def test_layered_pruned_linked_spn_cltree():
#
# creating all the data slices
# the slicing is a fake stub
rows = 5
cols = 5
var = 1
values = 2
vars = [2, 3]
var_values = [2, 2]
s_data = numpy.array([[0, 1], [1, 1], [1, 0], [0, 0]])
node_1 = SumNode()
node_1.id = 1
node_2 = ProductNode()
node_2.id = 2
node_3 = SumNode()
node_3.id = 3
# adding first level
weight_12 = 0.4
weight_13 = 0.6
node_1.add_child(node_2, weight_12)
node_1.add_child(node_3, weight_13)
node_4 = ProductNode()
node_4.id = 4
leaf_5 = CategoricalSmoothedNode(var,
values)
leaf_5.id = 5
# not adding the slice to the stack
node_2.add_child(node_4)
node_2.add_child(leaf_5)
node_6 = SumNode()
node_6.id = 6
node_7 = SumNode()
node_7.id = 7
weight_36 = 0.1
weight_37 = 0.9
node_3.add_child(node_6, weight_36)
node_3.add_child(node_7, weight_37)
node_8 = ProductNode()
node_8.id = 8
#
# this is a cltree
leaf_15 = CLTreeNode(vars=vars,
var_values=var_values,
data=s_data)
leaf_15.id = 15
node_4.add_child(node_8)
node_4.add_child(leaf_15)
leaf_13 = CategoricalSmoothedNode(var,
values)
leaf_13.id = 13
leaf_14 = CLTreeNode(vars=vars,
var_values=var_values,
data=s_data)
leaf_14.id = 14
node_8.add_child(leaf_13)
node_8.add_child(leaf_14)
leaf_9 = CLTreeNode(vars=vars,
var_values=var_values,
data=s_data)
leaf_9.id = 9
node_10 = ProductNode()
node_10.id = 10
leaf_18 = CategoricalSmoothedNode(var,
values)
leaf_18.id = 18
leaf_19 = CategoricalSmoothedNode(var,
values)
leaf_19.id = 19
node_10.add_child(leaf_18)
node_10.add_child(leaf_19)
weight_69 = 0.3
weight_610 = 0.7
node_6.add_child(leaf_9, weight_69)
node_6.add_child(node_10, weight_610)
node_11 = ProductNode()
node_11.id = 11
leaf_20 = CategoricalSmoothedNode(var,
values)
leaf_20.id = 20
leaf_21 = CategoricalSmoothedNode(var,
values)
leaf_21.id = 21
node_11.add_child(leaf_20)
node_11.add_child(leaf_21)
node_12 = ProductNode()
node_12.id = 12
leaf_22 = CLTreeNode(vars=vars,
var_values=var_values,
data=s_data)
leaf_22.id = 22
leaf_23 = CategoricalSmoothedNode(var,
values)
leaf_23.id = 23
node_12.add_child(leaf_22)
node_12.add_child(leaf_23)
weight_711 = 0.5
weight_712 = 0.5
node_7.add_child(node_11, weight_711)
node_7.add_child(node_12, weight_712)
print('Added nodes')
root_node = SpnFactory.layered_pruned_linked_spn(node_1)
print('ROOT nODE', root_node)
spn = SpnFactory.layered_linked_spn(root_node)
print('SPN', spn)
assert spn.n_layers() == 3
for i, layer in enumerate(spn.top_down_layers()):
if i == 0:
assert layer.n_nodes() == 1
elif i == 1:
assert layer.n_nodes() == 4
elif i == 2:
assert layer.n_nodes() == 10
def fit_structure(self, data):
#
# a queue containing the data slices to process
slices_to_process = deque()
# a stack for building nodes
building_stack = deque()
# a dict to keep track of id->nodes
node_id_assoc = {}
# creating the first slice
whole_slice = DataSlice.whole_slice(data.shape[0], data.shape[1])
slices_to_process.append(whole_slice)
cluster_first = self._cluster_first
#
# iteratively process & split slices
#
while slices_to_process:
# process a slice
current_slice = slices_to_process.popleft()
# pointers to the current data slice
current_instances = current_slice.instance_ids
current_features = current_slice.feature_ids
current_id = current_slice.id
n_features = len(current_features)
# if n_features > 1:
# # # print("removing Zeros")
# datarowsIdx = numpy.sum(data[current_instances, :][:, current_features], 1) > 0
# if not any(datarowsIdx):
# datarowsIdx[0] = True
# current_instances = current_slice.instance_ids[datarowsIdx]
n_instances = len(current_instances)
# if n_instances == 0:
# #too strong cutting the zeroes
# current_instances = [current_slice.instance_ids[0]]
# n_instances = len(current_instances)
slice_data_rows = data[current_instances, :]
current_slice_data = slice_data_rows[:, current_features]
