SHAP values give the contribution of a feature to a prediction made by a machine learning model. This is also true when we use SHAP for classification. For binary target variables, we interpret these values in terms of log odds. For multiclass targets, we use softmax. In this video, we will:
- Discuss the interpretations of SHAP for classification problems
- Give the Python code for displaying SHAP plots for categorical target variables
- Explore new ways of aggregating SHAP values for multiclass targets
This knowledge will become an essential part of your explainable AI (XAI) arsenal!
🚀 Free Course 🚀
*NOTE*: You will now get the XAI course for free if you sign up (not the SHAP course)
SHAP course: adataodyssey.com/courses/shap...
XAI course: adataodyssey.com/courses/xai-...
Newsletter signup: mailchi.mp/40909011987b/signup
🚀 Companion Article (no-paywall link): 🚀
towardsdatascience.com/shap-f...
🚀 Previous tutorial and other useful articles: 🚀
Intro to SHAP: towardsdatascience.com/introd...
Maths behind Shapley Values: towardsdatascience.com/from-s...
Limitations of SHAP: towardsdatascience.com/the-li...
🚀 Get in touch 🚀
Medium: / conorosullyds
Twitter: / conorosullyds
Mastodon: sigmoid.social/@conorosully
Website: adataodyssey.com/
Негізгі бет SHAP for Binary and Multiclass Target Variables | Code and Explanations for Classification Problems
Пікірлер: 20