Summary

mypy shows some issues in LightGBM's Python package.

mypy --ignore-missing-imports python-package/

python-package/lightgbm/compat.py:12: error: Name 'Series' already defined (possibly by an import)
python-package/lightgbm/compat.py:17: error: Name 'DataFrame' already defined (possibly by a

Not a high-priority at all, but it'd be more sensible for such a tutorial/testing utility corpus to be implemented elsewhere - maybe under /test/ or some other data- or doc- related module – rather than in gensim.models.word2vec.

Originally posted by @gojomo in RaRe-Technologies/gensim#2939 (comment)

Problem: the approximate method can still be slow for many trees
catboost version: master
Operating System: ubuntu 18.04
CPU: i9
GPU: RTX2080

Would be good to be able to specify how many trees to use for shapley. The model.predict and prediction_type versions allow this. lgbm/xgb allow this.

Is your feature request related to a problem? Please describe.
Currently, there are services that secure website from automation tools like ferret. Some of them send 405 in response to the DOCUMENT function call that make a ferret script fail with an error even though a page is available (not the original page, but usually a page with the captcha).

Describe the solution you'd like
It

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

Is your feature request related to a problem? Please describe.
The TimeSeriesForestCLassifier computes the importance curve for each of the extracted features in each time index. However, as the authors point out "different time indices are associated with different numbers of intervals", and, in particular, "the indices in the middle have more intervals than the indices on the edges of the t