The official python package for NimbleBox. Exposes all APIs as CLIs and contains modules to make ML 🌸

A complete production-ready MLOps framework with built-in distributed training, monitoring, and CI/CD. Deploy ML models to production with confidence using our battle-tested infrastructure.

End-to-end ML platform for Yelp business recommendations and sentiment analysis. Features collaborative filtering (ALS), NLP classification, FastAPI REST API, PySpark data processing, MLflow tracking, Docker deployment, and CI/CD automation. Academic/research project demonstrating production ML engineering.

Developed an image classification web app using CNN to differentiate cats and dogs. Achieved high accuracy, precision, recall, and F1 score. Pipeline involves data preprocessing, model training, Docker deployment on AWS ECS, user-friendly interface, and reliable CI/CD. Showcases deep learning's potential in image analysis.

A modular ML pipeline built with Python, scikit-learn, and Docker, featuring YAML-based config management, DVC tracking, CI/CD integration via GitHub Actions, and production-ready FastAPI deployment. Designed for reproducibility, scalability, and monitoring readiness (Prometheus/Grafana).

MLops 5th Sem Project

prod-overrun-ml : Machine learning predictor for production cost overruns in film projects. Uses gradient boosting and regression to forecast risks, analyze features (budget, script metrics, crew, etc.), and help secure better financing outcomes.

MLOps

End-to-end MLOps pipeline for hotel booking demand forecasting. Includes modular components for data ingestion, model training, evaluation, versioning, and deployment. Features configuration-based execution, CI/CD with GitHub Actions, and automated logging and testing.

Python for MLOps Course

AI-powered document chat application built with Retrieval-Augmented Generation (RAG), enabling users to upload documents, extract relevant context, and ask natural language questions through an intelligent conversational interface. Designed for efficient knowledge retrieval, accurate responses, and scalable real-world use cases.

End-to-end MLOps pipeline for house price prediction with multiple models, CI/CD, and API deployment.

A production-ready MLOps pipeline for detecting melanoma and other skin cancers using AWS SageMaker, with automated retraining, monitoring, and deployment.

MLOps (Machine Learning Operations) is a set of practices that combines Machine Learning (ML) and DevOps to automate, deploy, monitor, and manage machine learning models in production reliably and efficiently.

A machine learning project to predict water potability based on quality parameters, featuring an end-to-end MLOps pipeline, a web interface, and scalable deployment with monitoring and CI/CD support.

An ML system for automated medical signal analysis, evolving from deep learning research to a containerized MLOps pipeline.

End-to-end CNN MLOps pipeline with MLflow tracking, FastAPI deployment, and Docker.