def create_node_raking_from_diff_matrix(diff: pd.DataFrame,
removed_nodes: [int],
graph: gc.Graph,
save_info: sl.MemoryAccess,
save: bool = True) -> []:
utils.assure_same_labels([diff])
labels = diff.index.values.tolist()
dim = len(labels)
# init sums
node_pos_sums = {}
node_neg_sums = {}
for label in labels:
node_pos_sums[label] = 0
node_neg_sums[label] = 0
# sum values up
for i in range(dim):
for j in range(i):
label1 = labels[i]
label2 = labels[j]
value = diff.at[label1, label2]
if value > 0:
node_pos_sums[label1] += value
node_pos_sums[label2] += value
else:
node_neg_sums[label1] += value
node_neg_sums[label2] += value
pos_list = list(map(lambda x: (x, node_pos_sums[x]), node_pos_sums))
neg_list = list(map(lambda x: (x, node_neg_sums[x]), node_neg_sums))
complete_list = list(
map(lambda x: (x, node_pos_sums[x] - node_neg_sums[x]), node_pos_sums))
pos_list.sort(key=lambda x: -x[1])
neg_list.sort(key=lambda x: x[1])
complete_list.sort(key=lambda x: -x[1])
if save:
save_info.save_node_raking(removed_nodes, pos_list,
list(graph.neighbours(removed_nodes[-1])))
neighbours = list(graph.neighbours(removed_nodes[0]))
pos_list_labels = list(map(lambda x: x[0] in neighbours, pos_list))
neg_list_labels = list(map(lambda x: x[0] in neighbours, neg_list))
complete_list_labels = list(
map(lambda x: x[0] in neighbours, complete_list))
return pos_list, pos_list_labels, neg_list, neg_list_labels, complete_list, complete_list_labels
def create_target_vector(row_labels: [], graph: gc.Graph,
node_to_predict: int) -> pd.DataFrame:
"""
creates the target vector for classifier
:param row_labels: labels the target vector should be created
:param graph: graph including the removed node
:param node_to_predict: the node that is removed in the 2. embedding
:return:
"""
neighbours_of_removed_node = graph.neighbours(node_to_predict)
target = pd.DataFrame(False, row_labels, ["y"])
for neighbour in neighbours_of_removed_node:
# this prevents an error in case the original graph is used while 2 nodes are removed in the labels
# and they are connected
if neighbour in row_labels:
target.loc[neighbour] = True
return target
def _get_avg_degree_of_neighbours(graph: gc.Graph, node: int):
neighbours_mean = (list(
map(lambda n: graph.degree(n), list(graph.neighbours(node)))))
return sum(neighbours_mean) / len(neighbours_mean)