Skip to content

antongiannis/prometheusml

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

14 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Shows PrometheusML logo

Code style: black Contributor Covenant MIT License

PrometheusML Core is an open-source no-code platform for building machine learning and deep learning models, developed by yaiLab.

What exactly is PrometheusML and PrometheusML Core?

There are two versions of PrometheusML:

  • The open-source PrometheusML Core
  • The cloud data science assistant PrometheusML

PrometheusML Core allows anyone and everyone to build machine learning models in an interactive way through a UI, whilst PrometheusML is a cloud data science assistant that helps users build specialised machine learning models fast in physics-intense fields.

Is it free?

Yes, PrometheusML Core is completely free. You can use PrometheusML Core for free by following the installation steps in this repo.

Alternatively, to try out the cloud data science assistant PrometheusML on a free trial go to our website and press on Try it now!. You can also find more info on the data science assistant PrometheusML here.

How does PrometheusML Core work?

PrometheusML Core will help you build an entire machine learning pipeline without writing a single of code by guiding you through the entire process.

1. Select regression or classification template

template_selection.mp4

2. Data upload and evaluation

upload_exploration.mp4

3. Feature engineering

feature_selection.mp4

4. Algorithm selection

algorithm_selection.mp4

5. Model validation and deployment

model_validation.mp4

6. Making predictions

prediction.mp4

Canonical source

The canonical source of PrometheusML where all development takes place is hosted on GitLab.com.

Table of contents

Install PrometheusML

Install PrometheusML with the cloud native Docker Compose tool.

Important consideration! - The default Docker Compose configuration is not intended for production. It creates a proof of concept (PoC) implementation where all PrometheusML services are placed into a cluster.

Follow the next steps to quickly install and take advantage of PrometheusML:

1. Install Docker Desktop

You need to have Docker Compose installed on your computer. You can easily install it by taking advantage of the Docker Desktop installation. To install Docker Desktop go to their website.

2. Clone repository

Open your:

  • PowerShell for Windows
  • Terminal for Mac or Linux

... and type the following command:

git clone https://gitlab.com/yailab/prometheusml.git && cd prometheusml

3. Launch PrometheusML

Type some more commands in your PowerShell/Terminal as follows:

# Build the necessary image
docker compose build
# Run the multi-container application
docker compose up -d --remove-orphans

Note: You can stop PrometheusML by typing into your PowerShell/Terminal the command docker compose down.

4. You are done!

You can now access PrometheusML through the browser of your choice by typing the address localhost:5000.

5. Set up your username and password and get going!

You can create a new user by going to the registration page of your locally launched PrometheusML instance.

The created user comes preloaded with two templates, a general regression and a classification one. You can check out the tutorials videos that will guide you through the entire process of building a regression and a classification machine learning model.

Enjoy building machine learning models!

Documentation

The documentation of PrometheusML is under active development!

You can start with the following tutorial videos for a quick introduction:

Problem Description Dataset source Tutorial video
Regression Predict concrete strength Kaggle Youtube

Contributing to the documentation benefits everyone who uses PrometheusML. We encourage you to help us improve the documentation, and you don’t have to be an expert to do so! In fact, there are sections of the docs that are worse off after being written by experts. If something in the docs does not make sense to you, updating the relevant section after you figure it out is a great way to ensure it will help the next person.

Discussion on AI ethics

With great power comes great responsibility.

At yaiLab we aim to make AI accessible to everyone and believe in responsible AI use. We are super excited about AI’s ability to help humanity with its biggest problems, and committed to Ethical and Responsible AI.

The journey to responsible and accessible AI includes transparency and open inclusive discussion. Review our AI Ethics Policy and join our Discord channel to be part of the conversation for the future of responsible AI.

Contributing to PrometheusML

PrometheusML is an open source project, and we are very happy to accept community contributions. Please refer to the Contributing guide for more details.

Code of Conduct

Please treat others with respect and follow the guidelines articulated in the Community Code of Conduct.

Versioning

This project is maintained under the Semantic Versioning guidelines.

See the Releases section of our PrometheusML project for changelogs for each release version of PrometheusML.

Copyright and license

Code and documentation copyright 2022 yaiLab, Ltd.

See the LICENSE file for licensing information as it pertains the files in this repository.

Code released under the Apache 2.0 license.

Community

About

An end-to-end data-science assistant.

Resources

License

Code of conduct

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 51.2%
  • HTML 43.7%
  • JavaScript 3.6%
  • CSS 0.8%
  • Dockerfile 0.5%
  • Mako 0.1%
  • Shell 0.1%