13.4.3 Feature Permutation Importance Code Examples (L13: Feature Selection)

Sebastian's books: sebastianrasch...
This video shows code examples for computing permutation importance in mlxtend and scikit-learn.
Permutation importance is a model-agnostic, versatile way for computing the importance of features based on a machine learning classifier or regression model.
Code notebooks:
Wine data example: github.com/ras...
learning-fs21/blob/main/13-feature-selection/05_permutation-importance.ipynb
Using a random feature as a control: github.com/ras...
Checking correlated features: github.com/ras...

Slides: sebastianrasch...
Random forest importance video: • 13.3.2 Decision Trees ...
-------
This video is part of my Introduction of Machine Learning course.
Next video: • 13.4.4 Sequential Feat...
The complete playlist: • Intro to Machine Learn...
A handy overview page with links to the materials: sebastianrasch...
-------
If you want to be notified about future videos, please consider subscribing to my channel: / sebastianraschka

[@lucarubinetti2523]

Can you do some video about Shapley values for feature importance? Thanks a lot :)

[@liss9597]

Very thankful for this video and the entire set of videos. In min 7:08 X_test and y_test must be numpy array, right? If yes, should I use X_test.values and y_test.values or X_test.to_numpy() and y_test.to_numpy() ?? Thanks again!

[@sahanaseetharaman1440]

Thanks for the video! In this case, two of the features are perfectly correlated. What if the correlation is less than |1|? Also, what happens in the case of categorical features? Suppose there is a feature column with multiple categorical features, and we one-hot encode it, does it make sense to sum their feature importances to get the importance of that feature?

[@khaledsrrr]

Keep them coming ❤❤❤
I liked it

[@andrewm4894]

Great video really useful explanations

[@SebastianRaschka]

Glad you liked it

[@bezawitdagne5756]

Thank you so very much 💙🙏

[@monashaaban2337]

hi Sebastian Raschka, can you explain LDA with code please?

[@SebastianRaschka]

Coincidentally, I wrote about it here a few years back: sebastianraschka.com/Articles/2014_python_lda.html

[@monashaaban2337]

@@SebastianRaschka thank you.

[@ocamlmail]

Very useful, thank you!

[@mariajuanasadventures3672]

Thanks for the video

[@SebastianRaschka]

Glad you liked it!