def test_MMAE():
dt = 0.1
pos, zs = generate_data(120, noise_factor=0.2)
z_xs = zs[:, 0]
t = np.arange(0, len(z_xs) * dt, dt)
dt = 0.1
filters = [make_cv_filter(dt, noise_factor=0.2),
make_ca_filter(dt, noise_factor=0.2)]
H_cv = np.array([[1., 0, 0],
[0., 1, 0]])
H_ca = np.array([[1., 0., 0.],
[0., 1., 0.],
[0., 0., 1.]])
bank = MMAEFilterBank(filters, (0.5, 0.5), dim_x=3, H=(H_cv, H_ca))
xs, probs = [], []
for z in z_xs:
bank.predict()
bank.update(z)
xs.append(bank.x[0])
#print('p', bank.p)
probs.append(bank.p[0] / bank.p[1])
if DO_PLOT:
plt.subplot(121)
plt.plot(xs)
plt.subplot(122)
plt.plot(probs)
plt.title('probability ratio p(cv)/p(ca)')
def test_MMAE2():
dt = 0.1
pos, zs = generate_data(120, noise_factor=0.6)
z_xs = zs[:, 0]
t = np.arange(0, len(z_xs) * dt, dt)
dt = 0.1
ca = make_ca_filter(dt, noise_factor=0.6)
cv = make_ca_filter(dt, noise_factor=0.6)
cv.F[:,2] = 0 # remove acceleration term
cv.P[2,2] = 0
cv.Q[2,2] = 0
filters = [cv, ca]
H_ca = np.array([[1., 0., 0.],
[0., 1., 0.],
[0., 0., 1.]])
bank = MMAEFilterBank(filters, (0.5, 0.5), dim_x=3, H=(1., 1.))
xs, probs = [], []
cvxs, caxs = [], []
for i, z in enumerate(z_xs):
bank.predict()
bank.update(z)
xs.append(bank.x[0])
cvxs.append(cv.x[0])
caxs.append(ca.x[0])
print(i, cv.likelihood, ca.likelihood, bank.p)
#print('p', bank.p)
probs.append(bank.p[0] / bank.p[1])
if DO_PLOT:
plt.subplot(121)
plt.plot(xs)
plt.plot(pos[:, 0])
plt.subplot(122)
plt.plot(probs)
plt.title('probability ratio p(cv)/p(ca)')
plt.figure()
plt.plot(cvxs, label='CV')
plt.plot(caxs, label='CA')
plt.plot(pos[:, 0])
plt.legend()
plt.figure()
plt.plot(xs)
plt.plot(pos[:, 0])
def test_MMAE2():
dt = 0.1
pos, zs = generate_data(120, noise_factor=0.6)
z_xs = zs[:, 0]
dt = 0.1
ca = make_ca_filter(dt, noise_factor=0.6)
cv = make_ca_filter(dt, noise_factor=0.6)
cv.F[:, 2] = 0 # remove acceleration term
cv.P[2, 2] = 0
cv.Q[2, 2] = 0
filters = [cv, ca]
bank = MMAEFilterBank(filters, (0.5, 0.5), dim_x=3, H=ca.H)
xs, probs = [], []
cvxs, caxs = [], []
s = Saver(bank)
for i, z in enumerate(z_xs):
bank.predict()
bank.update(z)
xs.append(bank.x[0])
cvxs.append(cv.x[0])
caxs.append(ca.x[0])
print(i, cv.likelihood, ca.likelihood, bank.p)
s.save()
probs.append(bank.p[0] / bank.p[1])
s.to_array()
if DO_PLOT:
plt.subplot(121)
plt.plot(xs)
plt.plot(pos[:, 0])
plt.subplot(122)
plt.plot(probs)
plt.title('probability ratio p(cv)/p(ca)')
plt.figure()
plt.plot(cvxs, label='CV')
plt.plot(caxs, label='CA')
plt.plot(pos[:, 0])
plt.legend()
plt.figure()
plt.plot(xs)
plt.plot(pos[:, 0])
return bank
def test_MMAE2():
dt = 0.1
pos, zs = generate_data(120, noise_factor=0.6)
z_xs = zs[:, 0]
t = np.arange(0, len(z_xs) * dt, dt)
dt = 0.1
ca = make_ca_filter(dt, noise_factor=0.6)
cv = make_ca_filter(dt, noise_factor=0.6)
cv.F[:,2] = 0 # remove acceleration term
cv.P[2,2] = 0
cv.Q[2,2] = 0
filters = [cv, ca]
H_ca = np.array([[1., 0., 0.],
[0., 1., 0.],
[0., 0., 1.]])
