Deploy county new-cases forecasting model to production

[isaacmg]

As an organization we want to inform public policy makers and residents if their county could be at increased risk for an outbreak. In order to do this we need to have daily updated results on new data and a simple dashboard to display predicted cases along with the CI for a specific county. Targeted completion

• Run experiments with enhanced evaluation metrics #43 Run experiments with enhanced evaluation metrics
• Formal report detailing transfer results #52 Determine whether to use transfer and best hyper-parameters
• Report to select the "best models" #53 Select best models
• Have epidemiologist verify candidate models
• Test models on new data (July 10th+)
• Add inference mode to flow-forecast
• Create cloud function to save county CSV to bucket #61 Create cloud function to partition new cases by county
• Create Docker container for serving flow-forecast models and deploy.
• Create Airflow DAG that runs model(s) daily and persists results.