Alpha-automl

------------------
* Add support for time-series forecasting.
* Add support for semi-supervised classification.
* Add wrappers for HuggingFace and fastText.
* Add image encoders.
* Add datetime encoders.

------------------
* Add support for non-numeric features (e.g. categorical, datetime).
* Add support for PipelineProfiler.
* Add a encoder and decoder of labels for classification tasks.
* Implement a `Pipeline` class.

------------------
* Allow to add xgboost and lightgbm primitives on the fly.
* Add support for numeric datasets.
* Build pipelines using Sklearn infrastructure.

How to release a new version

* On `devel` branch:
* `git pull` to make sure everything is in sync with remote origin.
* Change the version in `alpha_automl/__init__.py` to the new version, e.g., `2.0.0` (using the format MAJOR.MINOR.PATCH).
* In `CHANGELOG.md`, change the first version, e.g. `2.0.0.dev0 (yyyy-mm-dd)` to the to-be-released version and date.
* Commit with message `Bump version for release`.
* `git push`

* On `main` branch:
* `git pull` to make sure everything is in sync with remote origin.
* Merge `devel` into `main` branch: `git merge devel`
* `git push`
* Release a package to PyPI:
* `rm -rf dist/`
* `python setup.py sdist bdist_wheel`
* `twine upload dist/*`
* Create a tag for the new version, `git tag <tag_name>` and push it `git push origin <tag_name>`

* On `devel` branch:
* `git merge main` to make sure `devel` is always on top of `main`.
* Change the version in `alpha_automl/__init__.py` appending `.dev0` to the future version, e.g. `2.1.0.dev0`.
* Add a new empty version on top of `CHANGELOG.md`, e.g. `2.1.0.dev0 (yyyy-mm-dd)`.
* Commit with message `Bump version for development`.
* `git push`