search

Chicago / food-inspections-evaluation

This repository contains the code to generate predictions of critical violations at food establishments in Chicago. It also contains the results of an evaluation of the effectiveness of those predictions.
http://chicago.github.io/food-inspections-evaluation/
Other
410 stars 130 forks source link

What is the actual operational product #63

Closed fgregg closed 9 years ago

fgregg commented 9 years ago

It seems like the final operational product should be some sort of prioritized list, but I don't see any code to generate anything like that. How does the model get turned into that product?

geneorama commented 9 years ago

The predictions are attached to the data in the 30 script. https://github.com/Chicago/food-inspections-evaluation/blob/master/CODE/30_glmnet_model.R#L123

The results are delivered as a list of food establishments with their corresponding score, just as it is shown in this evaluation period. However, this work represents a snapshot in time that was used to evaluate the efficacy of the model, and it is not intended to be an ongoing real time list.

fgregg commented 9 years ago

This repo does not represent an ongoing effort?

So, this: https://twitter.com/ChicagoCDO/status/598951252307922944

is not happening?

fgregg commented 9 years ago

Now i understand that this repo contains the current model and is aimed at improving that model. Noted that in the README that's in my PR.