Open amueller opened 4 years ago
From the point of view of putting a model pipeline into production, only the pipe.predict(X)
or pipe.predict_proba(X)
are essential. Otherwise said, at prediction time you don't have y
.
In this regard, like @amueller , I don't see the motivation for trans_modify
.
As for transforming y
, some fairness related methods augmenting the data do that.
cc @GaelVaroquaux
Coming back to SLEP 1 I don't see / remember the need for trans_modify. I'm now not sure why we need this. The motivation the SLEP gives is
I think that makes it much harder and I don't think it's as necessary as the training-time version.
Similarly I'm not sure I understand the motivation for
partial_fit_modify
.My main motivation in this would be to distinguish training time and test time, and that only requires a new method that basically replaces
fit_transform
within a pipeline or other meta-estimator.Not sure I like
fit_modify
for that. My thoughts right now would beforward
or maybefit_forward
(though that sounds too much like feed-forward - how aboutfeed
lol).modify
sounds like an in-place operation to me. D3M usesproduce
which is quite generic but might work (probablyfit_produce
,produce
is their version of bothpredict
andtransform
)