def test_opposite():
bn = pbn.SemiparametricBN(["a", "b"])
o = pbn.AddArc("a", "b", 1)
oppo = o.opposite(bn)
assert oppo.source() == 'a'
assert oppo.target() == 'b'
assert oppo.delta() == -1
assert type(oppo) == pbn.RemoveArc
o = pbn.RemoveArc("a", "b", 1)
oppo = o.opposite(bn)
assert oppo.source() == 'a'
assert oppo.target() == 'b'
assert oppo.delta() == -1
assert type(oppo) == pbn.AddArc
o = pbn.FlipArc("a", "b", 1)
oppo = o.opposite(bn)
assert oppo.source() == 'b'
assert oppo.target() == 'a'
assert oppo.delta() == -1
assert type(oppo) == pbn.FlipArc
bn.set_node_type("a", pbn.LinearGaussianCPDType())
o = pbn.ChangeNodeType("a", pbn.CKDEType(), 1)
oppo = o.opposite(bn)
assert oppo.node() == 'a'
assert oppo.node_type() == pbn.LinearGaussianCPDType()
assert oppo.delta() == -1
assert type(oppo) == pbn.ChangeNodeType
def test_holdout_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
hl = pbn.HoldoutLikelihood(df_null, 0.2, seed)
assert np.isclose(
hl.local_score(spbn, 'a', []),
numpy_local_score(pbn.CKDEType(),
hl.training_data().to_pandas(),
hl.test_data().to_pandas(), 'a', []))
assert np.isclose(
hl.local_score(spbn, 'b', ['a']),
numpy_local_score(pbn.LinearGaussianCPDType(),
hl.training_data().to_pandas(),
hl.test_data().to_pandas(), 'b', ['a']))
assert np.isclose(
hl.local_score(spbn, 'c', ['a', 'b']),
numpy_local_score(pbn.CKDEType(),
hl.training_data().to_pandas(),
hl.test_data().to_pandas(), 'c', ['a', 'b']))
assert np.isclose(
hl.local_score(spbn, 'd', ['a', 'b', 'c']),
numpy_local_score(pbn.LinearGaussianCPDType(),
hl.training_data().to_pandas(),
hl.test_data().to_pandas(), 'd', ['a', 'b', 'c']))
assert np.isclose(
hl.local_score(spbn, 'd', ['a', 'b', 'c']),
numpy_local_score(pbn.LinearGaussianCPDType(),
hl.training_data().to_pandas(),
hl.test_data().to_pandas(), 'd', ['b', 'c', 'a']))
assert hl.local_score(spbn, 'a') == hl.local_score(spbn, 'a',
spbn.parents('a'))
assert hl.local_score(spbn, 'b') == hl.local_score(spbn, 'b',
spbn.parents('b'))
assert hl.local_score(spbn, 'c') == hl.local_score(spbn, 'c',
spbn.parents('c'))
assert hl.local_score(spbn, 'd') == hl.local_score(spbn, 'd',
spbn.parents('d'))
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_apply():
gbn = pbn.GaussianNetwork(['a', 'b', 'c', 'd'])
assert gbn.num_arcs() == 0
assert not gbn.has_arc('a', 'b')
o = pbn.AddArc("a", "b", 1)
o.apply(gbn)
assert gbn.num_arcs() == 1
assert gbn.has_arc('a', 'b')
o = pbn.FlipArc("a", "b", 1)
o.apply(gbn)
assert gbn.num_arcs() == 1
assert not gbn.has_arc('a', 'b')
assert gbn.has_arc('b', 'a')
o = pbn.RemoveArc("b", "a", 1)
o.apply(gbn)
assert gbn.num_arcs() == 0
assert not gbn.has_arc('b', 'a')
o = pbn.ChangeNodeType("a", pbn.CKDEType(), 1)
with pytest.raises(ValueError) as ex:
o.apply(gbn)
assert "Wrong factor type" in str(ex.value)
spbn = pbn.SemiparametricBN(['a', 'b', 'c', 'd'])
assert spbn.num_arcs() == 0
o = pbn.ChangeNodeType("a", pbn.CKDEType(), 1)
assert (spbn.node_type('a') == pbn.UnknownFactorType())
o.apply(spbn)
assert (spbn.node_type('a') == pbn.CKDEType())
assert not spbn.has_arc('a', 'b')
o = pbn.AddArc("a", "b", 1)
o.apply(spbn)
assert spbn.num_arcs() == 1
assert spbn.has_arc('a', 'b')
o = pbn.FlipArc("a", "b", 1)
o.apply(spbn)
assert spbn.num_arcs() == 1
assert not spbn.has_arc('a', 'b')
assert spbn.has_arc('b', 'a')
o = pbn.RemoveArc("b", "a", 1)
o.apply(spbn)
assert spbn.num_arcs() == 0
assert not spbn.has_arc('b', 'a')
def test_holdout_score():
gbn = pbn.GaussianNetwork([('a', 'b'), ('a', 'c'), ('a', 'd'), ('b', 'c'),
('b', 'd'), ('c', 'd')])
hl = pbn.HoldoutLikelihood(df, 0.2, 0)
assert np.isclose(
hl.score(gbn),
(hl.local_score(gbn, 'a', []) + hl.local_score(gbn, 'b', ['a']) +
hl.local_score(gbn, 'c', ['a', 'b']) +
hl.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(hl.score(spbn),
(hl.local_score(spbn, 'a') + hl.local_score(spbn, 'b') +
hl.local_score(spbn, 'c') + hl.local_score(spbn, 'd')))
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_holdout_local_score_spbn():
spbn = pbn.SemiparametricBN([('a', 'b'), ('a', 'c'), ('a', 'd'),
('b', 'c'), ('b', 'd'), ('c', 'd')],
[('a', pbn.CKDEType()), ('c', pbn.CKDEType())])
hl = pbn.HoldoutLikelihood(df, 0.2, seed)
assert np.isclose(
hl.local_score(spbn, 'a', []),
numpy_local_score(pbn.CKDEType(),
hl.training_data().to_pandas(),
hl.test_data().to_pandas(), 'a', []))
assert np.isclose(
hl.local_score(spbn, 'b', ['a']),
numpy_local_score(pbn.LinearGaussianCPDType(),
hl.training_data().to_pandas(),
hl.test_data().to_pandas(), 'b', ['a']))
assert np.isclose(
hl.local_score(spbn, 'c', ['a', 'b']),
numpy_local_score(pbn.CKDEType(),
hl.training_data().to_pandas(),
hl.test_data().to_pandas(), 'c', ['a', 'b']))
assert np.isclose(
hl.local_score(spbn, 'd', ['a', 'b', 'c']),
numpy_local_score(pbn.LinearGaussianCPDType(),
hl.training_data().to_pandas(),
hl.test_data().to_pandas(), 'd', ['a', 'b', 'c']))
assert np.isclose(
hl.local_score(spbn, 'd', ['a', 'b', 'c']),
numpy_local_score(pbn.LinearGaussianCPDType(),
hl.training_data().to_pandas(),
hl.test_data().to_pandas(), 'd', ['b', 'c', 'a']))
assert hl.local_score(spbn, 'a') == hl.local_score(spbn, 'a',
spbn.parents('a'))
assert hl.local_score(spbn, 'b') == hl.local_score(spbn, 'b',
spbn.parents('b'))
assert hl.local_score(spbn, 'c') == hl.local_score(spbn, 'c',
spbn.parents('c'))
assert hl.local_score(spbn, 'd') == hl.local_score(spbn, 'd',
spbn.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']))