2

在多个算法上运行基准实验时，使用调整包装器等，每个算法都会返回多个模型。

提取每个单独的调整模型（具有各种超参数）以便可以单独访问它们并单独用于预测而没有其他模型的所有包袱等的规范方式或有效方式是什么？

可重现的例子

# Required Packages
# Load required packages
library(mlr)
#library(dplyr)
library(parallelMap)
library(parallel)

# Algorithms
iterations = 10L
cv_iters = 2
### classif.gamboost ############################################################################################################################
classif_gamboost = makeLearner("classif.gamboost", predict.type="prob")

##The wrappers are presented in reverse order of application
###One-Hot Encoding
classif_gamboost = makeDummyFeaturesWrapper(classif_gamboost, method = "1-of-n")
###Missing Data Imputation
classif_gamboost = makeImputeWrapper(classif_gamboost, classes = list(numeric = imputeConstant(-99999), integer = imputeConstant(-99999), factor = imputeConstant("==Missing==")), dummy.type = "numeric", dummy.classes = c("numeric","integer"))

##### Tuning #####
inner_resamp = makeResampleDesc("CV", iters=cv_iters)
ctrl = makeTuneControlRandom(maxit=iterations)
hypss = makeParamSet(
  makeDiscreteParam("baselearner", values=c("btree")), #,"bols","btree","bbs"
  makeIntegerParam("dfbase", lower = 1, upper = 5),
  makeDiscreteParam("family", values=c("Binomial")),
  makeDiscreteParam("mstop", values=c(10,50,100,250,500,1000))
)
classif_gamboost = makeTuneWrapper(classif_gamboost, resampling = inner_resamp, par.set = hypss, control = ctrl, measures = list(auc, logloss, f1, ber, acc, bac, mmce, timetrain), show.info=TRUE)
### classif.gamboost ############################################################################################################################

### Random Forest ############################################################################################################################
classif_rforest = makeLearner("classif.randomForestSRC", predict.type="prob")

##The wrappers are presented in reverse order of application
###One-Hot Encoding
classif_rforest = makeDummyFeaturesWrapper(classif_rforest, method = "1-of-n")
###Missing Data Imputation
classif_rforest = makeImputeWrapper(classif_rforest, classes = list(numeric = imputeConstant(-99999), integer = imputeConstant(-99999), factor = imputeConstant("==Missing==")), dummy.type = "numeric", dummy.classes = c("numeric","integer"))

##### Tuning #####
inner_resamp = makeResampleDesc("CV", iters=cv_iters)
ctrl = makeTuneControlRandom(maxit=iterations)
hypss = makeParamSet(
  makeIntegerParam("mtry", lower = 1, upper = 30)
  ,makeIntegerParam("ntree", lower = 100, upper = 500)
  ,makeIntegerParam("nodesize", lower = 1, upper = 100)
)
classif_rforest = makeTuneWrapper(classif_rforest, resampling = inner_resamp, par.set = hypss, control = ctrl, measures = list(auc, logloss, f1, ber, acc, bac, mmce, timetrain), show.info=TRUE)
### Random Forest ############################################################################################################################

trainData = mtcars
target_feature = "am"
training_task_name = "trainingTask"
trainData[[target_feature]] = as.factor(trainData[[target_feature]])
trainTask = makeClassifTask(id=training_task_name, data=trainData, target=target_feature, positive=1, fixup.data="warn", check.data=TRUE)

train_indices = 1:25
valid_indices = 26:32
outer_resampling = makeFixedHoldoutInstance(train_indices, valid_indices, nrow(trainData))

no_of_cores = detectCores()
parallelStartSocket(no_of_cores, level=c("mlr.tuneParams"), logging = TRUE)
lrns = list(classif_gamboost, classif_rforest)
res = benchmark(tasks = trainTask, learners = lrns, resampling = outer_resampling, measures = list(logloss, auc, f1, ber, acc, bac, mmce, timetrain), show.info = TRUE, models = TRUE, keep.pred = FALSE)
parallelStop()

models = getBMRModels(res)
models
4

1 回答 1

1

我建议训练一个具有train进一步处理功能的新模型，例如预测新数据点。您将使用完整的数据集进行训练，而不仅仅是一部分。

如果您想使用基准测试中的模型，您可以getBMRModels按照您已经发布的方式获取它们，然后获取您想要的特定模型。（使用模型获取特定的列表元素$ ...）

于 2018-04-09T13:52:11.573 回答