def test_sum_node_is_complete():
# create a sum node with a scope
scope = frozenset({0, 2, 7, 13})
sum_node = SumNode(var_scope=scope)
# creating children with same scope
children = [ProductNode(var_scope=scope) for i in range(4)]
for prod_node in children:
sum_node.add_child(prod_node, 1.0)
assert sum_node.is_complete()
# now altering one child's scope with one less var
children[0].var_scope = frozenset({0, 7, 13})
assert sum_node.is_complete() is False
# now adding one more
children[0].var_scope = scope
children[3].var_scope = frozenset({0, 2, 7, 13, 3})
assert not sum_node.is_complete()
# now checking with indicator input nodes
var = 4
sum_node = SumNode(var_scope=frozenset({var}))
children = [CategoricalIndicatorNode(var=var, var_val=i)
for i in range(4)]
for input_node in children:
sum_node.add_child(input_node, 1.0)
assert sum_node.is_complete()
def __init__(self, nodes=None, vars=None):
"""
WRITEME
"""
if nodes is None:
# self._vars = vars
nodes = [CategoricalIndicatorNode(var, i)
for var in range(len(vars))
for i in range(vars[var])]
# self._feature_vals = [2 for i in range(len(nodes))]
else:
# assuming the nodes are complete and coherent
vars_dict = {}
for node in nodes:
try:
vars_dict[node.var] += 1
except:
vars_dict[node.var] = 1
sorted_keys = sorted(vars_dict.items(), key=lambda t: t[0])
vars = [vals for id, vals in sorted_keys]
# self.feature_vals = compute_feature_vals(nodes)
CategoricalInputLayer.__init__(self, nodes, vars)
self._feature_vals = compute_feature_vals(nodes)
def test_categorical_indicator_node_create_and_eval():
# created a node on the first var and its first value
ind = CategoricalIndicatorNode(0, 0)
# seen x0 = 0 -> 1.
ind.eval(0)
assert ind.log_val == 0.
# this indicator is not fired
ind.eval(1)
assert ind.log_val == LOG_ZERO
# all indicators for that var are fired
ind.eval(MARG_IND)
assert ind.log_val == 0.
# the var has only 2 values, but the node does not know!
ind.eval(2)
assert ind.log_val == LOG_ZERO
def test_sum_layer_is_complete():
# creating two scopes and two sum nodes
scope1 = frozenset({0, 2, 3})
scope2 = frozenset({10})
sum_node_1 = SumNode(var_scope=scope1)
sum_node_2 = SumNode(var_scope=scope2)
# adding product nodes as children to the first, indicator the second
for i in range(4):
sum_node_1.add_child(ProductNode(var_scope=scope1), 1.0)
sum_node_2.add_child(CategoricalIndicatorNode(var=10, var_val=i), 1.0)
# creating sum layer
sum_layer = SumLayer(nodes=[sum_node_1, sum_node_2])
assert sum_layer.is_complete()
# now with errors in scope
scope3 = frozenset({6})
sum_node_1 = SumNode(var_scope=scope1)
sum_node_2 = SumNode(var_scope=scope3)
# adding product nodes as children to the first, indicator the second
for i in range(4):
sum_node_1.add_child(ProductNode(var_scope=scope1), 1.0)
sum_node_2.add_child(CategoricalIndicatorNode(var=10, var_val=i), 1.0)
# creating sum layer
sum_layer = SumLayer(nodes=[sum_node_1, sum_node_2])
assert not sum_layer.is_complete()
sum_node_2.var_scope = scope2