# is this a leaf node or we can split?
if n_features == 1 and (current_slice.doNotCluster or
n_instances <= self._min_instances_slice):
(feature_id, ) = current_features
if self.family == "poisson":
leaf_node = PoissonNode(data, current_instances,
current_features)
elif self.family == "gaussian":
leaf_node = GaussianNode(data, current_instances,
current_features)
# storing links
# input_nodes.append(leaf_node)
leaf_node.id = current_id
node_id_assoc[current_id] = leaf_node
# elif (current_slice_data.shape[0] < self._min_instances_slice):
# elif ( (n_instances <= self._min_instances_slice and n_features > 1) and current_slice_data.shape[0] < self._min_instances_slice):
# elif ((n_instances <= self._min_instances_slice and n_features > 1)):
elif n_features > 1 and (current_slice.doNotCluster or
n_instances <= self._min_instances_slice):
# print('into naive factorization')
child_slices = [
DataSlice(current_instances, [feature_id])
for feature_id in current_features
]
slices_to_process.extend(child_slices)
#children_ids = [child.id for child in child_slices]
for child_slice in child_slices:
child_slice.doNotCluster = current_slice.doNotCluster
current_slice.add_child(child_slice)
current_slice.type = ProductNode
building_stack.append(current_slice)
prod_node = ProductNode(data, current_instances,
current_features)
prod_node.id = current_id
node_id_assoc[current_id] = prod_node
else:
split_on_features = False
# first_run = False
#
# first run is a split on rows
if n_features == 1 or cluster_first:
cluster_first = False
else:
if self._ind_test_method == "pairwise_treeglm" or self._ind_test_method == "subsample":
fcdata = current_slice_data
if self._ind_test_method == "subsample":
#sampled_rows = 2000
#sampled_rows = math.floor(current_slice_data.shape[0]*10/100)
sampled_rows = self._sub_sample_rows
if sampled_rows < current_slice_data.shape[0]:
fcdata = current_slice_data[
numpy.random.choice(
current_slice_data.shape[0],
sampled_rows,
replace=False)]
else:
fcdata = current_slice_data
#Using R
#from pdn.independenceptest import getIndependentGroups
#feature_clusters = retrieve_clustering(getIndependentGroups(fcdata, alpha=self._alpha, family=self.family), current_features)
feature_clusters = retrieve_clustering(
getIndependentGroupsStabilityTest(
fcdata, alpha=self._alpha), current_features)
elif self._ind_test_method == "KMeans":
feature_clusters = retrieve_clustering(
cluster_rows(
(data[current_instances, :][:,
current_features]
).T,
n_clusters=2,
cluster_method=self._row_cluster_method,
n_iters=self._n_iters,
n_restarts=self._n_restarts,
cluster_prep_method="sqrt",
cluster_penalty=self._cluster_penalty,
rand_gen=self._rand_gen,
sklearn_args=self._sklearn_args),
current_instances)
split_on_features = len(feature_clusters) > 1
#
# have dependent components been found?
if split_on_features:
#
# splitting on columns
# print('---> Splitting on features')
# print(feature_clusters)
slices = [
DataSlice(current_instances, cluster)
for cluster in feature_clusters
]
slices_to_process.extend(slices)
current_slice.type = ProductNode
building_stack.append(current_slice)
for child_slice in slices:
current_slice.add_child(child_slice)
prod_node = ProductNode(data, current_instances,
current_features)
prod_node.id = current_id
node_id_assoc[current_id] = prod_node
else:
# print('---> Splitting on rows')
k_row_clusters = min(self._n_cluster_splits,
n_instances - 1)
if n_features == 1:
# do one kmeans run with K large enough to split into N min instances
k_row_clusters = math.floor(
n_instances / self._min_instances_slice) + 1
k_row_clusters = min(k_row_clusters, n_instances - 1)
clustering = retrieve_clustering(
cluster_rows(
data[current_instances, :][:, current_features],
n_clusters=k_row_clusters,
cluster_method=self._row_cluster_method,
n_iters=self._n_iters,
n_restarts=self._n_restarts,
cluster_prep_method=self._cluster_prep_method,
cluster_penalty=self._cluster_penalty,
rand_gen=self._rand_gen,
sklearn_args=self._sklearn_args),
current_instances)
cluster_slices = [
DataSlice(cluster, current_features)
for cluster in clustering
]
if len(clustering) < k_row_clusters:
for cluster_slice in cluster_slices:
cluster_slice.doNotCluster = True
n_instances_clusters = sum(
[len(cluster) for cluster in clustering])
cluster_weights = [
len(cluster) / n_instances_clusters
for cluster in clustering
]
slices_to_process.extend(cluster_slices)
current_slice.type = SumNode
building_stack.append(current_slice)
for child_slice, child_weight in zip(
cluster_slices, cluster_weights):
current_slice.add_child(child_slice, child_weight)
sum_node = SumNode(data, current_instances,
current_features)
sum_node.id = current_id
node_id_assoc[current_id] = sum_node
root_node = SpnFactory.pruned_spn_from_slices(node_id_assoc,
building_stack, True)
spn = SpnFactory.layered_linked_spn(root_node, data, self.config)
return spn
def test_layered_linked_spn():
# creating single nodes
# this code is replicated TODO: make a function
root = SumNode()
prod1 = ProductNode()
prod2 = ProductNode()
prod3 = ProductNode()
sum1 = SumNode()
sum2 = SumNode()
sum3 = SumNode()
sum4 = SumNode()
