🚢 Full Stack ML – Titanic Survival Prediction

This repository contains an end‑to‑end machine learning project that predicts Titanic passenger survival.
It demonstrates the complete workflow: data preprocessing, model training, and deployment with a Flask web application.
The frontend interface was created with the help of AI assistance, showing how modern AI tools can accelerate UI design while I focused on backend engineering and ML pipeline quality.

---

---

⚙️ Features

• Input passenger details (class, sex, age, siblings/spouses, parents/children, fare, embarkation port).
• Predict survival using a trained ML model.
• Simple, clean web interface built with Flask.
• Frontend design accelerated using AI assistance for layout and styling.
• End‑to‑end demonstration of ML deployment.

---

---

🚀 Getting Started

1. Clone the repository

git clone https://github.com/yaswanth-AIML/Full_Stack_ML.git
cd Full_Stack_ML
pip install -r requirements.txt
python app.py
 Open in browser
Visit: http://127.0.0.1:5000/
📊 Model Details
- Dataset: Titanic dataset (Kaggle).
- Features used: Pclass, Sex, Age, SibSp, Parch, Fare, Embarked.
- Model serialized with pickle for deployment.

🖼️ Demo
- Fill in passenger details in the form.
- Click Predict.
- The app will display:
- ✅ Survived
- ❌ Did not survive
📌 Future Improvements
- Add survival probability scores (% likelihood).
- Deploy on Heroku/Render for live demo.
- Enhance UI with Bootstrap or glassmorphism CSS.
- Experiment with advanced models (Random Forest, XGBoost).
---
###👨‍💻 Author
Yaswanth Vanacharla (Yash)
Computer Science student specializing in AI & backend engineering.
Frontend polished with AI assistance to accelerate design and focus on ML pipeline quality.
Focused on recruiter‑ready ML projects and portfolio polish.
---