我在学整洁模特。下面的代码运行良好：

library(tidyverse)
library(tidymodels)

# Draw a random sample of 2000 to try the models

set.seed(1234)

diamonds <- diamonds %>%    
  sample_n(2000)
  
diamonds_split <- initial_split(diamonds, prop = 0.80, strata="price")

diamonds_train <- training(diamonds_split)
diamonds_test <- testing(diamonds_split)

folds <- rsample::vfold_cv(diamonds_train, v = 10, strata="price")

metric <- metric_set(rmse,rsq,mae)

# Model KNN 

knn_spec <-
  nearest_neighbor(
    mode = "regression", 
    neighbors = tune("k"),
    engine = "kknn"
  ) 

knn_rec <-
  recipe(price ~ ., data = diamonds_train) %>%
  step_log(all_outcomes()) %>% 
  step_normalize(all_numeric_predictors()) %>% 
  step_dummy(all_nominal_predictors())

knn_wflow <- 
  workflow() %>% 
  add_model(knn_spec) %>%
  add_recipe(knn_rec)

knn_grid = expand.grid(k=c(1,5,10,30))

knn_res <- 
  tune_grid(
    knn_wflow,
    resamples = folds,
    metrics = metric,
    grid = knn_grid
  )

collect_metrics(knn_res)
autoplot(knn_res)

show_best(knn_res,metric="rmse")

# Best KNN 

best_knn_spec <-
  nearest_neighbor(
    mode = "regression", 
    neighbors = 10,
    engine = "kknn"
  ) 

best_knn_wflow <- 
  workflow() %>% 
  add_model(best_knn_spec) %>%
  add_recipe(knn_rec)

best_knn_fit <- last_fit(best_knn_wflow, diamonds_split)

collect_metrics(best_knn_fit)

但是，当我试图在训练集上拟合最佳模型并将其应用于测试集时，我遇到了问题。下面两行给予了错误：“step_log()中的错误：！步骤'log_mUSAb'中的new_data缺少以下必需列：运行rlang::last_trace()查看错误发生的位置。”

# Predict Manually

f1 = fit(best_knn_wflow,diamonds_train)
p1 = predict(f1,new_data=diamonds_test)