def max_individual(input: dit.Distribution,
conditional: np.ndarray,
eps: float = 0.01,
minimal_entropy_idx=None):
rvs = input.get_rv_names()
conditional = conditional / conditional.sum()
states = len(input.alphabet[0])
if not minimal_entropy_idx == 0 and not minimal_entropy_idx:
minimal_entropy_idx = np.argmin([
entropy(input.marginal([rv], rv_mode='indices').pmf)
for rv in range(len(rvs))
])
non_minimal_rvs = rvs[:minimal_entropy_idx] + rvs[minimal_entropy_idx + 1:]
non_minimal_marginal, minimal_conditional = input.condition_on(
non_minimal_rvs)
[d.make_dense() for d in minimal_conditional]
# minimal_conditional = np.stack([d.pmf for d in minimal_conditional])
# print("minimal_conditional:",minimal_conditional)
indiv_shape = (len(minimal_conditional), len(minimal_conditional[0]))
# minimal_conditional = minimal_conditional.flatten()
nudge_vector = np.zeros(indiv_shape)
rotated_conditional = R(conditional, minimal_entropy_idx, len(rvs), states)
total_max_impact = 0
# print(len(rvs), (eps / 2)/len(minimal_conditional))
for i, mc_dist in enumerate(minimal_conditional):
rows = rotated_conditional[i * states:(i + 1) * states, :]
max_impact = 0
for allignment in itertools.product(
[-1, 1], repeat=rotated_conditional.shape[1]):
allignment = np.array(allignment)
if np.all(allignment == 1) or np.all(allignment == -1):
continue
scores = np.sum(allignment * rows, axis=1)
# Add rotation of scores so that scores are well aligned.
# Weigh scores using the non_minimal_marginal
vector, impact = find_max_impact(scores, mc_dist.pmf, (eps / 2) /
len(minimal_conditional))
if impact > max_impact:
nudge_vector[i, :] = vector
max_impact = impact
total_max_impact += max_impact
return nudge_vector, total_max_impact, minimal_entropy_idx
def max_local(input: dit.Distribution,
conditional: np.ndarray,
eps: float = 0.01):
rvs = input.get_rv_names()
sorted_rvs = np.argsort([
entropy(input.marginal([rv], rv_mode='indices').pmf)
for rv in range(len(rvs))
])
nudge_vectors = np.zeros(
(input.outcome_length(), int(len(input) / 3), 3)
) # For each random variable we get (hopefully) a different nudge vector of len the input size
max_impacts = np.zeros(input.outcome_length())
for rv in sorted_rvs:
nudge_vectors[rv, :, :], max_impacts[rv], _ = max_individual(
input, conditional, eps / len(sorted_rvs), rv)
return nudge_vectors, max_impacts
def test_to_string8():
outcomes = ['00', '01', '10', '11']
pmf = [1/4]*4
d = Distribution(outcomes, pmf)
d = d.marginal([0])
s = d.to_string(show_mask='!')
s_ = """Class: Distribution
Alphabet: ('0', '1') for all rvs
Base: linear
Outcome Class: str
Outcome Length: 1 (mask: 2)
RV Names: None
x p(x)
0! 0.5
1! 0.5"""
assert_equal(s, s_)
def test_to_string8():
outcomes = ['00', '01', '10', '11']
pmf = [1/4]*4
d = Distribution(outcomes, pmf)
d = d.marginal([0])
s = d.to_string(show_mask='!')
s_ = """Class: Distribution
Alphabet: ('0', '1') for all rvs
Base: linear
Outcome Class: str
Outcome Length: 1 (mask: 2)
RV Names: None
x p(x)
0! 0.5
1! 0.5"""
assert s == s_
def test_to_string4():
# Basic with marginal
outcomes = ['00', '01', '10', '11']
pmf = [1/4]*4
d = Distribution(outcomes, pmf)
d = d.marginal([0])
s = d.to_string()
s_ = """Class: Distribution
Alphabet: ('0', '1') for all rvs
Base: linear
Outcome Class: str
Outcome Length: 1
RV Names: None
x p(x)
0 0.5
1 0.5"""
assert_equal(s, s_)
def test_to_string4():
# Basic with marginal
outcomes = ['00', '01', '10', '11']
pmf = [1/4]*4
d = Distribution(outcomes, pmf)
d = d.marginal([0])
s = d.to_string()
s_ = """Class: Distribution
Alphabet: ('0', '1') for all rvs
Base: linear
Outcome Class: str
Outcome Length: 1
RV Names: None
x p(x)
0 0.5
1 0.5"""
assert s == s_
def test_to_string5():
# Basic with marginal and mask
outcomes = ['00', '01', '10', '11']
pmf = [1 / 4] * 4
d = Distribution(outcomes, pmf)
d = d.marginal([0])
s = d.to_string(show_mask=True)
s_ = """Class: Distribution
Alphabet: ('0', '1') for all rvs
Base: linear
Outcome Class: str
Outcome Length: 1 (mask: 2)
RV Names: None
x p(x)
0* 0.5
1* 0.5"""
assert_equal(s, s_)
def max_local_nudge2(old_X: dit.Distribution,
YgivenX: np.ndarray,
eps: float = 0.01):
if old_X.outcome_length() == 1:
return max_global_nudge(old_X, YgivenX, eps)
mask = old_X._mask
base = old_X.get_base()
new_X = old_X.copy(base=base)
old_X.make_dense()
rvs = old_X.get_rv_names()
sorted_rvs = np.argsort([
entropy(old_X.marginal([rv], rv_mode='indices').pmf)
for rv in range(len(rvs))
])
oldshape = len(old_X)
outcomes = old_X.outcomes
# print("before", new_X.pmf.shape)
for i, rv in enumerate(sorted_rvs):
nudges, _ = max_nudge(new_X.copy('linear'),
YgivenX,
eps=(eps / len(sorted_rvs)),
nudge_type='individual',
minimal_entropy_idx=rv)
# print("local eps",sum([sum(abs(nudge)) for nudge in nudges]), eps, old_X.outcome_length())
new_X = do_max_individual_nudge(new_X, nudges, rv, True)
# print("after {}".format(i), new_X.pmf.shape)
new_X.make_dense()
newshape = len(new_X)
# if oldshape != newshape:
# print(nudges)
# print("after {} and making dense".format(i), new_X.pmf.shape)
dct = {o: new_X[o] if o in new_X.outcomes else 0.0 for o in outcomes}
#print(outcomes, dct)
new_X = dit.Distribution(dct)
new_X.set_rv_names(rvs)
new_X._mask = mask
return new_X
