search

WillKoehrsen / feature-selector

Feature selector is a tool for dimensionality reduction of machine learning datasets
GNU General Public License v3.0
2.22k stars 770 forks source link

can you clarify how you remove correlated features #47

Open Sandy4321 opened 3 years ago

Sandy4321 commented 3 years ago

can you clarify how you remove correlated features

as written in https://towardsdatascience.com/a-feature-selection-tool-for-machine-learning-in-python-b64dd23710f0

For each pair of correlated features, it identifies one of the features for removal (since we only need to remove one

so you just remove one from pair ?

ayush714 commented 3 years ago

Most variables are correlated with each other and thus they are highly redundant, let's say if you have two variables that are highly correlated, keeping the only one will help in dimensionality reduction and it doesn't cause that much loss of information.

One Question may arise you, Which Variable to keep? Keep the one that has a higher correlation with the target variable.

Sandy4321 commented 3 years ago

I see but Collinear Features how you calculated collinearity for categorical values ?

rajlm10 commented 3 years ago

Hi Sandy4321, I found a brilliant article that will help with your question : https://towardsdatascience.com/the-search-for-categorical-correlation-a1cf7f1888c9