I've built a model to predict wine quality and set up a remote server on DagsHub for tracking experiments.
MLflow-WQ-Presentation.mp4
This dataset is taken from : http://archive.ics.uci.edu/ml/datasets/Wine+Quality
Thanks to MLflow for providing this tutorials and examples
-
Clone the repository:
git clone https://github.com/CodeWithCharan/MLflow-Wine-Quality-Project.git
-
Create a
virtual environment
(optional): Virtual Environment Set Up -
Install the required dependencies:
pip install -r requirements.txt
-
Run
app.py
:python app.py
-
Go to
mlflow ui
:mlflow ui
-
mlflow ui will be running on
http://127.0.0.1:5000/
, so paste this URL -
Now, try different experiments and compare them:
python app.py 0.3 0.7
-
Create a remote server (optional): You have the option to integrate the project with any remote server, such as AWS, Azure, GCP, etc. In this project, I have used Dagshub as a remote server : https://dagshub.com/user/login