Skip to content

Repository for the "Predicting Armed Conflict with Protest Data" project

Notifications You must be signed in to change notification settings

prio-data/ViEWS_protest_data

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

23 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

ViEWS_protest_data

Repository for the "Predicting Armed Conflict with Protest Data" project.

The repository contains (1) a query-set and data management notebook including a complete set of calls to fetch and transform the features directly from the ViEWS database. While access to the database is not publicly available, we store the transformed features for each model as a list of dictionaries. A separate Jupyter notebook contains the main analysis and is divided into three parts including 1) the training and prediction of each specified model objects and 2) the evaluation of the predictions which allows to replicate each figure presented in this article. Note that the default setting of the notebook runs the analysis for conflict incidence. To receive the results for conflict onset and the robustness tests, the user should set run_outcome equals to 'onset', 'onset_np' or 'incidence_np' accordingly. The analysis partly relies on functions which are defined in separate python files. A list naming the features included in M0 - M9 is available as YAML file.

About

Repository for the "Predicting Armed Conflict with Protest Data" project

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published