ind1 = CategoricalIndicatorNode(var=0, var_val=0)
ind2 = CategoricalIndicatorNode(var=0, var_val=1)
ind3 = CategoricalIndicatorNode(var=1, var_val=0)
ind4 = CategoricalIndicatorNode(var=1, var_val=1)
ind5 = CategoricalIndicatorNode(var=2, var_val=0)
ind6 = CategoricalIndicatorNode(var=2, var_val=1)
ind7 = CategoricalIndicatorNode(var=2, var_val=2)
ind8 = CategoricalIndicatorNode(var=3, var_val=0)
ind9 = CategoricalIndicatorNode(var=3, var_val=1)
ind10 = CategoricalIndicatorNode(var=3, var_val=2)
ind11 = CategoricalIndicatorNode(var=3, var_val=3)
prod4 = ProductNode()
prod5 = ProductNode()
prod6 = ProductNode()
prod7 = ProductNode()
# linking nodes
root.add_child(prod1, 0.3)
root. add_child(prod2, 0.3)
root.add_child(prod3, 0.4)
prod1.add_child(sum1)
prod1.add_child(sum2)
prod2.add_child(ind7)
prod2.add_child(ind8)
prod2.add_child(ind11)
prod3.add_child(sum3)
prod3.add_child(sum4)
sum1.add_child(ind1, 0.3)
sum1.add_child(ind2, 0.3)
sum1.add_child(prod4, 0.4)
sum2.add_child(ind2, 0.5)
sum2.add_child(prod4, 0.2)
sum2.add_child(prod5, 0.3)
sum3.add_child(prod6, 0.5)
sum3.add_child(prod7, 0.5)
sum4.add_child(prod6, 0.5)
sum4.add_child(prod7, 0.5)
prod4.add_child(ind3)
prod4.add_child(ind4)
prod5.add_child(ind5)
prod5.add_child(ind6)
prod6.add_child(ind9)
prod6.add_child(ind10)
prod7.add_child(ind9)
prod7.add_child(ind10)
spn = SpnFactory.layered_linked_spn(root)
print(spn)
print(spn.stats())
def test_pruned_spn_from_slices():
#
# creating all the data slices
# the slicing is a fake stub
rows = 5
cols = 5
var = 1
values = 2
node_assoc = {}
building_stack = deque()
slice_1 = DataSlice.whole_slice(rows, cols)
slice_1.type = SumNode
node_1 = SumNode()
node_1.id = slice_1.id
node_assoc[node_1.id] = node_1
building_stack.append(slice_1)
slice_2 = DataSlice.whole_slice(rows, cols)
slice_2.type = ProductNode
node_2 = ProductNode()
node_2.id = slice_2.id
node_assoc[node_2.id] = node_2
building_stack.append(slice_2)
slice_3 = DataSlice.whole_slice(rows, cols)
slice_3.type = SumNode
node_3 = SumNode()
node_3.id = slice_3.id
node_assoc[node_3.id] = node_3
building_stack.append(slice_3)
# adding first level
slice_1.add_child(slice_2, 0.8)
slice_1.add_child(slice_3, 0.2)
slice_4 = DataSlice.whole_slice(rows, cols)
slice_4.type = ProductNode
node_4 = ProductNode()
node_4.id = slice_4.id
node_assoc[node_4.id] = node_4
building_stack.append(slice_4)
leaf_5 = CategoricalSmoothedNode(var,
values)
slice_5 = DataSlice.whole_slice(rows, cols)
leaf_5.id = slice_5.id
node_assoc[leaf_5.id] = leaf_5
# not adding the slice to the stack
slice_2.add_child(slice_4)
slice_2.add_child(slice_5)
slice_6 = DataSlice.whole_slice(rows, cols)
slice_6.type = SumNode
node_6 = SumNode()
node_6.id = slice_6.id
node_assoc[node_6.id] = node_6
building_stack.append(slice_6)
slice_7 = DataSlice.whole_slice(rows, cols)
slice_7.type = SumNode
node_7 = SumNode()
node_7.id = slice_7.id
node_assoc[node_7.id] = node_7
building_stack.append(slice_7)
slice_3.add_child(slice_6, 0.4)
slice_3.add_child(slice_7, 0.6)
slice_8 = DataSlice.whole_slice(rows, cols)
slice_8.type = ProductNode
node_8 = ProductNode()
node_8.id = slice_8.id
node_assoc[node_8.id] = node_8
building_stack.append(slice_8)
leaf_15 = CategoricalSmoothedNode(var,
values)
slice_15 = DataSlice.whole_slice(rows, cols)
leaf_15.id = slice_15.id
node_assoc[leaf_15.id] = leaf_15
slice_4.add_child(slice_8)
slice_4.add_child(slice_15)
leaf_13 = CategoricalSmoothedNode(var,
values)
slice_13 = DataSlice.whole_slice(rows, cols)
leaf_13.id = slice_13.id
node_assoc[leaf_13.id] = leaf_13
leaf_14 = CategoricalSmoothedNode(var,
values)
slice_14 = DataSlice.whole_slice(rows, cols)
leaf_14.id = slice_14.id
node_assoc[leaf_14.id] = leaf_14
slice_8.add_child(slice_13)
slice_8.add_child(slice_14)
slice_9 = DataSlice.whole_slice(rows, cols)
slice_9.type = ProductNode
node_9 = ProductNode()
node_9.id = slice_9.id
node_assoc[node_9.id] = node_9
building_stack.append(slice_9)
leaf_16 = CategoricalSmoothedNode(var,
values)
slice_16 = DataSlice.whole_slice(rows, cols)
leaf_16.id = slice_16.id
node_assoc[leaf_16.id] = leaf_16
leaf_17 = CategoricalSmoothedNode(var,
values)
slice_17 = DataSlice.whole_slice(rows, cols)
leaf_17.id = slice_17.id
node_assoc[leaf_17.id] = leaf_17
slice_9.add_child(slice_16)
slice_9.add_child(slice_17)
slice_10 = DataSlice.whole_slice(rows, cols)
slice_10.type = ProductNode
node_10 = ProductNode()
node_10.id = slice_10.id
node_assoc[node_10.id] = node_10
building_stack.append(slice_10)
leaf_18 = CategoricalSmoothedNode(var,
values)
slice_18 = DataSlice.whole_slice(rows, cols)
leaf_18.id = slice_18.id
node_assoc[leaf_18.id] = leaf_18
leaf_19 = CategoricalSmoothedNode(var,
values)
slice_19 = DataSlice.whole_slice(rows, cols)
leaf_19.id = slice_19.id
node_assoc[leaf_19.id] = leaf_19
slice_10.add_child(slice_18)
slice_10.add_child(slice_19)
slice_6.add_child(slice_9, 0.1)
slice_6.add_child(slice_10, 0.9)
slice_11 = DataSlice.whole_slice(rows, cols)
slice_11.type = ProductNode
node_11 = ProductNode()
node_11.id = slice_11.id
node_assoc[node_11.id] = node_11
building_stack.append(slice_11)
leaf_20 = CategoricalSmoothedNode(var,
values)
