def get_insert_dist(self, n_features, initial_seq):
if isinstance(initial_seq[0], int) \
or np.issubdtype(initial_seq[0], np.integer): #equal distribution
return DiscreteDistribution.from_samples(range(n_features))
else: #distribution based on initial sequence
return MultivariateGaussianDistribution.from_samples(
np.array(initial_seq))
def train_model(data: np.ndarray,
clusters: int = 5,
init_nodes: list = None) -> BayesianNetwork:
bn = BayesNet()
#Сluster the initial data in order to fill in a hidden variable based on the distribution of clusters
kmeans = KMeans(n_clusters=clusters, random_state=0).fit(data)
labels = kmeans.labels_
hidden_dist = DiscreteDistribution.from_samples(labels)
hidden_var = np.array(hidden_dist.sample(data.shape[0]))
new_data = np.column_stack((data, hidden_var))
latent = (new_data.shape[1]) - 1
#Train the network structure on data taking into account a hidden variable
bn = hc_rr(new_data, latent=latent, init_nodes=init_nodes)
structure = []
nodes = sorted(list(bn.nodes()))
for rv in nodes:
structure.append(tuple(bn.F[rv]['parents']))
structure = tuple(structure)
bn = BayesianNetwork.from_structure(new_data, structure)
bn.bake()
#Learn a hidden variable
hidden_var = np.array([np.nan] * (data.shape[0]))
new_data = np.column_stack((data, hidden_var))
bn.predict(new_data)
bn.fit(new_data)
bn.bake()
return (bn)
def get_match_dist(self, index, n_features, initial_seq):
if isinstance(initial_seq[index], int):
return DiscreteDistribution.from_samples(range(n_features))
#return DiscreteDistribution.from_samples(np.concatenate(
# (np.repeat(index, INITIAL_EMPHASIS), range(n_features))))
else:
return MultivariateGaussianDistribution.from_samples(
np.concatenate(
(np.tile(index,
(INITIAL_EMPHASIS, 1)), np.array(initial_seq))))
def worker(node: Type[BaseNode]) -> DiscreteParams:
parents = node.disc_parents + node.cont_parents
if not parents:
dist = DiscreteDistribution.from_samples(
data[node.name].values)
cprob = list(dict(sorted(dist.items())).values())
vals = sorted(
[str(x) for x in list(dist.parameters[0].keys())])
else:
dist = DiscreteDistribution.from_samples(
data[node.name].values)
vals = sorted(
[str(x) for x in list(dist.parameters[0].keys())])
dist = ConditionalProbabilityTable.from_samples(
data[parents + [node.name]].values)
params = dist.parameters[0]
cprob = dict()
for i in range(0, len(params), len(vals)):
probs = []
for j in range(i, (i + len(vals))):
probs.append(params[j][-1])
combination = [str(x) for x in params[i][0:len(parents)]]
cprob[str(combination)] = probs
return {"cprob": cprob, 'vals': vals}
def test_discrete():
d = DiscreteDistribution({'A': 0.25, 'C': 0.25, 'G': 0.25, 'T': 0.25})
assert_equal(d.log_probability('C'), -1.3862943611198906)
assert_equal(d.log_probability('A'), d.log_probability('C'))
assert_equal(d.log_probability('G'), d.log_probability('T'))
assert_equal(d.log_probability('a'), float('-inf'))
seq = "ACGTACGTTGCATGCACGCGCTCTCGCGC"
d.fit(list(seq))
assert_equal(d.log_probability('C'), -0.9694005571881036)
assert_equal(d.log_probability('A'), -1.9810014688665833)
assert_equal(d.log_probability('T'), -1.575536360758419)
seq = "ACGTGTG"
d.fit(list(seq), weights=[0., 1., 2., 3., 4., 5., 6.])
assert_equal(d.log_probability('A'), float('-inf'))
assert_equal(d.log_probability('C'), -3.044522437723423)
assert_equal(d.log_probability('G'), -0.5596157879354228)
d.summarize(list("ACG"), weights=[0., 1., 2.])
d.summarize(list("TGT"), weights=[3., 4., 5.])
d.summarize(list("G"), weights=[6.])