bank = MMAEFilterBank(filters, (0.5, 0.5), dim_x=3, H=(1., 1.))
xs, probs = [], []
cvxs, caxs = [], []
for i, z in enumerate(z_xs):
bank.predict()
bank.update(z)
xs.append(bank.x[0])
cvxs.append(cv.x[0])
caxs.append(ca.x[0])
print(i, cv.likelihood, ca.likelihood, bank.p)
#print('p', bank.p)
probs.append(bank.p[0] / bank.p[1])
def test_MMAE2():
dt = 0.1
pos, zs = generate_data(120, noise_factor=0.6)
z_xs = zs[:, 0]
t = np.arange(0, len(z_xs) * dt, dt)
dt = 0.1
ca = make_ca_filter(dt, noise_factor=0.6)
cv = make_ca_filter(dt, noise_factor=0.6)
cv.F[:,2] = 0 # remove acceleration term
cv.P[2,2] = 0
cv.Q[2,2] = 0
filters = [cv, ca]
H_ca = np.array([[1., 0., 0.],
[0., 1., 0.],
[0., 0., 1.]])
bank = MMAEFilterBank(filters, (0.5, 0.5), dim_x=3, H=(1., 1.))
xs, probs = [], []
cvxs, caxs = [], []
for i, z in enumerate(z_xs):
bank.predict()
bank.update(z)
xs.append(bank.x[0])
cvxs.append(cv.x[0])
caxs.append(ca.x[0])
print(i, cv.likelihood(z), ca.likelihood(z), bank.p)
#print('p', bank.p)
probs.append(bank.p[0] / bank.p[1])
if DO_PLOT:
plt.subplot(121)
plt.plot(xs)
plt.plot(pos[:, 0])
plt.subplot(122)
plt.plot(probs)
plt.title('probability ratio p(cv)/p(ca)')
plt.figure()
plt.plot(cvxs, label='CV')
plt.plot(caxs, label='CA')
plt.plot(pos[:, 0])
plt.legend()
plt.figure()
plt.plot(xs)
plt.plot(pos[:, 0])
def test_MMAE2():
dt = 0.1
pos, zs = generate_data(120, noise_factor=0.6)
z_xs = zs[:, 0]
dt = 0.1
ca = make_ca_filter(dt, noise_factor=0.6)
cv = make_ca_filter(dt, noise_factor=0.6)
cv.F[:, 2] = 0 # remove acceleration term
cv.P[2, 2] = 0
cv.Q[2, 2] = 0
filters = [cv, ca]
bank = MMAEFilterBank(filters, (0.5, 0.5), dim_x=3, H=ca.H)
xs, probs = [], []
cvxs, caxs = [], []
s = Saver(bank)
for i, z in enumerate(z_xs):
bank.predict()
bank.update(z)
xs.append(bank.x[0])
cvxs.append(cv.x[0])
caxs.append(ca.x[0])
print(i, cv.likelihood, ca.likelihood, bank.p)
s.save()
probs.append(bank.p[0] / bank.p[1])
s.to_array()
if DO_PLOT:
plt.subplot(121)
plt.plot(xs)
plt.plot(pos[:, 0])
plt.subplot(122)
plt.plot(probs)
plt.title('probability ratio p(cv)/p(ca)')
plt.figure()
plt.plot(cvxs, label='CV')
plt.plot(caxs, label='CA')
plt.plot(pos[:, 0])
plt.legend()
plt.figure()
plt.plot(xs)
plt.plot(pos[:, 0])
return bank