slice_20 = DataSlice.whole_slice(rows, cols)
leaf_20.id = slice_20.id
node_assoc[leaf_20.id] = leaf_20
leaf_21 = CategoricalSmoothedNode(var,
values)
slice_21 = DataSlice.whole_slice(rows, cols)
leaf_21.id = slice_21.id
node_assoc[leaf_21.id] = leaf_21
slice_11.add_child(slice_20)
slice_11.add_child(slice_21)
slice_12 = DataSlice.whole_slice(rows, cols)
slice_12.type = ProductNode
node_12 = ProductNode()
node_12.id = slice_12.id
node_assoc[node_12.id] = node_12
building_stack.append(slice_12)
leaf_22 = CategoricalSmoothedNode(var,
values)
slice_22 = DataSlice.whole_slice(rows, cols)
leaf_22.id = slice_22.id
node_assoc[leaf_22.id] = leaf_22
leaf_23 = CategoricalSmoothedNode(var,
values)
slice_23 = DataSlice.whole_slice(rows, cols)
leaf_23.id = slice_23.id
node_assoc[leaf_23.id] = leaf_23
slice_12.add_child(slice_22)
slice_12.add_child(slice_23)
slice_7.add_child(slice_11, 0.2)
slice_7.add_child(slice_12, 0.7)
root_node = SpnFactory.pruned_spn_from_slices(node_assoc,
building_stack)
print('ROOT nODE', root_node)
spn = SpnFactory.layered_linked_spn(root_node)
print('SPN', spn)
assert spn.n_layers() == 3
for i, layer in enumerate(spn.top_down_layers()):
if i == 0:
assert layer.n_nodes() == 1
elif i == 1:
assert layer.n_nodes() == 5
elif i == 2:
assert layer.n_nodes() == 12
def fit_structure(self, data, feature_sizes):
"""
data is a numpy array of size {n_instances X n_features}
feature_sizes is an array of integers representing feature ranges
"""
#
# resetting the data slice ids (just in case)
DataSlice.reset_id_counter()
tot_n_instances = data.shape[0]
tot_n_features = data.shape[1]
logging.info('Learning SPN structure on a (%d X %d) dataset',
tot_n_instances, tot_n_features)
learn_start_t = perf_counter()
#
# a queue containing the data slices to process
slices_to_process = deque()
# a stack for building nodes
building_stack = deque()
# a dict to keep track of id->nodes
node_id_assoc = {}
# creating the first slice
whole_slice = DataSlice.whole_slice(tot_n_instances, tot_n_features)
slices_to_process.append(whole_slice)
first_run = True
#
# iteratively process & split slices
#
while slices_to_process:
# process a slice
current_slice = slices_to_process.popleft()
# pointers to the current data slice
current_instances = current_slice.instance_ids
current_features = current_slice.feature_ids
current_id = current_slice.id
n_instances = len(current_instances)
n_features = len(current_features)
logging.info('\n*** Processing slice %d (%d X %d)', current_id,
n_instances, n_features)
logging.debug('\tinstances:%s\n\tfeatures:%s', current_instances,
current_features)
#
# is this a leaf node or we can split?
if n_features == 1:
logging.info('---> Adding a leaf (just one feature)')
(feature_id, ) = current_features
feature_size = feature_sizes[feature_id]
# slicing from the original dataset
slice_data_rows = data[current_instances, :]
current_slice_data = slice_data_rows[:, current_features]
# create the node
leaf_node = CategoricalSmoothedNode(
var=feature_id,
var_values=feature_size,
data=current_slice_data,
instances=current_instances,
alpha=self._alpha)
# print('lnvf', leaf_node._var_freqs)
# storing links
# input_nodes.append(leaf_node)
leaf_node.id = current_id
node_id_assoc[current_id] = leaf_node
logging.debug('\tCreated Smooth Node %s', leaf_node)
elif (n_instances <= self._min_instances_slice and n_features > 1):
#
# splitting the slice on each feature
logging.info('---> Few instances (%d), decompose all features',
n_instances)
#
# shall put a cltree or
if self._cltree_leaves:
logging.info('into a Chow-Liu tree')
#
# slicing data
slice_data_rows = data[current_instances, :]
current_slice_data = slice_data_rows[:, current_features]
current_feature_sizes = [
feature_sizes[i] for i in current_features
]
#
# creating a Chow-Liu tree as leaf
leaf_node = CLTreeNode(vars=current_features,
var_values=current_feature_sizes,
data=current_slice_data,
alpha=self._alpha)
#
# storing links
leaf_node.id = current_id
node_id_assoc[current_id] = leaf_node
logging.debug('\tCreated Chow-Liu Tree Node %s', leaf_node)
elif self._kde and n_instances > 1:
estimate_kernel_density_spn(current_slice, feature_sizes,
data, self._alpha,
node_id_assoc, building_stack,
slices_to_process)
# elif n_instances == 1: # FIXME: there is a bug here
else:
current_slice, slices_to_process, building_stack, node_id_assoc = \
self.make_naive_factorization(current_slice,
slices_to_process,
building_stack,
node_id_assoc)
else:
#
# slicing from the original dataset
slice_data_rows = data[current_instances, :]
current_slice_data = slice_data_rows[:, current_features]
split_on_features = False
#
# first run is a split on rows
if first_run:
logging.info('-- FIRST RUN --')
first_run = False
else:
#
# try clustering on cols
# logging.debug('...trying to split on columns')
split_start_t = perf_counter()
print(data.shape)
dependent_features, other_features = greedy_feature_split(
data, current_slice, feature_sizes, self._g_factor,
self._rand_gen)
split_end_t = perf_counter()
logging.info('...tried to split on columns in {}'.format(
split_end_t - split_start_t))
if len(other_features) > 0:
