scikit-opt

• Add a toolkit x2gray.
• Add a crossover fuction #79

• Add multiprocessing&multithreading

• Surport 3 kinds of accelerate strategy ( vectorization, parallel, cached)
• Surport class methods directly as the objective function

1. PSO now support nonlinear unequal constraint
2. Remove unbounded algorithm from PSO

1. Add input&output parameters
2. Bring all 7 algorithms into correspondence for parameters, as much as possible.

• Fix a critical bug in AFSA
• make up a doc to show parameters （only Chinese now, English is on the way）

In previous version, GA has an integer mode, which uses penalty function. It makes a lot of misunderstand, and misusage.
The integer mode is totally changed to a new algorithm in this version.
#32 #37 #59

Bug fixed #45 : input parameter in SA

bug: #34 ASFS, ASFA, AFSA

• Fix a vital bug about array copy in ACA
• GA&PSO: objective function supports vectorization calculation

Better GA for TSP

integer programming for GA

• Differential Evolution available
• Algorithm with constraint available
• Move operators to a path operators
• Remove old-style register UDF

• 3 types of Simulated Annealing: Fast, Boltzmann, Cauchy.
• Now Simulated Annealing is nearly perfect
• documents is more specific

• Almost perfect: Simulated Annealing for TSP
• New docs
• 2 animations (PSO and SA)

• PSO (Particle Swarm Optimization) with constraint
• Faster GA operators
• New documents framework

$pip install scikit-opt

• A new type of register
• Provide some operators

$pip install scikit-opt

• add immune algorithm, artificial fish swarm algorithm
• new operators for GA
• new types of udf

This is the first releases
See here
$pip install scikit-opt

This is the first releases
See here
$pip install scikit-opt