def test_leaf_categorical(self):
np.random.seed(17)
x = np.concatenate(
(
np.random.multivariate_normal([20, 20], np.eye(2), 500),
np.random.multivariate_normal([10, 10], np.eye(2), 500),
np.random.multivariate_normal([1, 1], np.eye(2), 500),
),
axis=0,
)
y = np.array([2] * 500 + [1] * 500 + [0] * 500).reshape(-1, 1)
data = concatenate_yx(y, x)
ds_context = Context(parametric_types=[Categorical])
ds_context.feature_size = 2
leaf = create_conditional_leaf(data, ds_context, [0])
l0 = likelihood(leaf, concatenate_yx(np.ones_like(y) * 0, x))
l1 = likelihood(leaf, concatenate_yx(np.ones_like(y) * 1, x))
l2 = likelihood(leaf, concatenate_yx(np.ones_like(y) * 2, x))
np.testing.assert_array_almost_equal(l0 + l1 + l2, 1.0)
self.assertTrue(np.all(l0[1000:1500] > 0.85))
self.assertTrue(np.all(l0[0:1000] < 0.15))
self.assertTrue(np.all(l1[500:1000] > 0.85))
self.assertTrue(np.all(l1[0:500] < 0.15))
self.assertTrue(np.all(l1[1000:1500] < 0.15))
self.assertTrue(np.all(l2[0:500] > 0.85))
self.assertTrue(np.all(l2[500:15000] < 0.15))
def test_leaf_bernoulli_bootstrap(self):
np.random.seed(17)
x = np.concatenate(
(
np.random.multivariate_normal([10, 10], np.eye(2), 100),
np.random.multivariate_normal([1, 1], np.eye(2), 100),
),
axis=0,
)
y = np.array([1] * 100 + [0] * 100).reshape(-1, 1)
data = concatenate_yx(y, x)
ds_context = Context(parametric_types=[Bernoulli])
ds_context.feature_size = 2
leaf = create_conditional_leaf(data, ds_context, [0])
l = likelihood(leaf, data)
neg_data = np.concatenate([1 - y, x], axis=1)
lneg = likelihood(leaf, neg_data)
np.testing.assert_array_almost_equal(l + lneg, 1.0)
self.assertTrue(np.all(l >= 0.5))
self.assertTrue(np.all(lneg < 0.5))
def test_leaf_gaussian(self):
np.random.seed(17)
x = np.concatenate(
(
np.random.multivariate_normal([10, 10], np.eye(2), 5000),
np.random.multivariate_normal([1, 1], np.eye(2), 5000),
),
axis=0,
)
y = np.array(
np.random.normal(20, 2, 5000).tolist() +
np.random.normal(60, 2, 5000).tolist()).reshape(-1, 1)
# associates y=20 with X=[10,10]
# associates y=60 with X=[1,1]
data = concatenate_yx(y, x)
ds_context = Context(parametric_types=[Gaussian])
ds_context.feature_size = 2
leaf = create_conditional_leaf(data, ds_context, [0])
self.assertFalse(np.any(np.isnan(likelihood(leaf, data))))
self.assertGreater(get_ll(leaf, [20, 10, 10]),
get_ll(leaf, [20, 1, 1]))
self.assertGreater(get_ll(leaf, [60, 1, 1]),
get_ll(leaf, [60, 10, 10]))
self.assertAlmostEqual(get_ll(leaf, [60, 1, 1]), 0.3476232862652)
self.assertAlmostEqual(get_ll(leaf, [20, 10, 10]), 0.3628922322773634)
def test_leaf_no_variance_gaussian(self):
np.random.seed(17)
x = np.concatenate(
(
np.random.multivariate_normal([10, 10], np.eye(2), 500),
np.random.multivariate_normal([1, 1], np.eye(2), 500),
),
axis=0,
)
y = np.array([1] * 1000).reshape(-1, 1)
data = concatenate_yx(y, x)
ds_context = Context(parametric_types=[Gaussian])
ds_context.feature_size = 2
leaf = create_conditional_leaf(data, ds_context, [0])
l = likelihood(leaf, data)
self.assertEqual(np.var(l[:, 0]), 0)
self.assertAlmostEqual(l[0, 0], 0.398942280401432)
data[:, 0] = 2
leaf = create_conditional_leaf(data, ds_context, [0])
l = likelihood(leaf, data)
self.assertEqual(np.var(l[:, 0]), 0)
self.assertAlmostEqual(l[0, 0], 0.398942280401432)
data3 = np.array(data)
data3[:, 0] = 3
leaf = create_conditional_leaf(data3, ds_context, [0])
l = likelihood(leaf, data)
self.assertAlmostEqual(np.var(l[:, 0]), 0)