split_on_features = True
#
# have dependent components been found?
if split_on_features:
#
# splitting on columns
logging.info(
'---> Splitting on features' +
' {} -> ({}, {})'.format(len(current_features),
len(dependent_features),
len(other_features)))
#
# creating two new data slices and putting them on queue
first_slice = DataSlice(current_instances,
dependent_features)
second_slice = DataSlice(current_instances, other_features)
slices_to_process.append(first_slice)
slices_to_process.append(second_slice)
children_ids = [first_slice.id, second_slice.id]
#
# storing link parent children
current_slice.type = ProductNode
building_stack.append(current_slice)
current_slice.add_child(first_slice)
current_slice.add_child(second_slice)
#
# creating product node
prod_node = ProductNode(
var_scope=frozenset(current_features))
prod_node.id = current_id
node_id_assoc[current_id] = prod_node
logging.debug('\tCreated Prod Node %s (with children %s)',
prod_node, children_ids)
else:
#
# clustering on rows
logging.info('---> Splitting on rows')
#
# at most n_rows clusters, for sklearn
k_row_clusters = min(self._n_cluster_splits,
n_instances - 1)
clustering = cluster_rows(
data,
current_slice,
n_clusters=k_row_clusters,
cluster_method=self._row_cluster_method,
n_iters=self._n_iters,
n_restarts=self._n_restarts,
cluster_penalty=self._cluster_penalty,
rand_gen=self._rand_gen,
sklearn_args=self._sklearn_args)
if len(clustering) < 2:
logging.info('\n\n\nLess than 2 clusters\n\n (%d)',
len(clustering))
logging.info('forcing a naive factorization')
current_slice, slices_to_process, building_stack, node_id_assoc = \
self.make_naive_factorization(current_slice,
slices_to_process,
building_stack,
node_id_assoc)
else:
# logging.debug('obtained clustering %s', clustering)
logging.info('clustered into %d parts (min %d)',
len(clustering), k_row_clusters)
# splitting
cluster_slices = [
DataSlice(cluster, current_features)
for cluster in clustering
]
cluster_slices_ids = [
slice.id for slice in cluster_slices
]
# cluster_prior = 5.0
# cluster_weights = [(slice.n_instances() + cluster_prior) /
# (n_instances + cluster_prior * len(cluster_slices))
# for slice in cluster_slices]
cluster_weights = [
slice.n_instances() / n_instances
for slice in cluster_slices
]
#
# appending for processing
slices_to_process.extend(cluster_slices)
#
# storing links
# current_slice.children = cluster_slices_ids
# current_slice.weights = cluster_weights
current_slice.type = SumNode
building_stack.append(current_slice)
for child_slice, child_weight in zip(
cluster_slices, cluster_weights):
current_slice.add_child(child_slice, child_weight)
#
# building a sum node
SCOPES_DICT[frozenset(current_features)] += 1
sum_node = SumNode(
var_scope=frozenset(current_features))
sum_node.id = current_id
node_id_assoc[current_id] = sum_node
logging.debug(
'\tCreated Sum Node %s (with children %s)',
sum_node, cluster_slices_ids)
learn_end_t = perf_counter()
logging.info('\n\n\tStructure learned in %f secs',
(learn_end_t - learn_start_t))
#
# linking the spn graph (parent -> children)
#
logging.info('===> Building tree')
link_start_t = perf_counter()
root_build_node = building_stack[0]
root_node = node_id_assoc[root_build_node.id]
logging.debug('root node: %s', root_node)
root_node = SpnFactory.pruned_spn_from_slices(node_id_assoc,
building_stack)
link_end_t = perf_counter()
logging.info('\tLinked the spn in %f secs (root_node %s)',
(link_end_t - link_start_t), root_node)
#
# building layers
#
logging.info('===> Layering spn')
layer_start_t = perf_counter()
spn = SpnFactory.layered_linked_spn(root_node)
layer_end_t = perf_counter()
logging.info('\tLayered the spn in %f secs',
(layer_end_t - layer_start_t))
logging.info('\nLearned SPN\n\n%s', spn.stats())
#logging.info('%s', SCOPES_DICT.most_common(30))
return spn
def test_categorical_to_indicator_input_layer():
#
# creating all the data slices
# the slicing is a fake stub
# rows = 5
# cols = 5
var_1 = 0
