Bump certifi from 2020.6.20 to 2020.11.8

See merge request !160

Bump scipy from 1.5.3 to 1.5.4

See merge request !158

Bump packaging from 20.4 to 20.7

See merge request !157

Bump mlxtend from 0.17.3 to 0.18.0

See merge request !155

Bump importlib-metadata from 2.0.0 to 3.1.0

See merge request !154

Bump attrs from 20.2.0 to 20.3.0

See merge request !153

Bumps [certifi](https://github.com/certifi/python-certifi) from 2020.6.20 to 2020.11.8.
- [Release notes](https://github.com/certifi/python-certifi/releases)
- [Commits](https://github.com/certifi/python-certifi/compare/2020.06.20...2020.11.08)

Bumps [scipy](https://github.com/scipy/scipy) from 1.5.3 to 1.5.4.
- [Release notes](https://github.com/scipy/scipy/releases)
- [Commits](https://github.com/scipy/scipy/compare/v1.5.3...v1.5.4)

Bumps [packaging](https://github.com/pypa/packaging) from 20.4 to 20.7.
- [Release notes](https://github.com/pypa/packaging/releases)
- [Changelog](https://github.com/pypa/packaging/blob/master/CHANGELOG.rst)
- [Commits](https://github.com/pypa/packaging/compare/20.4...20.7)

Bumps [mlxtend](https://github.com/rasbt/mlxtend) from 0.17.3 to 0.18.0.
- [Release notes](https://github.com/rasbt/mlxtend/releases)
- [Commits](https://github.com/rasbt/mlxtend/compare/0.17.3...0.18.0)

Bumps [importlib-metadata](https://github.com/python/importlib_metadata) from 2.0.0 to 3.1.0.
- [Release notes](https://github.com/python/importlib_metadata/releases)
- [Changelog](https://github.com/python/importlib_metadata/blob/master/CHANGES.rst)
- [Commits](https://github.com/python/importlib_metadata/compare/v2.0.0...v3.1.0)

Bumps [attrs](https://github.com/python-attrs/attrs) from 20.2.0 to 20.3.0.
- [Release notes](https://github.com/python-attrs/attrs/releases)
- [Changelog](https://github.com/python-attrs/attrs/blob/master/CHANGELOG.rst)
- [Commits](https://github.com/python-attrs/attrs/compare/20.2.0...20.3.0)

Rolling rework

See merge request !150

absolutly pandas conform tested - forward also works like pandas forward-hack, center is also tested

fixed constants detection. -there was the famous `ramp-up` error, because of the laggy implementation of pd.rolling ;)