Phishing Model Analytics

This project trains and evaluates a machine learning model for phishing detection.

Project Structure

• src/: Source code for the model and data loader.
• data/: Directory for labeled phishing datasets (CSV).
• evaluation/: Scripts to evaluate model performance (accuracy, precision, recall, F1-score) and store results.

Setup

1. Create a virtual environment: python -m venv venv
2. Activate the virtual environment: .\venv\Scripts\activate (Windows) or source venv/bin/activate (Mac/Linux)
3. Install dependencies: pip install -r requirements.txt

Running Evaluation

To evaluate the model, run the metrics script from the root directory:

python -m evaluation.calculate_metrics

To run it on a specific dataset:

python -m evaluation.calculate_metrics --data data/your_dataset.csv