Antoni Baum
Antoni Baum
This PR adds a new `display_id` argument to `tqdm_notebook` class. If specified, then the progress bar will be displayed in the IPython display with said id. If left unspecified, a...
### pycaret version checks - [X] I have checked that the issue still exists on the latest versions of the docs [here](https://pycaret.gitbook.io/docs/) ### Location of the documentation develop ### Documentation...
As explained in https://github.com/automl/ConfigSpace/issues/104, `None` cannot be used as a possible value because CS uses it to mark disabled hyperparameters. This can cause issues when `None` is a possible value...
We are currently converting to Pandas before initialising the DMatrix. We should consider using Arrow instead to avoid unnecessary copies. XGBoost has Arrow support - https://github.com/dmlc/xgboost/pull/7512
When `predict` is called on a distributed `RayDMatrix` that was already used for training, it will fail as `combine_data` requires `sharding` to be one of `RayShardingMode.INTERLEAVED` or `RayShardingMode.BATCH` but that...
`groups` in `DMatrix` cannot be currently set, limiting ranking functionality. Should be added at some point.
When a Modin object is created from an existing Pandas or Numpy object, an exception is raised: ``` E ray.exceptions.RayTaskError(AttributeError): ray::_RemoteRayXGBoostActor.train() (pid=969329, ip=172.31.43.110) E File "python/ray/_raylet.pyx", line 535, in ray._raylet.execute_task...
Signed-off-by: Antoni Baum ## Why are these changes needed? We always convert to numpy and then back to dataframe in `LightGBMPredictor`, and try to infer dtypes in between. This is...
### What happened + What you expected to happen XGBoost and LightGBM have special support for categorical features. If during training a pandas dataframe with Categorical columns is passed, then...
Signed-off-by: Antoni Baum If we cannot schedule communication actors on the driver node, relax the requirement to include any node.