Heart Disease Prediction ML Pipeline

This project provides a comprehensive machine learning pipeline for heart disease prediction using the UCI Heart Disease dataset. It includes data preprocessing, feature selection, model training, evaluation, and a user-friendly Streamlit web app for real-time predictions.

---

Directory Structure

Heart Disease Prediction ML Pipeline/
│
├── ui/
│   └── src/
│       └── app.py                # Streamlit web app
│
├── models/
│   ├── final_model.pkl           # Trained ML model (Random Forest)
│   └── scaler.pkl                # Scaler used for preprocessing
│
├── deployment/
│   └── ngrok_setup.txt           # Instructions for exposing app via ngrok
│
├── results/
│   └── evaluation_metrics.txt    # Model performance metrics
│
├── Notebook.ipynb                # Main Jupyter notebook (ML pipeline)
├── requirements.txt              # Python dependencies
├── .gitignore                    # Files/folders to ignore in git
└── README.md                     # Project documentation

---

Getting Started

1. Clone the Repository

git clone <repo-url>
cd Heart Disease Prediction ML Pipeline

2. Install Dependencies

pip install -r requirements.txt

3. Run the Streamlit App

streamlit run ui/src/app.py

The app will open in your browser at http://localhost:8501.

---

Streamlit App

• Location: ui/src/app.py
• Features:
  • Enter patient details to predict heart disease risk.
  • Uses the trained Random Forest model and scaler.
  • Displays prediction and probability.

---

Model Training & Evaluation

• Notebook: Notebook.ipynb

• Pipeline Steps:

  • Data loading and preprocessing
  • Feature selection (RFE, Chi-Square)
  • Model training (Logistic Regression, Decision Tree, Random Forest, SVM)
  • Evaluation (Accuracy, Precision, Recall, F1, ROC AUC)
  • Hyperparameter tuning
  • Saving best model and scaler

• Results:
  See results/evaluation_metrics.txt for detailed metrics.

---

Deployment

To expose your Streamlit app for external access, follow the instructions in deployment/ngrok_setup.txt using ngrok.

---

Requirements

See requirements.txt for all dependencies.