Home

Awesome

DS Build Week

Starter code to deploy your machine learning model as an API on Heroku. You can deploy a baseline in 10 minutes.

Tech stack

Getting started

Create a new repository from this template.

Clone the repo

git clone https://github.com/YOUR-GITHUB-USERNAME/YOUR-REPO-NAME.git

cd YOUR-REPO-NAME

Install dependencies

pipenv install --dev

git add Pipfile.lock

git commit -m "Add Pipfile.lock"

Activate the virtual environment

pipenv shell

Launch the app

uvicorn app.main:app --reload

File structure

.
└── app
    ├── __init__.py
    ├── main.py
    ├── routers
    │   ├── __init__.py
    │   └── predict.py
    └── tests
        ├── __init__.py
        ├── test_main.py
        └── test_predict.py

app/main.py is where you edit your app's title and description, which are displayed at the top of the your automatically generated documentation. This file also configures "Cross-Origin Resource Sharing", which you shouldn't need to edit.

app/routers/predict.py defines an API endpoint /predict which currently returns random predictions. In a notebook, train your model and pickle it. Then in this source code sfile, unpickle your model and edit the predict function to return real predictions.

When your API receives a POST request, FastAPI automatically parses and validates the request body JSON, using the Item class attributes and functions. Edit this class so it's consistent with the column names and types from your training dataframe.

app/tests/test_*.py is where you edit your pytest unit tests.

More instructions

Install additional packages

pipenv install PYPI-PACKAGE-NAME

Launch a Jupyter notebook

jupyter notebook

Run tests

pytest

Run linter

flake8

calmcode.io videos - flake8

Deploying to Heroku

Prepare Heroku

heroku login

heroku create YOUR-APP-NAME-GOES-HERE

heroku git:remote -a YOUR-APP-NAME-GOES-HERE

Deploy to Heroku

git add --all

git commit -m "Deploy to Heroku"

git push heroku main:master

heroku open

Deactivate the virtual environment

exit