assert sum_layer.is_complete()
sum_node_2.children[3].var_scope = scope3
assert not sum_layer.is_complete()
def test_categorical_input_layer():
print('categorical input layer')
# I could loop through alpha as well
alpha = 0.1
for var_id1 in range(len(vars)):
for var_id2 in range(len(vars)):
for var_val1 in range(vars[var_id1]):
print('varid1, varid2, varval1',
var_id1, var_id2, var_val1)
# var_id1 = 0
# var_val1 = 0
node1 = CategoricalIndicatorNode(var_id1,
var_val1)
# var_id2 = 0
var_vals2 = vars[var_id2]
node2 = CategoricalSmoothedNode(
var_id2, var_vals2, alpha, freqs[var_id2])
# creating the generic input layer
input_layer = CategoricalInputLayer([node1,
node2])
# evaluating according to an observation
input_layer.eval(obs)
layer_evals = input_layer.node_values()
print('layer eval nodes')
print(layer_evals)
# computing evaluation by hand
val1 = 1 if var_val1 == obs[var_id1] or obs[
var_id1] == MARG_IND else 0
logval1 = log(val1) if val1 == 1 else LOG_ZERO
logval2 = compute_smoothed_ll(
obs[var_id2], freqs[var_id2], vars[var_id2], alpha)
logvals = [logval1, logval2]
print('log vals')
print(logvals)
for logval, eval in zip(logvals, layer_evals):
if logval == LOG_ZERO:
# for zero log check this way for correctness
assert IS_LOG_ZERO(eval) is True
else:
assert_almost_equal(logval, eval, PRECISION)
def test_categorical_indicator_node_create_and_eval_keras():
alpha = 0.0
data = numpy.array([[1, 1, 1, 0],
[0, 0, 1, 0],
[0, 0, 1, 0],
[1, 0, 0, 0],
[1, 0, 1, 0],
[0, 1, 1, 0],
[MARG_IND, 0, 0, 1],
[MARG_IND, MARG_IND, MARG_IND, MARG_IND]]).astype(numpy.int32)
input = K.placeholder(ndim=2, dtype='int32')
for i, var in enumerate(vars):
for j in [0, 1]:
log_vals = []
print('var {} val {}'.format(i, j))
smi = CategoricalIndicatorNode(i, j)
print(smi)
smi.build_k(input)
for d in data:
# print(d)
smi.eval(d)
log_vals.append(smi.log_val)
print('smi values')
print(smi.log_val)
eval_input_node_f = K.function([input], [smi.log_vals])
keras_log_vals = eval_input_node_f([data])[0]
print('keras vals')
print(keras_log_vals)
assert_array_almost_equal(numpy.array(log_vals)[:, numpy.newaxis],
keras_log_vals,
decimal=4)
def linked_categorical_input_to_indicators(spn, input_layer=None):
"""
Convertes a linked spn categorical input layer into an indicator one
"""
#
# get child, parent relations for node relinking
child_assoc = retrieve_children_parent_assoc(spn)
#
# get input layer
cat_input_layer = spn.input_layer()
assert isinstance(cat_input_layer, CategoricalSmoothedLayerLinked)
#
# one indicator node for each var value
vars = cat_input_layer.vars()
if not vars:
vars = list(sorted({node.var for node in cat_input_layer.nodes()}))
feature_values = cat_input_layer.feature_vals()
# print('vars', vars)
# print('feature values', feature_values)
indicator_nodes = [
CategoricalIndicatorNode(var, val) for i, var in enumerate(vars)
for val in range(feature_values[i])
]
# for node in indicator_nodes:
# print(node)
indicator_map = defaultdict(set)
