/shiny-seshat

A scrubber for the Seshat Global History Databank

Primary LanguagePythonOtherNOASSERTION

DOI License: CC BY-NC-SA 4.0

Click here for downloadable releases of Shiny Seshat

Improved and analysis-ready

Shiny Seshat is a scrubbed derivative of the Seshat: Global History Databank featuring:

  • Imputation of missing values via the DataWig deep neural network
  • Numeric, temporally-resolved data points
  • Corrections of many human errors and typographical mistakes
  • And more!

Development setup

The program that scrubs the original Seshat datbank into Shiny Seshat is written in Python 3. If you wish to run it, first install these dependencies:

pip install numpy pandas datawig statsmodels hyperopt utm dill tqdm sklearn 

The process of fetching the original databank is automated. To download and begin scrubbing, simply run:

python scrub.py

Citation, Attribution & Licensing

If you wish to use Shiny Seshat in your work, please cite the following:

Shiny Seshat is a derivative work employing data from the Seshat Databank (seshatdatabank.info) under Creative Commons Attribution Non-Commercial (CC By-NC SA) licensing.

The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the official positions, either expressed or implied, of the Seshat Databank, its collaborative scholarly community, or the Evolution Institute.