Feature selection issue.

[Siji-chl]

Dear Zhao:
Thanks for your great works first!

In your paper, you said 'Using the univariate binary logistic regression analysis, all the features with p < 0.05 (which are statistically significant) were selected to construct a feature set for further analysis.' But in your code, you selected those features with p < 0.05 using 'f_classif' method in sklearn. Was something I misunderstand?

Look forward to your reply, thank you!

[MIILab-MTU]

Yes, to perform univariate analysis and select the most important features with p<0.05, we adopted f_classif in sklearn.

For more detail, please follow the original description in sklearn:
https://scikit-learn.org/stable/auto_examples/feature_selection/plot_feature_selection.html#sphx-glr-auto-examples-feature-selection-plot-feature-selection-py