1

我有一个漂亮的mlr3集成模型（组合glmnet和glm）用于二进制预测，请参阅此处的详细信息

library("mlr3verse")
library("dplyr")

# get example data
data(PimaIndiansDiabetes, package="mlbench")
data <- PimaIndiansDiabetes

# add an additional predictor "superdoc" which is not entered in the glmnet but in the final glm
set.seed(2323)
data %>% 
  rowwise() %>% 
  mutate(superdoc=case_when(diabetes=="pos" ~ as.numeric(sample(0:2,1)), TRUE~ 0)) %>% 
  ungroup -> data

# make a rather small train set
set.seed(23)
test.data <- sample_n(data,70,replace=FALSE)

# creat elastic net regression
glmnet_lrn = lrn("classif.cv_glmnet", predict_type = "prob")

# create the learner out-of-bag predictions
glmnet_cv1 = po("learner_cv", glmnet_lrn, id = "glmnet")

# PipeOp that drops 'superdoc', i.e. selects all except 'superdoc'
# (ID given to avoid ID clash with other selector)
drop_superdoc = po("select", id = "drop.superdoc",
                   selector = selector_invert(selector_name("superdoc")))

# PipeOp that selects 'superdoc' (and drops all other columns)
select_superdoc = po("select", id = "select.superdoc",
                     selector = selector_name("superdoc"))

# superdoc along one path, the fitted model along the other
stacking_layer = gunion(list(
  select_superdoc,
  drop_superdoc %>>% glmnet_cv1
)) %>>% po("featureunion", id = "union1")

# final logistic regression
log_reg_lrn = lrn("classif.log_reg", predict_type = "prob")

# combine ensemble model
ensemble = stacking_layer %>>% log_reg_lrn


#define tests
train.task <- TaskClassif$new("test.data", test.data, target = "diabetes")

# make ensemble learner
elearner = as_learner(ensemble)

   

ensemble$plot(html = FALSE)

如果我用不同的 set.seed 训练它，我会得到不同的系数。我认为这主要是由于在 glmnet 模型中输入的训练数据数量相当少，并且可以通过重复交叉验证来缓解。

# Train the Learner:
# seed 1
elearner = as_learner(ensemble)
set.seed(22521136)
elearner$train(train.task) -> seed1

# seed 2
elearner = as_learner(ensemble)
set.seed(12354)
elearner$train(train.task) -> seed2

# different coefficients of the glment  model
coef(seed1$model$glmnet$model, s ="lambda.min")
#> 9 x 1 sparse Matrix of class "dgCMatrix"
#>                        1
#> (Intercept) -6.238598277
#> age          .          
#> glucose      0.023462376
#> insulin     -0.001007037
#> mass         0.055587740
#> pedigree     0.322911217
#> pregnant     0.137419564
#> pressure     .          
#> triceps      .
coef(seed2$model$glmnet$model, s ="lambda.min")
#> 9 x 1 sparse Matrix of class "dgCMatrix"
#>                        1
#> (Intercept) -6.876802620
#> age          .          
#> glucose      0.025601712
#> insulin     -0.001500856
#> mass         0.063029550
#> pedigree     0.464369417
#> pregnant     0.155971123
#> pressure     .          
#> triceps      .

# different coefficients of the final regression model
seed1$model$classif.log_reg$model$coefficients
#>     (Intercept)        superdoc glmnet.prob.neg glmnet.prob.pos 
#>       -9.438452       23.710923        8.726956              NA
seed2$model$classif.log_reg$model$coefficients
#>     (Intercept)        superdoc glmnet.prob.neg glmnet.prob.pos 
#>       0.3698143      23.5362542      -5.5514365              NA

问题：

mlr3在我的集成模型中在哪里以及如何输入重复的交叉验证来缓解这些不同的结果？非常感谢任何帮助。

4

1 回答 1

3

感谢missuse 的评论、他的精彩教程（调整堆叠学习器）和mb706 的评论，我想我可以解决我的问题。

替换"classif.cv_glmnet"为"classif.glmnet"

# Add tuning

resampling = rsmp("repeated_cv")
resampling$param_set$values = list(repeats = 10, folds=5)


ps_ens = ParamSet$new(
  list(
    ParamDbl$new("glmnet.alpha", 0, 1),
    ParamDbl$new("glmnet.s", 0, 1)))

auto1 = AutoTuner$new(
  learner = elearner,
  resampling = resampling,
  measure = msr("classif.auc"),
  search_space = ps_ens,
  terminator = trm("evals", n_evals = 5), # to limit running time
  tuner = tnr("random_search")
)

用不同的训练set.seed得到相同的系数

# Train with different set.seed

#first
set.seed(22521136)
at1= auto1
at1$train(train.task) -> seed1

# second
set.seed(12354)
at2= auto1
at2$train(train.task) -> seed2


# Compare coefficients of the learners

# classif.log_reg
seed1$model$learner$model$classif.log_reg$model$coefficients
# (Intercept)        superdoc glmnet.prob.neg glmnet.prob.pos 
# 2.467855       21.570766       -6.966693              NA


seed2$model$learner$model$classif.log_reg$model$coefficients
# (Intercept)        superdoc glmnet.prob.neg glmnet.prob.pos 
# 2.467855       21.570766       -6.966693              NA


#classif.glmnet
coef(at1$learner$model$glmnet$model, alpha=at1$tuning_result$glmnet.alpha,s=at1$tuning_result$glmnet.s)
# 9 x 1 sparse Matrix of class "dgCMatrix"
# 1
# (Intercept) -3.3066981659
# age          0.0076392198
# glucose      0.0077516975
# insulin      0.0003389759
# mass         0.0133955320
# pedigree     0.3256754612
# pregnant     0.0686746156
# pressure     0.0081338885
# triceps     -0.0054976030

coef(at2$learner$model$glmnet$model, alpha=at2$tuning_result$glmnet.alpha,s=at2$tuning_result$glmnet.s)
# 9 x 1 sparse Matrix of class "dgCMatrix"
# 1
# (Intercept) -3.3066981659
# age          0.0076392198
# glucose      0.0077516975
# insulin      0.0003389759
# mass         0.0133955320
# pedigree     0.3256754612
# pregnant     0.0686746156
# pressure     0.0081338885
# triceps     -0.0054976030
于 2021-03-21T21:15:37.237 回答