[WIP] ENH: Resample additional arrays apart from X and y #463
Conversation
glemaitre
changed the title
|
Hello @glemaitre! Thanks for updating the PR. Cheers ! There are no PEP8 issues in this Pull Request. 🍻 Comment last updated on August 29, 2018 at 09:59 Hours UTC |
|
Sampling extra arrays could be easy in the case of prototype selection. However, what would be a good and meaningful default when new sample weight need to be created. Right now, I created an |
|
Ups I forgot to ping @jnothman in my last comment |
Codecov Report
@@ Coverage Diff @@
## master #463 +/- ##
==========================================
- Coverage 98.92% 98.57% -0.36%
==========================================
Files 85 75 -10
Lines 5324 4633 -691
==========================================
- Hits 5267 4567 -700
- Misses 57 66 +9
Continue to review full report at Codecov.
|
There was a problem hiding this comment.
Btw, I don't think returning non-X,y will work with the current handling of Pipeline.fit's kwargs. We really need sample prop routing to handle that case. Currently, the handling would be unambiguous if one of:
- the resampler is the last step, in which case we return any additional sample props like weights
- the resampler is the second-last step, and there is no fit_param called
last_step_name__sample_weight, in which case we pass all sample props into the last step'sfit, I think.
Otherwise, it's unclear where to pass the returned sample_weight given that **fit_params intends to prescribe this at the time Pipeline.fit is called.
| y_resampled : ndarray, shape (n_samples_new,) | ||
| The corresponding label of `X_resampled`. | ||
| sample_weight_resampled : ndarray, shape (n_samples_new,) |
There was a problem hiding this comment.
I would rather have a dict of non-X,y returned. (Optionally? In scikit-learn I would rather this be mandatory so we don't need to handle both cases.)
| ``sample_weight`` was not ``None``. | ||
| idx_resampled : ndarray, shape (n_samples_new,) | ||
| Indices of the selected features. This output is optional and only |
There was a problem hiding this comment.
Do you mean the selected samples?
| Resampled sample weights. This output is returned only if | ||
| ``sample_weight`` was not ``None``. | ||
| idx_resampled : ndarray, shape (n_samples_new,) |
There was a problem hiding this comment.
Could you explain why this should be returned from fit_resample, rather than stored as an attribute?
There was a problem hiding this comment.
I think that it was some original design (before it was in scikit-learn). But actually it would be better to keep it as an attribute with the single fit_resample.
If I understand well and from what I could see, Pipeline does not support |
|
You're right |
glemaitre
force-pushed
the
master
branch
2 times, most recently
from
bbf2b12 to
513203c
Compare
chkoar
changed the title
glemaitre
force-pushed
the
master
branch
2 times, most recently
from
f1bc189 to
8f87307
Compare
glemaitre
force-pushed
the
master
branch
3 times, most recently
from
eae6c6b to
ffdde80
Compare
|
@glemaitre #460 is closed but #457 is still open and probably relevant. Could we close this PR in favor of new one in the future? It is two years old. |
4 participants
Implement the last point of #462 and should be merged after it.
Partially addressing #460