Poseidonml

- Provided a way to run DeviceClassifier training and testing scripts from command line.
- Cleaned up some unused code and consolidated common operations into utils and model class.
- Fixed issue where Makefile built the OneLayer training container when building the test one.
- Updated redis to 3.1.0
- Updated numpy to 1.16.1

- Updated numpy to 1.16.0
- Updated pika to 0.13.0
- Included a conda yml file for a standalone/dev environment, and new Makefile options to build it.

- models have been retrained to fix a warning about invalid results when evaluating a pcap
- some unused code and module has been removed
- upgraded pytest to 4.1.0 and pytest-cov to 2.6.1

- upgraded scikit-learn to 0.20.2
- removed scipy
- cleaned up requirements.txt and setup.py
- fixed issue where redis was throwing error when saving decisions
- fixed error in eval_onelayer that was using nonexistent key
- Make train/eval/test process consistent for all models
- Fixed path error specific to python 3.5 that occurred when processing PCAP files
- PCAP directories can now be used when running model evals

- upgraded pytest to 4.0.2
- upgraded scikit-learn to 0.20.1
- improved README documentation
- upgraded redis to 3.0.1
- added pcap directory support
- re-enabled the behavior model
- includes the trained behavior model
- fixed hardcoded onelayer pickle file in randomforest
- fixed missing labels
- simplified rabbit connection
- replaced deprecated randomized logistic regression with random forest

- upgraded pytest to 3.9.1
- fixed a NoneType error when multiplying
- fixed an issue where the config file wasn't being read properly
- abstracted away the code to read the config file into one place