self.assertAlmostEqual(l[0, 0], 0.241970724519143)
def test_naive_factorization(self):
np.random.seed(17)
data = np.arange(0, 1000).reshape(-1, 8)
parent = Sum()
parent.children.append(None)
ctx = Context()
ctx.feature_size = 4
scope = [1, 3, 4, 6]
data2 = np.array(data)
result = naive_factorization(data=data2,
parent=parent,
pos=0,
context=ctx,
scope=list(scope))
self.assertListEqual(data.tolist(), data2.tolist())
self.assertEqual(parent.children[0], result[0][1]['parent'])
y, x = get_YX(data, 4)
self.assertEqual(len(result), len(scope))
for i, s in enumerate(scope):
r = result[i]
self.assertEqual(len(r), 2)
self.assertEqual(r[0], SplittingOperations.CREATE_LEAF_NODE)
self.assertEqual(type(r[1]['parent']), Product)
self.assertEqual(r[1]['pos'], i)
self.assertListEqual(r[1]['scope'], [s])
self.assertListEqual(r[1]['data'].tolist(),
concatenate_yx(y[:, i], x).tolist())
def test_conditional(self):
labels = np.c_[np.zeros((500, 1)), np.ones((500, 1))]
features = np.c_[
np.r_[np.random.normal(5, 1, (500, 2)), np.random.normal(10, 1, (500, 2))]
]
train_data = concatenate_yx(labels, features)
ds_context = Context(
parametric_types=[Bernoulli] * labels.shape[1]
).add_domains(labels)
ds_context.feature_size = 2
def label_conditional(y, x):
from sklearn.cluster import KMeans
clusters = KMeans(
n_clusters=2, random_state=17, precompute_distances=True
).fit_predict(y)
return clusters
spn = learn_cspn_structure(
train_data,
ds_context,
split_rows=get_split_conditional_rows_KMeans(),
split_cols=getCIGroup(),
create_leaf=create_conditional_leaf,
label_conditional=label_conditional,
cluster_univariate=True,
)
def test_leaf_mpe_bernoulli(self):
np.random.seed(17)
x = np.concatenate(
(
np.random.multivariate_normal([10, 10], np.eye(2), 5000),
np.random.multivariate_normal([1, 1], np.eye(2), 5000),
),
axis=0,
)
y = np.array([0] * 5000 + [1] * 5000).reshape(-1, 1)
# associates y=0 with X=[10,10]
# associates y=1 with X=[1,1]
data = concatenate_yx(y, x)
ds_context = Context(parametric_types=[Bernoulli])
ds_context.feature_size = 2
leaf = create_conditional_leaf(data, ds_context, [0])
res = mpe(leaf, np.array([np.nan, 10, 10]).reshape(-1, 3))
self.assertAlmostEqual(res[0, 0], 0)
res = mpe(leaf, np.array([np.nan, 1, 1]).reshape(-1, 3))
self.assertAlmostEqual(res[0, 0], 1)
res = mpe(leaf, np.array([np.nan, 1, 1, np.nan, 10, 10]).reshape(-1, 3))
self.assertAlmostEqual(res[0, 0], 1)
self.assertAlmostEqual(res[1, 0], 0)
with self.assertRaises(AssertionError):
mpe(leaf, np.array([np.nan, 1, 1, np.nan, 10, 10, 5, 10, 10]).reshape(-1, 3))
def test_leaf_mpe_gaussian(self):
np.random.seed(17)
x = np.concatenate(
(
np.random.multivariate_normal([10, 10], np.eye(2), 5000),
np.random.multivariate_normal([1, 1], np.eye(2), 5000),
),
axis=0,
)
y = np.array(np.random.normal(20, 2, 5000).tolist() + np.random.normal(60, 2, 5000).tolist()).reshape(-1, 1)
# associates y=20 with X=[10,10]
# associates y=60 with X=[1,1]
data = concatenate_yx(y, x)
ds_context = Context(parametric_types=[Gaussian])
ds_context.feature_size = 2
# leaf = create_conditional_leaf(data, ds_context, [0])
leaf = create_parametric_leaf(data, ds_context, [0])
res = mpe(leaf, np.array([np.nan, 10, 10]).reshape(-1, 3))
self.assertAlmostEqual(res[0, 0], 20.435226001909466)
res = mpe(leaf, np.array([np.nan, 1, 1]).reshape(-1, 3))
self.assertAlmostEqual(res[0, 0], 59.4752193542575)
