Omnixai

Fix an issues related to the default parameters in TabularTransform.

1. OmniXAI v1.3.0 includes an experimental GPT explainer. This explainer leverages the outcomes produced by SHAP and MACE to formulate the input prompt for ChatGPT. Subsequently, ChatGPT analyzes these results and generates the corresponding explanations that provide developers with a clearer understanding of the rationale behind the model's predictions.
2. Fixed some small issues in the explainers and visualization.
3. Updated the copyright.

1. Add what-if analysis for tabular data, e.g., users can change feature values and compare different models.
2. Revise the visualization dashboard to support Google Colab notebooks.
3. MACE now can generate counterfactual examples without using KNN search. This feature is mainly used for small datasets.

1. Support model bias analysis
2. Revise the documentations

1. Add global SHAP feature importance.
2. Add permutation feature importance.
3. Add a KNN-based counterfactual explainer.
4. Revise the dashboard figures for global explanations.
5. Fix some bugs and interface issues.

1. Support BentoML deployment for TabularExplainer, VisionExplainer and NLPExplainer.
2. Support JSON converters for all the explanation classes.
3. Fix a small bug in feature visualization when Torch > 1.7.