DOC improve conventions used in MAPE #30012
Merged
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
glemaitre
reviewed
Oct 7, 2024
sklearn/metrics/_regression.py
Outdated
Comment on lines
333
to
336
| MAPE output is a relative measure of error that does not have an upper bound, unlike typical percentages. | ||
| It can return values greater than 1 (e.g., 2 representing a 200% error). For example, an error of 1 | ||
| represents a 100% deviation from the true value. Read more in the | ||
| :ref:`User Guide <mean_absolute_percentage_error>`. |
There was a problem hiding this comment.
The first sentence is incorrect: typical percentage can exceed 100%. Also you need to make sure to not have more than 88 characters per line and no trailing space.
This is the reason for the linter CI to raise error.
Here is my suggestion to keep the docstring short.
Suggested change
| MAPE output is a relative measure of error that does not have an upper bound, unlike typical percentages. | |
| It can return values greater than 1 (e.g., 2 representing a 200% error). For example, an error of 1 | |
| represents a 100% deviation from the true value. Read more in the | |
| :ref:`User Guide <mean_absolute_percentage_error>`. | |
| Note that we are not using the common "percentage" definition: the percentage | |
| in the range [0, 100] is converted to a relative value in the range [0, 1] | |
| by dividing by 100. Thus, an error of 200% corresponds to a relative error of 2. | |
| Read more in the :ref:`User Guide <mean_absolute_percentage_error>`. |
doc/modules/model_evaluation.rst
Outdated
Comment on lines
2463
to
2464
| For example, if the true value is 1 and the predicted value is 2, the MAPE will be 1 (or 100% error). | ||
| Similarly, if the true value is 1 and the predicted value is 3, the MAPE will be 2 (or 200% error). |
There was a problem hiding this comment.
We should not document it here. Instead we should amend the note below (this is currently incorrect).
You can reuse part of my other suggestion to amend it.
There was a problem hiding this comment.
Sure @glemaitre, I will implement this fix.
glemaitre
reviewed
Oct 8, 2024
glemaitre
approved these changes
Oct 8, 2024
|
Thanks @Rachit23110261 |
BenJourdan
pushed a commit
to gregoryschwartzman/scikit-learn
that referenced
this pull request
Oct 11, 2024
Co-authored-by: Guillaume Lemaitre <guillaume@probabl.ai>
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.
Reference Issues/PRs
Fixes #30008.
What does this implement/fix? Explain your changes.
This pull request addresses an issue in the documentation related to the Mean Absolute Percentage Error (MAPE) formula. The following changes have been made:
These changes aim to improve user understanding and align the documentation with the intended use of the MAPE metric.
Any other comments?
Please feel free to reach out if there are any questions or if further adjustments are required. I appreciate your time and attention to this contribution.