interpret
Fit interpretable models. Explain blackbox machine learning.
Decision gist · record as of 2026-08-14
Yes. InterpretML is actively maintained, has low install friction, and fills a genuine need for interpretable ML in regulated and high-stakes domains. The Explainable Boosting Machine is a well-researched technique with published benchmarks. The main caveat is the unclear license status—verify the actual license in the repository before deploying in proprietary or regulated contexts. For model debugging, fairness auditing, and compliance-driven work, this is a solid choice.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.10 or later; the package supports Python 3.10, 3.11, 3.12, 3.13, and 3.14.
- Low install friction with a pure-Python wheel distribution.
- The package is actively maintained with a recent release and 6916 repository stars, indicating a stable, well-supported project.
License · maintenance · safety
(unclear) — License status is unclear—no SPDX identifier or raw license text is available in the metadata. Verify the actual license in the repository before use in proprietary or regulated contexts.
last release 2026-03-17 (150 days) · last repo commit 2026-08-10 · 6,916 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 407,758 downloads/mo, #6,885 on PyPI
Alternatives
Verify before relying
pip install interpret
from interpret.glassbox import ExplainableBoostingClassifier
ebm = ExplainableBoostingClassifier()
ebm.fit(X_train, y_train)
ebm_global = ebm.explain_global()- Whether the unclear license status reflects a missing metadata entry or an actual licensing ambiguity affecting commercial use.
- Performance characteristics and scalability limits for datasets smaller than the 100 million sample threshold mentioned.
What it is and what it does
InterpretML is a machine learning interpretability framework that unifies multiple techniques for understanding both interpretable models and blackbox predictions. It includes Explainable Boosting Machines (EBMs)—a modern take on Generalized Additive Models that combine gradient boosting with automatic interaction detection to achieve accuracy comparable to random forests and gradient boosted trees while remaining fully interpretable and editable by domain experts. The package also wraps blackbox explainers like SHAP, LIME, and partial dependence analysis.
You use it to train glassbox models directly or to attach explainers to existing blackbox models, then call explain_global() to understand feature contributions across your dataset or explain_local() to understand why the model made a specific prediction. It supports privacy-preserving variants (differentially private EBMs) and handles pandas dataframes, numpy arrays, and string data natively. The framework is designed for model debugging, feature engineering, fairness auditing, and regulatory compliance in high-risk domains like healthcare and finance.
Use it for
- Train an Explainable Boosting Machine when you need both accuracy and full interpretability for regulatory applications.
- Debug a blackbox model by attaching SHAP or LIME explainers to understand which features drove predictions.
- Detect fairness issues by examining global feature importance and local explanations across demographic groups.
- Engineer features by analyzing which interactions the model learned and which features matter most.
- Satisfy compliance requirements in finance or healthcare by producing exact, auditable explanations.
- Compare multiple models side-by-side using show() to visualize and contrast their explanations.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes.
InterpretML is actively maintained, has low install friction, and fills a genuine need for interpretable ML in regulated and high-stakes domains. The Explainable Boosting Machine is a well-researched technique with published benchmarks. The main caveat is the unclear license status—verify the actual license in the repository before deploying in proprietary or regulated contexts. For model debugging, fairness auditing, and compliance-driven work, this is a solid choice.
Install
interpret on PyPI
Before you install
Low install friction with a pure-Python wheel distribution. The package is actively maintained with a recent release and 6916 repository stars, indicating a stable, well-supported project.
Requires Python 3.10 or later; the package supports Python 3.10, 3.11, 3.12, 3.13, and 3.14.
License in practice
License status is unclear—no SPDX identifier or raw license text is available in the metadata. Verify the actual license in the repository before use in proprietary or regulated contexts.
Quickstart
pip install interpret
from interpret.glassbox import ExplainableBoostingClassifier
ebm = ExplainableBoostingClassifier()
ebm.fit(X_train, y_train)
ebm_global = ebm.explain_global()Verify before relying
- Whether the unclear license status reflects a missing metadata entry or an actual licensing ambiguity affecting commercial use.
- Performance characteristics and scalability limits for datasets smaller than the 100 million sample threshold mentioned.
Package facts
| License | Not declared unclear |
| Python support | Not specified |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 1 packageinterpret-core |
| Maintenance | Actively maintained 150 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 407,758 / month, #6,885 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 5 - Production/StableOperating System :: OS IndependentProgramming Language :: PythonProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.14Topic :: Scientific/Engineering :: Artificial Intelligence |
Evidence: interpret-0.7.8-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “glassbox vs blackbox models”
- interpretInterpretML provides interpretable machine learning models and…
- interpret-coreTrains interpretable machine learning models and explains blackbox…
- bbpbDecode and re-encode Protocol Buffer messages without access to the…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also interpret-core · skope-rules · shap · treeinterpreter · lime · captum · aplr · eli5 · dtreeviz · cleanlab