我试图为我的交叉验证工作流集绘制结果（K与平方比之和），但当我使用collect_metrics时，我没有看到可以针对平均误差绘制的K的独立列。

我已经从配置名称中解析出了K的值，但我不确定这是一种有效的方法：

tune_results <- wf_set %>%
  collect_metrics() %>%
  filter(.metric == "sse_ratio")

tune_results %>%
  ggplot(aes(x = as.numeric(stringr::str_sub(.config, -2, -1)), y = mean, color = wflow_id)) +
  geom_point() +
  geom_line() +
  theme_minimal() +
  ggtitle("Plot of WSS/TSS ratio by Cluster Number") +
  ylab("mean WSS/TSS ratio, over 10 folds") +
  xlab("Number of clusters") +
  scale_x_continuous(breaks = 1:10)

下面是我正在处理的示例的reprex，我已经将CV折叠更改为3以加快计算时间：

if (!requireNamespace("pacman", quietly = TRUE)) {
  message("Installing pacman...")
  install.packages("pacman")
}

#INSTALL PACKAGES
pacman::p_load(tidyverse, tidymodels, tidyclust, janitor, ClusterR, knitr, moments, visdat, skimr, DescTools)

mtcars <- mtcars %>%
  mutate(
    `am` = factor(`am`, labels = c(`0` = "auto", `1` = "man")),
    `vs` = factor(`vs`, labels = c(`0` = "V-shaped", `1` = "straight")),
    `cyl` = factor(`cyl`),
    `gear` = factor(`gear`),
    `carb` = factor(`carb`)
  )

# SET UP 10 FOLD CROSS VALIDATION
mtcars_cv <- vfold_cv(mtcars, v = 3)

# SET SEED FOR REPRODUCABILITY
set.seed(123)

# EDA ---------------------------------------------------------------------

# skimr::skim(mtcars)

# DescTools::Desc(mtcars)

# MODEL SPEC --------------------------------------------------------------

kmeans_spec <- k_means(num_clusters = tune())

# PREPROCESSING RECIPES ---------------------------------------------------

rec1 <- recipe(~., data = mtcars) %>%
  step_dummy(all_nominal_predictors()) %>%
  step_zv(all_predictors()) %>%
  step_normalize(all_numeric_predictors())

rec2 <- recipe(~., data = mtcars) %>%
  step_novel(all_nominal()) %>%
  step_dummy(all_nominal()) %>%
  step_zv(all_predictors()) %>%
  step_normalize(all_predictors()) %>%
  step_pca(all_predictors(), num_comp = 2)

rec3 <- recipe(~ ., data = mtcars) %>%
  step_dummy(all_nominal_predictors()) %>%
  step_zv(all_predictors()) %>% 
  step_normalize(all_numeric_predictors()) %>% 
  step_center(all_numeric())

clust_num_grid <- grid_regular(num_clusters(),
  levels = 10
)

# WORKFLOW ----------------------------------------------------------------

wf_set <- workflow_set(
  preproc = list(rec1, rec2, rec3),
  models = list(kmeans_spec)
)

# TUNE HYPER-PARAMETERS ---------------------------------------------------

tune_cluster_wf <- function(id) {
  tune_cluster(
    extract_workflow(wf_set, id),
    resamples = mtcars_cv,
    grid = clust_num_grid,
    metrics = cluster_metric_set(sse_within_total, sse_total, sse_ratio),
    control = tune::control_grid(save_pred = TRUE, extract = identity)
  )
}

wf_set$result <- map(wf_set$wflow_id, tune_cluster_wf)

tune_results <- wf_set %>%
  collect_metrics() %>%
  filter(.metric == "sse_ratio")

tune_results %>%
  ggplot(aes(x = as.numeric(stringr::str_sub(.config, -2, -1)), y = mean, color = wflow_id)) +
  geom_point() +
  geom_line() +
  theme_minimal() +
  ggtitle("Plot of WSS/TSS ratio by Cluster Number") +
  ylab("mean WSS/TSS ratio, over 10 folds") +
  xlab("Number of clusters") +
  scale_x_continuous(breaks = 1:10)