values_1 = 2
var_2 = 1
values_2 = 3
var_3 = 2
values_3 = 4
node_1 = SumNode()
node_1.id = 1
node_2 = ProductNode()
node_2.id = 2
node_3 = SumNode()
node_3.id = 3
# adding first level
weight_12 = 0.4
weight_13 = 0.6
node_1.add_child(node_2, weight_12)
node_1.add_child(node_3, weight_13)
node_4 = ProductNode()
node_4.id = 4
leaf_5 = CategoricalSmoothedNode(var_1, values_1)
leaf_5.id = 5
# not adding the slice to the stack
node_2.add_child(node_4)
node_2.add_child(leaf_5)
node_6 = SumNode()
node_6.id = 6
node_7 = SumNode()
node_7.id = 7
weight_36 = 0.1
weight_37 = 0.9
node_3.add_child(node_6, weight_36)
node_3.add_child(node_7, weight_37)
node_8 = ProductNode()
node_8.id = 8
leaf_15 = CategoricalSmoothedNode(var_2, values_2)
leaf_15.id = 15
node_4.add_child(node_8)
node_4.add_child(leaf_15)
leaf_13 = CategoricalSmoothedNode(var_3, values_3)
leaf_13.id = 13
leaf_14 = CategoricalSmoothedNode(var_1, values_1)
leaf_14.id = 14
node_8.add_child(leaf_13)
node_8.add_child(leaf_14)
node_9 = ProductNode()
node_9.id = 9
leaf_16 = CategoricalSmoothedNode(var_2, values_2)
leaf_16.id = 16
leaf_17 = CategoricalSmoothedNode(var_3, values_3)
leaf_17.id = 17
node_9.add_child(leaf_16)
node_9.add_child(leaf_17)
node_10 = ProductNode()
node_10.id = 10
leaf_18 = CategoricalSmoothedNode(var_2, values_2)
leaf_18.id = 18
leaf_19 = CategoricalSmoothedNode(var_2, values_2)
leaf_19.id = 19
node_10.add_child(leaf_18)
node_10.add_child(leaf_19)
weight_69 = 0.3
weight_610 = 0.7
node_6.add_child(node_9, weight_69)
node_6.add_child(node_10, weight_610)
node_11 = ProductNode()
node_11.id = 11
leaf_20 = CategoricalSmoothedNode(var_1, values_1)
leaf_20.id = 20
leaf_21 = CategoricalSmoothedNode(var_3, values_3)
leaf_21.id = 21
node_11.add_child(leaf_20)
node_11.add_child(leaf_21)
node_12 = ProductNode()
node_12.id = 12
leaf_22 = CategoricalSmoothedNode(var_1, values_1)
leaf_22.id = 22
leaf_23 = CategoricalSmoothedNode(var_3, values_3)
leaf_23.id = 23
node_12.add_child(leaf_22)
node_12.add_child(leaf_23)
weight_711 = 0.5
weight_712 = 0.5
node_7.add_child(node_11, weight_711)
node_7.add_child(node_12, weight_712)
root_node = SpnFactory.layered_pruned_linked_spn(node_1)
print('ROOT nODE', root_node)
spn = SpnFactory.layered_linked_spn(root_node)
print('SPN', spn)
assert spn.n_layers() == 3
for i, layer in enumerate(spn.top_down_layers()):
if i == 0:
assert layer.n_nodes() == 1
elif i == 1:
assert layer.n_nodes() == 5
elif i == 2:
assert layer.n_nodes() == 12
#
# changing input layer
spn = linked_categorical_input_to_indicators(spn)
print('Changed input layer to indicator variables')
print(spn)
def test_layered_pruned_linked_spn_cltree():
#
# creating all the data slices
# the slicing is a fake stub
rows = 5
cols = 5
var = 1
values = 2
vars = [2, 3]
var_values = [2, 2]
s_data = numpy.array([[0, 1], [1, 1], [1, 0], [0, 0]])
node_1 = SumNode()
node_1.id = 1
node_2 = ProductNode()
node_2.id = 2
node_3 = SumNode()
node_3.id = 3
# adding first level
weight_12 = 0.4
weight_13 = 0.6
node_1.add_child(node_2, weight_12)
node_1.add_child(node_3, weight_13)
node_4 = ProductNode()
node_4.id = 4
leaf_5 = CategoricalSmoothedNode(var, values)
leaf_5.id = 5
# not adding the slice to the stack
node_2.add_child(node_4)
node_2.add_child(leaf_5)
node_6 = SumNode()
node_6.id = 6
node_7 = SumNode()
node_7.id = 7
weight_36 = 0.1
weight_37 = 0.9
node_3.add_child(node_6, weight_36)
node_3.add_child(node_7, weight_37)
node_8 = ProductNode()
node_8.id = 8
#
# this is a cltree
leaf_15 = CLTreeNode(vars=vars, var_values=var_values, data=s_data)
leaf_15.id = 15
node_4.add_child(node_8)
node_4.add_child(leaf_15)
leaf_13 = CategoricalSmoothedNode(var, values)
leaf_13.id = 13
leaf_14 = CLTreeNode(vars=vars, var_values=var_values, data=s_data)
leaf_14.id = 14
node_8.add_child(leaf_13)
node_8.add_child(leaf_14)
leaf_9 = CLTreeNode(vars=vars, var_values=var_values, data=s_data)
leaf_9.id = 9
node_10 = ProductNode()
node_10.id = 10
