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

Point based features #165

Closed j-t-t closed 5 years ago

j-t-t commented 5 years ago

Adding the point-based features to the pipeline. This includes updating initialize_city/pipeline, and making sure that point-based features get pulled into the model. Before, features were processed if you ran standardize_point_data, but the pipeline didn't run standardize_point_data, and the new features weren't included anywhere other than the inters/non_inters maps

Also added some tests that didn't make it into the previous point-based features PR

codecov[bot] commented 5 years ago

Codecov Report

Merging #165 into master will increase coverage by 1.17%. The diff coverage is 30%.

@@            Coverage Diff             @@
##           master     #165      +/-   ##
==========================================
+ Coverage    38.7%   39.88%   +1.17%     
==========================================
  Files          26       26              
  Lines        2651     2678      +27     
==========================================
+ Hits         1026     1068      +42     
+ Misses       1625     1610      -15

terryf82 commented 5 years ago

I'm good to merge this in but there's a conflict now in src/data/make_dataset.py (possibly as a result of the centerpoints PR I just merged?)

j-t-t commented 5 years ago

Since @terryf82 said it was fine, I'm merging this since I've fixed the conflicts