[WIP] ENH Allow precomputed mask as input for MissingIndicator #13514
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Should this be marked MRG? |
|
Yes but it contains #13491 so it will be easier to review it when the previous PR is merged. |
|
Any update on this? The other PR was split up and merged, right? |
|
This is more complicated than expected. For dense array, the mask has the right shape but for sparse matrices, the mask is the mask of the data array, which is not enough to reconstruct the array. I'm closing it. I'll reopen later if I find a better way to do it. (the only use case it to avoid computing the mask twice in imputers with missing_indicator) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Allows to avoid recomputing the mask when it's already been computed by another estimator. For example, to stack a
MissingIndicatoron aSimpleImputeras being developed in #12583.I chose to add another possible value for the
missing_valuesparameter, and interpret X as the mask in that case. It's like metric='precomputed' in some estimators.I developed this PR on top of #13491 for convenience, so it contains unrelated changes for now. This is why I mark it as wip.