def test_cvl_local_score_gbn():
gbn = pbn.GaussianNetwork([('a', 'b'), ('a', 'c'), ('a', 'd'), ('b', 'c'),
('b', 'd'), ('c', 'd')])
cvl = pbn.CVLikelihood(df, 10, seed)
assert np.isclose(
cvl.local_score(gbn, 'a', []),
numpy_local_score(pbn.LinearGaussianCPDType(), df, 'a', []))
assert np.isclose(
cvl.local_score(gbn, 'b', ['a']),
numpy_local_score(pbn.LinearGaussianCPDType(), df, 'b', ['a']))
assert np.isclose(
cvl.local_score(gbn, 'c', ['a', 'b']),
numpy_local_score(pbn.LinearGaussianCPDType(), df, 'c', ['a', 'b']))
assert np.isclose(
cvl.local_score(gbn, 'd', ['a', 'b', 'c']),
numpy_local_score(pbn.LinearGaussianCPDType(), df, 'd',
['a', 'b', 'c']))
assert np.isclose(cvl.local_score(gbn, 'd', ['a', 'b', 'c']),
cvl.local_score(gbn, 'd', ['b', 'c', 'a']))
assert cvl.local_score(gbn,
'a') == cvl.local_score(gbn, 'a', gbn.parents('a'))
assert cvl.local_score(gbn,
'b') == cvl.local_score(gbn, 'b', gbn.parents('b'))
assert cvl.local_score(gbn,
'c') == cvl.local_score(gbn, 'c', gbn.parents('c'))
assert cvl.local_score(gbn,
'd') == cvl.local_score(gbn, 'd', gbn.parents('d'))
def test_create_change_node():
gbn = pbn.GaussianNetwork(['a', 'b', 'c', 'd'])
cv = pbn.CVLikelihood(df)
node_op = pbn.ChangeNodeTypeSet()
with pytest.raises(ValueError) as ex:
node_op.cache_scores(gbn, cv)
assert "can only be used with non-homogeneous" in str(ex.value)
def test_cvl_create():
s = pbn.CVLikelihood(df)
assert len(list(s.cv)) == 10
s = pbn.CVLikelihood(df, 5)
assert len(list(s.cv)) == 5
s = pbn.CVLikelihood(df, 10, 0)
assert len(list(s.cv)) == 10
s2 = pbn.CVLikelihood(df, 10, 0)
assert len(list(s2.cv)) == 10
for (train_cv, test_cv), (train_cv2, test_cv2) in zip(s.cv, s2.cv):
assert train_cv.equals(
train_cv2), "Train CV DataFrames with the same seed are not equal."
assert test_cv.equals(
test_cv2), "Test CV DataFrames with the same seed are not equal."
with pytest.raises(ValueError) as ex:
s = pbn.CVLikelihood(df, SIZE + 1)
assert "Cannot split" in str(ex.value)
def test_cvl_local_score_spbn():
spbn = pbn.SemiparametricBN([('a', 'b'), ('a', 'c'), ('a', 'd'),
('b', 'c'), ('b', 'd'), ('c', 'd')],
[('a', pbn.CKDEType()), ('c', pbn.CKDEType())])
cvl = pbn.CVLikelihood(df, 10, seed)
assert np.isclose(cvl.local_score(spbn, 'a', []),
numpy_local_score(pbn.CKDEType(), df, 'a', []))
assert np.isclose(
cvl.local_score(spbn, 'b', ['a']),
numpy_local_score(pbn.LinearGaussianCPDType(), df, 'b', ['a']))
assert np.isclose(cvl.local_score(spbn, 'c', ['a', 'b']),
numpy_local_score(pbn.CKDEType(), df, 'c', ['a', 'b']))
assert np.isclose(
cvl.local_score(spbn, 'd', ['a', 'b', 'c']),
numpy_local_score(pbn.LinearGaussianCPDType(), df, 'd',
['a', 'b', 'c']))
assert np.isclose(
cvl.local_score(spbn, 'd', ['a', 'b', 'c']),
numpy_local_score(pbn.LinearGaussianCPDType(), df, 'd',
['b', 'c', 'a']))
assert cvl.local_score(spbn,
'a') == cvl.local_score(spbn, 'a',
spbn.parents('a'))
assert cvl.local_score(spbn,
'b') == cvl.local_score(spbn, 'b',
spbn.parents('b'))
assert cvl.local_score(spbn,
