def get_example_3():
"""get a binarized example, whose original graph is
more complicated than the above example
"""
g = DiGraph()
g.add_nodes_from(range(1, 10))
g.add_edges_from([(1, 2), (1, 3), (1, 7),
(2, 4), (2, 5), (2, 6),
(2, 7), (3, 8), (3, 9)])
rewards = range(1, 10)
for r, n in zip(rewards, g.nodes()):
g.node[n]['r'] = r
# all edges have cost 2 except 1 -> 2 and 1 -> 3(cost 1)
for s, t in g.edges():
g[s][t]['c'] = 2
g[1][2]['c'] = 1
g[1][3]['c'] = 1
g = binarize_dag(g,
vertex_weight_key='r',
edge_weight_key='c',
dummy_node_name_prefix='d_')
# parameters and expected output
U = [0, 2, 3, 4, 100]
expected_edges_set = [
[],
[(1, 7)],
[(1, 'd_1'), ('d_1', 3), (3, 9)],
[(1, 'd_1'), ('d_1', 3), (3, 9), ('d_1', 2)],
# (1, 7) removed to make it a tree
list(set(g.edges()) - set([(1, 7)]))
]
return (g, U, expected_edges_set)
def load(fname):
def clean_bool(string):
if string == "0":
return None
else:
return string
def to_bool(string):
if string == "1" or string == "True":
return True
elif string == "0" or string == "False":
return False
else:
return string
def to_float(string):
if string == "None":
return None
try:
return float(string)
except:
return string
mode = "node0"
nodes = []
edges = []
pointers = set()
outputs = None
inputs = None
named_ranges = {}
infile = gzip.GzipFile(fname, 'rb')
for line in infile.read().splitlines():
line = line.decode("utf-8")
if line == "====":
mode = "node0"
continue
if line == "-----":
cellmap_temp = {n.address(): n for n in nodes}
Range = RangeFactory(cellmap_temp)
mode = "node0"
continue
elif line == "edges":
cellmap = {n.address(): n for n in nodes}
mode = "edges"
continue
elif line == "outputs":
mode = "outputs"
continue
elif line == "inputs":
mode = "inputs"
continue
elif line == "named_ranges":
mode = "named_ranges"
continue
if mode == "node0":
[
address, formula, python_expression, is_range, is_named_range,
is_pointer, should_eval
] = line.split(SEP)
formula = clean_bool(formula)
python_expression = clean_bool(python_expression)
is_range = to_bool(is_range)
is_named_range = to_bool(is_named_range)
is_pointer = to_bool(is_pointer)
should_eval = should_eval
mode = "node1"
elif mode == "node1":
if is_range:
reference = json.loads(
line
) if is_pointer else line # in order to be able to parse dicts
vv = Range(reference)
if is_pointer:
if not is_named_range:
address = vv.name
pointers.add(address)
cell = Cell(address, None, vv, formula, is_range,
is_named_range, should_eval)
cell.python_expression = python_expression
nodes.append(cell)
else:
value = to_bool(to_float(line))
cell = Cell(address, None, value, formula, is_range,
is_named_range, should_eval)
cell.python_expression = python_expression
if formula:
if 'OFFSET' in formula or 'INDEX' in formula:
pointers.add(address)
cell.compile()
nodes.append(cell)
elif mode == "edges":
source, target = line.split(SEP)
edges.append((cellmap[source], cellmap[target]))
elif mode == "outputs":
outputs = line.split(SEP)
elif mode == "inputs":
inputs = line.split(SEP)
elif mode == "named_ranges":
k, v = line.split(SEP)
named_ranges[k] = v
G = DiGraph()
G.add_nodes_from(nodes)
G.add_edges_from(edges)
print("Graph loading done, %s nodes, %s edges, %s cellmap entries" %
(len(G.nodes()), len(G.edges()), len(cellmap)))
return (G, cellmap, named_ranges, pointers, outputs, inputs)
