IDS MLOps Project

Intrusion Detection System with Machine Learning and MLOps Pipeline.

Installation

git clone https://github.com/hibaa23/ids-mlops-project.git
cd ids-mlops-project
python -m venv venv
venv\Scripts\activate
pip install -r requirements.txt

Dataset

This project uses the CIC-IDS2017 dataset.

Due to the large size of the CSV files, the dataset is not stored in this repository.

You can download it from the official source:

🔗 https://www.unb.ca/cic/datasets/ids-2017.html

After downloading, place the files in:

data/raw/

Utilisation

# Preprocessing
python src/preprocessing.py

# Training
python src/train.py

# API
python src/api.py

Structure

ids-mlops-project/
├── data/
│   ├── raw/
│   └── processed/
├── notebooks/
├── models/
├── src/
│   ├── preprocessing.py
│   ├── train.py
│   ├── model_registry.py
│   └── api.py
├── tests/
├── requirements.txt
└── README.md

Technologies

• Python 3.9+
• scikit-learn, XGBoost
• MLflow
• FastAPI
• Docker