def test_x_squared_optimization(self):
def objective_func(x):
return x**2
var_init = np.array([2])
optimizer = Optimizer(objective_func, var_init)
min_value, var_value = optimizer.gd_optimize(tolerance=0.0000001,
num_iterations=1000)
self.assertAlmostEqual(min_value, 0, places=5)
self.assertAlmostEqual(var_value[0], 0, places=5)
def test_x_y_z_squared_optimization(self):
def objective_func(x, y, z):
return x**2 + y**2 + z**2
var_init = np.array([-15, 100, -20])
optimizer = Optimizer(objective_func, var_init)
min_value, var_value = optimizer.gd_optimize(tolerance=0.0000001,
num_iterations=1000)
self.assertAlmostEqual(min_value, 0, places=5)
self.assertAlmostEqual(var_value[0], 0, places=5)
self.assertAlmostEqual(var_value[1], 0, places=5)
self.assertAlmostEqual(var_value[2], 0, places=5)
def objective_func(x):
return x[0]**2 + x[1]**2 + x[2]**2
var_init = np.array([-15, 100, -20])
optimizer = Optimizer(objective_func, var_init, scalar=False)
min_value, var_value = optimizer.gd_optimize(tolerance=0.0000001,
num_iterations=1000)
self.assertAlmostEqual(min_value, 0, places=5)
self.assertAlmostEqual(var_value[0], 0, places=5)
self.assertAlmostEqual(var_value[1], 0, places=5)
self.assertAlmostEqual(var_value[2], 0, places=5)