[英]Error with H2O: "no slot of name "leader"
I am getting the following error, after trying to get most important variables with H2o Package in a classification binary problem with Rstudio.在 Rstudio 的分类二进制问题中尝试使用 H2o Package 获取最重要的变量后,出现以下错误。
Error in h(simpleError(msg, call)): error in evaluating the argument 'object' in selecting a method for function 'h2o.varimp': no slot of name "leader" for this object of class "H2OBinomialModel"
h(simpleError(msg,call))中的错误:在为 function 'h2o.varimp' 选择方法时评估参数 'object' 时出错:class“H2OBinomialModel”的这个 object 没有名称“leader”的插槽
Previous Error comes after applying the following steps.应用以下步骤后出现上一个错误。
# Lookup best Algorithm for this classification challenge (binary).
rautoml<- h2o.automl(y = target,x = independientes,
training_frame = train_h2o,
validation_frame = test_h2o, # Podría probar hacer el test contra el futuro.
nfolds = 3,
max_runtime_secs = 300,
sort_metric = 'AUC'
)
#Get the best model from previous step
rautoml_winner <- rautoml@leader
###### Winner model is a StackedEnsemble_AllModels####
#Get the most important variables.
h2o.varimp(rautoml_winner@leader)
And then last code produces this error.然后最后一个代码产生这个错误。
Error in h(simpleError(msg, call)): error in evaluating the argument 'object' in selecting a method for function 'h2o.varimp': no slot of name "leader" for this object of class "H2OBinomialModel"
h(simpleError(msg,call))中的错误:在为 function 'h2o.varimp' 选择方法时评估参数 'object' 时出错:class“H2OBinomialModel”的这个 object 没有名称“leader”的插槽
The h2o.varimp(rautoml_winner@leader)
makes no sense since the rautoml_winner
is already the leader model (= the best model according to the sort metric from the automl). h2o.varimp(rautoml_winner@leader)
没有意义,因为rautoml_winner
已经是领导者 model(= 根据 automl 的排序指标的最佳 model)。 Removing the @leader
would fix it for all models except for the Stacked Ensembles which do not have variable importance calculated during training.删除
@leader
将为所有模型修复它,但 Stacked Ensembles 除外,它在训练期间没有计算变量重要性。
You can still get variable importance for Stacked Ensembles using the permutation variable importance, eg, h2o.permutation_importance(rautoml_winner, test_h2o)
.您仍然可以使用排列变量重要性(例如
h2o.permutation_importance(rautoml_winner, test_h2o)
获得堆叠集成的可变重要性。 See the documentation for more information.有关详细信息,请参阅文档。
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.