for ind_node in indicator_nodes:
indicator_map[ind_node.var].add(ind_node)
sum_nodes = []
#
# as many sum nodes as cat nodes
for node in cat_input_layer.nodes():
sum_node = SumNode(var_scope=frozenset([node.var]))
sum_nodes.append(sum_node)
for ind_node in sorted(indicator_map[node.var],
key=lambda x: x.var_val):
sum_node.add_child(ind_node,
numpy.exp(node._var_probs[ind_node.var_val]))
#
# removing links to parents
parents = child_assoc[node]
for p_node in parents:
#
# assume it to be a product node
# TODO: generalize
assert isinstance(p_node, ProductNode)
p_node.children.remove(node)
p_node.add_child(sum_node)
#
# creating layer
sum_layer = SumLayerLinked(sum_nodes)
indicator_layer = CategoricalIndicatorLayerLinked(indicator_nodes)
cat_input_layer.disconnect_layer()
spn.set_input_layer(indicator_layer)
spn.insert_layer(sum_layer, 0)
return spn
def test_categorical_indicator_layer_vars():
# create indicator nodes first
ind1 = CategoricalIndicatorNode(var=0, var_val=0)
ind2 = CategoricalIndicatorNode(var=3, var_val=0)
ind3 = CategoricalIndicatorNode(var=3, var_val=1)
ind4 = CategoricalIndicatorNode(var=2, var_val=0)
ind5 = CategoricalIndicatorNode(var=1, var_val=1)
ind6 = CategoricalIndicatorNode(var=2, var_val=1)
ind7 = CategoricalIndicatorNode(var=1, var_val=0)
ind8 = CategoricalIndicatorNode(var=0, var_val=1)
ind9 = CategoricalIndicatorNode(var=2, var_val=2)
ind10 = CategoricalIndicatorNode(var=3, var_val=2)
ind11 = CategoricalIndicatorNode(var=3, var_val=3)
# building the layer from nodes
layer = CategoricalIndicatorLayer(nodes=[ind1, ind2,
ind3, ind4,
ind5, ind6,
ind7, ind8,
ind9, ind10, ind11])
# checking for the construction of the vars property
layer_vars = layer.vars()
assert vars == layer_vars
def test_spn_set_get_weights():
# create a simple spn
root_node = SumNode()
root_layer = SumLayer([root_node])
prod_node_1 = ProductNode()
prod_node_2 = ProductNode()
root_node.add_child(prod_node_1, 0.5)
root_node.add_child(prod_node_2, 0.5)
prod_layer = ProductLayer([prod_node_1,
prod_node_2])
sum_node_1 = SumNode()
sum_node_2 = SumNode()
sum_node_3 = SumNode()
prod_node_1.add_child(sum_node_1)
prod_node_1.add_child(sum_node_2)
prod_node_2.add_child(sum_node_2)
prod_node_2.add_child(sum_node_3)
sum_layer = SumLayer([sum_node_1, sum_node_2,
sum_node_3])
ind_node_1 = CategoricalIndicatorNode(var=0, var_val=1)
ind_node_2 = CategoricalIndicatorNode(var=0, var_val=1)
ind_node_3 = CategoricalIndicatorNode(var=0, var_val=1)
ind_node_4 = CategoricalIndicatorNode(var=0, var_val=1)
ind_node_5 = CategoricalIndicatorNode(var=0, var_val=1)
input_layer = CategoricalInputLayer(nodes=[ind_node_1,
ind_node_2,
ind_node_3,
ind_node_4,
ind_node_5])
sum_node_1.add_child(ind_node_1, 0.2)
sum_node_1.add_child(ind_node_2, 0.2)
sum_node_2.add_child(ind_node_2, 0.2)
sum_node_2.add_child(ind_node_3, 0.2)
sum_node_2.add_child(ind_node_4, 0.2)
sum_node_3.add_child(ind_node_4, 0.2)
sum_node_3.add_child(ind_node_5, 0.2)
spn = Spn(input_layer=input_layer,
