使sklearn中的网格搜索功能忽略空模型 [英] Make grid search functions in sklearn to ignore empty models

问题描述

使用 python 和 scikit-learn，我想做一个网格搜索.但是我的一些模型最终是空的.如何让网格搜索功能忽略这些模型?

Using python and scikit-learn, I'd like to do a grid search. But some of my models end up being empty. How can I make the grid search function to ignore those models?

我想我可以有一个评分函数，如果模型为空则返回 0，但我不确定如何.

I guess I can have a scoring function which returns 0 if the models is empty, but I'm not sure how.

predictor = sklearn.svm.LinearSVC(penalty='l1', dual=False, class_weight='auto')
param_dist = {'C': pow(2.0, np.arange(-10, 11))}
learner = sklearn.grid_search.GridSearchCV(estimator=predictor,
                                           param_grid=param_dist,
                                           n_jobs=self.n_jobs, cv=5,
                                           verbose=0)
learner.fit(X, y)

我的数据的方式是这个 learner 对象将选择一个 C 对应于一个空模型.知道如何确保模型不为空吗?

My data's in a way that this learner object will choose a C corresponding to an empty model. Any idea how I can make sure the model's not empty?

编辑:空模型"是指选择了 0 个要使用的功能的模型.特别是对于 l1 正则化模型，这很容易发生.所以在这种情况下，如果SVM中的C足够小，优化问题就会找到0向量作为系数的最优解.因此 predictor.coef_ 将是 0s 的向量.

EDIT: by an "empty model" I mean a model that has selected 0 features to use. Specially with an l1 regularized model, this can easily happen. So in this case, if the C in the SVM is small enough, the optimization problem will find the 0 vector as the optimal solution for the coefficients. Therefore predictor.coef_ will be a vector of 0s.

推荐答案

尝试实现自定义评分器，类似于:

Try to implement custom scorer, something similar to:

import numpy as np

def scorer_(estimator, X, y):
    # Your criterion here
    if np.allclose(estimator.coef_, np.zeros_like(estimator.coef_)):
        return 0
    else:
        return estimator.score(X, y)

learner = sklearn.grid_search.GridSearchCV(...
                                           scoring=scorer_)

这篇关于使sklearn中的网格搜索功能忽略空模型的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！