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
113 stars 40 forks source link

Points-based schema, updated notebooks #151

Closed j-t-t closed 5 years ago

j-t-t commented 5 years ago

I want to get this merged so that @shreyapandit can base her upcoming standardization tests on it. It has a bunch of different things, but the main thing is adding generic point-based data to the maps. (See note below that we're not actually using the point-based data in the model yet)

A couple of things in here: -Fixed a bug that didn't populate the width from osm since the python3 conversion -Added a width_per_lane feature -Added a standardize_point_data script, and accompanying schema/instance file -Made standardize_util.py for things that were either duplicate, or might want to be duplicate. Added a test file for this -Updated create_segments.py to populate the point data into the inters/non_inters geojson and json files -Added a data source to the Cambridge config file. This was just for testing purposes on getting the point-based data working. I haven't done the update to add it to the vz_predict file yet. -Moved all the python2 notebooks into a directory named python2 -Converted vision_zero_analysis.ipynb and general_analysis.ipynb to python3

j-t-t commented 5 years ago

I should add that the test coverage goes down a smidge, from 38.12 on master to 37.8. Will be writing test for standardize_point_data.py but wanted to get the functionality merged into master first