import matplotlib.pyplot as plt import numpy as np from util_plot import AddPlot is_3d = True plots = AddPlot(is_3d) ax, data_dim = plots.returns # Make goal as gene gene_num = 5 chromosome_num = 10 p_arr = np.random.rand(chromosome_num, gene_num) v_arr = np.random.rand(chromosome_num, gene_num) pbest_arr = np.zeros((chromosome_num, gene_num)) pbest_fit_arr = np.zeros(chromosome_num) gbest = None gbest_path = None gbest_fitness = 0.0 # Create points and paths points = np.random.rand(1 + gene_num, data_dim) paths = np.repeat([points], chromosome_num, axis=0) # Parameters inertia_weight = 0.7298 const_vp = 1.5 const_vg = 1.5 early_stop_fitness = 1.0 i = 0
import numpy as np import matplotlib.pyplot as plt from util_plot import AddPlot is_3d = True ax, gene_num = AddPlot(is_3d).returns chromosome_num = 10 population_shape = (chromosome_num, gene_num) test_goal = np.random.rand(gene_num) iteration = 0 iteration_num = 100 # Parameters mutation_rate = 0.3 crossover_rate = 0.3 selection_ratio = 0.3 selection_num = int(chromosome_num * selection_ratio) copy_num = chromosome_num - selection_num best_goal = None best_fitness = 0.0 early_stop_fitness = 0.98 # First time we generate population using Uniform Distribution population = np.random.rand(*population_shape) while True:
import matplotlib.pyplot as plt import numpy as np from util_plot import AddPlot is_3d = True ax, data_dim = AddPlot(is_3d).returns # Make goal as gene gene_num = 5 chromosome_num = 10 # Create points and paths points = np.random.rand(1 + gene_num, data_dim) paths = np.repeat([points], chromosome_num, axis=0) population = np.repeat([np.arange(gene_num)], chromosome_num, axis=0) list(map(np.random.shuffle, population)) # Parameters mutation_rate = 0.3 selection_ratio = 0.7 selection_num = int(chromosome_num * selection_ratio) copy_num = chromosome_num - selection_num best_fitness = 0.0 early_stop_fitness = 1.0 iteration = 0 iter_num = 100 while True:
import matplotlib.pyplot as plt
import numpy as np
from sklearn import datasets
from util_plot import AddPlot
is_3d = True
ax, point_dim = AddPlot(is_3d).returns
# import some data to play with
iris = datasets.load_iris()
X = iris.data[:, :point_dim] # we only take the first point_dim features.
y = iris.target
if is_3d:
test_point = np.array([7, 4, 3])
else:
test_point = np.array([7, 4])
# Set number of neighbors and (x, y) of test point.
neighbors_K = 3
distant_arr = np.zeros(len(y))
for i, (point, color_idx) in enumerate(zip(X, y)):
# Plot all points
ax.scatter(*point, color="C%d" % color_idx, s=50, alpha=0.1)
distant_arr[i] = np.linalg.norm(test_point - point)
# Get neighbor points from sorted distance
min_idx = np.argsort(distant_arr)[:neighbors_K]
neighbor_points = X[min_idx]
import numpy as np
import matplotlib.pyplot as plt
from util_plot import AddPlot
is_3d = True
ax, particle_dim = AddPlot(is_3d).returns
n_particles = 10
particles_shape = (n_particles, particle_dim)
test_goal = np.random.rand(particle_dim)
iteration = 0
best_goal = None
best_distant = None
while True:
distant_list = []
if best_goal is None:
# First time we generate particles using Uniform Distribution
rand_particles = np.random.rand(*particles_shape)
else:
# Randomly generate particles using Normal Distribution
sigma = 1 / (4 * iteration)
rand_particles = best_goal + sigma * np.random.randn(*particles_shape)
ax.scatter(*rand_particles.T, s=50, alpha=0.5)
ax.scatter(*test_goal, s=200, marker="*", alpha=1.0)
for p in rand_particles:
import numpy as np
import matplotlib.pyplot as plt
from util_plot import AddPlot
is_3d = True
ax, point_dim = AddPlot(is_3d).returns
n_cluster_points = 100
cluster_shape = (n_cluster_points, point_dim)
# Randomly generate clusters using Normal Distribution (randn)
rand_points1 = 0 + 2 * np.random.randn(*cluster_shape)
rand_points2 = 10 + 3 * np.random.randn(*cluster_shape)
if is_3d:
rand_points3 = [20, 0, 5] + 2 * np.random.randn(*cluster_shape)
rand_points4 = [20, 20, 10] + 1.5 * np.random.randn(*cluster_shape)
else:
rand_points3 = [20, 0] + 2 * np.random.randn(*cluster_shape)
rand_points4 = [20, 20] + 1.5 * np.random.randn(*cluster_shape)
all_points = (rand_points1, rand_points2, rand_points3, rand_points4)
points_num = n_cluster_points * len(all_points)
all_points = np.concatenate(all_points, axis=0)
def neighborhood_points(xs, x_centroid, dist=3):
eligible_x = []
for x in xs:
distance = np.linalg.norm(x - x_centroid)
if distance <= dist:
eligible_x.append(x)
import matplotlib.pyplot as plt
import numpy as np
from util_plot import AddPlot
p = AddPlot(is_3d=True, with_lc=True)
ax1, _ = p.returns
x_min = -4
x_max = 4
y_min = -4
y_max = 4
z_min = 0
z_max = 13
# Add step to make more smooth and more slow
x = np.arange(x_min, x_max, 0.5)
y = np.arange(y_min, y_max, 0.5)
xx, yy = np.meshgrid(x, y, sparse=True)
def reversed_ackley_function(x, y):
z = 15 - (-20 * np.exp(-0.2 * (np.sqrt(0.5 * (x**2 + y**2)))) - np.exp(
0.5 * (np.cos(2 * np.pi * x) + np.cos(2 * np.pi * y))) + np.e + 20)
return z
zz = reversed_ackley_function(xx, yy)
def plot_ackley():
ax1.set_xlim(x_min, x_max)
import time
import numpy as np
import matplotlib.pyplot as plt
from util_plot import AddPlot
is_3d = True
ax, point_dim = AddPlot(is_3d).returns
n_cluster_points = 100
cluster_shape = (n_cluster_points, point_dim)
means_K = 4
early_stop_distant = 0.01
# Randomly generate clusters using Normal Distribution (randn)
rand_points1 = 0 + 2 * np.random.randn(*cluster_shape)
rand_points2 = 10 + 3 * np.random.randn(*cluster_shape)
if is_3d:
rand_points3 = [20, 0, 5] + 2 * np.random.randn(*cluster_shape)
rand_points4 = [30, 20, 10] + 1.5 * np.random.randn(*cluster_shape)
else:
rand_points3 = [20, 0] + 2 * np.random.randn(*cluster_shape)
rand_points4 = [30, 20] + 1.5 * np.random.randn(*cluster_shape)
points_num = n_cluster_points * means_K
all_points = np.concatenate(
(rand_points1, rand_points2, rand_points3, rand_points4))
# We random choice centroids from points.
rand_indexes = np.random.choice(all_points.shape[0], means_K, replace=False)
centroids = all_points[rand_indexes]