Preliminary Analysis of the dataset is done in the file: network_intrusion_detection.ipynb Performed operations to understand the dataset and it's possible ways to reduce dimensionality for faster training of models:
- Correlation Matrix between all features
- Feature Importance
- PCA
- Chi-Squared test
Final Phase where same ML models as the paper used plus some additional models used on reduced but most important features to generate similar accuracy: final_project.ipynb