ValueError：求解器 lbfgs 仅支持“l2”或“无”惩罚，得到 l1 惩罚

Question

我正在使用带有 LogisticRegression 的嵌入式方法（L1 - Lasso）运行分类问题的特征选择过程。

我正在运行以下代码：

from sklearn.linear_model import Lasso, LogisticRegression
from sklearn.feature_selection import SelectFromModel

# using logistic regression with penalty l1.
selection = SelectFromModel(LogisticRegression(C=1, penalty='l1'))
selection.fit(x_train, y_train)

但我得到了异常（在fit命令上）：

   selection.fit(x_train, y_train)
   File "C:\Python37\lib\site-packages\sklearn\feature_selection\_from_model.py", line 222, in fit
   self.estimator_.fit(X, y, **fit_params)
   File "C:\Python37\lib\site-packages\sklearn\linear_model\_logistic.py", line 1488, in fit
   solver = _check_solver(self.solver, self.penalty, self.dual)
   File "C:\Python37\lib\site-packages\sklearn\linear_model\_logistic.py", line 445, in _check_solver
   "got %s penalty." % (solver, penalty))
   ValueError: Solver lbfgs supports only 'l2' or 'none' penalties, got l1 penalty.

我跑下python 3.7.6和sscikit-learn version is 0.22.2.post1

出了什么问题，我该如何解决？

Answer 1

这在文档中得到了澄清。

求解器：{'newton-cg', 'lbfgs', 'liblinear', 'sag', 'saga'}, default='lbfgs'

...

• 'newton-cg'、'lbfgs'、'sag' 和 'saga' 处理 L2 或无惩罚

• 'liblinear' 和 'saga' 也处理 L1 惩罚

像这样调用它：

LogisticRegression(C=1, penalty='l1', solver='liblinear')