mlr3嵌套重采样中extract_inner_fselect_results返回NULL的解决建议

在mlr3的嵌套重采样流程中：

• 若不指定store_models=TRUE，运行后报错Error: No model stored
• 若同时在AutoFSelector和外层resample中设置store_models=TRUE，会因内存占用过高导致RStudio崩溃
• 仅在AutoFSelector中设置store_models=TRUE时，能正常提取性能指标，但调用extract_inner_fselect_results()和extract_inner_fselect_archives()返回NULL，无法获取特征选择的相关结果

用户的原始代码如下：

MSvCon<-read.csv("MS v Control Proteomics Final.csv", row.names=1)

MSvCon$Status<-as.factor(MSvCon$Status)

MSvCon[,2:4399]<-scale(MSvCon[,2:4399], center=TRUE, scale=TRUE)

set.seed(123, "L'Ecuyer")

task = as_task_classif(MSvCon, target = "Status")

learner = lrn("classif.ranger", importance = "impurity", num.trees=10000)

set_threads(learner, n = 8)

measure = msr("classif.fbeta", beta=1, average="micro")

terminator = trm("none")

resampling_inner = rsmp("repeated_cv", folds = 10, repeats = 10)

at = AutoFSelector$new(
  learner = learner,
  resampling = resampling_inner,
  measure = measure,
  terminator = terminator,
  fselect = fs("rfe", n_features = 1, feature_fraction = 0.5, recursive = FALSE),
  store_models=TRUE)

resampling_outer = rsmp("repeated_cv", folds = 10, repeats = 10)

rr = resample(task, at, resampling_outer)

核心问题是：外层resample未保存AutoFSelector的特征选择结果，同时全量保存模型会导致内存溢出。可通过以下方式平衡需求与内存占用：

• 精准控制AutoFSelector的保存内容：关闭完整模型保存（store_models = FALSE）避免内存占用过高，同时开启特征选择结果和存档的保存（store_fselect_results = TRUE、store_fselect_archive = TRUE），确保能提取所需的特征信息。
• 外层resample需保存AutoFSelector实例：设置store_models = TRUE，但由于AutoFSelector已关闭模型保存，此时仅会保存特征选择相关的轻量数据，不会导致内存崩溃。
• 额外内存优化：适当降低classif.ranger的num.trees参数（比如从10000调整为1000），在性能可接受的前提下进一步减少内存占用；提取完特征选择结果后，立即删除重采样结果对象rr手动释放内存。

修改后的关键代码部分：

# 初始化AutoFSelector，精准控制保存内容
at = AutoFSelector$new(
  learner = learner,
  resampling = resampling_inner,
  measure = measure,
  terminator = terminator,
  fselect = fs("rfe", n_features = 1, feature_fraction = 0.5, recursive = FALSE),
  store_models = FALSE,          # 不保存完整模型，降低内存
  store_fselect_results = TRUE,  # 保存特征选择结果
  store_fselect_archive = TRUE   # 保存特征选择存档
)

# 外层resample开启保存，但仅保存轻量的特征选择结果
rr = resample(task, at, resampling_outer, store_models = TRUE)

# 现在可以正常提取特征选择结果
inner_results = extract_inner_fselect_results(rr)
inner_archives = extract_inner_fselect_archives(rr)

内容的提问来源于stack exchange，提问作者awaldman