt() 来堆叠数据的分类标签以生成多个并排的 boxpot

How to use melt() from the reshape2 package to stack categorical labels of data to produce multiple side-by-side boxpots

我正在尝试使用 R 中 “reshape2” 包中的 melt() function 来堆叠数据框,同时为单个观察保留分类标签。我的问题是如何调整 Eric Cai's code Code 以在 behaviours$Family(一个 2 级因子列)级别上生成多个并排的缺口箱线图,这些箱线图由数据的每个行为变量分组 -设置称为 behviours(下面提供了一个 link 到虚拟数据)?

我的目标是用图例为每个家庭 (V4=red and W3 = blue) 对这些多缺口箱线图进行颜色编码。但是,在尝试使用 melt() 函数排列数据框时,我遇到了尺寸问题,我无法从中破译。如果有人可以提供帮助,那么非常感谢。

在堆栈溢出页面的底部找到了可重现的虚拟数据

 Here is an example:

 I am trying to follow Eric Cai's instructions
 (1) Stack the data:
     (a) Retain the categorical (2 level factor column) for family [,1]
     (b) Retain all behavioural variables [,2:13]

  #Set vectors for labelling the data

                      behaviours.label=c("Swimming", 
                                         "Not.Swimming",
                                         "Running", 
                                         "Not.Running",
                                         "Fighting",
                                         "Not.Fighting",
                                         "Resting",
                                         "Not.Resting",
                                         "Hunting",
                                         "Not.Hunting",
                                         "Grooming",
                                         "Not.Grooming")

                         family.labels=c("V4", "G8",
                                         "V4", "G8",
                                         "V4", "G8",
                                         "V4", "G8",
                                         "V4", "G8",
                                         "V4", "G8",
                                         "V4", "G8",
                                         "V4", "G8",
                                         "V4", "G8",
                                         "V4", "G8",
                                         "V4", "G8",
                                         "V4", "G8")

    library(tidyr)                        
    data_long <- gather(behaviours, x, Mean.Value, Swimming:Not.Grooming)
    head(data_long)  

    # stack the data while retaining the Family and behavioural variables 

    stacked.data = melt(behaviours, id = c('Family', 'behaviours'))

    # remove the column that gives the column name variable
    stacked.data = stacked.data[, -3]

    #head(stacked.data)
    colnames(stacked.data)<-c("Family", "Behaviours", "Values")

生成箱形图

生成一个名为boxplots.double的对象,它将使用公式 text{Mean.value ~ Family + Behaviours} 将图分成 12 组双胞胎(即,每个行为将在单个图中的 behaviours$family 级别分组)。在 Eric Cai 的代码中,“at = ”是一个选项,用于指定箱形图沿水平轴的位置,xaxt = 'n' 抑制默认水平轴,该轴使用 axis() 和 title()

   boxplots.double = boxplot(values~Family + Behaviours, 
                             data = stacked.data, 
                             at = c(1:24), 
                             xaxt='n',
                             ylim = c(min(0, min(-3)), 
                             max(7, na.rm = T)),
                             notch=TRUE,
                             col = c("red", "blue"),
                             names = c("V4", "G8"),
                             cex.axis=1.0,
                             srt=45)

  axis(side=1, at=c(1.8, 6.8), labels=c("Swimming", 
                                       "Not.Swimming",
                                       "Running", 
                                       "Not.Running",
                                       "Fighting",
                                       "Not.Fighting",
                                       "Resting",
                                       "Not.Resting",
                                       "Hunting",
                                       "Not.Hunting",
                                       "Grooming",
                                       "Not.Grooming"), line=0.5, lwd=0)

错误信息

   Error in axis(side = 1, at = 1:24, labels = c("V4", "G8"), xaxt = "n",     : 
  'at' and 'labels' lengths differ, 24 != 2
  In addition: Warning message:
  In bxp(list(stats = c(-1.20186549488911, -0.970033304559564,   -0.465271399251147,  :
  some notches went outside hinges ('box'): maybe set notch=FALSE

在理查德·特尔福德 (Richard Telford) 好心提供帮助后,此代码生成了多个并排箱线图,这些箱线图使用包含在包裹 reshape2

   clear the working directory
   rm(list=ls())

   data(behaviours)

   #Set vectors for labelling the data

   behaviours.labels=c("Swimming",  
                       "Not.Swimming",
                       "Running", 
                       "Not.Running",
                       "Fighting",
                       "Not.Fighting",
                       "Resting",
                       "Not.Resting",
                       "Hunting",
                       "Not.Hunting",
                       "Grooming",
                       "Not.Grooming")

       family.labels=c("V4", "G8",
                       "V4", "G8",
                       "V4", "G8",
                       "V4", "G8",
                       "V4", "G8",
                       "V4", "G8",
                       "V4", "G8",
                       "V4", "G8",
                       "V4", "G8",
                       "V4", "G8",
                       "V4", "G8",
                       "V4", "G8")

      library(tidyr)

      #Structure the data from wide to long format 

      data_long <- gather(behaviours, x, Mean.Value, Swimming:Not.Grooming)
      head(data_long)    

   library(reshape2)

   # stack the data while retaining Family and Values calculated from behaviours[,2:13] using the melt() function

   stacked.data = melt(data_long, id = c('Family', 'x'))
   head(stacked.data)

   # remove the column that gives the column name of the `variable' from all.data

   stacked.data = stacked.data[, -3]
   head(stacked.data)

   #Rename the column headings

   colnames(stacked.data)<-c("Family", "Behaviours", "Values")    

   #Generate the side-by-side boxplots

   windows(height=10, width=14)
   par(mar = c(9, 7, 4, 4)+0.3, mgp=c(5, 1.5, 0))

   boxplots.double = boxplot(Values~Family + Behaviours, 
                             data = stacked.data, 
                             at = c(1:24), 
                             ylim = c(min(0, min(0)), 
                                      max(1.8, na.rm = T)),
                             xaxt = "n",
                             notch=TRUE,
                             col = c("red", "blue"),
                             cex.axis=0.7,
                             cex.labels=0.7,
                             ylab="Values", 
                             xlab="Behaviours",
                             space=1)

   axis(side = 1, at = seq(2, 24, by = 2), labels = FALSE)
   text(seq(2, 24, by=2), par("usr")[3] - 0.2, labels=unique(behaviours.labels), srt = 45, pos = 1, xpd = TRUE, cex=0.8)
   legend("topright", title = "Family", cex=1.0, legend=c("V4" , "G8"), fill=c("Blue", "Red"), lty = c(1,1))