Train a model, based on date and various other parameters, and get predictions on utilization.
Requirements
- You need to have Docker installed
Run in root folder,
cp .env.example .env
docker-compose build && docker-compose up -d
Login to the container,
docker exec -it ai /bin/bash -c "TERM=$TERM exec bash"
To check it works,
python predict.py 1
You should see, something like,
[[ 0 0 0 0 0 0 0 0 75 76 78 79 82 83 86 83 82 79 78 75 73 0 0 0]
[ 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0]
[ 0 0 0 0 0 0 0 0 66 68 69 71 73 75 77 75 73 70 68 65 64 0 0 0]]