An integrated Python toolbox for interpretable machine learning

March 30, 2025 by Dr. Agus Sudjianto: Farewell PiML, Hello MoDeVa!

After three impactful years of empowering model developers and validators, we’re thrilled to introduce the next evolution: MoDeVa – MOdel DEvelopment & VAlidation.

MoDeVa builds on the success of PiML, taking transparency, interpretability, and robustness in machine learning to a whole new level. Whether you’re in a high-stakes regulatory setting or exploring cutting-edge model architectures, MoDeVa is built to support your journey.

Why MoDeVa?

• Next-Gen Models: Interpretable ML models like Boosted Trees, Mixture of Experts, and Neural Trees—built for confident decision-making.

• Model Hacking Redefined: Tools to uncover failure modes, analyze robustness, reliability and resilience.

• Interactive Statistical Visualizations: Bring models to life with dynamic graphs that go beyond static charts.

• Seamless Validation: Effortlessly validate external black-box models using flexible wrappers.

Check it out here: https://modeva.ai/

PiML (or π-ML, /ˈpaɪ·ˈem·ˈel/) is a new Python toolbox for interpretable machine learning model development and validation. Through low-code interface and high-code APIs, PiML supports a growing list of inherently interpretable ML models:

1. GLM: Linear/Logistic Regression with L1 ∨ L2 Regularization
2. GAM: Generalized Additive Models using B-splines
3. Tree: Decision Tree for Classification and Regression
4. FIGS: Fast Interpretable Greedy-Tree Sums (Tan, et al. 2022)
5. XGB1: Extreme Gradient Boosted Trees of Depth 1, with optimal binning (Chen and Guestrin, 2016; Navas-Palencia, 2020)
6. XGB2: Extreme Gradient Boosted Trees of Depth 2, with effect purification (Chen and Guestrin, 2016; Lengerich, et al. 2020)
7. EBM: Explainable Boosting Machine (Nori, et al. 2019; Lou, et al. 2013)
8. GAMI-Net: Generalized Additive Model with Structured Interactions (Yang, Zhang and Sudjianto, 2021)
9. ReLU-DNN: Deep ReLU Networks using Aletheia Unwrapper and Sparsification (Sudjianto, et al. 2020)

PiML also works for arbitrary supervised ML models under regression and binary classification settings. It supports a whole spectrum of outcome testing, including but not limited to the following:

1. Accuracy: popular metrics like MSE, MAE for regression tasks and ACC, AUC, Recall, Precision, F1-score for binary classification tasks.
2. Explainability: post-hoc global explainers (PFI, PDP, ALE) and local explainers (LIME, SHAP).
3. Fairness: disparity test and segmented analysis by integrating the solas-ai package.
4. WeakSpot: identification of weak regions with high residuals by slicing techniques.
5. Overfit: identification of overfitting regions according to train-test performance gap.
6. Reliability: assessment of prediction uncertainty by split conformal prediction techniques.
7. Robustness: evaluation of performance degradation under covariate noise perturbation.
8. Resilience: evaluation of performance degradation under different out-of-distribution scenarios.

Installation | Examples | Usage | Citations

pip install PiML 

Click the ipynb links to run examples in Google Colab:

1. BikeSharing data: ipynb
2. CaliforniaHousing data: ipynb
3. TaiwanCredit data: ipynb
4. Fairness_SimuStudy1 data: ipynb
5. Fairness_SimuStudy2 data: ipynb
6. Upload custom data in two ways: ipynb
7. Deal with external models: ipynb

Begin your own PiML journey with this demo notebook.

The same examples can also be run by high-code APIs:

1. BikeSharing data: ipynb
2. CaliforniaHousing data: ipynb
3. TaiwanCredit data: ipynb
4. Model saving: ipynb
5. Results return: ipynb

from piml import Experiment
exp = Experiment()

exp.data_loader()

exp.data_summary()

exp.data_prepare()

exp.data_quality()

exp.feature_select()

exp.eda()

exp.model_train()

exp.model_explain()

exp.model_interpret() 

exp.model_diagnose()

exp.model_compare()

exp.model_fairness()

exp.model_fairness_compare()

For example, train a complex LightGBM with depth 7 and register it to the experiment:

from lightgbm import LGBMClassifier
exp.model_train(LGBMClassifier(max_depth=7), name='LGBM-7')

Then, compare it to inherently interpretable models (e.g. XGB2 and GAMI-Net):

exp.model_compare()

@article{sudjianto2023piml,
title={PiML Toolbox for Interpretable Machine Learning Model Development and Diagnostics},
author={Sudjianto, Agus and Zhang, Aijun and Yang, Zebin and Su, Yu and Zeng, Ningzhou},
year={2023}
}

@article{sudjianto2021designing,
title={Designing Inherently Interpretable Machine Learning Models},
author={Sudjianto, Agus and Zhang, Aijun},
journal={arXiv preprint:2111.01743},
year={2021}
}

@article{sudjianto2020unwrapping,
title={Unwrapping the black box of deep ReLU networks: interpretability, diagnostics, and simplification},
author={Sudjianto, Agus and Knauth, William and Singh, Rahul and Yang, Zebin and Zhang, Aijun},
journal={arXiv preprint:2011.04041},
year={2020}
}

@article{yang2021gami,
title={GAMI-Net: An explainable neural network based on generalized additive models with structured interactions},
author={Yang, Zebin and Zhang, Aijun and Sudjianto, Agus},
journal={Pattern Recognition},
volume={120},
pages={108192},
year={2021}
}

@article{tan2022fast,
title={Fast interpretable greedy-tree sums (FIGS)},
author={Tan, Yan Shuo and Singh, Chandan and Nasseri, Keyan and Agarwal, Abhineet and Yu, Bin},
journal={arXiv preprint arXiv:2201.11931},
year={2022}
}

@inproceedings{lou2013accurate,
title={Accurate intelligible models with pairwise interactions},
author={Lou, Yin and Caruana, Rich and Gehrke, Johannes and Hooker, Giles},
booktitle={Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining},
pages={623--631},
year={2013},
organization={ACM}
} 

@inproceedings{lengerich2020purifying,
title={Purifying interaction effects with the functional anova: An efficient algorithm for recovering identifiable additive models},
author={Lengerich, Benjamin and Tan, Sarah and Chang, Chun-Hao and Hooker, Giles and Caruana, Rich},
booktitle={International Conference on Artificial Intelligence and Statistics},
pages={2402--2412},
year={2020},
organization={PMLR}
}

@article{nori2019interpretml,
title={InterpretML: A Unified Framework for Machine Learning Interpretability},
author={Nori, Harsha and Jenkins, Samuel and Koch, Paul and Caruana, Rich},
journal={arXiv preprint:1909.09223},
year={2019}
}