Implementation:Interpretml Interpret Explain Global

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

Overview

Explain_Global is a concrete tool for generating global model explanations provided by the InterpretML EBM classes.

Description

The explain_global method on ExplainableBoostingClassifier/Regressor generates a global explanation containing per-term shape function data, importance scores, and visualization metadata. It assembles continuous bar chart data for each term's shape function and a horizontal bar chart for overall feature importance. The returned EBMExplanation object can be passed to show() for interactive visualization.

Usage

Call this method on a fitted EBM to obtain a global explanation suitable for visualization, auditing, or programmatic analysis.

Code Reference

Source Location

Repository: interpretml/interpret
File: python/interpret-core/interpret/glassbox/_ebm/_ebm.py
Lines: 2047--2324

Signature

def explain_global(self, name=None):
    """Provide global explanation for model.
    Args:
        name: User-defined explanation name.
    Returns:
        An explanation object, visualizing feature-value pairs
        as horizontal bar chart.
    """

Import

from interpret.glassbox import ExplainableBoostingClassifier
# Then: ebm.explain_global(name="My Global Explanation")

I/O Contract

Inputs

Name	Type	Required	Description
`self`	fitted EBM model	Yes	The fitted ExplainableBoostingClassifier or ExplainableBoostingRegressor instance
`name`	str / None	No	User-defined explanation name

Outputs

Name	Type	Description
EBMExplanation	EBMExplanation (extends FeatureValueExplanation)	Global feature importance data, continuous bar charts per term, and horizontal bar overall summary

Usage Examples

Generating and Visualizing a Global Explanation

from interpret.glassbox import ExplainableBoostingClassifier
from interpret import show

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

# Generate global explanation
global_exp = ebm.explain_global(name="EBM Global")

# Visualize overall feature importance
show(global_exp)

# Visualize a specific feature's shape function
show(global_exp, key=0)  # First term

Related Pages

Page Connections

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

Principle

Implementation

Heuristic

Environment