PiML 0.4.0.post1

A low-code interpretable machine learning toolbox in Python.

An integrated Python toolbox for interpretable machine learning

pip install PiML

:rocket: October 31, 2022: V0.4.0 is released with enriched models and enhanced diagnostics.

:rocket: July 26, 2022: V0.3.0 is released with classic statistical models.

:rocket: June 26, 2022: V0.2.0 is released with high-code APIs.

:loudspeaker: May 4, 2022: V0.1.0 is launched with low-code UI/UX.

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. XGB2: Extreme Gradient Boosted Trees of Depth 2 (Chen and Guestrin, 2016; Lengerich, et al. 2020)
6. EBM: Explainable Boosting Machine (Nori, et al. 2019; Lou, et al. 2013)
7. GAMI-Net: Generalized Additive Model with Structured Interactions (Yang, Zhang and Sudjianto, 2021)
8. 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 ot 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.