d.from_summaries()
assert_equal(d.log_probability('A'), float('-inf'))
assert_equal(round(d.log_probability('C'), 4), -3.0445)
assert_equal(round(d.log_probability('G'), 4), -0.5596)
d = DiscreteDistribution({'A': 0.0, 'B': 1.0})
d.summarize(list("ABABABAB"))
d.summarize(list("ABAB"))
d.summarize(list("BABABABABABABABABA"))
d.from_summaries(inertia=0.75)
assert_equal(d.parameters[0], {'A': 0.125, 'B': 0.875})
d = DiscreteDistribution({'A': 0.0, 'B': 1.0})
d.summarize(list("ABABABAB"))
d.summarize(list("ABAB"))
d.summarize(list("BABABABABABABABABA"))
d.from_summaries(inertia=0.5)
assert_equal(d.parameters[0], {'A': 0.25, 'B': 0.75})
d.freeze()
d.fit(list('ABAABBAAAAAAAAAAAAAAAAAA'))
assert_equal(d.parameters[0], {'A': 0.25, 'B': 0.75})
d = DiscreteDistribution.from_samples(['A', 'B', 'A', 'A'])
assert_equal(d.parameters[0], {'A': 0.75, 'B': 0.25})
d = DiscreteDistribution.from_samples(['A', 'B', 'A', 'A'],
pseudocount=0.5)
assert_equal(d.parameters[0], {'A': 0.70, 'B': 0.30})
d = DiscreteDistribution.from_samples(['A', 'B', 'A', 'A'], pseudocount=6)
assert_equal(d.parameters[0], {'A': 0.5625, 'B': 0.4375})
e = Distribution.from_json(d.to_json())
assert_equal(e.name, "DiscreteDistribution")
assert_equal(e.parameters[0], {'A': 0.5625, 'B': 0.4375})
f = pickle.loads(pickle.dumps(e))
assert_equal(f.name, "DiscreteDistribution")
assert_equal(f.parameters[0], {'A': 0.5625, 'B': 0.4375})
def test_discrete_robust_json_serialization():
d = DiscreteDistribution.from_samples(['A', 'B', 'A', 'A'], pseudocount=6)
e = from_json(d.to_json())
assert_equal(e.name, "DiscreteDistribution")
assert_equal(e.parameters[0], {'A': 0.5625, 'B': 0.4375})
def test_discrete():
d = DiscreteDistribution({'A': 0.25, 'C': 0.25, 'G': 0.25, 'T': 0.25})
assert_equal(d.log_probability('C'), -1.3862943611198906)
assert_equal(d.log_probability('A'), d.log_probability('C'))
assert_equal(d.log_probability('G'), d.log_probability('T'))
assert_equal(d.log_probability('a'), float('-inf'))
seq = "ACGTACGTTGCATGCACGCGCTCTCGCGC"
d.fit(list(seq))
assert_equal(d.log_probability('C'), -0.9694005571881036)
assert_equal(d.log_probability('A'), -1.9810014688665833)
assert_equal(d.log_probability('T'), -1.575536360758419)
seq = "ACGTGTG"
d.fit(list(seq), weights=[0., 1., 2., 3., 4., 5., 6.])
assert_equal(d.log_probability('A'), float('-inf'))
assert_equal(d.log_probability('C'), -3.044522437723423)
assert_equal(d.log_probability('G'), -0.5596157879354228)
d.summarize(list("ACG"), weights=[0., 1., 2.])
d.summarize(list("TGT"), weights=[3., 4., 5.])
d.summarize(list("G"), weights=[6.])
d.from_summaries()
assert_equal(d.log_probability('A'), float('-inf'))
assert_equal(round(d.log_probability('C'), 4), -3.0445)
assert_equal(round(d.log_probability('G'), 4), -0.5596)
d = DiscreteDistribution({'A': 0.0, 'B': 1.0})
d.summarize(list("ABABABAB"))
d.summarize(list("ABAB"))
d.summarize(list("BABABABABABABABABA"))
d.from_summaries(inertia=0.75)
assert_equal(d.parameters[0], {'A': 0.125, 'B': 0.875})
d = DiscreteDistribution({'A': 0.0, 'B': 1.0})
d.summarize(list("ABABABAB"))
d.summarize(list("ABAB"))
d.summarize(list("BABABABABABABABABA"))
d.from_summaries(inertia=0.5)
assert_equal(d.parameters[0], {'A': 0.25, 'B': 0.75})
d.freeze()
d.fit(list('ABAABBAAAAAAAAAAAAAAAAAA'))
assert_equal(d.parameters[0], {'A': 0.25, 'B': 0.75})
d = DiscreteDistribution.from_samples(['A', 'B', 'A', 'A'])
assert_equal(d.parameters[0], {'A': 0.75, 'B': 0.25})
d = DiscreteDistribution.from_samples(['A', 'B', 'A', 'A'], pseudocount=0.5)
assert_equal(d.parameters[0], {'A': 0.70, 'B': 0.30})
d = DiscreteDistribution.from_samples(['A', 'B', 'A', 'A'], pseudocount=6)
assert_equal(d.parameters[0], {'A': 0.5625, 'B': 0.4375})
e = Distribution.from_json(d.to_json())
assert_equal(e.name, "DiscreteDistribution")
assert_equal(e.parameters[0], {'A': 0.5625, 'B': 0.4375})
f = pickle.loads(pickle.dumps(e))
assert_equal(f.name, "DiscreteDistribution")
assert_equal(f.parameters[0], {'A': 0.5625, 'B': 0.4375})