Implementation:Interpretml Interpret To Jsonable

Field	Value
Sources	Repo: InterpretML
Domains	Model_Persistence, Interoperability
Updated	2026-02-07

Overview

Concrete tool for serializing a fitted EBM to JSON format provided by the InterpretML library.

Description

The to_jsonable function converts a fitted EBM model into a JSON-compatible Python dictionary. It supports four detail levels controlling which attributes are included. The output can be passed to json.dumps() for file storage.

Usage

Call this to serialize a fitted EBM for storage, API transmission, or model merging workflows.

Code Reference

Field	Value
Source	interpretml/interpret
File	python/interpret-core/interpret/glassbox/_ebm/_json.py
Lines	321-388

Signature:

def to_jsonable(ebm, detail="all"):
    """Converts the model to a JSONable representation.
    Args:
        detail: 'minimal', 'interpretable', 'mergeable', 'all'
    Returns:
        JSONable object
    """

Import:

from interpret.glassbox._ebm._json import to_jsonable

I/O Contract

Inputs:

Parameter	Type	Required	Description
ebm	fitted EBM	Yes	A fitted ExplainableBoostingClassifier or ExplainableBoostingRegressor instance
detail	str	No	Detail level: "minimal", "interpretable", "mergeable", or "all"

Outputs:

Type	Description
dict	Dictionary with "version" and "ebm" keys containing full model serialization

Usage Examples

import json
from interpret.glassbox import ExplainableBoostingClassifier
from interpret.glassbox._ebm._json import to_jsonable

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

# Serialize to JSON
model_dict = to_jsonable(ebm, detail="all")
with open("ebm_model.json", "w") as f:
    json.dump(model_dict, f)

Related Pages

Page Connections

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

Principle

Implementation

Heuristic

Environment