How mayadispeler/firewall-threat-detection works
Project type and purpose
• This is a data-science / small analytics application with a Streamlit dashboard front-end. Its primary goal is to process raw firewall logs, run an anomaly-detection model (Isolation Forest), and expose the results in an interactive UI for analysts.
File structure
• Top‐level files:
• 01_data_eda.ipynb, 02_model.ipynb – exploratory data analysis & model‐training notebooks
• Approach.md – detailed pipeline steps
• dashboard.py – Streamlit script powering the UI
• data_synthesis.py – script to generate or preprocess the dataset
• requirements.txt – Python dependencies
• model.joblib (generated) – serialized trained model
• No separate “src” or “backend” folder; scripts and notebooks coexist at root.
README for additional insights
• Confirms a 3-step pipeline: EDA → model build (Isolation Forest) → dashboard display
• Mentions environment setup, package list, and commands to rerun pipeline or re-generate data.