layers=[sum_layer, prod_layer, root_layer])
print(spn)
# storing these weights
curr_weights = spn.get_weights()
# setting the new weights
spn.set_weights(weights_ds)
# getting them again
new_weights = spn.get_weights()
# comparing them
assert new_weights == weights_ds
# now setting back the previous one
spn.set_weights(curr_weights)
# getting them back again
old_weights = spn.get_weights()
# and checking
assert old_weights == curr_weights
def build_linked_layered_spn(print_spn=True):
#
# building an indicator layer
ind_x_00 = CategoricalIndicatorNode(0, 0)
ind_x_01 = CategoricalIndicatorNode(0, 1)
ind_x_10 = CategoricalIndicatorNode(1, 0)
ind_x_11 = CategoricalIndicatorNode(1, 1)
ind_x_20 = CategoricalIndicatorNode(2, 0)
ind_x_21 = CategoricalIndicatorNode(2, 1)
input_layer = CategoricalIndicatorLayer(
[ind_x_00, ind_x_01, ind_x_10, ind_x_11, ind_x_20, ind_x_21])
#
# sum layer
#
sum_node_1 = SumNode(frozenset([0]))
sum_node_1.add_child(ind_x_00, 0.1)
sum_node_1.add_child(ind_x_01, 0.9)
sum_node_2 = SumNode(frozenset([0]))
sum_node_2.add_child(ind_x_00, 0.4)
sum_node_2.add_child(ind_x_01, 0.6)
sum_node_3 = SumNode(frozenset([1]))
sum_node_3.add_child(ind_x_10, 0.3)
sum_node_3.add_child(ind_x_11, 0.7)
sum_node_4 = SumNode(frozenset([1]))
sum_node_4.add_child(ind_x_10, 0.6)
sum_node_4.add_child(ind_x_11, 0.4)
sum_node_5 = SumNode(frozenset([2]))
sum_node_5.add_child(ind_x_20, 0.5)
sum_node_5.add_child(ind_x_21, 0.5)
sum_node_6 = SumNode(frozenset([2]))
sum_node_6.add_child(ind_x_20, 0.2)
sum_node_6.add_child(ind_x_21, 0.8)
sum_layer_1 = SumLayerLinked([
sum_node_1, sum_node_2, sum_node_3, sum_node_4, sum_node_5, sum_node_6
])
#
# product nodes
#
# xy
prod_node_7 = ProductNode(frozenset([0, 1]))
prod_node_7.add_child(sum_node_1)
prod_node_7.add_child(sum_node_3)
prod_node_8 = ProductNode(frozenset([0, 1]))
prod_node_8.add_child(sum_node_2)
prod_node_8.add_child(sum_node_4)
prod_node_9 = ProductNode(frozenset([0, 1]))
prod_node_9.add_child(sum_node_1)
prod_node_9.add_child(sum_node_3)
#
# yz
prod_node_10 = ProductNode(frozenset([1, 2]))
prod_node_10.add_child(sum_node_4)
prod_node_10.add_child(sum_node_5)
prod_node_11 = ProductNode(frozenset([1, 2]))
prod_node_11.add_child(sum_node_4)
prod_node_11.add_child(sum_node_6)
prod_layer_2 = ProductLayerLinked(
[prod_node_7, prod_node_8, prod_node_9, prod_node_10, prod_node_11])
#
# sum nodes
#
# xy
sum_node_12 = SumNode(frozenset([0, 1]))
sum_node_12.add_child(prod_node_7, 0.1)
sum_node_12.add_child(prod_node_8, 0.9)
sum_node_13 = SumNode(frozenset([0, 1]))
sum_node_13.add_child(prod_node_8, 0.7)
sum_node_13.add_child(prod_node_9, 0.3)
#
# yz
sum_node_14 = SumNode(frozenset([1, 2]))
sum_node_14.add_child(prod_node_10, 0.6)
sum_node_14.add_child(prod_node_11, 0.4)
sum_layer_3 = SumLayerLinked([sum_node_12, sum_node_13, sum_node_14])
#
# product nodes
prod_node_15 = ProductNode(frozenset([0, 1, 2]))
prod_node_15.add_child(sum_node_12)
prod_node_15.add_child(sum_node_6)
