search

antoinecarme / pyaf

PyAF is an Open Source Python library for Automatic Time Series Forecasting built on top of popular pydata modules.
BSD 3-Clause "New" or "Revised" License
459 stars 72 forks source link

User Guide #1

Open antoinecarme opened 7 years ago

antoinecarme commented 7 years ago

At least

  1. API documentation in Python code
  2. Some examples
antoinecarme commented 7 years ago

Added some doc/notebook describing the use of exogenous variables.

https://github.com/antoinecarme/pyaf/blob/master/docs/PyAF_Exogenous.ipynb

antoinecarme commented 7 years ago

need a similar doc with hierarchical and grouped time series.

antoinecarme commented 7 years ago

TODO : Document the algorithmic details of PyAF.

Done :

https://github.com/antoinecarme/pyaf/issues/35

https://github.com/antoinecarme/pyaf/blob/master/docs/PyAF_Algorithmic_Aspects.ipynb

antoinecarme commented 1 year ago

Probably, there will be no user guide.

Expect jupyter notebooks on specific aspects when needed or a new feature is implemented.

It is more suitable to have jupyter notebooks with detailed examples on how to use PyAF for such or such task.

Theoretical aspects are better covered in text books. For PyAF, the reference is still this one (please buy the book, it is constantly updated and improving) :

Forecasting: Principles and Practice (3rd ed) Rob J Hyndman and George Athanasopoulos https://otexts.com/fpp3/ Chinese translation : https://otexts.com/fppcn/