def test_independence(self, graph_gen, seed, num_nodes):
"""
test whether the relation is accurate, implicitely tests sequence of
nodes.
"""
sm = graph_gen(num_nodes=num_nodes, seed=seed, weight=None)
nodes = sm.nodes()
df = generate_binary_dataframe(
sm,
n_samples=100000,
distribution="normal",
seed=seed,
noise_scale=0.5,
intercept=False,
)
tol = 0.05
for node in nodes:
if node == "aa":
continue
joint_proba, factored_proba = calculate_proba(df, "aa", node)
if node == "ab":
# this is the only link
assert not np.isclose(
joint_proba, factored_proba, atol=tol, rtol=0), df.mean()
else:
assert np.isclose(joint_proba,
factored_proba,
atol=tol,
rtol=0)
def test_f1score_generated_binary(self):
""" Binary strucutre learned should have good f1 score """
np.random.seed(10)
sm = generate_structure(5, 2.0)
df = generate_binary_dataframe(sm,
1000,
intercept=False,
noise_scale=0.1,
seed=10)
dist_type_schema = {i: "bin" for i in range(df.shape[1])}
sm_fitted = from_pandas(
df,
dist_type_schema=dist_type_schema,
lasso_beta=0.1,
ridge_beta=0.0,
w_threshold=0.1,
use_bias=False,
)
right_edges = sm.edges
n_predictions_made = len(sm_fitted.edges)
n_correct_predictions = len(
set(sm_fitted.edges).intersection(set(right_edges)))
n_relevant_predictions = len(right_edges)
precision = n_correct_predictions / n_predictions_made
recall = n_correct_predictions / n_relevant_predictions
f1_score = 2 * (precision * recall) / (precision + recall)
assert f1_score > 0.8
def test_dataframe(self, graph, distribution, noise_std, intercept, seed,
kernel):
"""
Tests equivalence of dataframe wrapper
"""
data = generate_binary_data(
graph,
100,
distribution,
noise_scale=noise_std,
seed=seed,
intercept=intercept,
kernel=kernel,
)
df = generate_binary_dataframe(
graph,
100,
distribution,
noise_scale=noise_std,
seed=seed,
intercept=intercept,
kernel=kernel,
)
assert np.array_equal(data, df[list(graph.nodes())].values)
