Model interpretability (SHAP, LIME) in ML Python - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is model interpretability in machine learning?

Model interpretability means understanding how a machine learning model makes its decisions. It helps us see which features affect the predictions and why.

intermediate

What does SHAP stand for and what is its purpose?

SHAP stands for SHapley Additive exPlanations. It explains the output of any machine learning model by assigning each feature an importance value for a particular prediction.

intermediate

How does LIME help in interpreting machine learning models?

LIME (Local Interpretable Model-agnostic Explanations) explains individual predictions by approximating the model locally with a simple interpretable model, like a linear model.

advanced

What is the main difference between SHAP and LIME?

SHAP provides consistent and theoretically sound feature importance values based on game theory, while LIME focuses on local approximations and may vary depending on the sampled data around the prediction.

beginner

Why is model interpretability important in real-life applications?

Interpretability builds trust, helps detect errors or bias, and ensures models meet legal or ethical standards, especially in sensitive areas like healthcare or finance.

What does SHAP primarily provide for a machine learning model?

A Model training speed improvements

B A simpler model to replace the original

C Data preprocessing techniques

D Feature importance values for each prediction

SHAP assigns importance values to features for each prediction, explaining how much each feature contributed.

LIME explains model predictions by:

A Creating a local simple model around the prediction

B Using deep neural networks

C Ignoring feature values

D Changing the original model

LIME approximates the complex model locally with a simple interpretable model to explain predictions.

Which of the following is a key advantage of SHAP over LIME?

A SHAP values are consistent and based on game theory

B SHAP is faster to compute in all cases

C SHAP only works with linear models

D SHAP ignores feature interactions

SHAP provides consistent, theoretically grounded explanations using Shapley values from game theory.

Why is model interpretability especially important in healthcare?

A To avoid using any features

B To ensure decisions are understandable and trustworthy

C To reduce data size

D To speed up model training

In healthcare, understanding model decisions helps doctors trust and safely use AI predictions.

Which method is model-agnostic, meaning it can explain any model?

A Only LIME

B Only SHAP

C Both SHAP and LIME

D Neither SHAP nor LIME

Both SHAP and LIME can explain predictions from any machine learning model.

Explain in your own words how SHAP helps interpret a machine learning model's prediction.

Think about how SHAP assigns credit to each feature for a single prediction.

Describe the main idea behind LIME and how it explains model predictions locally.

Consider how LIME looks at a small neighborhood around a prediction.

Practice

1. What is the main purpose of using SHAP or LIME in machine learning?

easy

A. To improve the speed of model training

B. To reduce the number of features in the dataset

C. To increase the size of the training dataset

D. To explain why a model made a specific prediction

Solution

1. Step 1: Understand model interpretability tools

   SHAP and LIME are designed to explain model predictions by showing feature importance.

2. Step 2: Identify their main use

   They help users understand why a model made a certain prediction, increasing trust.

3. Final Answer:

   To explain why a model made a specific prediction -> Option D

4. Quick Check:

   Interpretability = Explanation [OK]

Hint: SHAP and LIME explain predictions, not speed or data size [OK]

Common Mistakes:

• Confusing interpretability with model training speed
• Thinking SHAP/LIME reduce dataset size
• Assuming they automatically improve model accuracy

2. Which of the following is the correct way to import the SHAP library in Python?

easy

A. from shap import explain

B. import SHAP

C. import shap

D. import SHAP as sp

Solution

1. Step 1: Recall Python import syntax

   Python imports are case-sensitive; the SHAP library is lowercase 'shap'.

2. Step 2: Check each option

   import shap uses correct lowercase import. import SHAP uses uppercase which is invalid. from shap import explain tries to import a non-existent module 'explain'. import SHAP as sp uses uppercase which is invalid.

3. Final Answer:

   import shap -> Option C

4. Quick Check:

   Python imports are case-sensitive [OK]

Hint: Python imports match exact package name in lowercase [OK]

Common Mistakes:

• Using uppercase letters in import statements
• Importing non-existent submodules
• Using uncommon aliases without explanation

3. Given the following Python code using LIME, what will exp.as_list() return?

import lime.lime_tabular
explainer = lime.lime_tabular.LimeTabularExplainer(training_data, feature_names=features)
exp = explainer.explain_instance(test_instance, model.predict_proba)
print(exp.as_list())

medium

A. A list of tuples showing feature names and their importance scores for the test instance

B. The predicted class label for the test instance

C. The training data used to build the explainer

D. A plot object visualizing the model's decision

Solution

1. Step 1: Understand LIME explanation output

   The explain_instance method returns an explanation object. Calling as_list() gives feature importance as a list of (feature, weight) tuples.

2. Step 2: Match output to options

   A list of tuples showing feature names and their importance scores for the test instance correctly describes this list. The predicted class label for the test instance is the predicted label, which as_list() does not return. The training data used to build the explainer is training data, unrelated here. A plot object visualizing the model's decision is a plot, which requires a different method.

3. Final Answer:

   A list of tuples showing feature names and their importance scores for the test instance -> Option A

4. Quick Check:

   LIME explanation list = feature importance [OK]

Hint: LIME's as_list() shows feature importance tuples [OK]

Common Mistakes:

• Confusing explanation list with predicted label
• Expecting training data from explanation
• Thinking as_list() returns a plot

4. You run SHAP on a model but get an error: AttributeError: 'TreeExplainer' object has no attribute 'shap_values'. What is the likely cause?

medium

A. You used an outdated SHAP version missing the shap_values method

B. The model is not a tree-based model supported by TreeExplainer

C. You forgot to import the SHAP library

D. The input data is missing feature names

Solution

1. Step 1: Understand TreeExplainer requirements

   TreeExplainer works only with tree-based models like XGBoost or LightGBM. Using it on unsupported models causes attribute errors.

2. Step 2: Analyze error cause

   The error suggests the method shap_values is missing, likely because the model type is unsupported by TreeExplainer.

3. Final Answer:

   The model is not a tree-based model supported by TreeExplainer -> Option B

4. Quick Check:

   TreeExplainer needs tree models [OK]

Hint: TreeExplainer only supports tree models, else error occurs [OK]

Common Mistakes:

• Assuming missing import causes this error
• Blaming outdated SHAP version without checking model type
• Ignoring model compatibility with explainer

5. You want to explain predictions of a complex neural network on tabular data. Which approach best combines SHAP and LIME to get both global and local interpretability?

hard

A. Use SHAP's DeepExplainer for global feature importance and LIME for local explanations on individual samples

B. Use LIME only, as SHAP does not support neural networks

C. Use SHAP's TreeExplainer for local explanations and LIME for global explanations

D. Use neither; neural networks cannot be interpreted

Solution

1. Step 1: Identify SHAP and LIME strengths

   SHAP's DeepExplainer supports neural networks and provides global feature importance. LIME excels at explaining individual predictions locally.

2. Step 2: Combine for best interpretability

   Using SHAP for global insights and LIME for local explanations gives a full understanding of model behavior.

3. Final Answer:

   Use SHAP's DeepExplainer for global feature importance and LIME for local explanations on individual samples -> Option A

4. Quick Check:

   SHAP global + LIME local = best combo [OK]

Hint: SHAP global + LIME local = full interpretability [OK]

Common Mistakes:

• Thinking SHAP does not support neural networks
• Confusing TreeExplainer with DeepExplainer
• Believing neural networks cannot be interpreted