“结果中的一个或多个因素水平没有数据”或“停止失败”答案

【问题标题】："One or more factor levels in the outcome has no data" or "Failed Stopping"“结果中的一个或多个因素水平没有数据”或“停止失败”
【发布时间】：2021-10-31 20:47:31
【问题描述】：

在 R 中，我正在尝试打包如下数据框：

library(datasets)
require(e1071)

fit <- function(x,y,method="rpart", control = rpart.control(maxdepth=1,maxsurrogate = 0)){
  train(x,y,method,control=control)
}

getmode <- function(v) {
  uniqv <- unique(v)
  uniqv[which.max(tabulate(match(v, uniqv)))]
}

bagged <- bag(x = iris[, names(iris) != "Species"],
              y = iris$Species,
              B=4,
              bagControl = bagControl(
                fit = fit,
                predict = predict,
                aggregate = getmode)
              )

我收到错误消息：

Something is wrong; all the Accuracy metric values are missing:
    Accuracy       Kappa    
 Min.   : NA   Min.   : NA  
 1st Qu.: NA   1st Qu.: NA  
 Median : NA   Median : NA  
 Mean   :NaN   Mean   :NaN  
 3rd Qu.: NA   3rd Qu.: NA  
 Max.   : NA   Max.   : NA  
 NA's   :3     NA's   :3    
Error in fitter(btSamples[[iter]], x = x, y = y, ctrl = bagControl, v = vars,  : 
  task 1 failed - "Stopping"

改用 ldaBag 中的函数，有效

library(datasets)
require(e1071)

bagged <- bag(x = iris[, names(iris) != "Species"],
              y = iris$Species,
              B=4,
              bagControl = bagControl(
                fit = ldaBag$fit,
                predict = ldaBag$pred,
                aggregate = ldaBag$aggregate)
)

那么我的自定义拟合和聚合函数有什么问题？

【问题讨论】：

请修剪您的代码，以便更容易找到您的问题。请按照以下指南创建minimal reproducible example。

标签： r dataframe classification

【解决方案1】：

原来我需要包 rpart

require(rpart)

我通过在不同环境中测试代码发现了这一点，该环境启用了警告 - 尽管我从未有意识地禁用它们，但它们在以前的环境中被禁用。

因此，我看不到完整的消息：

Error in fitter(btSamples[[iter]], x = x, y = y, ctrl = bagControl, v = vars,  : 
  task 1 failed - "Stopping"
In addition: There were 50 or more warnings (use warnings() to see the first 50)
> warnings()
Warning messages:
1: In (function (kind = NULL, normal.kind = NULL, sample.kind = NULL)  ... :
  non-uniform 'Rounding' sampler used
2: model fit failed for Resample01: cp=0 Error in rpart.control(maxdepth = 1, maxsurrogate = 0) : 
  could not find function "rpart.control"

我使用 options(warn=0) 回应了警告

【讨论】：