Partial Dependency Plots from AutoML

129464
New Contributor

I have built an AutoML model, and I would like for it to add Partial Dependency Plots for the final/best model. I am trying to add this to the code generated, but not having any luck. This is the code I attempted.

from sklearn.inspection import PartialDependenceDisplay

# Create Partial Dependency Plots for each class

n_classes = len(model.classes_)

for target_class in range(n_classes):

  target_label = model.classes_[target_class]

  print(f"Partial dependency plots for class {target_label}:")

   

  display = PartialDependenceDisplay.from_estimator(

    model, X_train, np.arange(X_train.shape[1]), target=target_label

  )

  display.figure_.set_size_inches(12, 😎

  display.figure_.suptitle(f"Partial dependency plots for class {target_label}")

  plt.subplots_adjust(hspace=0.4, wspace=0.4)

  plt.show()