x_location = y_data.index(min(y_data))
max_expected_improvement = 0
max_points = []
max_points_unnormalized = []
print("xi - ", xi)
# logging.info("xi - %f", xi)
print("iter - ", i)
# logging.info("iter - %i", i)
for pool_size in range(thread_pool_min, thread_pool_max + 1):
x = [pool_size]
x_val = [x[0]]
# may be add a condition to stop explorering the already expored locations
ei = gaussian_ei(np.array(x_val).reshape(1, -1), model, minimum, xi)
if ei > max_expected_improvement:
max_expected_improvement = ei
max_points = [x_val]
elif ei == max_expected_improvement:
max_points.append(x_val)
if max_expected_improvement == 0:
print("WARN: Maximum expected improvement was 0. Most likely to pick a random point next")
# logging.info("WARN: Maximum expected improvement was 0. Most likely to pick a random point next")
next_x = x_data[x_location]
# logging.info(next_x)
Y_plot_data = function(X_plot_data, plot_number)
minimum = min(y_data)
x_location = y_data.index(min(y_data))
max_expected_improvement = 0
max_points = []
print("xi -", xi)
print("iteration -", i)
for pool_size in range(thread_pool_min, thread_pool_max + 1):
x_val = [pool_size]
# may be add a condition to stop explorering the already expored locations
feed_val = np.array(x_val).reshape(1, -1)
#ei = gaussian_ei(np.array(x_val).reshape(1, -1), model, minimum, xi)
ei = gaussian_ei(feed_val, model, minimum, xi)
if ei > max_expected_improvement:
max_expected_improvement = ei
max_points = [x_val]
elif ei == max_expected_improvement:
max_points.append(x_val)
#else:
#print("WARN: Expected improvement < Max value")
if max_expected_improvement == 0:
print("WARN: Maximum expected improvement was 0. Most likely to pick a random point next")
if keep_min < 10: