https://github.com/alexliap/sk_serve

Deployment of a Scikit-Learn model and it's column transformations made easy.
https://github.com/alexliap/sk_serve

machine-learning mlops model-deployment scikit-learn

Last synced: 27 days ago
JSON representation

Deployment of a Scikit-Learn model and it's column transformations made easy.

• Host: GitHub
• URL: https://github.com/alexliap/sk_serve
• Owner: alexliap
• License: mit
• Created: 2024-08-03T15:13:07.000Z (3 months ago)
• Default Branch: master
• Last Pushed: 2024-09-23T17:00:26.000Z (about 1 month ago)
• Last Synced: 2024-09-27T20:05:17.933Z (about 1 month ago)
• Topics: machine-learning, mlops, model-deployment, scikit-learn
• Language: Python
• Homepage: https://alexliap.github.io/sk_serve/
• Size: 2.66 MB
• Stars: 0
• Watchers: 2
• Forks: 0
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# sk-serve

![deploy on pypi](https://github.com/alexliap/sk_serve/actions/workflows/publish_package.yaml/badge.svg)

![PyPI Version](https://img.shields.io/pypi/v/simple-serve?label=pypi%20package)

![Downloads](https://static.pepy.tech/badge/simple-serve)

Deployment of a Scikit-Learn model and it's column transformations with a single endpoint. Only a traditional Scikit-Learn model is needed and a ColumnTransformer object (sklearn.compose) to deploy your model. Validation of input data is also supported with pydantic.

### Usage

See the [Examples](https://github.com/alexliap/sk_serve/tree/master/examples) section of the repository.

### Installation

The package exists on PyPI (with a different name though) so you can install it directly to your environment by running the command

```terminal

pip install simple-serve

```

### Dependencies

* pydantic

* fastapi

* pandas

* scikit-learn

Additional packages for development:

* pyright

* pre-commit

### Development

If you want to contribute you fork the repository and clone it on your machine

```terminal

git clone https://github.com/alexliap/sk_serve.git

```

And after you create you environment (either venv or conda) and activate it then run this command

```terminal

pip install -e ".[dev]"

```

That way not only the required dependencies are installed but also the development ones.

Also this makes it so that when you import the code to test it, you can do it like any other module but containing the changes you made locally.

Before you decide to commit, run the following command to reformat code in order to be in the acceptable style.

```terminal

pre-commit install

pre-commit run --all-files

```