在 R 的 stabsel 中使用 penalty.factor

Question

我想在 glmnet 套索上使用 stabsel 来进行变量选择。我正在按照 https://github.com/hofnerb/stabs 上的示例进行操作，并且效果很好。

不过，我还想强制包含几个变量。这可以在 glmnet 中使用参数 'penalty.factor' 实现，但是将 args.fitfun 中的此参数传递给 stabsel 结果错误（见下文）。

data("bodyfat", package = "TH.data")
pfac=c(0,0,0,1,0,1,1,1,1)
stab.glmnet <- stabsel(x = bodyfat[, -2], y = bodyfat[,2],
                           fitfun = glmnet.lasso, cutoff = 0.75,
                           PFER = 1, args.fitfun=list(penalty.factor = pfac))
Error in res[[1]] : subscript out of bounds
In addition: Warning message:
In run_stabsel(fitter = fit_model, args.fitter = args.fitfun, n = n,      :
100 fold(s) encountered an error. Results are based on 0 folds only.
Original error message(s):
Error : Matrices must have same number of columns in rbind2(.Call(dense_to_Csparse, x), y)
Error : Matrices must have same number of columns in rbind2(.Call(dense_to_Csparse, x), y)
Error : Matrices must have same number of columns in rbind2(.Call(dense_to_Csparse, x), y)
Error : Matrices must have same number of columns in rbind2(.Call(dense_to_Csparse, x), y)
Error : Matrices must have same number of columns in rbind2(.Call(dense_to_Csparse, x), y)
Error : Matrices must have same number of columns in rbind2(.Call(dense_to_Csparse, x), y)
Error : Matrices must have same number of columns in rbind2(.Call(dense_to_Csparse, x), y)
Error : Matrices must have same number of columns in rbind2(.Call(dense_to_Csparse, x), y)
Error : Matrices must have same number of columns in rbind2(.Call(dense_to_Csparse, x), y)
Error : Matrices must have same number of columns in rbind2(.Call(dense_to_Csparse, x [... truncated]

如有任何帮助，我们将不胜感激！

Answer 1

我明白了。由于我们通过设置 penalty.factor 强制包括 n 个变量，我们需要调整三个 stabsel 变量（截止、PFER、q）以确保我们允许在每次重采样中至少选择 n 个变量。

见https://github.com/hofnerb/stabs/blob/master/README.md 和 http://onlinelibrary.wiley.com/doi/10.1111/j.1467-9868.2010.00740.x/full 更多细节。

在 R 的 stabsel 中使用 penalty.factor

Use penalty.factor in stabsel in R

r

stability

feature-selection

glmnet