prod_node_16 = ProductNode(frozenset([0, 1, 2]))
prod_node_16.add_child(sum_node_13)
prod_node_16.add_child(sum_node_5)
prod_node_17 = ProductNode(frozenset([0, 1, 2]))
prod_node_17.add_child(sum_node_2)
prod_node_17.add_child(sum_node_14)
prod_layer_4 = ProductLayerLinked(
[prod_node_15, prod_node_16, prod_node_17])
#
# root
sum_node_18 = SumNode(frozenset([0, 1, 2]))
sum_node_18.add_child(prod_node_15, 0.2)
sum_node_18.add_child(prod_node_16, 0.2)
sum_node_18.add_child(prod_node_17, 0.6)
sum_layer_5 = SumLayerLinked([sum_node_18])
#
# creating the spn
layers = [
sum_layer_1, prod_layer_2, sum_layer_3, prod_layer_4, sum_layer_5
]
nodes = [node for layer in layers for node in layer.nodes()]
spn = SpnLinked(input_layer=input_layer, layers=layers)
if print_spn:
print(spn)
return spn, layers, nodes
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_linked_to_theano_indicator():
# creating single nodes
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)
# building layers from nodes
root_layer = SumLayerLinked([root])
prod_layer = ProductLayerLinked([prod1, prod2, prod3])
sum_layer = SumLayerLinked([sum1, sum2, sum3, sum4])
aprod_layer = ProductLayerLinked([prod4, prod5, prod6, prod7])
ind_layer = CategoricalIndicatorLayer(nodes=[
ind1, ind2, ind3, ind4, ind5, ind6, ind7, ind8, ind9, ind10, ind11
])
# creating the linked spn
spn_linked = SpnLinked(
input_layer=ind_layer,
layers=[aprod_layer, sum_layer, prod_layer, root_layer])
print(spn_linked)
# converting to theano repr
spn_theano = SpnFactory.linked_to_theano(spn_linked)
print(spn_theano)
# time for some inference comparison
for instance in I:
print('linked')
res_l = spn_linked.eval(instance)
print(res_l)
print('theano')
res_t = spn_theano.eval(instance)
print(res_t)
assert_array_almost_equal(res_l, res_t)
def build_linked_spn_from_scope_graph(scope_graph,
k,
root_scope=None,
feature_values=None):
"""
Turning a ScopeGraph into an SPN by puttin k sum nodes for each scope
and a combinatorial number of product nodes to wire the partition nodes
This is the algorithm used in Poon2011 and is shown (and used) as BuildSPN in Dennis2012
"""
if not root_scope:
root_scope = scope_graph.root
n_vars = len(root_scope.vars)
if not feature_values:
#
# assuming binary r.v.s
feature_values = [2 for _i in range(n_vars)]
#
# adding leaves
leaves_dict = defaultdict(list)
leaves_list = []
for var in sorted(root_scope.vars):
for var_val in range(feature_values[var]):
leaf = CategoricalIndicatorNode(var, var_val)
leaves_list.append(leaf)
leaves_dict[var].append(leaf)
input_layer = CategoricalIndicatorLayer(nodes=leaves_list,
vars=list(sorted(root_scope.vars)))
#
# in a first pass we need to assign each scope/region k sum nodes
sum_nodes_assoc = {}
for r in scope_graph.traverse_scopes(root_scope=root_scope):
num_sum_nodes = k
if r == root_scope:
num_sum_nodes = 1
added_sum_nodes = [
SumNode(var_scope=r.vars) for i in range(num_sum_nodes)
]
#
# creating a sum layer
sum_layer = SumLayer(added_sum_nodes)
