def test_distributions_normal_random_sample(): d = NormalDistribution(0, 1) x = numpy.array([ 0.44122749, -0.33087015, 2.43077119, -0.25209213, 0.10960984]) assert_array_almost_equal(d.sample(5, random_state=5), x) assert_raises(AssertionError, assert_array_almost_equal, d.sample(5), x)
def test_distributions_normal_random_sample(): d = NormalDistribution(0, 1) x = numpy.array([ 0.44122749, -0.33087015, 2.43077119, -0.25209213, 0.10960984]) assert_array_almost_equal(d.sample(5, random_state=5), x) assert_raises(AssertionError, assert_array_almost_equal, d.sample(5), x)
def visit_helper(self, k):
""" Returns a tuple x,y that coresponds
to the coords which we will manipulate"""
mu_x, mu_y, sigma = int(round(k.pt[0])), int(round(k.pt[1])), k.size
# Remember, it may be wise to expand simga - greater varience = less honed attack
sigma += self.params.SIGMA_CONSTANT
d_x = NormalDistribution(mu_x, sigma)
d_y = NormalDistribution(mu_y, sigma)
x = d_x.sample()
y = d_y.sample()
if (self.params.small_image):
x /= self.params.inflation_constant
y /= self.params.inflation_constant
if (x >= self.params.X_SHAPE):
x = self.params.X_SHAPE - 1
elif (x < 0):
x = 0
if (y >= self.params.Y_SHAPE):
y = self.params.Y_SHAPE - 1
elif (y < 0):
y = 0
return int(x), int(y)
def sample_from_kp(k):
mu_x, mu_y, sigma = int(round(k.pt[0])), int(round(k.pt[1])), k.size
# Remember, it may be wise to expand simga
# greater varience = less honed attack
sigma += params.SIGMA_CONSTANT
d_x = NormalDistribution(mu_x, sigma)
d_y = NormalDistribution(mu_y, sigma)
x = d_x.sample()
y = d_y.sample()
if (params.small_image):
x /= params.inflation_constant
y /= params.inflation_constant
x = int(x)
y = int(y)
if (x >= params.X_SHAPE):
x = params.X_SHAPE - 1
elif (x < 0):
x = 0
if (y >= params.Y_SHAPE):
y = params.Y_SHAPE - 1
elif (y < 0):
y = 0
return int(x), int(y)
