def test_kl_simple():
# verified by hand
# Dhat(P||Q) = \log m/(n-1) + d / n \sum_{i=1}^n \log \nu_k(i)/rho_k(i)
x = np.reshape([0., 1, 3], (3, 1))
y = np.reshape([.2, 1.2, 3.2, 7.2], (4, 1))
n = x.shape[0]
m = y.shape[0]
x_to_y = np.log(
m /
(n - 1)) + 1 / n * (np.log(1.2 / 3) + np.log(.8 / 2) + np.log(1.8 / 3))
y_to_x = np.log(n / (m - 1)) + 1 / m * (np.log(.8 / 3) + np.log(1.2 / 2) +
np.log(2.2 / 3) + np.log(6.2 / 6))
# NOTE: clamping makes this test useless.
x_to_y = max(x_to_y, 0)
y_to_x = max(y_to_x, 0)
res = estimate_divs(Features([x, y]), specs=['kl'], Ks=[2]).squeeze()
assert res[0, 0] == 0
assert res[1, 1] == 0
assert np.allclose(res[1, 0], y_to_x), "{} vs {}".format(res[1, 0], y_to_x)
assert np.allclose(res[0, 1], x_to_y), "{} vs {}".format(res[0, 1], x_to_y)
def check_div(feats, expected, specs, Ks, name, min_dist=None, **args):
capturer = capture_output(True, True, merge=False)
with capturer:
ds = estimate_divs(feats,
specs=specs,
Ks=Ks,
min_dist=min_dist,
**args)
argstr = ', '.join('{}={}'.format(k, v) for k, v in iteritems(args))
for spec_i, spec in enumerate(specs):
for K_i, K in enumerate(Ks):
calc = ds[:, :, spec_i, K_i]
exp = expected[:, :, spec_i, K_i]
diff = np.abs(calc - exp)
i, j = np.unravel_index(np.argmax(diff), calc.shape)
msg = "bad results for {}:{}, K={}\n".format(name, spec, K) + \
"(max diff {} = |{} - {}| at {},{})".format(
diff[i, j], calc[i, j], exp[i, j], i, j)
f = partial(assert_close, calc, exp, atol=5e-5, msg=msg)
f.description = \
"divs: {} - {}, K={} - {}".format(name, spec, K, argstr)
yield f,
def test_js_simple():
# verified by hand
x = np.reshape([0, 1, 3], (3, 1))
y = np.reshape([.2, 1.2, 3.2, 6.2], (4, 1))
mix_ent = np.log(2) + np.log(3) + psi(2) \
+ (np.log(.2) + np.log(.8) + np.log(1.8) - psi(1) - 2*psi(2)) / 6 \
+ (np.log(.2) + np.log(2) + np.log(3.2) - psi(1) - 3*psi(2)) / 8
x_ent = np.log(2) + (np.log(3) + np.log(2) + np.log(3)) / 3
y_ent = np.log(3) + (np.log(3) + np.log(2) + np.log(3) + np.log(5)) / 4
right_js = mix_ent - (x_ent + y_ent) / 2
expected = np.array([[0, right_js], [right_js, 0]])
# TODO: what about clamping???
est = estimate_divs(Features([x, y]), specs=['js'], Ks=[2],
status_fn=None).squeeze()
assert_close(est, expected, atol=5e-5, msg="JS estimate not as expected")
def test_js_simple():
# verified by hand
x = np.reshape([0, 1, 3], (3, 1))
y = np.reshape([.2, 1.2, 3.2, 6.2], (4, 1))
mix_ent = np.log(2) + np.log(3) + psi(2) \
+ (np.log(.2) + np.log(.8) + np.log(1.8) - psi(1) - 2*psi(2)) / 6 \
+ (np.log(.2) + np.log(2) + np.log(3.2) - psi(1) - 3*psi(2)) / 8
x_ent = np.log(2) + (np.log(3) + np.log(2) + np.log(3)) / 3
y_ent = np.log(3) + (np.log(3) + np.log(2) + np.log(3) + np.log(5)) / 4
right_js = mix_ent - (x_ent + y_ent) / 2
expected = np.array([[0, right_js], [right_js, 0]])
# TODO: what about clamping???
est = estimate_divs(Features([x, y]), specs=['js'], Ks=[2],
status_fn=None).squeeze()
assert_close(est, expected, atol=5e-5, msg="JS estimate not as expected")
def check_div(feats, expected, specs, Ks, name, min_dist=None, **args):
capturer = capture_output(True, True, merge=False)
with capturer:
ds = estimate_divs(feats, specs=specs, Ks=Ks, min_dist=min_dist, **args)
argstr = ', '.join('{}={}'.format(k, v) for k, v in iteritems(args))
for spec_i, spec in enumerate(specs):
for K_i, K in enumerate(Ks):
calc = ds[:, :, spec_i, K_i]
exp = expected[:, :, spec_i, K_i]
diff = np.abs(calc - exp)
i, j = np.unravel_index(np.argmax(diff), calc.shape)
msg = "bad results for {}:{}, K={}\n".format(name, spec, K) + \
"(max diff {} = |{} - {}| at {},{})".format(
diff[i, j], calc[i, j], exp[i, j], i, j)
f = partial(assert_close, calc, exp, atol=5e-5, msg=msg)
f.description = \
"divs: {} - {}, K={} - {}".format(name, spec, K, argstr)
yield f,
def test_kl_simple():
# verified by hand
# Dhat(P||Q) = \log m/(n-1) + d / n \sum_{i=1}^n \log \nu_k(i)/rho_k(i)
x = np.reshape([0., 1, 3], (3, 1))
y = np.reshape([.2, 1.2, 3.2, 7.2], (4, 1))
n = x.shape[0]
m = y.shape[0]
x_to_y = np.log(m / (n-1)) + 1/n * (
np.log(1.2 / 3) + np.log(.8 / 2) + np.log(1.8 / 3))
y_to_x = np.log(n / (m-1)) + 1/m * (
np.log(.8 / 3) + np.log(1.2 / 2) + np.log(2.2 / 3) + np.log(6.2 / 6))
# NOTE: clamping makes this test useless.
x_to_y = max(x_to_y, 0)
y_to_x = max(y_to_x, 0)
res = estimate_divs(Features([x, y]), specs=['kl'], Ks=[2]).squeeze()
assert res[0, 0] == 0
assert res[1, 1] == 0
assert np.allclose(res[1, 0], y_to_x), "{} vs {}".format(res[1, 0], y_to_x)
assert np.allclose(res[0, 1], x_to_y), "{} vs {}".format(res[0, 1], x_to_y)