sum_nodes_assoc[r] = sum_layer
#
# if this is a univariate scope, we link it to leaves corresponding to its r.v.
if r.is_atomic():
single_rv = set(r.vars).pop()
rv_leaves = leaves_dict[single_rv]
uniform_weight = 1.0 / len(rv_leaves)
for s in added_sum_nodes:
for leaf in rv_leaves:
s.add_child(leaf, uniform_weight)
#
# linking to input layer
sum_layer.add_input_layer(input_layer)
input_layer.add_output_layer(sum_layer)
layers = []
#
# looping again to add and wire product nodes
for r in scope_graph.traverse_scopes(root_scope=root_scope):
sum_layer = sum_nodes_assoc[r]
layers.append(sum_layer)
for p in r.partitions:
sum_layer_descs = [sum_nodes_assoc[r_p] for r_p in p.scopes]
sum_nodes_lists = [
list(layer.nodes()) for layer in sum_layer_descs
]
num_prod_nodes = numpy.prod([len(r_p) for r_p in sum_nodes_lists])
#
# adding product nodes
added_prod_nodes = [
ProductNode(var_scope=r.vars) for i in range(num_prod_nodes)
]
#
# adding product layer and linking
prod_layer = ProductLayer(added_prod_nodes)
sum_layer.add_input_layer(prod_layer)
prod_layer.add_output_layer(sum_layer)
for desc in sum_layer_descs:
prod_layer.add_input_layer(desc)
desc.add_output_layer(prod_layer)
layers.append(prod_layer)
#
# linking to parents
sum_nodes_parents = sum_layer.nodes()
for sum_node in sum_nodes_parents:
uniform_weight = 1.0 / (len(added_prod_nodes) *
len(r.partitions))
for prod_node in added_prod_nodes:
sum_node.add_child(prod_node, uniform_weight)
#
# linking to children
sum_nodes_to_wire = list(itertools.product(*sum_nodes_lists))
assert len(added_prod_nodes) == len(sum_nodes_to_wire)
for prod_node, sum_nodes in zip(added_prod_nodes,
sum_nodes_to_wire):
for sum_node in sum_nodes:
prod_node.add_child(sum_node)
#
# toposort
layers = topological_layer_sort(layers)
spn = LinkedSpn(layers=layers, input_layer=input_layer)
return spn
def test_build_linked_spn_from_scope_graph():
#
# creating a region graph as an input scope graph
n_cols = 2
n_rows = 2
coarse = 2
#
# create initial region
root_region = Region.create_whole_region(n_rows, n_cols)
region_graph = create_poon_region_graph(root_region, coarse=coarse)
# print(region_graph)
print('# partitions', region_graph.n_partitions())
print('# regions', region_graph.n_scopes())
print(region_graph)
#
#
k = 2
spn = build_linked_spn_from_scope_graph(region_graph, k)
print(spn)
print(spn.stats())
#
# back to the scope graph
root_layer = list(spn.root_layer().nodes())
assert len(root_layer) == 1
root = root_layer[0]
scope_graph = get_scope_graph_from_linked_spn(root)
print(scope_graph)
assert scope_graph == region_graph
#
# building an spn from scratch
#
# building leaf nodes
n_vars = 4
vars = [0, 1, 2, 3]
leaves = [
CategoricalIndicatorNode(var, val) for var in range(n_vars)
for val in [0, 1]
]
input_layer = CategoricalIndicatorLayer(nodes=leaves, vars=vars)
#
# building root
root_node = SumNode(var_scope=frozenset(vars))
root_layer = SumLayer([root_node])
#
# building product nodes
prod_list_1 = [ProductNode(var_scope=vars) for i in range(4)]
prod_list_2 = [ProductNode(var_scope=vars) for i in range(4)]
