Как решить проблему переменной длины?

Question

У меня есть набор данных, который выглядит следующим образом, я пытаюсь выполнить тест Крускала Уоллиса на нем

Код r для этого выглядит следующим образом:

my_data <- read.csv('NBvariants_KWtest.csv',header = TRUE)
head(my_data)
levels(my_data$NaiveBayesvariant)
my_data$NaiveBayesvariant <- ordered(my_data$NaiveBayesvariant,
                         levels = c("I", "II", "III","IV","V","VI"))
library(dplyr)
group_by(my_data, NaiveBayesvariant) %>%
  summarise(
    count = n(),
    mean = mean(accuracy, na.rm = TRUE),
    sd = sd(accuracy, na.rm = TRUE),
    median = median(accuracy, na.rm = TRUE),
    IQR = IQR(accuracy, na.rm = TRUE)
  )

library("ggpubr")
ggboxplot(my_data, x = "NaiveBayesvariant", y = "Accuracy", 
          color = "NaiveBayesvariant", palette = c("#00AFBB", "#E7B800", "#FC4E07","#00AFBB", "#E7B800", "#FC4E07"),
          order = c("I", "II", "III","IV","V","VI"),
          ylab = "Accuracy", xlab = "Naive Bayes variant")

ggline(my_data, x = "NaiveBayesvariant", y = "Accuracy", 
       add = c("mean_se", "jitter"), 
       order = c("I", "II", "III","IV", "V", "VI"),
       ylab = "Naive Bayes variant", xlab = "Accuracy")


kruskal.test(accuracy ~ NaiveBayesvariant, data = my_data)

Однако я получаю эту ошибку:

> kruskal.test(accuracy ~ NaiveBayesvariant, data = my_data)
Error in model.frame.default(formula = accuracy ~ NaiveBayesvariant, data = my_data) : 
  variable lengths differ (found for 'NaiveBayesvariant')
> kruskal.test(accuracy ~ NaiveBayesvariant, data = my_data