cobra

cobra copied to clipboard

Implementation for #126: supporting evaluation & forward feature selection for custom metrics (e.g. lift)

4

====> **Do not merge yet!** See below for explanation.

sandervh14

Tuning classification model on different metrics (lift, recall, precision,...)

1

# Tuning classification model on different metrics (lift, recall, precision,...) now a classification cobra model can only be tuned on AUC ## Task Description This issue will...

hendrikdewinter8

Warn user when trying to preprocess unsupported datatypes

2

I often get questions about the exotic errors thrown when users call Cobra's preprocessor. The error messages are too exotic for developers to understand that the datatypes they are passing...

sandervh14

Raise warning when categorical variable left unprocessed

2

Add a clear warning if categorical variable is returned untouched after preprocessing (no significant categories to keep).

sborms

I would like to append the model pipeline dict with relevant preprocessor pipelines. Some kind of "export model for scoring" possibility. The model.serialize JSON would then only contain the prepocessor...

PietAgoras

Make variable naming (and other) in plots customizable

1

Make names of variables, titles, axes, ... in plots maximally customizable.

sborms

When only a single category is put into Other, it makes more sense to keep the naming of that category.

sborms

Preprocessing - improve additive smoothing in target encoder

2

# Preprocessing: improve additive smoothing in target encoder ## Task Description Additive smoothing in the target encoder prevents possible overfitting, but is disabled by default, with the default weight=0 parameter...

sandervh14

Documentation improvements to reap: - Create a GitHub Action such that whenever we push to master, the Sphinx docs files are automatically built and the cobra.io website is recreated -...

JanBenisek

Unexpected bin limit rounding

1

While reviewing a pull request, I tested the below method with some extra things. I noticed this: ``` @pytest.mark.parametrize("n_bins, auto_adapt_bins, data, expected", [ (2, False, # Variable contains floats, nans...

sandervh14