Digital DNA Toolbox

This project has been possible thanks to SAGE Ocean Concept Grants 2018.

This project was build upon the scikit-learn template in order to be compatible with the scikit-learn pipelines and (hyper)parameter search, while facilitating testing (including some API compliance), documentation, open source development, packaging, and continuous integration.

Installation

This module in order to work needs:

• Python v3.6.x or greater
• numpy package
• glcr python module - available here

You can download and install digitaldna as follow:

git clone https://github.com/WAFI-CNR/ddna-toolbox
cd ddna-toolbox
git clone https://github.com/WAFI-CNR/glcr

pip install numpy 
pip install glcr/.
pip install .

Getting started

If the installation is successful, and digitaldna is correctly installed, you should be able to execute the following in Python:

from digitaldna.lcs import LongestCommonSubsequence
X = ['banana', 'ananan', 'anana', 'hanoi', 'banas']
estimator = LongestCommonSubsequence()
estimator.fit_predict(X)

Some usage examples can be found in the documentation website.

You can find other examples in this page

Credits and Aknowledgement

This library has been made possible thanks to the collaboration and contribution of:

• SAGE Publishing
• Bellomo Salvatore
• Cresci Stefano
• Gagliano Giuseppe
• Martella Antonio
• Spognardi Angelo
• Tesconi Maurizio
• ... and all the contributors of this opensource library

Want to contribute?

If you want to contribute you can refer to the scikit-learn template documentation:

• scikit-learn template homepage
• scikit-learn template source code
• scikit-learn Contributing section

Useful links

• Social Fingerprinting: Detection of Spambot Groups Through DNA-Inspired Behavioral Modeling
• Exploiting Digital DNA for the Analysis of Similarities in Twitter Behaviours
• Linear Time Algorithms for Generalizations of the Longest Common Substring Problem
• Scikit-learn Template Documentation