FIX: Allow pipeline
to handle fit
and transform
and allows adding tSNE
#3
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Outdated suggestions cannot be applied.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
Closes #4
What does this implement/fix? Explain your changes.
Currently, the pipeline feature does not allow users to insert tSNE dimensionality reduction algorithm into a pipeline. This is because it only allows transformers with the "transform" and either one of "fit" or "fit_transform" methods, and since tSNE only has the "fit_transform" method, it fails that sanity test and causes an error. This is done because by adding tSNE to pipeline it makes it essentially a single pass, however, a user should have the option of creating a single pass pipeline.
I fixed this by added a new sanity check, which checked that either "fit_transform" or both "fit" and "transform" are present, which removes this issue and allows users to add tSNE to their pipeline. Rather than an error, we now return a warning that an intermediate step does not have transform.
Any other comments?
I also changed a similar error message which ensured the last estimator in the pipeline may also contain "fit_transform"