leaf_18 = CategoricalSmoothedNode(var, values)
leaf_18.id = 18
leaf_19 = CategoricalSmoothedNode(var, values)
leaf_19.id = 19
node_10.add_child(leaf_18)
node_10.add_child(leaf_19)
weight_69 = 0.3
weight_610 = 0.7
node_6.add_child(leaf_9, weight_69)
node_6.add_child(node_10, weight_610)
node_11 = ProductNode()
node_11.id = 11
leaf_20 = CategoricalSmoothedNode(var, values)
leaf_20.id = 20
leaf_21 = CategoricalSmoothedNode(var, values)
leaf_21.id = 21
node_11.add_child(leaf_20)
node_11.add_child(leaf_21)
node_12 = ProductNode()
node_12.id = 12
leaf_22 = CLTreeNode(vars=vars, var_values=var_values, data=s_data)
leaf_22.id = 22
leaf_23 = CategoricalSmoothedNode(var, values)
leaf_23.id = 23
node_12.add_child(leaf_22)
node_12.add_child(leaf_23)
weight_711 = 0.5
weight_712 = 0.5
node_7.add_child(node_11, weight_711)
node_7.add_child(node_12, weight_712)
print('Added nodes')
root_node = SpnFactory.layered_pruned_linked_spn(node_1)
print('ROOT nODE', root_node)
spn = SpnFactory.layered_linked_spn(root_node)
print('SPN', spn)
assert spn.n_layers() == 3
for i, layer in enumerate(spn.top_down_layers()):
if i == 0:
assert layer.n_nodes() == 1
elif i == 1:
assert layer.n_nodes() == 4
elif i == 2:
assert layer.n_nodes() == 10
def test_pruned_spn_from_slices():
#
# creating all the data slices
# the slicing is a fake stub
rows = 5
cols = 5
var = 1
values = 2
node_assoc = {}
building_stack = deque()
slice_1 = DataSlice.whole_slice(rows, cols)
slice_1.type = SumNode
node_1 = SumNode()
node_1.id = slice_1.id
node_assoc[node_1.id] = node_1
building_stack.append(slice_1)
slice_2 = DataSlice.whole_slice(rows, cols)
slice_2.type = ProductNode
node_2 = ProductNode()
node_2.id = slice_2.id
node_assoc[node_2.id] = node_2
building_stack.append(slice_2)
slice_3 = DataSlice.whole_slice(rows, cols)
slice_3.type = SumNode
node_3 = SumNode()
node_3.id = slice_3.id
node_assoc[node_3.id] = node_3
building_stack.append(slice_3)
# adding first level
slice_1.add_child(slice_2, 0.8)
slice_1.add_child(slice_3, 0.2)
slice_4 = DataSlice.whole_slice(rows, cols)
slice_4.type = ProductNode
node_4 = ProductNode()
node_4.id = slice_4.id
node_assoc[node_4.id] = node_4
building_stack.append(slice_4)
leaf_5 = CategoricalSmoothedNode(var, values)
slice_5 = DataSlice.whole_slice(rows, cols)
leaf_5.id = slice_5.id
node_assoc[leaf_5.id] = leaf_5
# not adding the slice to the stack
slice_2.add_child(slice_4)
slice_2.add_child(slice_5)
slice_6 = DataSlice.whole_slice(rows, cols)
slice_6.type = SumNode
node_6 = SumNode()
node_6.id = slice_6.id
node_assoc[node_6.id] = node_6
building_stack.append(slice_6)
slice_7 = DataSlice.whole_slice(rows, cols)
slice_7.type = SumNode
node_7 = SumNode()
node_7.id = slice_7.id
node_assoc[node_7.id] = node_7
building_stack.append(slice_7)
slice_3.add_child(slice_6, 0.4)
slice_3.add_child(slice_7, 0.6)
slice_8 = DataSlice.whole_slice(rows, cols)
slice_8.type = ProductNode
node_8 = ProductNode()
node_8.id = slice_8.id
node_assoc[node_8.id] = node_8
building_stack.append(slice_8)
leaf_15 = CategoricalSmoothedNode(var, values)
slice_15 = DataSlice.whole_slice(rows, cols)
leaf_15.id = slice_15.id
node_assoc[leaf_15.id] = leaf_15
slice_4.add_child(slice_8)
slice_4.add_child(slice_15)
leaf_13 = CategoricalSmoothedNode(var, values)
slice_13 = DataSlice.whole_slice(rows, cols)
leaf_13.id = slice_13.id
node_assoc[leaf_13.id] = leaf_13
leaf_14 = CategoricalSmoothedNode(var, values)
slice_14 = DataSlice.whole_slice(rows, cols)
leaf_14.id = slice_14.id
node_assoc[leaf_14.id] = leaf_14
slice_8.add_child(slice_13)
slice_8.add_child(slice_14)
slice_9 = DataSlice.whole_slice(rows, cols)
slice_9.type = ProductNode
node_9 = ProductNode()
node_9.id = slice_9.id
node_assoc[node_9.id] = node_9
building_stack.append(slice_9)
leaf_16 = CategoricalSmoothedNode(var, values)
slice_16 = DataSlice.whole_slice(rows, cols)
leaf_16.id = slice_16.id
node_assoc[leaf_16.id] = leaf_16
leaf_17 = CategoricalSmoothedNode(var, values)
