def cmp_max_mutation_vs_mutation_rate():
X, y = read_xy_data(
'../data/ga/griewank/max_mutation_amount,mutation_rate.dat')
b = get_regression_coef(X, y)
x1_start = 0.1
x1_step = 0.1
x1_end = 1.0
x2_start = 0.1
x2_step = 0.1
x2_end = 1.0
fig = plt.figure()
ax1 = fig.add_subplot(111, projection='3d')
ax1.set_zlim(3, 9)
for i, row in enumerate(X):
ax1.scatter(row[1], row[2], y[i])
pltx = np.arange(x1_start, x1_end + x1_step, x1_step)
plty = np.arange(x2_start, x2_end + x2_step, x2_step)
pltX, pltY = np.meshgrid(pltx, plty)
F = b[0] + b[1] * pltX + b[2] * pltY + b[3] * pltX * pltX + b[
4] * pltX * pltY + b[5] * pltY * pltY
ax1.plot_wireframe(pltX, pltY, F)
ax1.contour(pltX, pltY, F, zdir='z', offset=3, cmap=cm.jet)
ax1.set_title(
'Response Surface of Mutation Rate vs Maximum Mutation Allowed of GA on Griewank Function'
)
ax1.set_xlabel('Mutation Amount')
ax1.set_ylabel('Mutation Rate')
ax1.set_zlabel('Mean Euclidean Distance from Global Minimum')
plt.show()
def cmp_cp_vs_cg():
X, y = read_xy_data('cp,cg_ackley.dat')
b = get_regression_coef(X, y)
x1_start = 0.0
x1_step = 0.05
x1_end = 1.0
x2_start = 0.0
x2_step = 0.05
x2_end = 1.0
fig = plt.figure()
ax1 = fig.add_subplot(111, projection='3d')
ax1.set_zlim(0, 1)
for i, row in enumerate(X):
ax1.scatter(row[1],row[2],y[i])
pltx = np.arange(x1_start, x1_end+x1_step, x1_step)
plty = np.arange(x2_start, x2_end+x2_step, x2_step)
pltX, pltY = np.meshgrid(pltx, plty)
F = b[0] + b[1]*pltX + b[2]*pltY + b[3]*pltX*pltX + b[4]*pltX*pltY + b[5]*pltY*pltY
#ax1.plot_wireframe(pltX, pltY, F)
ax1.set_xlabel('CP')
ax1.set_ylabel('CG')
ax1.set_zlabel('Objective Function Value')
plt.show()
def create_bulk_var_cmp_graphs():
import ga_tests
input_loc = '../tmp/'
output_loc = '../tmp/'
x1_start = 0.1
x1_step = 0.1
x1_end = 1.0
x2_start = 0.1
x2_step = 0.1
x2_end = 1.0
tests = ga_tests.tests
functions = ga_tests.functions
for f in functions:
for t in tests.items():
names = t[1]
x1_name = names['x1']
x2_name = names['x2']
filename = input_loc + gen_filename(x1_name, x2_name, f)
(X, y) = read_xy_data(filename)
b = get_regression_coef(X, y)
fig = plt.figure()
ax1 = fig.add_subplot(111, projection='3d')
#ax1.set_zlim(3, 9)
for i, row in enumerate(X):
ax1.scatter(row[1], row[2], y[i])
pltx = np.arange(x1_start, x1_end + x1_step, x1_step)
plty = np.arange(x2_start, x2_end + x2_step, x2_step)
pltX, pltY = np.meshgrid(pltx, plty)
F = b[0] + b[1] * pltX + b[2] * pltY + b[3] * pltX * pltX + b[
4] * pltX * pltY + b[5] * pltY * pltY
#ax1.plot_wireframe(pltX, pltY, F)
ax1.contour(pltX, pltY, F, zdir='z', offset=0, cmap=cm.jet)
ax1.set_title(
'Response Surface of Mutation Rate vs Selection Cutoff of GA on Griewank Function'
)
ax1.set_xlabel('Selection Cutoff')
ax1.set_ylabel('Mutation Rate')
ax1.set_zlabel('Mean Euclidean Distance from Global Minimum')
plt.show()
def plot_data(x1_info, x2_info, func, zbounds=None):
c_i = 0
to_plot = [0.1, 0.5, 0.9]
x1_var = x1_info[NAME]
x2_var = x2_info[NAME]
x1_name = x1_var.replace('_', ' ').title()
x2_name = x2_var.replace('_', ' ').title()
func = func + '_function'
func_name = func.replace('_', ' ').title()
