Skip to content

model_diagnostics() - plotting residuals runs very long with 430K training instances #341

@konradsemsch

Description

@konradsemsch

Hi,

first of all, thanks for a great package and book - really a big fan of your work!

Coming to the question - I have run an explainer on a LightGBM model with 432920 instances of training data. When I want to inspect the residuals I first run:

res = explainer_test.model_diagnostics()

which takes very little to complete, but when I then want to create any plot e.g.:

res.plot(variable = "ids", yvariable = "residuals")

it takes between 20-30 minutes to complete. Do you also see a similar behaviour in your tests?

Metadata

Metadata

Assignees

Labels

Python 🐍Related to Pythonquestion ❔Further information is requested

Type

No type
No fields configured for issues without a type.

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions