Question

我最近发现了folds中的xgb.cv参数，它允许指定验证集的索引。然后在xgb.cv.mknfold内调用辅助函数xgb.cv，然后将每个折叠的剩余索引作为相应折叠的训练集的索引。

问题：我可以通过xgboost界面中的任何接口指定训练和验证索引吗？

我的主要动机是执行时间序列交叉验证，我不希望将“非验证”索引自动指定为训练数据。举例说明我想做的事情：

# assume i have 100 strips of time-series data, where each strip is X_i
# validate only on 10 points after training
fold1:  train on X_1-X_10, validate on X_11-X_20
fold2:  train on X_1-X_20, validate on X_21-X_30
fold3:  train on X_1-X_30, validate on X_31-X_40
...

目前，使用folds参数将迫使我使用剩余的示例作为验证集，这极大地增加了误差估计的方差，因为剩余数据远远超过训练数据并且可能有很大差异从训练数据中分配，尤其是早期折叠。这就是我的意思：

fold1:  train on X_1-X_10, validate on X_11-X100 # huge error
...

如果方便（即不要求我撬开源代码），我会接受其他软件包的解决方案，并且不会使原来的xgboost实现中的效率无效。

Answer 1

我认为问题的底部是错误的方法，应该说：

请我将其余示例用作培训集

似乎还没有提到提到的辅助函数xgb.cv.mknfold。请注意，我的 xgboost 版本是0.71.2。

但是，似乎确实可以通过对xgb.cv进行小的修改（例如，像这样：

xgb.cv_new <- function(params = list(), data, nrounds, nfold, label = NULL, 
          missing = NA, prediction = FALSE, showsd = TRUE, metrics = list(), 
          obj = NULL, feval = NULL, stratified = TRUE, folds = NULL, folds_train = NULL, 
          verbose = TRUE, print_every_n = 1L, early_stopping_rounds = NULL, 
          maximize = NULL, callbacks = list(), ...) {
  check.deprecation(...)
  params <- check.booster.params(params, ...)
  for (m in metrics) params <- c(params, list(eval_metric = m))
  check.custom.obj()
  check.custom.eval()
  if ((inherits(data, "xgb.DMatrix") && is.null(getinfo(data, 
                                                        "label"))) || (!inherits(data, "xgb.DMatrix") && is.null(label))) 
    stop("Labels must be provided for CV either through xgb.DMatrix, or through 'label=' when 'data' is matrix")
  if (!is.null(folds)) {
    if (!is.list(folds) || length(folds) < 2) 
      stop("'folds' must be a list with 2 or more elements that are vectors of indices for each CV-fold")
    nfold <- length(folds)
  }
  else {
    if (nfold <= 1) 
      stop("'nfold' must be > 1")
    folds <- generate.cv.folds(nfold, nrow(data), stratified, 
                               label, params)
  }
  params <- c(params, list(silent = 1))
  print_every_n <- max(as.integer(print_every_n), 1L)
  if (!has.callbacks(callbacks, "cb.print.evaluation") && verbose) {
    callbacks <- add.cb(callbacks, cb.print.evaluation(print_every_n, 
                                                       showsd = showsd))
  }
  evaluation_log <- list()
  if (!has.callbacks(callbacks, "cb.evaluation.log")) {
    callbacks <- add.cb(callbacks, cb.evaluation.log())
  }
  stop_condition <- FALSE
  if (!is.null(early_stopping_rounds) && !has.callbacks(callbacks, 
                                                        "cb.early.stop")) {
    callbacks <- add.cb(callbacks, cb.early.stop(early_stopping_rounds, 
                                                 maximize = maximize, verbose = verbose))
  }
  if (prediction && !has.callbacks(callbacks, "cb.cv.predict")) {
    callbacks <- add.cb(callbacks, cb.cv.predict(save_models = FALSE))
  }
  cb <- categorize.callbacks(callbacks)
  dall <- xgb.get.DMatrix(data, label, missing)
  bst_folds <- lapply(seq_along(folds), function(k) {
    dtest <- slice(dall, folds[[k]])
    if (is.null(folds_train))
      dtrain <- slice(dall, unlist(folds[-k]))
    else
      dtrain <- slice(dall, folds_train[[k]])
    handle <- xgb.Booster.handle(params, list(dtrain, dtest))
    list(dtrain = dtrain, bst = handle, watchlist = list(train = dtrain, 
                                                         test = dtest), index = folds[[k]])
  })
  rm(dall)
  basket <- list()
  num_class <- max(as.numeric(NVL(params[["num_class"]], 1)), 
                   1)
  num_parallel_tree <- max(as.numeric(NVL(params[["num_parallel_tree"]], 
                                          1)), 1)
  begin_iteration <- 1
  end_iteration <- nrounds
  for (iteration in begin_iteration:end_iteration) {
    for (f in cb$pre_iter) f()
    msg <- lapply(bst_folds, function(fd) {
      xgb.iter.update(fd$bst, fd$dtrain, iteration - 1, 
                      obj)
      xgb.iter.eval(fd$bst, fd$watchlist, iteration - 1, 
                    feval)
    })
    msg <- simplify2array(msg)
    bst_evaluation <- rowMeans(msg)
    bst_evaluation_err <- sqrt(rowMeans(msg^2) - bst_evaluation^2)
    for (f in cb$post_iter) f()
    if (stop_condition) 
      break
  }
  for (f in cb$finalize) f(finalize = TRUE)
  ret <- list(call = match.call(), params = params, callbacks = callbacks, 
              evaluation_log = evaluation_log, niter = end_iteration, 
              nfeatures = ncol(data), folds = folds)
  ret <- c(ret, basket)
  class(ret) <- "xgb.cv.synchronous"
  invisible(ret)
}

我刚刚添加了一个可选参数folds_train = NULL，并以这种方式稍后在函数内部使用了它（见上文）：

if (is.null(folds_train))
  dtrain <- slice(dall, unlist(folds[-k]))
else
  dtrain <- slice(dall, folds_train[[k]])

然后您可以使用该功能的新版本，例如如下所示：

# save original version
orig <- xgboost::xgb.cv

# devtools::install_github("miraisolutions/godmode")
godmode:::assignAnywhere("xgb.cv", xgb.cv_new)

# now you can use (call) xgb.cv with the additional argument

# once you are done, or may want to switch back to the original version
# (if you restart R you will also be back to the original version):
godmode:::assignAnywhere("xgb.cv", orig)

因此，现在您应该可以使用额外的参数调用函数，为训练数据提供额外的索引。

请注意，我还没有时间进行测试。

Answer 2

根据 xgboost::xgb.cv 文档，您可以通过 folds 参数（默认为 NULL！）传递自定义测试索引。它需要作为一个列表传递，其中每个元素都是一个索引向量。

例如，如果你想做一个时间序列的分裂，你可以这样做：

create_test_idx <- function(size) {
  half_size <- round(size / 2)
  step <- round(0.1 * half_size)
  starts <- seq(from = half_size, to = size - step, by = step)
  return(lapply(starts, function(x) return(c(as.integer(x), as.integer(size)))))
}

my_custom_idx <- create_test_idx(nrow(my_train_data))

然后（例如），

xgbcv <- xgboost::xgb.cv(
    params = params,
    data = mydata,
    nrounds = 10000,
    folds = my_custom_idx,
    showsd = T,
    verbose = 0,
    early_stopping_rounds = 200,
    maximize = F
  )

如何在R包XGBoost中为xgb.cv指定训练和测试索引

2 个答案: