Python package which helps to debug machine learning classifiers and explain their predictions.
Open source
24 alternativesLIME
LIME provides explanations for predictions made by machine learning classifiers.
About LIME
LIME is an open source Python package for explaining individual predictions made by machine learning classifiers. It works with text classifiers, classifiers that act on tabular data (numerical or categorical arrays), and image classifiers. The package name stands for local interpretable model-agnostic explanations.
LIME treats the model as a black box. It perturbs the instance being explained, weights the perturbed samples by their proximity to that instance, and fits a sparse linear model around it. The result is a local approximation of the model's behaviour near that one prediction, not a complete description of the model. Any classifier with two or more classes can be used if it provides a function that takes raw text or a numpy array and returns a probability for each class. Built-in support is included for scikit-learn classifiers. Explanations can be produced as HTML for embedding in IPython notebooks, or as matplotlib visualizations.
Key features
- Explains individual predictions of text classifiers
- Explains individual predictions of tabular data classifiers
- Explains individual predictions of image classifiers
- Built-in support for scikit-learn classifiers
- HTML explanation output that can be embedded in IPython notebooks
- Installable from PyPI with pip install lime
Best for: Machine learning practitioners and data scientists who need to understand why a classifier made a particular prediction.
Good for
- Open source, released under the BSD-2-Clause license
- Works with any black-box classifier that outputs class probabilities
- Includes tutorials for text, tabular, and image classifiers
Watch out for
- Explanations are local approximations and not necessarily valid across the whole model
- Python 2 is no longer supported after version 0.2.0
- Matplotlib visualizations are less polished than the HTML output, according to the project
LIME at a glance
- Website
- github.com/marcotcr/lime
- Category
- AI & Machine Learning › AI Data & Analytics
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 6, 2026 · Online when checked
- Listed
- Oct 5, 2026
LIME alternatives
Tools and sites you could use instead, ranked by how closely they match.
This Swift library builds machine learning predictions using linear regression.
Open source
24 alternatives
MCGrad calibrates machine learning predictions across the full dataset and across segments defined by input features.
Open source
24 alternatives
PredictionBuilder builds machine learning predictions using linear regression.
Open source
24 alternatives
19 Questions assigns attributes to objects using machine learning and Bayesian inference, according to its project description.
Open source
24 alternatives
oneDAL is a C++ and DPC++ library for accelerated machine learning routines on tabular data, governed by the UXL Foundation.
Open source
24 alternativesPopular in AI Data & Analytics
Well-known listings from the same topic.
Dotgetdot.aiForvioforvio.comFluidAI Medicalfluidai.mdApache Zeppelinzeppelin.apache.orgSola Securitysola.securityQuadraticquadratichq.com
LIME FAQ
Does LIME need access to the internals of the model?
No. LIME treats the classifier as a black box. It needs a function that accepts raw text or a numpy array and returns a probability for each class.
How is LIME installed?
The lime package is available on PyPI and can be installed with pip install lime. The repository can also be cloned and installed with pip install .
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.