Ktrain

New:
- N/A

Changed
- added `class_weight` parameter to `lr_find` for imbalanced datasets
- removed pins for `cchardet` and `scikitlearn` from `setup.py`
- added version check for `eli5` fork
- removed `scipy` pin from `setup.py`
- Allow TensorFlow 2.3 for Python 3.8
- Request manual installation of `shap` in `TabularPredictor.explain` instead of inclusion in `setup.py`

Fixed:
- N/A

New:
- N/A

Changed
-N/A

Fixed:
- include metrics check in `is_classifier` function to support with non-standard loss functions

New:
- N/A

Changed
-N/A

Fixed:
- Ensure transition to `YTransform` is backwards compatibility for `StandardTextPreprocessor` and `BertPreprocessor`

New:
- N/A

Changed
- `TextPreprocessor` instances now use `YTransform` class to transform targets
- `texts_from_df`, `texts_from_csv`, and `texts_from_array` employ the use of either `YTransformDataFrame` or `YTransform`
- `images_from_df`, `images_from_fname`, `images_from_csv`, and `imagas_from_array` use `YTransformDataFrame` or `YTransform`
- Extra imports removed from PyTorch-based `zsl.core.ZeroShotClassifier` and `summarization.core.TransformerSummarizer`. If necessary,
both can now be used without having TensorFlow installed by installing ktrain using `--no-deps` and importing these modules using
a method like [this](https://stackoverflow.com/a/58423785).

Fixed:
- N/A

New:
- N/A/

Changed
- `NERPredictor.predict` was changed to accept an optional `custom_tokenizer` argument

Fixed:
- N/A

New:
- N/A

Changed
- N/A

Fixed:
- added missing `num_classes` argument to `to_categorical`