data-mining

Summary

mypy shows some issues in LightGBM's Python package.

mypy \
    --exclude='python-package/compile/|python-package/build' \
    --ignore-missing-imports \
    python-package/

python-package/lightgbm/compat.py:12: error: Name 'Series' already defined (possibly by an import)
python-package

It would be great to have FBeta, F2, or F0.5 metrics to be implemented without the need for a custom metric class defined by user.

catboost version: 0.26

The official instructions say to use joblib for pickling PyOD models.

This fails for AutoEncoders, or any other TensorFlow-backed model as far as I can tell. The error is:

>>> dump(model, 'model.joblib')
...
TypeError: can't pickle _thread.RLock objects

Note that it's not sufficient to save the underlying Keras S

It's been awhile since I updated e2e tests and there are some of them that are filing (most of them are related to examples).

Also, we need to add e2e tests that cover headers and cookies for both drivers.

Section 2 of the forecasting notebook explains the main classes of forecasters.

Since we wrote this, we have introduced and extended the all_estimators registry lookup which can be used to list all forecasters, and the all_tags lookup which can list all forecaster tags (both in the registry module).

I think it would be a good idea to add usage of these two utility functions at the star

What's your use case?
In other words, what's your pain point?

Variable names and their icons are shown as vertical header. This

• is ugly,
• doesn't show the selection properly,
• doesn't allow sorting by variable names,
• doesn't allow selection by dragging across a range of variables (though one can drag across rows in the table itself),
• and possibly something else.

<img wi