new Topics: Coronavirus | AI | Data Science | Deep Learning | Machine Learning | Python | R | Statistics

KDnuggets Home » News :: 2013 :: Feb :: Software :: DEAP 0.9: Distributed Evolutionary Algorithms in Python ( 13:n03 )

DEAP 0.9: Distributed Evolutionary Algorithms in Python


DEAP (Distributed Evolutionary Algorithms in Python) is a novel evolutionary computation framework for rapid prototyping and testing of ideas. DEAP 0.9.0 has many improvements, including SCOOP , a distributed task module allowing concurrent parallel programming.



DEAPDEAP (Distributed Evolutionary Algorithms in Python) is a novel evolutionary computation framework for rapid prototyping and testing of ideas. Its design departs from most other existing frameworks in that it seeks to make algorithms explicit and data structures transparent, as opposed to the more common black box type of frameworks.

This release includes :

  • major overhaul of the genetic programming with significant speed increase;
  • new state of the art operators to control bloat in GP;
  • ability to do GP with arbitrary Python objects, i.e. NumPy vectors and matrices;
  • several new examples from diverse fields;
  • organization of the examples by category;
  • examples are now compatible with Python 2 and 3 out of the box;
  • and several other changes.

A major change for DEAP is that from 0.9.0, the easy distribution module DTM will be replaced by SCOOP (Scalable COncurrent Operations in Python), a distributed task module allowing concurrent parallel programming on various environments, from heterogeneous grids to supercomputers. This new project is led by Yannick Hold-Geoffroy (@yannickhold) in close association with DEAP's developers. You can download the last release at the following web page.

scoop.googlecode.com/

Your feedback and comments are welcome at goo.gl/2HiO1 or deap-users at googlegroups dot com. You can also follow us on Twitter @deapdev, and on our blog deapdev.wordpress.com/.

François-Michel De Rainville
Félix-Antoine Fortin
Marc-André Gardner
Christian Gagné
Marc Parizeau

Laboratoire de vision et systèmes numériques
Département de génie électrique et génie informatique
Université Laval
Quebec City (Quebec), Canada


Sign Up

By subscribing you accept KDnuggets Privacy Policy