Kernel explainer for MLPRegressor
Given your familiarity with the admissions dataset, you will employ SHAP's Kernel Explainer to explain an MLPRegressor trained on this data. This method will allow you to critically assess how different features impact the model's predictions and verify these insights against your existing understanding of the dataset.
X
containing the predictors and y
containing the admission decisions, along with the pre-trained MLPRegressor model
, have been pre-loaded for you.
This exercise is part of the course
Explainable AI in Python
Exercise instructions
- Create a SHAP Kernel Explainer using the MLPRegressor
model
and a k-means summary of 10 samples fromX
. - Generate
shap_values
forX
. - Compute the mean absolute SHAP values to identify key factors affecting admissions.
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
import shap
# Create a SHAP Kernel Explainer
explainer = ____
# Calculate SHAP values
shap_values = ____
# Calculate mean absolute SHAP values
mean_abs_shap = ____
plt.bar(X.columns, mean_abs_shap)
plt.title('Mean Absolute SHAP Values for MLPRegressor')
plt.xticks(rotation=45)
plt.show()