Bareddy Charitha’s Post

Excited to Share My MLOps Capstone Project: End-to-End Sentiment Analysis Pipeline I’m happy to share that I have successfully completed my MLOps Capstone Project on Sentiment Analysis, where I built a complete end-to-end machine learning pipeline and deployed it using modern MLOps practices. This project focuses on analyzing text data and automatically classifying it into sentiments while implementing industry-level practices such as experiment tracking, data versioning, containerization, CI/CD, and cloud deployment. Key Highlights of the Project • Built a modular ML pipeline including data ingestion, preprocessing, feature engineering, model training, and evaluation • Implemented experiment tracking using MLflow with DagsHub • Applied data and model versioning using DVC with remote storage • Developed a Flask web application to interact with the trained model • Containerized the application using Docker • Implemented CI/CD automation using GitHub Actions • Deployed the application using AWS services and Kubernetes (EKS) • Integrated Prometheus and Grafana for monitoring the deployed application Tech Stack Python | Scikit-learn | MLflow | DVC | Flask | Docker | Kubernetes (EKS) | AWS | Prometheus | Grafana | GitHub Actions Through this project, I gained hands-on experience in building scalable and production-ready machine learning systems using MLOps principles, from development to deployment and monitoring. A sincere thank you to Vikash Das Sir for the incredible guidance and learning resources. His explanations and practical approach to MLOps helped me understand how to design and implement real-world ML systems. This project has been a great learning experience, and I look forward to continuing my journey in Machine Learning, MLOps, and AI systems. I would love to hear your feedback and suggestions! #MLOps #MachineLearning #SentimentAnalysis #DataScience #MLflow #DVC #Docker #AWS #Kubernetes #Prometheus #Grafana #LearningJourney #VikashDasSir github repo : https://lnkd.in/d3xzF9Cy