def naive_bayes_plus_parents(
categories: int = 3,
samples: int = 500,
parents: int = 3,
children: int = 3,
p_z: float = 0.9,
p_c: float = 0.9,
percentage_not_missing: float = 0,
seed: int = 22,
) -> Tuple[pd.DataFrame, StructureModel, Dict, np.array]:
"""
p0 ... pn
\\ | /
z
/ | \\
c0 ... cm
z = mode of parents with probability p_z, otherwise mode of parents + 1 mod n_categories
c0 = z with prob. p_c, otherwise it is z + 1 mod n_categories
if no p are give, sample z from the categories uniformly
Args:
categories: number of categories
samples: number of samples
parents: number of parents, n as shown above
children: number of children, m as above
p_z: probability that z = mode(parents)
p_c: probability that children equals parent
percentage_not_missing: percentage of the LV that is provided. The default is 0, i.e. the LV is not observed
seed: seed for random generator
Returns:
data: sampled pandas dataframe, missing data on z
sm: structure model
node_states: dictionary of list of states for each node
true_lv_values: true values of latent variable
"""
def mode(lst: Iterable) -> Any:
return Counter(lst).most_common()[0][0] if len(lst) > 0 else np.nan
np.random.seed(seed)
par_samples = np.random.choice(categories, size=[samples, parents])
if parents == 0:
true_lv_values = np.random.choice(categories, size=[samples, 1])
else:
true_lv_values = np.array(
[
[(mode(el) + np.random.choice(2, p=[p_z, 1 - p_z])) % categories]
for el in par_samples
]
)
child_samples = np.random.random(size=[samples, children])
aux = true_lv_values.repeat(children, axis=1)
child_samples = np.where(child_samples < p_c, aux, (aux + 1) % categories)
df = pd.concat(
[
pd.DataFrame(par_samples, columns=[f"p_{i}" for i in range(parents)]),
pd.DataFrame(child_samples, columns=[f"c_{i}" for i in range(children)]),
pd.DataFrame(true_lv_values, columns=["z"]),
],
axis=1,
)
df.loc[int(samples * percentage_not_missing) :, "z"] = np.nan
sm = StructureModel()
sm.add_edges_from([(f"p_{i}", "z") for i in range(parents)])
sm.add_edges_from([("z", f"c_{i}") for i in range(children)])
node_states = {"z": list(range(categories))}
for i in range(parents):
node_states[f"p_{i}"] = list(range(categories))
for i in range(children):
node_states[f"c_{i}"] = list(range(categories))
return df, sm, node_states, true_lv_values
def test_graph_not_a_dag(self):
graph = StructureModel()
graph.add_edges_from([(0, 1), (1, 2), (2, 0)])
with pytest.raises(ValueError, match="Provided graph is not a DAG"):
_ = sem_generator(graph=graph, seed=42)