slice_17 = DataSlice.whole_slice(rows, cols)
leaf_17.id = slice_17.id
node_assoc[leaf_17.id] = leaf_17
slice_9.add_child(slice_16)
slice_9.add_child(slice_17)
slice_10 = DataSlice.whole_slice(rows, cols)
slice_10.type = ProductNode
node_10 = ProductNode()
node_10.id = slice_10.id
node_assoc[node_10.id] = node_10
building_stack.append(slice_10)
leaf_18 = CategoricalSmoothedNode(var, values)
slice_18 = DataSlice.whole_slice(rows, cols)
leaf_18.id = slice_18.id
node_assoc[leaf_18.id] = leaf_18
leaf_19 = CategoricalSmoothedNode(var, values)
slice_19 = DataSlice.whole_slice(rows, cols)
leaf_19.id = slice_19.id
node_assoc[leaf_19.id] = leaf_19
slice_10.add_child(slice_18)
slice_10.add_child(slice_19)
slice_6.add_child(slice_9, 0.1)
slice_6.add_child(slice_10, 0.9)
slice_11 = DataSlice.whole_slice(rows, cols)
slice_11.type = ProductNode
node_11 = ProductNode()
node_11.id = slice_11.id
node_assoc[node_11.id] = node_11
building_stack.append(slice_11)
leaf_20 = CategoricalSmoothedNode(var, values)
slice_20 = DataSlice.whole_slice(rows, cols)
leaf_20.id = slice_20.id
node_assoc[leaf_20.id] = leaf_20
leaf_21 = CategoricalSmoothedNode(var, values)
slice_21 = DataSlice.whole_slice(rows, cols)
leaf_21.id = slice_21.id
node_assoc[leaf_21.id] = leaf_21
slice_11.add_child(slice_20)
slice_11.add_child(slice_21)
slice_12 = DataSlice.whole_slice(rows, cols)
slice_12.type = ProductNode
node_12 = ProductNode()
node_12.id = slice_12.id
node_assoc[node_12.id] = node_12
building_stack.append(slice_12)
leaf_22 = CategoricalSmoothedNode(var, values)
slice_22 = DataSlice.whole_slice(rows, cols)
leaf_22.id = slice_22.id
node_assoc[leaf_22.id] = leaf_22
leaf_23 = CategoricalSmoothedNode(var, values)
slice_23 = DataSlice.whole_slice(rows, cols)
leaf_23.id = slice_23.id
node_assoc[leaf_23.id] = leaf_23
slice_12.add_child(slice_22)
slice_12.add_child(slice_23)
slice_7.add_child(slice_11, 0.2)
slice_7.add_child(slice_12, 0.7)
root_node = SpnFactory.pruned_spn_from_slices(node_assoc, building_stack)
print('ROOT nODE', root_node)
spn = SpnFactory.layered_linked_spn(root_node)
print('SPN', spn)
assert spn.n_layers() == 3
for i, layer in enumerate(spn.top_down_layers()):
if i == 0:
assert layer.n_nodes() == 1
elif i == 1:
assert layer.n_nodes() == 5
elif i == 2:
assert layer.n_nodes() == 12
def test_layered_linked_spn():
# creating single nodes
# this code is replicated TODO: make a function
root = SumNode()
prod1 = ProductNode()
prod2 = ProductNode()
prod3 = ProductNode()
sum1 = SumNode()
sum2 = SumNode()
sum3 = SumNode()
sum4 = SumNode()
ind1 = CategoricalIndicatorNode(var=0, var_val=0)
ind2 = CategoricalIndicatorNode(var=0, var_val=1)
ind3 = CategoricalIndicatorNode(var=1, var_val=0)
ind4 = CategoricalIndicatorNode(var=1, var_val=1)
ind5 = CategoricalIndicatorNode(var=2, var_val=0)
ind6 = CategoricalIndicatorNode(var=2, var_val=1)
ind7 = CategoricalIndicatorNode(var=2, var_val=2)
ind8 = CategoricalIndicatorNode(var=3, var_val=0)
ind9 = CategoricalIndicatorNode(var=3, var_val=1)
ind10 = CategoricalIndicatorNode(var=3, var_val=2)
ind11 = CategoricalIndicatorNode(var=3, var_val=3)
prod4 = ProductNode()
prod5 = ProductNode()
prod6 = ProductNode()
prod7 = ProductNode()
# linking nodes
root.add_child(prod1, 0.3)
root.add_child(prod2, 0.3)
root.add_child(prod3, 0.4)
prod1.add_child(sum1)
prod1.add_child(sum2)
prod2.add_child(ind7)
prod2.add_child(ind8)
prod2.add_child(ind11)
prod3.add_child(sum3)
prod3.add_child(sum4)
sum1.add_child(ind1, 0.3)
sum1.add_child(ind2, 0.3)
sum1.add_child(prod4, 0.4)
sum2.add_child(ind2, 0.5)
sum2.add_child(prod4, 0.2)
sum2.add_child(prod5, 0.3)
sum3.add_child(prod6, 0.5)
sum3.add_child(prod7, 0.5)
sum4.add_child(prod6, 0.5)
sum4.add_child(prod7, 0.5)
prod4.add_child(ind3)
prod4.add_child(ind4)
prod5.add_child(ind5)
prod5.add_child(ind6)
prod6.add_child(ind9)
prod6.add_child(ind10)
prod7.add_child(ind9)
prod7.add_child(ind10)
spn = SpnFactory.layered_linked_spn(root)
print(spn)
print(spn.stats())