search

insight-lane / crash-model

Build a crash prediction modeling application that leverages multiple data sources to generate a set of dynamic predictions we can use to identify potential trouble spots and direct timely safety interventions.
https://insightlane.org
MIT License
112 stars 40 forks source link

Feature configuration #225

Closed j-t-t closed 5 years ago

j-t-t commented 5 years ago

This task standardizes features so that all of the features can be defined in the city's config file, and all steps of the pipeline read from the config file. -Updated all the config files for demo cities to run with the new feature set up -Added a config file for somerville, which I was using for testing -Created a script that will batch geocode addresses. This lives under tools/geocode_batch.py. Although it shouldn't be part of the pipeline, it was a useful tool for me, since Somerville's crash data didn't include latitude/longitude -Created a script in tools/update_configs.py to be able to add new features at the command line, instead of having to modify the contents of the file manually. At the moment, features can only be added (instead of modified or deleted), but a list of config files can be given to all be updated.

codecov[bot] commented 5 years ago

Codecov Report

Merging #225 into master will increase coverage by 0.32%. The diff coverage is 60.71%.

@@            Coverage Diff            @@
##           master    #225      +/-   ##
=========================================
+ Coverage   54.18%   54.5%   +0.32%     
=========================================
  Files          32      34       +2     
  Lines        3191    3315     +124     
=========================================
+ Hits         1729    1807      +78     
- Misses       1462    1508      +46