0

我遵循了这个问题的答案：Tukey test results on geom_boxplot with facet_grid

这很棒，但我也想比较它们之间的各个方面。换句话说，首先将所有结果按字母顺序排列，然后将其划分为多个方面（我有水平和垂直方面）。我怎样才能做到这一点？另外，如何重新排序字母以从第一个方面的第一个变量中的“a”开始，然后是“b”第二个变量等等？我尝试了以下方法，但它没有像我想要的那样工作。

TUKEY <- TukeyHSD(ANOVA, ordered = TRUE)

这是一个可重现的代码（生成图的代码取自上面的链接），数据取自这个链接（http://sape.inf.usi.ch/quick-reference/ggplot2/facet）

d=expand.grid(obs=0:10, benchmark=c('antlr', 'bloat', 'chart'), gc=c('CopyMS', 'GenCopy', 'GenImmix'), opt=c('on', 'off', 'valid'), heapSize=seq(from=1.5, to=4, by=0.5))
d$time = rexp(nrow(d), 0.01)+1000
d$time = d$time + abs(d$heapSize-3)*100
d$time[d$opt=='on'] = d$time[d$opt=='on']-200

d$time[d$opt=='on' & d$benchmark=='bloat'] = d$time[d$opt=='on' & d$benchmark=='bloat'] + 190

generate_label_df <- function(TUKEY, variable){

  # Extract labels and factor levels from Tukey post-hoc 
  Tukey.levels <- variable[,4]
  Tukey.labels <- data.frame(multcompLetters(Tukey.levels)['Letters'])

  #I need to put the labels in the same order as in the boxplot :
  Tukey.labels$treatment=rownames(Tukey.labels)
  Tukey.labels=Tukey.labels[order(Tukey.labels$treatment) , ]
  return(Tukey.labels)
}


TUKEYplot <- function(df){

  p<-ggplot(data=df)+
    aes(x = opt, y = time, colour = opt) +
    geom_boxplot() +
    facet_grid(gc~benchmark) +
    theme_linedraw() +
    theme(axis.text.x=element_text(angle=45, hjust=1)) +
    ylim(min(df$time),max(df$time)+0.05) +
    labs(x = "type", y= "time", color = "state") +
    theme(strip.background = element_rect(colour = "black", fill = "white")) +
    theme(strip.text = element_text(colour = "black", size=12)) +
    theme(axis.text=element_text(size=12)) +
    theme(legend.text=element_text(size=12)) +
    theme(legend.title=element_text(size=12,face="bold")) +
    theme(axis.title=element_text(size=14,face="bold")) +
    scale_color_npg()
  for (facetk2 in as.character(unique(df$gc))) {   
    for (facetk in as.character(unique(df$benchmark))) {   
      subdf <- subset(df, df$benchmark==facetk & df$gc==facetk2)
      model=lm(time ~ opt, data=subdf)
      ANOVA=aov(model)
      # Tukey test to study each pair of treatment :
      TUKEY <- TukeyHSD(ANOVA)
      print(TUKEY)
      labels <- generate_label_df(TUKEY , TUKEY$`opt`)
      names(labels) <- c('Letters', 'opt')
      yvalue <- aggregate(.~opt, data=subdf, quantile, probs=.75)  
      final <- merge(labels, yvalue)
      final$benchmark <-  facetk
      final$gc <-  facetk2

      p <- p + geom_text(data = final,  aes(x=opt, y=time, label=Letters), 
                         vjust=-1.2, hjust=-.5, show.legend = FALSE, size=5)
    }
  }
  return (p)
}

p1<-TUKEYplot(d)
p1

更新：我想做的视觉帮助：

原图：

原来的

部分所需的情节：

部分更新

4

1 回答 1

1

我终于想出了如何做到这一点，所以我发布了答案！基本上，将 Tukey 的计算排除在循环之外，在交互上使用 ANOVA 并在允许我想做的事情之后应用 Tukey。然后将标签分成列（确保您的数据不包含“：”，如果包含，您可以使用重值），然后在数据的级别上循环。

TUKEYplot <- function(df){

  p<-ggplot(data=df)+
    aes(x = opt, y = time, colour = opt) +
    geom_boxplot() +
    facet_grid(gc~benchmark) +
    theme_linedraw() +
    theme(axis.text.x=element_text(angle=45, hjust=1)) +
    ylim(min(df$time),max(df$time)+0.05) +
    labs(x = "type", y= "time", color = "state") +
    theme(strip.background = element_rect(colour = "black", fill = "white")) +
    theme(strip.text = element_text(colour = "black", size=12)) +
    theme(axis.text=element_text(size=12)) +
    theme(legend.text=element_text(size=12)) +
    theme(legend.title=element_text(size=12,face="bold")) +
    theme(axis.title=element_text(size=14,face="bold")) +
    scale_color_npg()

  model=lm(time ~ gc*benchmark*opt, data=df)
  ANOVA=aov(model)
  # Tukey test to study each pair of treatment :
  TUKEY <- TukeyHSD(ANOVA)
  all_labels <- generate_label_df(TUKEY , TUKEY$`gc:benchmark:opt`)
  sep_labels<- all_labels %>% separate(col=treatment, into= c("gc", "benchmark", "opt"), sep=":")

  for (facetk2 in as.character(unique(df$gc))) {   
    for (facetk in as.character(unique(df$benchmark))) {   
      subdf <- subset(df, df$benchmark==facetk & df$gc==facetk2)
      labels <- subset(sep_labels, sep_labels$benchmark==facetk & sep_labels$gc==facetk2)
      labels <- subset(labels, select = -c(gc,benchmark))

      names(labels) <- c('Letters', 'opt')
      yvalue <- aggregate(.~opt, data=subdf, quantile, probs=.75)  
      final <- merge(labels, yvalue)
      final$benchmark <-  facetk
      final$gc <-  facetk2

      p <- p + geom_text(data = final,  aes(x=opt, y=time, label=Letters), 
                         vjust=-1.2, hjust=-.5, show.legend = FALSE, size=5)
    }
  }
  return (p)
}

结果图像：（无法嵌入图像，因为我没有足够的声誉..）

结果

于 2019-05-20T15:25:46.733 回答