Repository navigation
Separate pipeline_parameters from custom_hyperparameters - #2317
Conversation
…yperparameter ranges
bchen1116
left a comment
There was a problem hiding this comment.
Nice job, Parthiv! Left a few nits and testing suggestions.
dsherry
left a comment
There was a problem hiding this comment.
@ParthivNaresh this is really excellent! And comprehensive. I left a few code organization things, in particular moving the ValueError for skopt parameters sneaking into custom_parameters to a different location, but not much.
| self._frozen_pipeline_parameters = {} | ||
|
|
||
| parameters = copy.copy(self.pipeline_parameters) | ||
| custom_hyperparameters = copy.copy(self.custom_hyperparameters) |
There was a problem hiding this comment.
Why do a copy here? We copy parameters on the previous line because we then create a modified version where we add the pipeline-level parameters (time series config etc). But we don't do that for the custom hyperparameters, right?
There was a problem hiding this comment.
Ah thanks, initially I was considering modifying the custom_hyperparameters based on other criteria but forgot to change this back.
freddyaboulton
left a comment
There was a problem hiding this comment.
@ParthivNaresh Looks great to me! I left a minor comment that's similar to @dsherry `s suggestion but other than that this is awesome.
Fixes #2130
This PR deals with separating the
custom_hyperparametersargument from its current pipeline implementation toAutoMLSearchinstead. This is the first step before we replaceallowed_pipelineswithallowed_component_graphsand keep time series specifications withinproblem_configuration.Document comparing the differences between the previous implementation and this one can be found here.