Jump to content

Connect Leeroopedia MCP: Equip your AI agents to search best practices, build plans, verify code, diagnose failures, and look up hyperparameter defaults.

Implementation:Interpretml Interpret Show

From Leeroopedia


Field Value
Sources InterpretML
Domains Visualization, User_Interface
Last Updated 2026-02-07 12:00 GMT

Overview

Show is a concrete tool for rendering interactive explanation visualizations provided by the InterpretML library.

Description

The show function is the primary entry point for visualizing model explanations. It accepts one or more Explanation objects and a key selector, delegates to the auto-detected visualization provider, and renders interactive charts. With key=-1 it shows the overall summary; with key=N it shows the Nth term/sample.

Usage

Call show() whenever you want to visualize an explanation in a Jupyter notebook or browser.

Code Reference

Source Location

Repository
interpretml/interpret
File
python/interpret-core/interpret/visual/_interactive.py
Lines
136--160

Signature

def show(explanation, key=-1, **kwargs):
    """Provides an interactive visualization for a given explanation(s).
    Args:
        explanation: Either a scalar Explanation or list of Explanations.
        key: Specific index of explanation to visualize. -1 for overall.
        **kwargs: Kwargs passed to provider's render() call.
    """

Import

from interpret import show

I/O Contract

Inputs

Name Type Required Description
explanation Explanation or list[Explanation] Yes One or more Explanation objects to visualize
key int No Specific index of explanation to visualize; -1 for overall (default: -1)
**kwargs keyword arguments No Kwargs passed to provider's render() call

Outputs

Name Type Description
None None Side effect: renders visualization in notebook or browser

Usage Examples

Global and Local Visualization

from interpret.glassbox import ExplainableBoostingClassifier
from interpret import show

ebm = ExplainableBoostingClassifier()
ebm.fit(X_train, y_train)

# Global explanation
global_exp = ebm.explain_global()
show(global_exp)          # Overall importance
show(global_exp, key=0)   # First feature shape

# Local explanation
local_exp = ebm.explain_local(X_test[:5], y_test[:5])
show(local_exp, key=0)    # First sample explanation

# Compare multiple explanations
show([global_exp, local_exp])

Related Pages

Page Connections

Double-click a node to navigate. Hold to expand connections.
Principle
Implementation
Heuristic
Environment