fam4r / bsc-di-project

Malicious and Benign Websites Classification

Data Intensive Applications: Project

Requirements

This repo provides a virtual environment support, no other installation providers are supported, if you want to directly install packages in your system, please search yourself their names (pipenv graph | grep -v '-') and how to do.

Install Pipenv.

Pipenv

$ pipenv install
$ pipenv run ipython kernel install --user --name=diproj --display-name "Py3 DIA - Project"

Run

Execute

$ pipenv run jupyter notebook

Then a tab should have been opened in your browser.

If you used the virtual environment installation, choose the kernel diproj (or the chosen name).

Project description

References

• Malicious and Benign Websites: Classify by application and network features

Fix arff dataset

$ wget <ds_url.arff> -O <ds_name>.arff
$ sed -i "s/{ /{/g" <ds_name>.arff
$ sed -i "s/ }/}/g" <ds_name>.arff

Convert arff dataset to csv

$ pipenv run ./arff2csv.py