/XAI_Labs

Explainable AI laboratories

Primary LanguageJupyter Notebook

X-AI Labs

Task 01: Regression for generated clusters

The original dataset consists of several clusters generated by different linear laws.

  • For each point in the test set, determine the vector of feature importances
  • Cluster the resulting importance vectors
  • Determine the law by which each of the clusters are generated

ML Models:

  1. XGBoost (Extreme gradient boost) with GridSearchCV hyperparameter tuning
    Files:
    notebook: xai_clusters_gen_xgboost.ipynb
    model: xgb_clusters_gen_v1.pkl
  2. LGBM (Light gradient boost machines) with GridSearchCV hyperparameter tuning
    Files:
    notebook: xai_clusters_gen_lgbm.ipynb
    model: lgbm_clusters_gen_v1.pkl
  3. NAF (Neural Attention Forest) without hyperparameter tuning
    Files:
    notebook: xai_clusters_gen_naf.ipynb (just global explanations)

X-AI Algorithms:

  1. Tree-SHAP (Shapley additive explanation) for global and local explanations

X-AI Visualizations:

  1. For global explanations
    • Feature importance bar plots
    • Bar plots with hierarchical clustering among features
    • Summary plots
    • Heat maps
    • Partial Dependency Plots (PDP)
  2. For local explanations
    • Force plots
    • Decision plots
    • Waterfall plots