title = 'Response Surface of %s vs %s of %s on %s' % (x1_name, x2_name, \
algorithm_name, func_name)
fig = plt.figure()
ax1 = fig.add_subplot(111, projection='3d')
if zbounds is not None:
ax1.set_zlim(zbounds[0], zbounds[1])
for j in to_plot:
f = 'rosenbrock/cutoff_vs_rate_(mma_%.2f)_' % j
filename = input_loc + f + func + '.dat'
#filename = input_loc + gen_filename(x1_var, x2_var, func)
(X, y) = read_xy_data(filename)
b = get_regression_coef(X, y)
#for i, row in enumerate(X):
# ax1.scatter(row[1],row[2],y[i], color=colors[c_i])
pltx = np.arange(x1_start, x1_end + x1_step, x1_step)
plty = np.arange(x2_start, x2_end + x2_step, x2_step)
pltX, pltY = np.meshgrid(pltx, plty)
F = b[0] + b[1] * pltX + b[2] * pltY + b[3] * pltX * pltX + b[
4] * pltX * pltY + b[5] * pltY * pltY
ax1.plot_wireframe(pltX, pltY, F, color=colors[c_i])
#ax1.contour(pltX, pltY, F, zdir='z', offset=0, cmap=cm.jet)
c_i += 1
if c_i > 6:
c_i = 0
ax1.set_title(title)
ax1.set_xlabel(x1_name)
ax1.set_ylabel(x2_name)
ax1.set_zlabel('Median Euclidean Distance from Global Minimum')
ax1.legend(to_plot, title='Max Allowed Mutation Size', loc='lower left')
plt.show()
def optimize_3d(X, y, x1_step, x2_step, x3_step):
x1_start = min(X[:, 1])
x1_end = max(X[:, 1])
x2_start = min(X[:, 2])
x2_end = max(X[:, 2])
x3_start = min(X[:, 3])
x3_end = max(X[:, 3])
# get regression coefficients
b = regression_utils.get_regression_coef(X, y)
opt = {'disp': False}
sol = minimize(objective_3d_function, [0.5, 0.5, 0.5], method='SLSQP', \
bounds=((0,1), (0,1), (0,1)), options = opt)
return sol
def plot_data(ax, mma_arr, func, zbounds=None):
c_i = 0
to_plot = mma_arr
algorithm_name = "Genetic Algorithm"
x1_name = 'Selection Cutoff'
x2_name = 'Mutation Rate'
x1_start = 0.1
x1_step = 0.1
x1_end = 1.0
x2_start = 0.1
x2_step = 0.1
x2_end = 1.0
func_file = func + '_function'
func_name = func + ' function'
func_name = func_name.title()
title = 'Response Surface of %s vs %s of %s on %s' % (x1_name, x2_name, \
algorithm_name, func_name)
if zbounds is not None:
ax.set_zlim(zbounds[0], zbounds[1])
for j in to_plot:
f = '%s/cutoff_vs_rate_(mma_%.2f)_' % (func, j)
filename = '../data/ga/' + f + func_file + '.dat'
#filename = input_loc + gen_filename(x1_var, x2_var, func)
(X, y) = read_xy_data(filename)
b = get_regression_coef(X, y)
pltx = np.arange(x1_start, x1_end + x1_step, x1_step)
plty = np.arange(x2_start, x2_end + x2_step, x2_step)
pltX, pltY = np.meshgrid(pltx, plty)
F = b[0] + b[1] * pltX + b[2] * pltY + b[3] * pltX * pltX + b[
4] * pltX * pltY + b[5] * pltY * pltY
ax.plot_wireframe(pltX, pltY, F, color=colors[c_i])
c_i += 1
if c_i > 6:
c_i = 0
ax.legend(to_plot, title='Max Allowed Mutation Size', loc='lower left')
ax.set_title(title)
ax.set_xlabel('Selection Cutoff')
ax.set_ylabel('Mutation Rate')
ax.set_zlabel('Median Euclidean Distance from Global Minimum')
def get_pso_two_d_accuracy(o_algorithm, o_settings, o_function, \
x1_start, x1_step, x1_end, \
x2_start, x2_step, x2_end, \
x1_name, x2_name, \
population_size=50, num_tests_per_point=10, plot=True, \
