# Refer: https://arxiv.org/pdf/1308.4008.pdf (Momin, J. A. M. I. L., & Yang, X. S. (2013). A literature survey of benchmark functions for global optimization problems. Journal of Mathematical Modelling and Numerical Optimisation, 4(2), 150-194.) import numpy as np import matplotlib.pyplot as plt import pso_solver pso_solver.setSeed(1) lower = xlower = ylower = zlower = -20 upper = xupper = yupper = zupper = 20 particleList = pso_solver.createRandomParticleList(3, numParticles=100, lower=lower, upper=upper) # Testing on Rosenbrock function f = lambda x, y, z: 100 * ((z - y**2)**2 + (y - x**2)**2) + ((x-1)**2 + (y-1)**2 + (z-1)**2) pso_solver.psoVisualizeTrivariate(particleList, f, xlower, xupper, ylower, yupper, zlower, zupper, c1=1, c2=1, W=0.5, numIters=20, maxFlag=False, sleepTime=0.5, accuracy=2, verbose=False)
import numpy as np
import matplotlib.pyplot as plt
import pso_solver
pso_solver.setSeed()
lower = xlower = 0
upper = xupper = 2 * np.pi
particleList = pso_solver.createRandomParticleList(1,
numParticles=10,
lower=lower,
upper=upper)
# Testing on a univariate function
f = lambda x: np.cos(x)
pso_solver.psoVisualizeUnivariate(particleList,
f,
xlower,
xupper,
c1=1,
c2=1,
W=0.5,
numIters=30,
maxFlag=False,
sleepTime=0.1,
density=100,
fColor='b',
particleColor='r',
accuracy=2,
verbose=False)