🚀 7-Day End-to-End Machine Learning Engineering Bootcamp

An intensive, production-oriented Machine Learning Engineering repository covering the full lifecycle of ML systems: from raw data cleaning and classical ML models to Deep Learning, RAG/GenAI pipelines, and MLOps containerization.

---

📌 Repository Architecture & Daily Progression

Data Ingestion ➔ Feature Engineering ➔ ML/DL Modeling ➔ RAG Integration ➔ FastAPI Serving ➔ Docker Container

Day	Module Focus	Technologies Used	Output / Deliverable
Day 01	Data Preprocessing & Pipelines	Pandas, NumPy, Scikit-Learn	Modular Data Cleaning & Transformer Script
Day 02	Classical ML & Hyperparameter Tuning	XGBoost, Optuna, Joblib	Model Artifact & Evaluation Report
Day 03	Deep Learning from Scratch	PyTorch, BatchNorm, Dropout	Custom ANN Training & Loss Curve
Day 04	Specialized Architectures & Transformers	ResNet18, Hugging Face (DistilBERT)	Computer Vision & NLP Classifiers
Day 05	GenAI & RAG Pipeline	LangChain, ChromaDB, HuggingFace	Context-Aware Document Querying System
Day 06	MLOps: Serving & Containerization	FastAPI, Pydantic, Docker	Production-Ready Dockerized REST API
Day 07	System Integration & Portfolio Setup	Markdown, Git, System Design	End-to-End Portfolio & Documentation

---

⚡ Quick Start & Execution Guide

1. Clone the Repository

git clone [https://github.com/YOUR_USERNAME/7-Days-ML-Bootcamp.git](https://github.com/YOUR_USERNAME/7-Days-ML-Bootcamp.git)
cd 7-Days-ML-Bootcamp

2. Run the Dockerized ML Service (Day 6 Component)

cd Day06_MLOps_FastAPI_Docker
docker build -t ml-service:v1 .
docker run -p 8000:8000 ml-service:v1

Access interactive API documentation at: http://localhost:8000/docs

3. Run the RAG Pipeline (Day 5 Component)

cd Day05_GenAI_RAG_Pipeline
python -m venv venv && source venv/bin/activate  # On Windows: venv\Scripts\activate
pip install -r requirements.txt
python rag_pipeline.py

---

🛠️ Key Technical Highlights

• Automated Data Processing: Leak-free pipelines using Scikit-Learn ColumnTransformer.
• Hyperparameter Optimization: Bayesian optimization driven by Optuna for XGBoost.
• Modern Deep Learning: Custom PyTorch training loop incorporating AdamW and regularization techniques.
• Vector Search & RAG: Local semantic embeddings stored in ChromaDB for instant text retrieval.
• Production MLOps: API validation via Pydantic models and multi-stage Dockerfile creation.

---

📄 License

This project is licensed under the MIT License - see the LICENSE file for details. '''

Machine Learning Artifacts & Databases

*.joblib *.pth *.safetensors artifacts/ chroma_db/

System Files

.DS_Store .vscode/