def compute_label_histogram(self, g):
""" Compute the neighborhood hash of a graph g and return
the histogram of the hashed labels.
"""
g_hash = ml.neighborhood_hash(g)
g_x = ml.label_histogram(g_hash)
return g_x
def compute_label_histogram(self, g):
""" Compute the neighborhood hash of a graph g and return
the histogram of the hashed labels.
"""
g_hash = ml.neighborhood_hash(g)
g_x = ml.label_histogram(g_hash)
return g_x
def add_weights_to_nodes(g, w, show_labels=True):
g_hash = ml.neighborhood_hash(g)
# initialize the weight for every node in g_hash
for n, nh in g_hash.node.iteritems():
idx = int("".join([str(i) for i in nh["label"]]), 2)
w_nh = w[idx]
g_hash.node[n]["label"] = w_nh
# create a copy of the weighted graph
g_hash_weighted = g_hash.copy()
# aggregate the weights of each node with the
# original weight of its caller
for n, nh in g_hash.node.iteritems():
for neighbor in g_hash.neighbors(n):
g_hash_weighted.node[neighbor]["label"] += g_hash.node[n]["label"]
# create array of the node weigths
g_weights = []
for n, nh in g_hash_weighted.node.iteritems():
g_weights.append(nh["label"])
# normalize weight between 0.5 and 1 to plot
g_weights = np.array(g_weights)
g_weights.sort()
g_weights_norm = normalize_weights(g_weights)
g_weights_norm = g_weights_norm[::-1]
d_w_norm = dict(zip(g_weights, g_weights_norm))
# add normalized weight as color to each node
for n, nh in g_hash_weighted.node.iteritems():
w = g_hash_weighted.node[n]["label"]
g_hash_weighted.node[n]["style"] = "filled"
g_hash_weighted.node[n]["fillcolor"] = "0.000 0.000 {0}".format(
d_w_norm[w])
# write function name in the label of the node or remove label
if show_labels:
for n, nh in g_hash_weighted.node.iteritems():
node_text = (n[0].split("/")[-1] + n[1] + "\n" +
str(g_hash_weighted.node[n]["label"]))
g_hash_weighted.node[n]["label"] = node_text
else:
for n, nh in g_hash_weighted.node.iteritems():
g_hash_weighted.node[n]["label"] = ""
return g_hash_weighted
def get_high_ranked_neighborhoods(self,
fcg_file,
sorted_weights_idx,
n_weights=3):
"""
Retrieve the neighborhoods in a hashed graph with maximum weights.
n_weights:
:param fcg_file: path of file containing a fcg
:param sorted_weights_idx: index that sort the weights from the
linear classifier
:param n_weights: number of weights with maximum value to retrieve
the associated neighborhoods
:returns: a list of matching neighborhoods.
"""
# g = FCG.build_fcg(fcg_file)
g = pz.load(fcg_file)
g_hash = ml.neighborhood_hash(g)
bits = len(instructionSet.INSTRUCTION_CLASS_COLOR)
neighborhoods = []
remaining_weights = n_weights
for idx in sorted_weights_idx:
if remaining_weights > 0:
label_decimal = idx / self.b
label_bin = np.binary_repr(label_decimal, bits)
label = np.array([int(i) for i in label_bin])
matching_neighborhoods = []
for m, nh in g_hash.node.iteritems():
if np.array_equal(nh["label"], label):
neighborhood = "{0} {1}.{2}({3})".format(
remaining_weights, m[0], m[1], m[2])
matching_neighborhoods.append(neighborhood)
if matching_neighborhoods:
remaining_weights -= 1
neighborhoods += matching_neighborhoods
else:
del g
del g_hash
return neighborhoods
def get_high_ranked_neighborhoods(self, fcg_file,
sorted_weights_idx, n_weights=3):
"""
Retrieve the neighborhoods in a hashed graph with maximum weights.
n_weights:
:param fcg_file: path of file containing a fcg
:param sorted_weights_idx: index that sort the weights from the
linear classifier
:param n_weights: number of weights with maximum value to retrieve
the associated neighborhoods
:returns: a list of matching neighborhoods.
"""
# g = FCG.build_fcg(fcg_file)
g = pz.load(fcg_file)
g_hash = ml.neighborhood_hash(g)
bits = len(instructionSet.INSTRUCTION_CLASS_COLOR)
neighborhoods = []
remaining_weights = n_weights
for idx in sorted_weights_idx:
if remaining_weights > 0:
label_decimal = idx / self.b
label_bin = np.binary_repr(label_decimal, bits)
label = np.array([int(i) for i in label_bin])
matching_neighborhoods = []
for m, nh in g_hash.node.iteritems():
if np.array_equal(nh["label"], label):
neighborhood = "{0} {1}.{2}({3})".format(remaining_weights,
m[0], m[1], m[2])
matching_neighborhoods.append(neighborhood)
if matching_neighborhoods:
remaining_weights -= 1
neighborhoods += matching_neighborhoods
else:
del g
del g_hash
return neighborhoods
def get_high_ranked_neighborhoods(fcgnx_file,
w,
sorted_weights_idx,
show_small=False,
weights=1):
# g = FCGextractor.build_cfgnx(fcgnx_file)
g = nx.read_gpickle(fcgnx_file)
g_hash = ml.neighborhood_hash(g)
neighborhoods = []
remaining_weights = weights
for idx in sorted_weights_idx:
if remaining_weights > 0:
label_bin = np.binary_repr(idx, 15)
label = np.array([int(i) for i in label_bin])
matching_neighborhoods = []
for m, nh in g_hash.node.iteritems():
if np.array_equal(nh["label"], label):
neighbors_l = g_hash.neighbors(m)
if neighbors_l:
neighbors = '\n'.join([str(i) for i in neighbors_l])
matching_neighborhoods.append("{0}\n{1}\n{2}\n".format(
w[idx], m, neighbors))
else:
if show_small:
matching_neighborhoods.append("{0}\n{1}\n".format(
w[idx], m))
if matching_neighborhoods:
remaining_weights -= 1
neighborhoods += matching_neighborhoods
else:
n_nodes = g_hash.number_of_nodes()
del g
del g_hash
return neighborhoods, n_nodes
