-
Follow the instructions in ../hyperparameters/ to train and upload and model to S3.
-
Create and activate a virtual environment (note you must create a fresh virtual environment to use zappa), e.g.
python -m virtualenv venv && source venv/bin/activate
-
Install the requirements:
pip install -r requirements.txt
-
Run
zappa init
and accept all the defaults -
Run
zappa deploy
. The output of this command (orzappa status
) includes the publicamazonaws.com
URL of your deployed flask application. It will look something likehttps://abcdef123.execute-api.us-east-1.amazonaws.com/dev/
-
Visit
your_amazonaws_url/predict?feature_1=3&feature_2=6
to get a prediction.
modelserver
Folders and files
Name | Name | Last commit date | ||
---|---|---|---|---|
parent directory.. | ||||