A game theory approach to measuring spatial effects from machine learning models. GeoShapley is built on Shapley value and Kernel SHAP estimator.
GeoShapley can be installed from PyPI:
$ pip install geoshapleyGeoShapley can explain any model that takes data + coordiantes as the input. Currently, coordinates need to be put as the last two columns of your pandas.DataFrame(X_geo).
Below shows an example on how to explain a trained NN model.
from geoshapley import GeoShapleyExplainer
from sklearn.neural_network import MLPRegressor
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X_geo, y, random_state=1)
#Fit a NN model based on training data
mlp_model = MLPRegressor().fit(X_train, y_train)
#Specify a small background data
background = X_train.sample(100).values
#Initilize a GeoShapleyExplainer
mlp_explainer = GeoShapleyExplainer(mlp_model.predict, background)
#Explain the data
mlp_rslt = mlp_explainer.explain(X_geo)
#Make a shap-style summary plot
mlp_rslt.summary_plot()
#Make partial dependence plots of the primary (non-spatial) effects
mlp_rslt.partial_dependence_plots()
#Calculate spatially varying explanations
mlp_svc = mlp_rslt.get_svc()Li, Z. (2023). GeoShapley: A Game Theory Approach to Measuring Spatial Effects in Machine Learning Models. arXiv preprint https://doi.org/10.48550/arXiv.2312.03675