Predicting how a customer will feel about a product before they order it

A MLOps project using ZenML to build a production-ready pipeline to predict the customer satisfaction score for the next purchase Integration of tools like MLflow for deployment and tracking

Firstly install all the basic python libraries for machine learning

then coming to ZenML

pip install "zenml["server"]"
zenml init
zenml up

To run run_deployment.py file

zenml integration install mlflow -y

zenml experiment-tracker register mlflow_tracker --flavor=mlflow
zenml model-deployer register mlflow --flavor=mlflow
zenml stack register mlflow_stack -a default -o default -d mlflow -e mlflow_tracker --set

This mainly consists of several steps like

• Ingestion of data
• cleaning of data
• training of model
• evaluation of model

Run two pipelines

• Training pipeline

python run_pipeline.py

• Continuous deployment

python run_deployment.py

For usage where it takes the features as input

streamlit run streamlit_app.py

link for the dataset is here data