Optimisation modules built for optimization problem during thesis

Jérôme BUISINE 39dd88a8f3 Fix initialization of solution issue; Fix load of UCB checkpoint		4 年之前
.github	df8251b5ac new package name : macop; use of new policy for operators	4 年之前
docs	39dd88a8f3 Fix initialization of solution issue; Fix load of UCB checkpoint	4 年之前
examples	39dd88a8f3 Fix initialization of solution issue; Fix load of UCB checkpoint	4 年之前
macop	39dd88a8f3 Fix initialization of solution issue; Fix load of UCB checkpoint	4 年之前
.gitignore	feb1e4263c enable solutions dynamic imports using python package	4 年之前
CONTRIBUTING.md	df8251b5ac new package name : macop; use of new policy for operators	4 年之前
LICENSE	3589fb944b Initial commit	5 年之前
README.md	feb1e4263c enable solutions dynamic imports using python package	4 年之前
__init__.py	0a1b108095 First version of OR framework	5 年之前
build.sh	df8251b5ac new package name : macop; use of new policy for operators	4 年之前
logo_macop.png	df8251b5ac new package name : macop; use of new policy for operators	4 年之前
requirements.txt	4fbbbf39d3 documentation updates for algorithms	4 年之前
setup.py	39dd88a8f3 Fix initialization of solution issue; Fix load of UCB checkpoint	4 年之前

Minimalist And Customizable Optimization Package

Description

macop is an optimization Python package which not implement the whole available algorithms in the literature but let you the possibility to quickly develop and test your own algorithm and strategies. The main objective of this package is to be the most flexible as possible and hence, to offer a maximum of implementation possibilities.

Modules

algorithms: generic and implemented OR algorithms
evaluator: example of an evaluation function to use (you have to implement your own evaluation function)
solutions: solutions used to represent problem data
operators: mutators, crossovers update of solution. This folder also has policies folder to manage the way of update and use solution.
callbacks: callbacks folder where Callback class is available for making callback instructions every number of evaluations.

Note: you can pass a custom validator function to the algorithm in order to check is solution is always correct for your needs after an update.

How to use ?

Fully documentation of package with examples is available.

You can also see examples of use:

in the knapsackExample.py python file for mono-objective.
in the knapsackMultiExample.py python file for multi-objective.

Add as dependency

git submodule add https://github.com/jbuisine/macop.git

License

The MIT License

README.md