Xgboost for survival 在 R 中使用 mlr

Question

我想在 R 中的右截尾生存数据上使用 mlr 运行 xgboost。xgboost 代码列出了一个 objective 函数 survival:cox，它说：

survival:cox: Cox regression for right censored survival time data (negative values are considered right censored).

我正在使用的 Mlr 2 仅支持回归和分类学习器的 xgboost。如果我尝试使用 xgboost 的内置回归学习器，它会使用 mse 作为评估指标。所以我尝试将指标更改为 cindex 并得到错误

Measures: cindex cindex
Error in FUN(X[[i]], ...) : Measure cindex does not support task type regr!

然后我尝试为 xgboost 编写一个新的生存学习器，它只是回归学习器的一个副本，但是 "Regr" 更改为 "Surv"，当然它期望目标为有 2 列 - 时间和状态 - 并且不接受负时间，而 xgboost 只需要一列 - 时间 - 并假设任何具有负时间值的行都被审查。

下面是我试过的。有什么方法可以在 mlr2 或 mlr3 中实现这一点？

为 xgboost 使用内置回归学习器：

    data(veteran)
    veteran_xgb <- veteran
    veteran_xgb <- veteran_xgb[c("trt", "karno", "diagtime", "age", "prior", "time")]
    veteran_xgb$time <- ifelse(veteran$status==1, veteran$time, -veteran$time)

    xgb.task <- makeRegrTask(id="XGBOOST_VET", data = veteran_xgb, target="time")
    xgb_learner <- makeLearner(id="xgboost",
                              cl="regr.xgboost",
                              predict.type = "response",
                              par.vals = list(
                                  objective = "survival:cox",
                                  eval_metric = "cox-nloglik",
                                  nrounds = 200
                                )
                              )

    learners = list(xgb_learner)
    outer = makeResampleDesc("CV", iters=5) # Benchmarking
    bmr = benchmark(learners, xgb.task, outer, show.info = TRUE)

为 xgboost 使用自定义 surv 学习器：

    data(veteran)
    veteran_xgb <- veteran
    veteran_xgb <- veteran_xgb[c("trt", "karno", "diagtime", "age", "prior", "time", "status")]
    veteran_xgb$time <- ifelse(veteran$status==1, veteran$time, -veteran$time)

    xgb.task <- makeSurvTask(id="XGBOOST_VET", data = veteran_xgb, target = c("time", "status"))
    xgb_learner <- makeLearner(id="xgboost",
                              cl="surv.xgboost",
                              predict.type = "response",
                              par.vals = list(
                                  objective = "survival:cox",
                                  eval_metric = "cox-nloglik",
                                  nrounds = 200
                                )
                              )

    learners = list(xgb_learner)
    outer = makeResampleDesc("CV", iters=5) # Benchmarking
    surv.measures = list(cindex)
    bmr = benchmark(learners, xgb.task, outer, surv.measures, show.info = TRUE)

文件 RLearner_surv_xgboost.R 可以从此处的 OneDrive 下载 https://1drv.ms/u/s!AjTjdzp0sDJRrhZtZF5-HZF2BrBB?e=FNLS94

Answer 1

我找到了解决方案并在此处更新了我的自定义学习器：https://1drv.ms/u/s!AjTjdzp0sDJRrhewy0yx3Wot3FiI?e=sxRrTN

诀窍是修改 trainlearner.surv.xgboost 函数。作为生存学习者，它期望传递的数据具有包含 2 列时间和状态的目标。但是在那个学习器中，我们可以计算 xgboost 期望的目标，对删失数据使用负时间，然后将这个新的 single-column 目标传递给 xgboost:

 trainLearner.surv.xgboost = function(.learner, .task, .subset, .weights = NULL,  ...) {
  parlist = list(...)

  if (is.null(parlist$objective))
  {
    parlist$objective = "survival:cox"
    parlist$eval_metric = "cox-nloglik"
  }

  task.data = getTaskData(.task, .subset, target.extra = TRUE)
  survtime <- ifelse(task.data$target$status==1, task.data$target$time, -task.data$target$time)

  parlist$data = xgboost::xgb.DMatrix(data = data.matrix(task.data$data), label = survtime)

  if (!is.null(.weights))
    xgboost::setinfo(parlist$data, "weight", .weights)

  if (is.null(parlist$watchlist))
    parlist$watchlist = list(train = parlist$data)

  do.call(xgboost::xgb.train, parlist)
}

然后使用这个新学习器：

library(xgboost)
library(survival)
library(mlr)
source("RLearner_surv_xgboost.R")

data(veteran)
veteran.xgb <- veteran[, !(names(veteran) %in% c("celltype"))]

xgb.task <- makeSurvTask(id="XGBOOST_VET", data = veteran.xgb, target = c("time", "status"))
surv.measures = list(cindex)
outer= makeResampleDesc("CV", iters=5)

xgb.learner <- makeLearner(id="xgboost",
                          cl="surv.xgboost",
                          predict.type = "response")
learners = list(xgb.learner)
bmr = benchmark(learners, xgb.task, outer, surv.measures, show.info = TRUE)

Xgboost for survival 在 R 中使用 mlr

Xgboost for survival using mlr in R

r

mlr

xgboost

survival