# loosely-policies-analytics

## Folders

- `analysis/`
    - Contains data analysis + offline and in-situ training code.
    - More info in `analysis/README.md`.
- `simulation/`
    - Contains the simulator source code and script to run the experiments from the paper.
- `slides_recap/`
    - Just backup slides. Nothing interesting.

## Experiments

### In-situ

Simulations are carried using previous CCGrid2022 data.
These simulations are done in the file `analysis/in-situ.R`.
The idea is to use a single policy each day (round-robin) until the model performance reaches 80%.
For that, a day corresponds to a single simulation result from CCGrid2022 with a particular policy.
Since we have 200 runs per policy from CCGrid2022, a single run result can be cherry-pick to simulate one day.

### Offline

First, models are trained and predictions are generated.
This is done in `analysis/offline.R`.
Predictions are stored in `analysis/inputs/input_*.csv`.
Then, simulations are executed with those policy predictions as inputs.
This is done in `simulations/results/paper.sh`.