Tools to manipulate energy time-series and contracts, and to perform forecasts.
Project description
enda
What is it?
enda is a Python package that provides tools to manipulate timeseries data in conjunction with contracts data for analysis and forecasts.
Its main goal is to help Rescoop.eu build various applications, such as short-term electricity load and production forecasts, specifically for the RescoopVPP project. Hence some tools in this package perform TSO (transmission network operator) and DNO (distribution network operator) data wrangling for several European countries, as well as weather data.
Main Features
Here are some things enda does well:
- Provide robust machine learning algorithms for short-term electricty load (and soon production) forecasts, developed by Enercoop and originally based on Komi Nagbe's thesis (http://www.theses.fr/s148364).
- Manipulate contracts data coming from your ERP and turn it into timeseries you can use for analysis, visualisation and machine learning.
- Timeseries-specific detection of missing data, like time gaps and frequency changes.
- Date-time feature engineering robust to timezone hazards.
Where to get it
The source code is currently hosted on GitHub at: https://github.com/enercoop/enda
Binary installers for the latest released version are available at the Python Package Index (PyPI) (for now not on Conda.
# PyPI
pip install enda
How to get started ?
Check out the guides : https://github.com/enercoop/enda/tree/main/guides .
Hard dependencies
- Pandas - the main dataframe manipulation tool for python, advanced timeseries management included.
- Pandas itself has hard and optional dependencies, checkout https://pandas.pydata.org/pandas-docs/stable/getting_started/install.html .
Optional dependencies
Optional dependencies are used only for specific methods. Enda will give an error if the method called requires a dependency that is not installed.
Enda can work with some machine learning "backends" :
- Scikit-learn
- H2O - an efficient machine learning framework You can also easily implement your own ml-backend by implementing enda's ModelInterface.
Other optional dependencies :
License
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.