Feature selection with NaN

Question

Azura Hashim 2018-3-14

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/388267-feature-selection-with-nan

回答： Prajit T R 2018-3-22

Hi,

I have a high dimensional data where I've managed to build a classification model using fitctree that is returning satisfactory accuracy. The predictors contain a decent proportion of unknown values represented as NaN.

I chose fitctree because it can handle the unknowns. Now I need to reduce the number of predictors using feature selection because recording all the predictors in the final model is not practical.

Is there a feature selection function that will ignore unknown values? I have looked at fscnca and stepwiselm but both don't seem to work. Removing rows containing NaN in the predictor will ignore many other potentially useful predictors and there is no easy way to replace/estimate the unknowns.

Thank you.

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Prajit T R 2018-3-22

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/388267-feature-selection-with-nan#answer_311295

Hi Azura,

Have you tried the 'fillmissing' function in MATLAB? See the following link: Fillmissing

F = fillmissing(A,method) fills missing entries using the method specified by method, which can be one of the following: previous, next, nearest, linear,spline, pchip.

Cheers