Customer Satisfaction prediction with MLOps

For Demo Please visit: https://youtu.be/WYPCLE6CHS8

Overview

CustSatMLOps is a project aimed at predicting customer satisfaction using machine learning algorithms. It integrates MLOps practices using ZenML and MLflow for streamlined deployment and management.

Features

Data Processing: Includes scripts for data cleaning and preprocessing.
Model Training: Implements various ML algorithms for training models.
MLOps Integration: Utilizes ZenML for pipeline orchestration and MLflow for experiment tracking and model management.
Deployment: Provides tools for deploying models into production.

Pipeline structure

Installation

Clone the repository:

git clone https://github.com/mirsaidl/CustSatMLOps.git

Navigate to the project directory:
```
cd CustSatMLOps
```
Install the required packages:
```
pip install -r requirements.txt
```
Starting with ZenML 0.20.0, ZenML comes bundled with a React-based dashboard. This dashboard allows you to observe your stacks, stack components and pipeline DAGs in a dashboard interface. To access this, you need to launch the ZenML Server and Dashboard locally, but first you must install the optional dependencies for the ZenML server:

pip install zenml["server"]
zenml up

If you are running the run_deployment.py script, you will also need to install some integrations using ZenML:

zenml integration install mlflow -y

The project can only be executed with a ZenML stack that has an MLflow experiment tracker and model deployer as a component. Configuring a new stack with the two components are as follows:

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

Usage

Run the pipeline:
```
python run_pipeline.py
```

Deploy the model:

python run_deployment.py --config deploy
python run_deployment.py --config predict

Run Streamlit on local:
```
streamlit run app.py
```

Repository Structure

data/: Contains the dataset.
pipelines/: Defines the ML pipelines.
steps/: Contains steps for data processing, training, and evaluation.
src/: Source code for the project.
requirements.txt: List of dependencies.

Acknowledgements

This project utilizes ZenML and MLflow for implementing MLOps.