PerfSPEC Learning Phase - ABOUT

Based in PrefSPEC: Performance Profiling-based Proactive Security Policy Enforcement for Containers document presented in [1], this repository contains source files used to generate and process data.

What is done so far ?

Good look and feel and interactions among processing, analisys and presentation layers
Using better software packages management like uv to complement Python pip
A notebook open like Marimo to support alternative dataframes engines like Polars rather than Pandas
Use settings and structures to play with different settinigs and options
Implement a customize one LSTM model within notebooks
Use of different metrics to apply to the training models with custumezable adjustments
Use notebooks as python scripts for command-line use cases like collect predictions or automatic train models
Use Dry to reuse code and centralize common tasks like settings or loading resources. This is main use and existence of lib_perfspec.py
Spliting basic tasks among seveal specific notebooks:
- Preprocessing data collection to generate clean and usefull (critical actions) info to train models and ranking prepare_perfspec.py
- Train models to get predictions train_perfspec.py
- Get predictions from existing models run_perfspec.py
- Review and analisys trained models for better results model_perfspec.py