rbind()只迭代最后3个anova结果吗？

Question

我编写了一个循环，在其中迭代给定.csv的列，并运行anova和posthoc测试。然后将每个结果组合到一个数据框架中，并将其导出到一个.csv文件中。但是，我无法获得rbind()来构建我的data.frame。在这方面有什么帮助吗？下面是脚本：

​

setwd("~/School/Lab/mice/sugar_study_2015/MG-RAST and Metagenassist/Trimmed/R. CSV")
#Save your Datasheet into variable X
x <- read.csv("T0_B_Class_Anova.csv")

x = x[1:9,]
x[is.na(x)] <- 0

DF.Anova <- data.frame()
DF.Tukey <- data.frame()

#Counts through the columns
for(i in 2:(ncol(x)-1)){
  columns <- names(x[i])
 
##Runs an ANOVA - 'Group' being a grouping factor
  anovaresult <- anova(aov(x[,i]~Group,data=x))
  
  DF.Anova <- rbind(DF.Anova, anovaresult)
 
  ##fix anova into data frame
  Famall = colnames(x)
  Famall = as.data.frame(Famall)
  Famall = Famall[2:83,]
  Famall = as.data.frame(Famall)
  DFanovanames = rep(Famall, each = 2)
  DFanovanames = as.data.frame(DFanovanames)
  #install.packages("tidyr")
  library(tidyr)
  anovanames = data.frame(Names=unlist(DFanovanames, use.names = FALSE))
  o.anovanames = dplyr::arrange(anovanames, Names)
###dont forget to change this**************************
  finalanova_BFT0 = cbind(rn = rownames(DF.Anova), DF.Anova, o.anovanames)
 
##Runs Tukeys Post-hoc test on Anova
  posthocresult <- TukeyHSD(aov(x[,i]~Group,data=x))
 
  DF.Tukey <- rbind(DF.Tukey, posthocresult$Group)
 
  ##fix tukey into data frame
  Famname = colnames(x)
  Famname = as.data.frame(Famname)
  Famname = Famname[2:83,]
  Famname = as.data.frame(Famname)
  DFposthocnames = rep(Famname, each = 3)
  DFposthocnames = data.frame(DFposthocnames)
  #install.packages("tidyr")
  library(tidyr)
  library(dplyr)
  posthocnames = data.frame(Names=unlist(DFposthocnames, use.names = FALSE))
  o.posthocnames = dplyr::arrange(posthocnames, Names)
###dont forget to change this****************************
  finalposthoc_BFT0 = cbind(rn = rownames(DF.Tukey), DF.Tukey, o.posthocnames)
                           
##Prints posthoc results into txt file
  print(columns)
  print(anovaresult)
  print(posthocresult)
}
 
write.csv(finalanova_BFT0, file="testfinalanova_BCT0")
write.csv(finalposthoc_BFT0, file="finalposthoc_BCT0")

​

您可以找到示例.csv 这里

Answer 1

假设您想要的输出是两个不同测试的摘要结果的2个dataframes。您可以通过使用来自map包的purrr函数和来自broom包的tidy函数来实现这一点。我保存了你发布的csv，并将其保存为anova-question-data.csv。如果要使用setwd，我建议您验证数据读取是否正确。下面是我用来获取这两个数据帧的代码：

# read in the data
df <- read_csv(file = "anova-question-data.csv")

# create a list to loop over in the `map` call. 
loop_list <- colnames(df[,-1])

# create a list of data frames using the `tidy` function from `broom`
anova_list <- map(loop_list, function(x){
  anova_results <- anova(aov(df[[x]]~df[["Group"]]))

  # this tidies the results from the anova test and add a new 
  # column with the column name being tested. 
  # if bacteria is not your desired name, feel free to change it as 
  # it will not affect any of the rest of the code
  output <- broom::tidy(anova_results) %>%
    mutate(bacteria = x)
})

# use `do.call` to bind the dataframes in anova_list together
anova_df <- anova_list %>%
  do.call(rbind, .)

# repeat the exact same process only changing `anova` with `TukeyHSD`
posthoc_list <- map(loop_list, function(x){
  posthoc_results <- TukeyHSD(aov(df[[x]]~df[["Group"]]))

  output <- broom::tidy(posthoc_results) %>%
    mutate(bacteria = x)
 })

posthoc_df <- posthoc_list %>%
  do.call(rbind, .)

这给出了以下两个输出(我只打算打印前5行)：

> head(anova_df, 5)
         term    df        sumsq       meansq  statistic   p.value            bacteria
 1 df[["Group"]]  2 1.265562e-07 6.327809e-08 0.02650174 0.9739597       Acidobacteria
 2     Residuals  6 1.432617e-05 2.387695e-06         NA        NA       Acidobacteria
 3 df[["Group"]]  2 9.332880e-02 4.666440e-02 0.84001916 0.4768300      Actinobacteria
 4     Residuals  6 3.333096e-01 5.555159e-02         NA        NA      Actinobacteria
 5 df[["Group"]]  2 9.114521e-04 4.557261e-04 1.08994816 0.3946484 Alphaproteobacteria


> head(posthoc_df, 5)
           term comparison      estimate     conf.low   conf.high adj.p.value       bacteria
1 df[["Group"]]      HF-CO  2.234233e-04 -0.003647709 0.004094556   0.9829095  Acidobacteria
2 df[["Group"]]     HFS-CO -4.903533e-05 -0.003920168 0.003822097   0.9991677  Acidobacteria
3 df[["Group"]]     HFS-HF -2.724587e-04 -0.004143591 0.003598674   0.9747264  Acidobacteria
4 df[["Group"]]      HF-CO  2.345822e-01 -0.355886402 0.825050849   0.4856694 Actinobacteria
5 df[["Group"]]     HFS-CO  1.907267e-01 -0.399741917 0.781195333   0.6084817 Actinobacteria