'c') == cvl.local_score(spbn, 'c',
spbn.parents('c'))
assert cvl.local_score(spbn,
'd') == cvl.local_score(spbn, 'd',
spbn.parents('d'))
assert np.isclose(
cvl.local_score_node_type(spbn, pbn.LinearGaussianCPDType(), 'a', []),
numpy_local_score(pbn.LinearGaussianCPDType(), df, 'a', []))
assert np.isclose(
cvl.local_score_node_type(spbn, pbn.CKDEType(), 'b', ['a']),
numpy_local_score(pbn.CKDEType(), df, 'b', ['a']))
assert np.isclose(
cvl.local_score_node_type(spbn, pbn.LinearGaussianCPDType(), 'c',
['a', 'b']),
numpy_local_score(pbn.LinearGaussianCPDType(), df, 'c', ['a', 'b']))
assert np.isclose(
cvl.local_score_node_type(spbn, pbn.CKDEType(), 'd', ['a', 'b', 'c']),
numpy_local_score(pbn.CKDEType(), df, 'd', ['a', 'b', 'c']))
assert np.isclose(
cvl.local_score_node_type(spbn, pbn.CKDEType(), 'd', ['a', 'b', 'c']),
numpy_local_score(pbn.CKDEType(), df, 'd', ['b', 'c', 'a']))
def test_cvl_score():
gbn = pbn.GaussianNetwork([('a', 'b'), ('a', 'c'), ('a', 'd'), ('b', 'c'),
('b', 'd'), ('c', 'd')])
cv = pbn.CVLikelihood(df, 10, 0)
assert np.isclose(
cv.score(gbn),
(cv.local_score(gbn, 'a', []) + cv.local_score(gbn, 'b', ['a']) +
cv.local_score(gbn, 'c', ['a', 'b']) +
cv.local_score(gbn, 'd', ['a', 'b', 'c'])))
spbn = pbn.SemiparametricBN([('a', 'b'), ('a', 'c'), ('a', 'd'),
('b', 'c'), ('b', 'd'), ('c', 'd')],
[('a', pbn.CKDEType()), ('c', pbn.CKDEType())])
assert np.isclose(cv.score(spbn),
(cv.local_score(spbn, 'a') + cv.local_score(spbn, 'b') +
cv.local_score(spbn, 'c') + cv.local_score(spbn, 'd')))
def test_cvl_local_score_gbn_null():
gbn = pbn.GaussianNetwork([('a', 'b'), ('a', 'c'), ('a', 'd'), ('b', 'c'),
('b', 'd'), ('c', 'd')])
np.random.seed(0)
a_null = np.random.randint(0, SIZE, size=100)
b_null = np.random.randint(0, SIZE, size=100)
c_null = np.random.randint(0, SIZE, size=100)
d_null = np.random.randint(0, SIZE, size=100)
df_null = df.copy()
df_null.loc[df_null.index[a_null], 'a'] = np.nan
df_null.loc[df_null.index[b_null], 'b'] = np.nan
df_null.loc[df_null.index[c_null], 'c'] = np.nan
df_null.loc[df_null.index[d_null], 'd'] = np.nan
cvl = pbn.CVLikelihood(df_null, 10, seed)
assert np.isclose(
cvl.local_score(gbn, 'a', []),
numpy_local_score(pbn.LinearGaussianCPDType(), df_null, 'a', []))
assert np.isclose(
cvl.local_score(gbn, 'b', ['a']),
numpy_local_score(pbn.LinearGaussianCPDType(), df_null, 'b', ['a']))
assert np.isclose(
cvl.local_score(gbn, 'c', ['a', 'b']),
numpy_local_score(pbn.LinearGaussianCPDType(), df_null, 'c',
['a', 'b']))
assert np.isclose(
cvl.local_score(gbn, 'd', ['a', 'b', 'c']),
numpy_local_score(pbn.LinearGaussianCPDType(), df_null, 'd',
['a', 'b', 'c']))
assert np.isclose(cvl.local_score(gbn, 'd', ['a', 'b', 'c']),
cvl.local_score(gbn, 'd', ['b', 'c', 'a']))
assert cvl.local_score(gbn,
'a') == cvl.local_score(gbn, 'a', gbn.parents('a'))
assert cvl.local_score(gbn,
'b') == cvl.local_score(gbn, 'b', gbn.parents('b'))
assert cvl.local_score(gbn,
'c') == cvl.local_score(gbn, 'c', gbn.parents('c'))