save_histograms=True, response_surface=True, debug=False):
if response_surface:
plot = True
# turn off settings that slow us down
o_settings = optimize_settings(o_settings)
func_name = o_function.func_globals['__name__']
tests = {}
hist_num_bins = 150
o_settings['population_size'] = population_size
num_tests_per = num_tests_per_point
x1_srt = x1_start
x1_e = x1_end
x1_stp = x1_step
x2_srt = x2_start
x2_e = x2_end
x2_stp = x2_step
num_tests = int(( (int(100*x1_e)-int(100*x1_srt))/int(100*x1_stp) + 1 )* \
( (int(100*x2_e)-int(100*x2_srt))/int(100*x2_stp) + 1 ))
X = np.ones(shape=(num_tests, 6))
y = np.zeros(shape=(num_tests, 1))
n = 0
if plot:
fig = plt.figure()
ax1 = fig.add_subplot(111, projection='3d')
if o_function != griewank_function.objective_function:
ax1.set_zlim(0, 1)
for i in np.arange(x1_srt, x1_e + x1_stp, x1_stp):
for j in np.arange(x2_srt, x2_e + x2_stp, x2_stp):
# set settings for this test
o_settings[x1_name] = i
o_settings[x2_name] = j
# initial variables
values = []
euclid_distance = []
test_name = 'cp' + '(' + str(o_settings['cp']) + ')' + ',' + \
'cg' + '(' + str(o_settings['cg']) + ')'
print("Running test %s on %s" % (test_name, func_name))
# create histogram plot if true
if save_histograms:
hist_fig = plt.figure()
hist_ax = hist_fig.add_subplot(111)
# run optimization algorithm
for k in range(0, num_tests_per):
algorithm = o_algorithm(o_settings, o_function)
algorithm.run()
# save enf values
values.append(algorithm.get_best_x().get_fval())
# euclidean distance
squares = 0
for pos in algorithm.get_best_x().pos:
if o_function == rosenbrock_function.objective_function:
squares += (pos - 1)**2
elif o_function == easom_function.objective_function:
squares += (pos - np.pi)**2
else:
squares += pos**2
euclid_distance.append(np.sqrt(squares))
# save histogram if true
if save_histograms:
hist_ax.hist(euclid_distance,
hist_num_bins,
range=(0, 9),
normed=True)
hist_fig.savefig(test_name + '.png')
plt.close(hist_fig)
# find average and save data
#avg = sum(values)/len(values)
#avg = median(values)
#avg = sum(euclid_distance)/len(euclid_distance)
avg = np.median(euclid_distance)
tests[test_name] = avg
if plot:
ax1.scatter(i, j, avg)
X[n][1] = i
X[n][2] = j
X[n][3] = i * i
X[n][4] = i * j
X[n][5] = j * j
y[n] = avg
# increment test number
n += 1
# fname = gen_filename(x1_name, x2_name, func_name)
# write_xy_data(X, y, fname)
if debug:
print("\n*** DATA ***")
print("X")
print(X)
print("\ny")
print(y)
print("\ntests")
print(tests)
if response_surface:
# get regression coefficients
b = regression_utils.get_regression_coef(X, y)
pltx = np.arange(x1_start, x1_end + x1_step, x1_step)
plty = np.arange(x2_start, x2_end + x2_step, x2_step)
pltX, pltY = np.meshgrid(pltx, plty)
F = b[0] + b[1] * pltX + b[2] * pltY + b[3] * pltX * pltX + b[
4] * pltX * pltY + b[5] * pltY * pltY
ax1.plot_wireframe(pltX, pltY, F)
if plot:
print("\nPlotting ...")
x1_name = x1_name[0].upper() + x1_name[1:]
x2_name = x2_name[0].upper() + x2_name[1:]
ax1.set_xlabel(x1_name)
ax1.set_ylabel(x2_name)
ax1.set_zlabel('Average Euclidean Distance from Global Minimum')
plt.show()
return (X, y)