Implementation:Interpretml Interpret TreeInterpreter

Knowledge Sources	Interpretml Interpret
Domains	Machine_Learning, Interpretability
Last Updated	2026-02-07 12:00 GMT

Overview

TreeInterpreter is a greybox explainer that wraps the treeinterpreter package to provide local feature contribution explanations for scikit-learn tree-based models within the InterpretML API.

Description

This class provides an InterpretML-compatible wrapper around the treeinterpreter package by andosa:

• TreeInterpreter: Extends ExplainerMixin with explainer type "specific" (greybox). It decomposes a tree-based model's prediction for each instance into per-feature contributions plus a bias term, showing how each feature pushed the prediction from the base value.

Supported scikit-learn models (from the treeinterpreter package):

• • DecisionTreeRegressor / DecisionTreeClassifier
  • ExtraTreeRegressor / ExtraTreeClassifier
  • RandomForestRegressor / RandomForestClassifier
  • ExtraTreesRegressor / ExtraTreesClassifier

The class handles both classification and regression. For binary classification, it extracts contributions for the positive class (index 1). Background data is optional but can be provided to determine feature names and types.

The output is a FeatureValueExplanation with per-instance breakdowns showing feature names, contribution scores, feature values, and a bias (intercept) term.

Usage

Use TreeInterpreter when you need to understand per-feature contributions for individual predictions from scikit-learn tree models or random forests. It requires the treeinterpreter package (pip install treeinterpreter).

Code Reference

Source Location

• Repository: Interpretml_Interpret
• File: python/interpret-core/interpret/greybox/_treeinterpreter.py

Signature

class TreeInterpreter(ExplainerMixin):
    available_explanations = ["local"]
    explainer_type = "specific"

    def __init__(self, model, data=None, feature_names=None, feature_types=None):

    def explain_local(self, X, y=None, name=None, **kwargs):

Import

from interpret.greybox import TreeInterpreter

I/O Contract

Constructor Inputs

Name	Type	Required	Description
model	scikit-learn tree model	Yes	A scikit-learn tree or forest model (see supported list above)
data	numpy array or compatible	No	Optional background data used to determine feature names and types
feature_names	list of str	No	List of feature names
feature_types	list of str	No	List of feature types

explain_local Inputs

Name	Type	Required	Description
X	numpy array or compatible	Yes	Instances to explain
y	numpy array	No	True labels for performance metrics
name	str	No	User-defined explanation name
**kwargs	varies	No	Additional keyword arguments passed to treeinterpreter.predict

Outputs

Name	Type	Description
explanation	FeatureValueExplanation	Local explanation with per-instance feature contribution breakdowns and bias term

Usage Examples

Random Forest Example

from interpret.greybox import TreeInterpreter
from sklearn.ensemble import RandomForestClassifier
from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split

X, y = load_breast_cancer(return_X_y=True)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)

model = RandomForestClassifier(n_estimators=100).fit(X_train, y_train)

ti = TreeInterpreter(model, data=X_train)
local_exp = ti.explain_local(X_test[:5], y_test[:5], name="RF TreeInterpreter")
local_exp.visualize(key=0)  # Feature contributions for first test instance

Regression Example

from interpret.greybox import TreeInterpreter
from sklearn.ensemble import RandomForestRegressor
import numpy as np

X = np.random.randn(200, 4)
y = X[:, 0] * 2 + X[:, 1] + np.random.randn(200) * 0.1

model = RandomForestRegressor(n_estimators=50).fit(X, y)

ti = TreeInterpreter(model, feature_names=["f0", "f1", "f2", "f3"])
local_exp = ti.explain_local(X[:3], y[:3])
local_exp.visualize(key=0)

Related Pages

• Principle:Interpretml_Interpret_Tree_Interpretation