Surprise GridSearchCV with Pipeline and custom Transformers

[agatr]

Description

Is it possible to use Pipeline with Surprise GridSearchCV? I've tried to create a pipeline with custom Transformers (for transforming data frame into Surprise Dataset), but the steps within Pipeline don't seem to be connected. My code:

`
def run_gs(model, data, grid_params):
pipeline = Pipeline([(('Reader Transformer', ReaderTransformer()),
('Model', model)])
grid_search = GridSearchCV(pipeline, grid_params, cv=3)
grid_search.fit(data)
return self.grid_search

`

Alternatively, is it possible to use Surprise model with 'normal' sklearn GridSearchCV? I've tried that as well, but with no luck either.

Versions

macOS-10.16-x86_64-i386-64bit
Python 3.8.5 (default, Sep 4 2020, 02:22:02)
[Clang 10.0.0 ]
surprise 1.1.1

[NicolasHug]

Hi @agatr , sorry, sklearn and surprise aren't really compatible with one-another. I assume the Pipeline you're referring to is from sklearn, but there's no support for surprise with it.