Partial Dependence Plots

While feature importance shows what variables most affect predictions, partial dependence plots show how a feature affects predictions.

For linear or regression models, partial dependence plots can be interpreted similarly to the coefficients in those models. Though, partial dependence plots on sophisticated models can capture more complex patterns than coefficients from simple models.

How It Works

Like permutation importance, partial dependence plots are calculated after a model has been fit.

Instead of shuffling the feature, we repeatedly alter the value for one variable to make a series of predictions and plot the predicted outcome.

2D Partial Dependence Plots

If you are curious about interactions between features, 2D partial dependence plots are also useful, where x-axis denotes a feature and y-axis another feature and the contour line denotes the predicted outcome.

Reference