Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/bitnulleins/autoDS
AutoML Web Frontend for automated Data Science
https://github.com/bitnulleins/autoDS
autods automl pycaret streamlit webapp
Last synced: 11 days ago
JSON representation
AutoML Web Frontend for automated Data Science
- Host: GitHub
- URL: https://github.com/bitnulleins/autoDS
- Owner: bitnulleins
- License: mit
- Created: 2024-04-28T14:22:20.000Z (7 months ago)
- Default Branch: main
- Last Pushed: 2024-06-12T08:10:13.000Z (5 months ago)
- Last Synced: 2024-08-01T19:49:33.437Z (3 months ago)
- Topics: autods, automl, pycaret, streamlit, webapp
- Language: Python
- Homepage:
- Size: 244 KB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
*autoDS* stands for Automatic Data Science and is an Open-Source tool that automates as many phases of the data science life cycle as possible. This tool makes it possible to automatically train a regression model for a specific label, use it to make predictions and deploy it as an API.
- **Upload data**: Load the pre-processed data set, select the label and prepare for next steps.
- **EDA**: Explore data in deeply with Exploratory Data Analysis.
- **Training**: A (new) best model is trained with AutoML.
- **Prediction**: You can make predictions with an old or new model.
- **Deployment**: You can deploy the trained model to an API, used for other systems.
## Screenshot
## How to use
Don't forget to rename [sample.env](sample.env) to `.env`!
**Step: 1 Install dependencies via `pip`**
```
python3 -m pip install pipenv
python3 -m pipenv install
```
**Step 2: Run server**
```shell
python3 -m pipenv run server
```
**Step 3: Test API after successfully run**
```shell
python3 -m pipenv run api
```
Call URL http://localhost:8501 or change frontend with [configuration](./.streamlit).
## Used tech stack
- Backend: Python 3.11
- API: [FastAPI](https://github.com/tiangolo/fastapi)
- Frontend: [Streamlit](https://github.com/streamlit)
- AutoML: [PyCaret](https://github.com/pycaret/pycaret)
- EDA: [Pandas and YData Profiling](https://github.com/ydataai/ydata-profiling)