assert cvl.local_score(gbn,
'd') == cvl.local_score(gbn, 'd', gbn.parents('d'))
def test_find_max():
spbn = pbn.SemiparametricBN(['a', 'b', 'c', 'd'])
cv = pbn.CVLikelihood(df)
arcs = pbn.ArcOperatorSet()
node_type = pbn.ChangeNodeTypeSet()
arcs.cache_scores(spbn, cv)
spbn.set_unknown_node_types(df)
node_type.cache_scores(spbn, cv)
arcs_max = arcs.find_max(spbn)
node_max = node_type.find_max(spbn)
pool = pbn.OperatorPool([arcs, node_type])
pool.cache_scores(spbn, cv)
op_combined = pool.find_max(spbn)
if arcs_max.delta() >= node_max.delta():
assert op_combined == arcs_max
else:
assert op_combined == node_max
def test_cvl_local_score_null_spbn():
spbn = pbn.SemiparametricBN([('a', 'b'), ('a', 'c'), ('a', 'd'),
('b', 'c'), ('b', 'd'), ('c', 'd')],
[('a', pbn.CKDEType()), ('c', pbn.CKDEType())])
np.random.seed(0)
a_null = np.random.randint(0, SIZE, size=100)
b_null = np.random.randint(0, SIZE, size=100)
c_null = np.random.randint(0, SIZE, size=100)
d_null = np.random.randint(0, SIZE, size=100)
df_null = df.copy()
df_null.loc[df_null.index[a_null], 'a'] = np.nan
df_null.loc[df_null.index[b_null], 'b'] = np.nan
df_null.loc[df_null.index[c_null], 'c'] = np.nan
df_null.loc[df_null.index[d_null], 'd'] = np.nan
cvl = pbn.CVLikelihood(df_null, 10, seed)
assert np.isclose(cvl.local_score(spbn, 'a', []),
numpy_local_score(pbn.CKDEType(), df_null, 'a', []))
assert np.isclose(
cvl.local_score(spbn, 'b', ['a']),
numpy_local_score(pbn.LinearGaussianCPDType(), df_null, 'b', ['a']))
assert np.isclose(
cvl.local_score(spbn, 'c', ['a', 'b']),
numpy_local_score(pbn.CKDEType(), df_null, 'c', ['a', 'b']))
assert np.isclose(
cvl.local_score(spbn, 'd', ['a', 'b', 'c']),
numpy_local_score(pbn.LinearGaussianCPDType(), df_null, 'd',
['a', 'b', 'c']))
assert np.isclose(
cvl.local_score(spbn, 'd', ['a', 'b', 'c']),
numpy_local_score(pbn.LinearGaussianCPDType(), df_null, 'd',
['b', 'c', 'a']))
assert cvl.local_score(spbn,
'a') == cvl.local_score(spbn, 'a',
spbn.parents('a'))
assert cvl.local_score(spbn,
'b') == cvl.local_score(spbn, 'b',
spbn.parents('b'))
assert cvl.local_score(spbn,
'c') == cvl.local_score(spbn, 'c',
spbn.parents('c'))
assert cvl.local_score(spbn,
'd') == cvl.local_score(spbn, 'd',
spbn.parents('d'))
assert np.isclose(
cvl.local_score_node_type(spbn, pbn.LinearGaussianCPDType(), 'a', []),
numpy_local_score(pbn.LinearGaussianCPDType(), df_null, 'a', []))
assert np.isclose(
cvl.local_score_node_type(spbn, pbn.CKDEType(), 'b', ['a']),
numpy_local_score(pbn.CKDEType(), df_null, 'b', ['a']))
assert np.isclose(
cvl.local_score_node_type(spbn, pbn.LinearGaussianCPDType(), 'c',
['a', 'b']),
numpy_local_score(pbn.LinearGaussianCPDType(), df_null, 'c',
['a', 'b']))
assert np.isclose(
cvl.local_score_node_type(spbn, pbn.CKDEType(), 'd', ['a', 'b', 'c']),
numpy_local_score(pbn.CKDEType(), df_null, 'd', ['a', 'b', 'c']))
assert np.isclose(
cvl.local_score_node_type(spbn, pbn.CKDEType(), 'd', ['a', 'b', 'c']),
numpy_local_score(pbn.CKDEType(), df_null, 'd', ['b', 'c', 'a']))