Argus + ML + ramle

Machine Learning Engine

Argus provides a rich source of transactional network data that is suitable for many machine learning algorithms. Whether you are interested in credit card fraud approaches to cyber security, or pattern recognition to identify user network use behavior, Argus enables a platform that can support Bayesian deep learning, as well as supervised, unsupervised, semi-supervised learning, regression, instanced-based, regularization, decision tree, clustering, association rule learning, dimensional reduction, or ensemble analytics.

Python is a great platform for processing Argus data.  Use Argus tools to generate general or specific network transactional data, collect, store, process, reduce, aggregate and extract the features needed for you ML analytics, and use Python and its libraries and functions, to analyze and visualize all that data.  

These posts will describe in parts the steps needed to build an Argus ML workflow, reading data from Argus,  inputing into a Python Panda’s dataframe, and then performing some basic exploratory data analysis.

Getting ramle

You can get ramle from GitHub.

Installing Packages

These examples require the installation of specific Python packages which can be installed using the following commands:

pip install package-name
conda install package-name

Reading Argus Data

To prepare Argus data for Python, simply generate a .csv file.

ra -r argus.file -c , > argus.csv

Argus Data Analysis

Explore the data using Pandas

In this introduction, we show some simple data summarizations, unique lists, box plots and a scatter plot; basic tools for argus data analysis.


Here are some example projects / workflows that groups are working on.







© Copyright QoSient, LLC.
All Rights Reserved.
site by spliteye