-
-
Notifications
You must be signed in to change notification settings - Fork 25.9k
[MRG+1] added a new section on model persistence #3084
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[MRG+1] added a new section on model persistence #3084
Conversation
|
||
In the specific case of the scikit, it may be more interesting to use | ||
joblib's replacement of pickle (``joblib.dump`` & ``joblib.load``), | ||
which is more efficient on big data, but can only pickle to the disk |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
...which is more efficient on objects that carry large numpy arrays internally as is often the case for fitted scikit-learn estimators.
Apart from my comments, this looks good. +1 for merge once they are addressed. |
Addressed ogrisel comments in 640bff9 |
@@ -22,3 +22,4 @@ | |||
Dataset loading utilities <datasets/index.rst> | |||
modules/scaling_strategies.rst | |||
modules/computational_performance.rst | |||
model_persistence.rst |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I'm not sure about this positioning. For example, after (or within) model selection and evaluation seems more coherent.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
+1
For the sake of consistency, I'd rather avoid the use of "you": we don't address the reader directly in the rest of the doc. Besides that +1 for merge once @jnothman 's comments have been taken into account. |
Fixed by #3317 |
Fix for issue #1332