prod_nodes_1 = prod_list_1 + prod_list_2
product_layer_1 = ProductLayer(prod_nodes_1)
for p in prod_nodes_1:
root_node.add_child(p, 1.0 / len(prod_nodes_1))
#
# build sum nodes
sum_list_1 = [SumNode() for i in range(2)]
sum_list_2 = [SumNode() for i in range(2)]
sum_list_3 = [SumNode() for i in range(2)]
sum_list_4 = [SumNode() for i in range(2)]
sum_layer_2 = SumLayer(sum_list_1 + sum_list_2 + sum_list_3 + sum_list_4)
sum_pairs = []
for s_1 in sum_list_1:
for s_2 in sum_list_2:
sum_pairs.append((s_1, s_2))
for p, (s_1, s_2) in zip(prod_list_1, sum_pairs):
p.add_child(s_1)
p.add_child(s_2)
sum_pairs = []
for s_3 in sum_list_3:
for s_4 in sum_list_4:
sum_pairs.append((s_3, s_4))
for p, (s_3, s_4) in zip(prod_list_2, sum_pairs):
p.add_child(s_3)
p.add_child(s_4)
#
# again product nodes
prod_list_3 = [ProductNode() for i in range(4)]
prod_list_4 = [ProductNode() for i in range(4)]
prod_list_5 = [ProductNode() for i in range(4)]
prod_list_6 = [ProductNode() for i in range(4)]
product_layer_3 = ProductLayer(prod_list_3 + prod_list_4 + prod_list_5 +
prod_list_6)
for s in sum_list_1:
for p in prod_list_3:
s.add_child(p, 1.0 / len(prod_list_3))
for s in sum_list_2:
for p in prod_list_4:
s.add_child(p, 1.0 / len(prod_list_4))
for s in sum_list_3:
for p in prod_list_5:
s.add_child(p, 1.0 / len(prod_list_5))
for s in sum_list_4:
for p in prod_list_6:
s.add_child(p, 1.0 / len(prod_list_6))
#
# build sum nodes
sum_list_5 = [SumNode() for i in range(2)]
sum_list_6 = [SumNode() for i in range(2)]
sum_list_7 = [SumNode() for i in range(2)]
sum_list_8 = [SumNode() for i in range(2)]
sum_layer_4 = SumLayer(sum_list_5 + sum_list_6 + sum_list_7 + sum_list_8)
sum_pairs = []
for s_5 in sum_list_5:
for s_7 in sum_list_7:
sum_pairs.append((s_5, s_7))
for p, (s_5, s_7) in zip(prod_list_3, sum_pairs):
p.add_child(s_5)
p.add_child(s_7)
sum_pairs = []
for s_6 in sum_list_6:
for s_8 in sum_list_8:
sum_pairs.append((s_6, s_8))
for p, (s_6, s_8) in zip(prod_list_4, sum_pairs):
p.add_child(s_6)
p.add_child(s_8)
sum_pairs = []
for s_5 in sum_list_5:
for s_6 in sum_list_6:
sum_pairs.append((s_5, s_6))
for p, (s_5, s_6) in zip(prod_list_5, sum_pairs):
p.add_child(s_5)
p.add_child(s_6)
sum_pairs = []
for s_7 in sum_list_7:
for s_8 in sum_list_8:
sum_pairs.append((s_7, s_8))
for p, (s_7, s_8) in zip(prod_list_6, sum_pairs):
p.add_child(s_7)
p.add_child(s_8)
#
# linking to input layer
for s in sum_list_5:
for i in leaves[0:2]:
s.add_child(i, 0.5)
for s in sum_list_6:
for i in leaves[2:4]:
s.add_child(i, 0.5)
for s in sum_list_7:
for i in leaves[4:6]:
s.add_child(i, 0.5)
for s in sum_list_8:
for i in leaves[6:]:
s.add_child(i, 0.5)
lspn = LinkedSpn(input_layer=input_layer,
layers=[
sum_layer_4, product_layer_3, sum_layer_2,
product_layer_1, root_layer
])
print(lspn)
print(lspn.stats())
#
# trying to evaluate them
input_vec = numpy.array([[1., 1., 1., 0.], [0., 0., 0., 0.],
[0., 1., 1., 0.],
[MARG_IND, MARG_IND, MARG_IND, MARG_IND]]).T
res = spn.eval(input_vec)
print('First evaluation')
print(res)
res = lspn.eval(input_vec)
print('Second evaluation')
print(res)