Data Analysis, Machine Learning, Bro, and You! by Brian Wylie

Originally recorded September 12, 2017

In this presentation we will give live demonstrations of a new open source project called BroThon: Bro + Python (). With a simple ‘pip install’ and a few lines of Python we can dynamically monitor any active Bro log and easily convert the log data into a Pandas DataFrame. We can also turn that DataFrame into a numpy ndarray (matrix/tensor) ready for the statsmodels and scikit-learn libraries. The BroThon package has classes for these transformations that handle all the details:
* Streaming generators (zero copy) into DataFrames
* Type conversion (int, float, str, datetimes, timedeltas)
* Automatic numerical normalization (serialized properly for train/eval)
* Automatic categorical detection and ‘one-hot’ encoding (with proper serialization)

We’ll run through several example use cases as part of the presentation:
* Bro to Pandas
* Bro to Scikit

Brian Wylie works for Kitware.