在python中创建进化计算的框架。
ecsp的Python项目详细描述
ecspy(python中的进化计算)是一个 在python中创建进化计算。另外,ecspy 提供易于使用的标准遗传算法(ga),进化 策略、分布算法估计、差分 面向用户的进化算法(dea)和粒子群优化算法(pso) 他们不需要太多的定制。
要求
- Requires at least Python 2.6 (not compatible with Python 3+).
- Numpy and Matplotlib are required if the line plot observer is used.
- Parallel Python (pp) is required if parallel_evaluation_pp is used.
许可证
此软件包是在GNU通用公共许可下分发的 版本3.0(gplv3)。此许可证可在网上找到 http://www.opensource.org/licenses/gpl-3.0.html。
包装结构
ECSpy由以下模块组成:
- analysis.py – provides tools for analyzing the results of an EC
- archivers.py – defines useful archiving methods, particularly for EMO algorithms
- benchmarks.py – defines several single- and multi-objective benchmark optimization problems
- ec.py – provides the basic framework for an EvolutionaryComputation and specific ECs
- emo.py – provides the Pareto class for multiobjective optimization along with specific EMOs (e.g. NSGA-II)
- evaluators.py – defines useful evaluation schemes, such as parallel evaluation
- migrators.py – defines a few built-in migrators, including migration via network and migration among concurrent processes
- observers.py – defines a few built-in observers, including screen, file, and plotting observers
- replacers.py – defines standard replacement schemes such as generational and steady-state replacement
- selectors.py – defines standard selectors (e.g., tournament)
- swarm.py – provides a basic particle swarm optimizer
- terminators.py – defines standard terminators (e.g., exceeding a maximum number of generations)
- topologies.py – defines standard topologies for particle swarms
- variators.py – defines standard variators (crossover and mutation schemes such as n-point crossover)
资源
- Homepage: http://ecspy.googlecode.com
- Email: aaron.lee.garrett@gmail.com