res = mpe(leaf, np.array([np.nan, 1, 1, np.nan, 10, 10]).reshape(-1, 3))
self.assertAlmostEqual(res[0, 0], 59.4752193542575)
self.assertAlmostEqual(res[1, 0], 20.435226001909466)
with self.assertRaises(AssertionError):
mpe(leaf, np.array([np.nan, 1, 1, np.nan, 10, 10, 5, 10, 10]).reshape(-1, 3))
def test_create_conditional(self):
np.random.seed(17)
data = np.arange(0, 1000).reshape(-1, 8)
parent = Sum()
parent.children.append(None)
ctx = Context()
ctx.feature_size = 4
scope = [1, 3, 4, 6]
data2 = np.array(data)
K = int(data.shape[0] * 0.25)
split_idx = np.array([0] * K + [1] * (data.shape[0] - K))
np.random.shuffle(split_idx)
y, x = get_YX(data, 4)
def label_conditional(local_y, local_x):
self.assertListEqual(local_y.tolist(), y.tolist())
self.assertListEqual(local_x.tolist(), x.tolist())
return split_idx
result = create_conditional(data=data2,
parent=parent,
pos=0,
context=ctx,
scope=list(scope),
label_conditional=label_conditional)
self.assertListEqual(data.tolist(), data2.tolist())
self.assertEqual(len(result), 2)
for i, r in enumerate(result):
self.assertEqual(r[0], SplittingOperations.GET_NEXT_OP)
self.assertIn('data', r[1])
self.assertEqual(parent.children[0], r[1]['parent'])
self.assertEqual(r[1]['pos'], i)
self.assertListEqual(scope, r[1]['scope'])
self.assertEqual(r[1]['data'].shape[1], data.shape[1])
conditional_node = result[0][1]['parent']
child_idx = conditional_supervised_likelihood(
conditional_node,
[np.zeros((data.shape[0], 1)),
np.ones((data.shape[0], 1))], data)
self.assertListEqual(result[0][1]['data'].tolist(),
data[child_idx[:, 0] == 0, :].tolist())
self.assertListEqual(result[1][1]['data'].tolist(),
data[child_idx[:, 0] == 1, :].tolist())
def test_create_sum_with_split(self):
np.random.seed(17)
data = np.arange(0, 1000).reshape(-1, 8)
parent = Sum()
parent.children.append(None)
ctx = Context()
ctx.feature_size = 4
scope = [1, 3, 4, 6]
data2 = np.array(data)
K = int(data.shape[0] * 0.25)
split_idx = np.array([0] * K + [1] * (data.shape[0] - K))
np.random.shuffle(split_idx)
def split_rows(data, context, scope):
result = []
result.append((data[split_idx == 0, :], scope, 0.25))
result.append((data[split_idx == 1, :], scope, 0.75))
return result
result = create_sum(data=data2,
parent=parent,
pos=0,
context=ctx,
scope=list(scope),
split_rows=split_rows,
split_on_sum=True)
self.assertListEqual(data.tolist(), data2.tolist())
self.assertEqual(len(result), 2)
for i, r in enumerate(result):
self.assertEqual(r[0], SplittingOperations.GET_NEXT_OP)
self.assertIn('data', r[1])
self.assertEqual(parent.children[0], r[1]['parent'])
self.assertEqual(r[1]['pos'], i)
self.assertListEqual(scope, r[1]['scope'])
self.assertEqual(r[1]['data'].shape[1], data.shape[1])
self.assertEqual(r[1]['data'].shape[0],
int(np.sum(split_idx == i)))
self.assertListEqual(result[0][1]['data'].tolist(),
data[split_idx == 0, :].tolist())
self.assertListEqual(result[1][1]['data'].tolist(),
data[split_idx == 1, :].tolist())
self.assertAlmostEqual(np.sum(parent.children[0].weights), 1.0)
def test_leaf_sampling(self):
np.random.seed(17)
x = np.concatenate(
(
np.random.multivariate_normal([10, 10], np.eye(2), 5000),
np.random.multivariate_normal([1, 1], np.eye(2), 5000),
),
axis=0,
)
y = np.array(
np.random.normal(20, 2, 5000).tolist() +
np.random.normal(60, 2, 5000).tolist()).reshape(-1, 1)
# associates y=20 with X=[10,10]
# associates y=60 with X=[1,1]
data = concatenate_yx(y, x)
ds_context = Context(parametric_types=[Gaussian])
