错误消息：tune_grid（）中的所有模型均失败。请参阅`.notes`列。调整随机森林模型的参数时

Question

bos <- read_csv("boston_train.csv") %>% clean_names()

bos %>%
  mutate_if(is.character, factor) -> bos

然后我分割数据并进行k折叠

# -- set a random seed for repeatablity 
set.seed(42)

# -- performs our train / test split 
split <- initial_split(bos, prop = 0.7)

# -- extract the training data form our bananna split 
train <- training(split)
# -- extract the test data 
test <- testing(split)

tree_fold <- vfold_cv(train, 10)

sprintf("Train PCT : %1.2f%%", nrow(train)/ nrow(bos) * 100)
sprintf("Test  PCT : %1.2f%%", nrow(test)/ nrow(bos) * 100)

我的目标变量是一个连续变量，我需要我的随机森林来做回归问题

# recipe 
rf_recipe <- recipe(av_total ~ ., data=train) %>%
  step_rm(pid, zipcode) %>%
  step_meanimpute(all_numeric(), -all_outcomes()) %>%
  step_log(all_numeric()) %>%
  step_modeimpute(all_nominal(),-all_outcomes()) %>%
  step_dummy(all_nominal(), -all_outcomes())

#tuning parameters
rf_model <- rand_forest(
  mtry = tune(),
  trees = 10,
  min_n= tune()
  ) %>%
  set_engine("ranger",
             importance = "permutation") %>%
  set_mode("regression")

rf_wf <- workflow() %>%
  add_recipe(rf_recipe) %>%
  add_model(rf_model)

rf_grid <- grid_random(mtry(c(5,7)),
                       min_n(c(15,20)),
                       size = 10)
# do parallel
all_cores <- detectCores(logical = TRUE)
sprintf("# of Logical Cores: %d", all_cores)
cl <- makeCluster(all_cores)
registerDoParallel(cl)

然后我遇到了错误，无论我如何更改食谱或调整过程，仍然存在

set.seed(52)
rf_tune_rs <- rf_wf %>%
  tune_grid(
  resamples = tree_fold,
  grid = rf_grid,
  control = control_resamples(save_pred = TRUE)
)

Answer 1

我通过在食谱中添加step_unknown项来解决此问题