Metrics as methods of models #64
Assignees
Comments
lars-reimann
added
enhancement 💡
This was referenced Mar 24, 2023
lars-reimann
added a commit
that referenced
this issue
Mar 24, 2023
Closes #64. ### Summary of Changes Metrics are now methods of classifiers and regressors. They also take a validation or test set as input now instead of two columns representing predicated and expected values. --------- Co-authored-by: lars-reimann <[email protected]>
lars-reimann
pushed a commit
that referenced
this issue
Mar 26, 2023
## [0.4.0](v0.3.0...v0.4.0) (2023-03-26) ### Features * better names for properties of `TaggedTable` ([#74](#74)) ([fee398b](fee398b)) * change the name of a `Column` ([#76](#76)) ([ec539eb](ec539eb)) * metrics as methods of models ([#77](#77)) ([bc63693](bc63693)), closes [#64](#64) * optionally pass type to column ([#79](#79)) ([64aa429](64aa429)), closes [#78](#78) * remove `target_name` parameter of `predict` ([#70](#70)) ([b513454](b513454)), closes [#9](#9) * rename `tagged_table` parameter of `fit` to `training_set` ([#71](#71)) ([8655521](8655521)) * return `TaggedTable` from `predict` ([#73](#73)) ([5d5f5a6](5d5f5a6))
|
🎉 This issue has been resolved in version 0.4.0 🎉 The release is available on:
Your semantic-release bot 📦🚀 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Is your feature request related to a problem?
In some sense metrics are a property of models (in connection with some data).
Desired solution
Think about whether it makes sense to have them as methods on models. This should be easy to implement once #60 is done.
Possible alternatives (optional)
No response
Screenshots (optional)
No response
Additional Context (optional)
If this gets implemented, #63 is no longer needed.
The text was updated successfully, but these errors were encountered: