#PSO
import pyswarms as ps
from pyswarms.single.global_best import GlobalBestPSO
import matplotlib.pyplot as plt
from pyswarms.utils.plotters import plot_cost_history
from pyswarms.utils.plotters.formatters import Mesher, Designer
import numpy as np
import math


def func(x):
    y=(x[:,0]-6)**2+(x[:,1]-7)**2
    g1=-3*x[:,0]-2*x[:,1]+6
    g2 = -x[:,0] + x[:,1] -3
    g3 = x[:,0]+ x[:,1] -7
    g4 = 2/3*x[:,0]- x[:,1] - 4/3
    c=9999
    f=1*y[:]+c*np.maximum(g1[:],0)**2+c*np.maximum(g2[:],0)**2+c*np.maximum(g3[:],0)**2+c*(g4[:])**2
    return f

options = {'c1': 0.5, 'c2': 0.3, 'w': 0.9}

x_max = 10 * np.ones(2)
x_min = -1 * x_max
bounds = (x_min, x_max)

optimizer = GlobalBestPSO(n_particles=100, dimensions=2, options=options,bounds=bounds)

cost, pos = optimizer.optimize(func, iters=200)
print(cost,pos)

plot_cost_history(optimizer.cost_history)
plt.show()

#GENETIC
import math
import numpy as np
from genetic_algorithm.main import genetic_optimisation
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
import numpy as np

def func(x):

    y=(x[0]-6)**2+(x[1]-7)**2
    g1=-3*x[0]-2*x[1]+6
    g2 = -x[0] + x[1] -3
    g3 = x[0] + x[1] -7
    g4 = 2/3*x[0] - x[1] - 4/3
    c=-1*9999
    f=-1*y+c*max(g1,0)**2+c*max(g2,0)**2+c*max(g3,0)**2+c*(g4,0)**2
    return f

def fitness(x):
    x = list(x.values())
    return func(x)

x1v = np.arange(-6, 6, 0.01)
x2v = np.arange(-6, 6, 0.01)
x1, x2 = np.meshgrid(x1v, x2v)
f = np.zeros((len(x1),len(x2)))

for i in range(0,len(x1),1):
    for j in range(0,len(x1),1):
        f[i,j]=func((x1[i,j], x2[i,j]))

fig = plt.figure()
ax = fig.gca(projection='3d')
p1 = ax.plot_surface(x1, x2, f)
plt.show()

param_space = {"x1": [-5, 5],"x2": [-5, 5]}

xopt=genetic_optimisation(input_model=fitness, param_space=param_space, pop_size=100, num_parents=2,
                     max_num_generations=500, mutation_prob=0.5, stoping_rounds=50, integer_params=[])

print(xopt.get('best fitness'))
print(xopt.get('best params'))