Customer Segmentation is a KMeans based Clustering app based on the MallCustomer Dataset
Download Docker Desktop
run the IDE in a conda env
Download Anaconda 3
Project based on the cookiecutter data science project template.
Build the docker at the root of the app
docker-compose up --build
web server @ 0.0.0.0:5000
MLflow server @ 0.0.0:5001
add the data set to data_given\dataset
dvc add dataset.csv
change the model parameters in the params.yaml file
to run ML pipelines
dvc repro
The experiments are captured in the local SQLite dB
run MLflow tracking server without docker
mlflow server --backend-store-uri sqlite:///customerSegmentationmlflow.db --default-artifact-root .\artifacts -h 0.0.0.0 -p 5001
run web app
python app.py
experiment the code using jupyter lab
jupyter lab notebooks/
Azure Container registry setup
https://docs.microsoft.com/en-us/azure/container-instances/tutorial-docker-compose
Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.