ds_context.feature_size = 2
leaf = create_conditional_leaf(data, ds_context, [0])
res = sample_instances(
leaf,
np.array([np.nan, 10, 10] * 1000).reshape(-1, 3), 17)
self.assertAlmostEqual(np.mean(res[:, 0]), 20.456669723751173)
res = sample_instances(leaf,
np.array([np.nan, 1, 1] * 1000).reshape(-1, 3),
17)
self.assertAlmostEqual(np.mean(res[:, 0]), 59.496663076099196)
res = sample_instances(
leaf,
np.array([np.nan, 1, 1, np.nan, 10, 10] * 1000).reshape(-1, 3), 17)
self.assertAlmostEqual(np.mean(res[::2, 0]), 59.546359637084564)
self.assertAlmostEqual(np.mean(res[1::2, 0]), 20.452118792501008)
with self.assertRaises(AssertionError):
sample_instances(
leaf,
np.array([np.nan, 1, 1, np.nan, 10, 10, 5, 10,
10]).reshape(-1, 3), 17)
def test_leaf_no_variance_bernoulli(self):
np.random.seed(17)
x = np.concatenate(
(
np.random.multivariate_normal([10, 10], np.eye(2), 500),
np.random.multivariate_normal([1, 1], np.eye(2), 500),
),
axis=0,
)
y = np.array([1] * 1000).reshape(-1, 1)
data = concatenate_yx(y, x)
ds_context = Context(parametric_types=[Bernoulli])
ds_context.feature_size = 2
leaf = create_conditional_leaf(data, ds_context, [0])
l = likelihood(leaf, data)
self.assertTrue(np.all(l >= 0.5))
def test_remove_non_informative_features(self):
np.random.seed(17)
data = np.arange(0, 1000).reshape(-1, 8)
data[:, 1] = 1
data[:, 3] = 3
parent = Sum()
parent.children.append(None)
ctx = Context()
ctx.feature_size = 4
scope = [1, 3, 4, 6]
data2 = np.array(data)
y, x = get_YX(data, 4)
uninformative_features_idx = np.var(y, 0) == 0
result = remove_non_informative_features(
data=data2,
parent=parent,
pos=0,
context=ctx,
scope=list(scope),
uninformative_features_idx=uninformative_features_idx)
self.assertListEqual(data.tolist(), data2.tolist())
self.assertEqual(len(parent.children[0].children), len(result))
resulting_scopes = [[3], [6], [1, 4]]
resulting_data_y = [y[:, 1], y[:, 3], y[:, [0, 2]]]
for i, r in enumerate(result):
self.assertEqual(len(r), 2)
self.assertEqual(type(r[1]['parent']), Product)
self.assertEqual(parent.children[0], r[1]['parent'])
self.assertListEqual(r[1]['scope'], resulting_scopes[i])
self.assertEqual(r[1]['pos'], i)
self.assertListEqual(
r[1]['data'].tolist(),
concatenate_yx(resulting_data_y[i], x).tolist())
def test_leaf_sampling_categorical(self):
np.random.seed(17)
x = np.concatenate(
(
np.random.multivariate_normal([20, 20], np.eye(2), 500),
np.random.multivariate_normal([10, 10], np.eye(2), 500),
np.random.multivariate_normal([1, 1], np.eye(2), 500),
),
axis=0,
)
y = np.array([2] * 500 + [1] * 500 + [0] * 500).reshape(-1, 1)
data = concatenate_yx(y, x)
ds_context = Context(parametric_types=[Categorical])
ds_context.feature_size = 2
leaf = create_conditional_leaf(data, ds_context, [0])
res = sample_instances(
leaf,
np.array([np.nan, 10, 10] * 1000).reshape(-1, 3), RandomState(17))
self.assertAlmostEqual(np.mean(res[:, 0]), 1, 1)
res = sample_instances(leaf,
np.array([np.nan, 1, 1] * 1000).reshape(-1, 3),
RandomState(17))
self.assertAlmostEqual(np.mean(res[:, 0]), 0, 1)
res = sample_instances(
leaf,
np.array([np.nan, 1, 1, np.nan, 10, 10] * 1000).reshape(-1, 3),
RandomState(17))
self.assertAlmostEqual(np.mean(res[::2, 0]), 0, 1)
self.assertAlmostEqual(np.mean(res[1::2, 0]), 1, 1)
with self.assertRaises(AssertionError):
sample_instances(
leaf,
np.array([np.nan, 1, 1, np.nan, 10, 10, 5, 10,
10]).reshape(-1, 3), RandomState(17))
