Implementation:Interpretml Interpret LimeTabular

Metadata

Field	Value
Sources	Repo: InterpretML, Doc: LIME
Domains	Interpretability, Feature_Attribution
Updated	2026-02-07
Type	Wrapper Doc (wraps lime.lime_tabular.LimeTabularExplainer)

Overview

Wrapper tool for computing LIME explanations for blackbox models on tabular data, integrating the lime library into the InterpretML API.

Description

The LimeTabular class wraps lime.lime_tabular.LimeTabularExplainer. It initializes with a model and reference data, then generates per-sample explanations showing feature importance via locally fitted linear models.

Usage

Use this when you need LIME-based local explanations through the InterpretML visualization pipeline.

Code Reference

Field	Value
Source	interpretml/interpret
File	python/interpret-core/interpret/blackbox/_lime.py
Lines	16-172
Import	`from interpret.blackbox import LimeTabular`
External	lime.lime_tabular.LimeTabularExplainer (lazy import)

Signature:

class LimeTabular(ExplainerMixin):
    available_explanations = ["local"]
    explainer_type = "blackbox"

    def __init__(self, model, data, feature_names=None, feature_types=None, **kwargs):
    def explain_local(self, X, y=None, name=None, **kwargs):

I/O Contract

Init inputs:

Parameter	Type	Required
model	predict function	Yes
data	reference data	Yes
feature_names	list	No
feature_types	list	No

explain_local inputs:

Parameter	Type	Required
X	ndarray	Yes
y	ndarray	No
name	str	No

explain_local output: FeatureValueExplanation

Usage Examples

from interpret.blackbox import LimeTabular
from interpret import show

lime_exp = LimeTabular(rf.predict_proba, X_train)
local_explanation = lime_exp.explain_local(X_test[:5], y_test[:5], name="LIME")
show(local_explanation, key=0)

Related Pages

Page Connections

Double-click a node to navigate. Hold to expand connections.

Principle

Implementation

Heuristic

Environment