tidymodels -使用step_ns()的fit_resamples中出现错误

Question

我正在尝试编写一个函数来拟合使用step_ns()的配方的重采样。由于某种原因，我收到错误消息：

Fold01: recipe: Error: Not all variables in the recipe are present in the supplied training set

对于所有的折叠，依此类推。然后

警告消息：All models failed in [fit_resamples()]. See the .notes column.

这是我的代码：

compare_basis_exp_to_base_mod <- function (data, outcome, metric, ...) {

  outcome <- rlang::enquo(outcome)
  metric <- rlang::enquo(metric)
  
  pred_list <- colnames(data)
  
  outcome_str <- substring(deparse(substitute(outcome)), 2)
  outcome_str_id <- which(colnames(data) %in% outcome_str)
  
  predictor <- pred_list[-outcome_str_id]
  
  data <- data %>% 
    rename(prediction = !!outcome)

  res <- tibble(splits = list(), id = character(), .metrics = list(), 
                .notes = list(), .predictions = list(), pred = character())
  
  rec_without_splines <- recipe(prediction ~ ., data = data) %>%
    prep()
  
  rec_with_splines <- recipe(prediction ~ ., data = data) %>%
    step_ns(all_predictors(), ...) %>% 
    prep()
  
  folds_without_splines <- vfold_cv(juice(rec_without_splines), strata = prediction)
  
  folds_with_splines <- vfold_cv(juice(rec_with_splines), strata = prediction)
  

  mod <- linear_reg() %>% 
    set_engine("lm")

  mod_without_splines <- fit_resamples(mod,
                                       rec_without_splines,
                                       folds_without_splines,
                                       metrics = metric_set(!!metric),
                                       control = control_resamples(save_pred = TRUE)) %>%
    mutate(pred = "no_splines")
  
  mod_with_splines <- fit_resamples(mod,
                                    rec_with_splines,
                                    folds_with_splines,
                                    metrics = metric_set(!!metric),
                                    control = control_resamples(save_pred = TRUE)) %>%
    mutate(pred = "with_splines")

  res <- mod_without_splines %>%
    bind_rows(mod_with_splines)
  
  return (res)
}

基本上，参数data接受一个包含两列的表，而outcome是结果列的名称。除了使用这个函数(我只是在这里使用tidymodel，因为我是新手)，我只想了解是什么导致了这个错误，以及如何修复它。在评估mod_with_splines时出现错误。

here也遇到了类似的问题。但我不知道这是否和我的问题有关。在传递给fit_resamples之前我不能不准备食谱。(或者我是这么认为的)

任何帮助都将不胜感激。谢谢。

Answer 1

您的问题来自于试图在已经通过相同配方运行的数据集上应用配方。

如果我们假设预测变量是X1和X2，那么rec_with_splines应该是这些变量。但由于folds_with_splines包含rec_with_splines的优化结果，因此folds_with_splines实际上包含X1_ns_1、X1_ns_2、X2_ns_1和X2_ns_2。不是X1和X2。

我建议使用workflows将预处理和建模步骤结合起来。并将原始数据传递给vfold_cv()。

library(tidymodels)
compare_basis_exp_to_base_mod <- function (data, outcome, metric, ...) {

  outcome <- rlang::enquo(outcome)
  metric <- rlang::enquo(metric)
  
  pred_list <- colnames(data)
  
  outcome_str <- substring(deparse(substitute(outcome)), 2)
  outcome_str_id <- which(colnames(data) %in% outcome_str)
  
  predictor <- pred_list[-outcome_str_id]
  
  data <- data %>% 
    rename(prediction = !!outcome)
  
  rec_without_splines <- recipe(prediction ~ ., data = data) %>%
    prep()
  
  rec_with_splines <- recipe(prediction ~ ., data = data) %>%
    step_ns(all_predictors(), ...)
  
  mod <- linear_reg() %>% 
    set_engine("lm")
 
  wf_without_splines <- workflow() %>%
    add_recipe(rec_without_splines) %>%
    add_model(mod)
  
  wf_with_splines <- workflow() %>%
    add_recipe(rec_with_splines) %>%
    add_model(mod)
  
  data_folds <- vfold_cv(data, strata = prediction)

  mod_without_splines <- fit_resamples(wf_without_splines,
                                       data_folds,
                                       metrics = metric_set(!!metric),
                                       control = control_resamples(save_pred = TRUE)) %>%
    mutate(pred = "no_splines")
  
  mod_with_splines <- fit_resamples(wf_with_splines,
                                    data_folds,
                                    metrics = metric_set(!!metric),
                                    control = control_resamples(save_pred = TRUE)) %>%
    mutate(pred = "with_splines")

  res <- mod_without_splines %>%
    bind_rows(mod_with_splines)
  
  return (res)
}

res <- compare_basis_exp_to_base_mod(mtcars, mpg, rmse)