def compute_indexes(G: nx.Graph, method, negative, positive):
if method == 'resource_allocation':
return nx.resource_allocation_index(
G, negative), nx.resource_allocation_index(G, positive)
elif method == 'jaccard_coefficient':
return nx.jaccard_coefficient(G, negative), nx.jaccard_coefficient(
G, positive)
elif method == 'adamic_adar':
return nx.adamic_adar_index(G, negative), nx.adamic_adar_index(
G, positive)
elif method == 'preferential_attachment':
return nx.preferential_attachment(
G, negative), nx.preferential_attachment(G, positive)
elif method == 'sorensen_neighbours':
return ([(u, v, sorensen_index(G, u, v)) for u, v in negative],
[(u, v, sorensen_index(G, u, v)) for u, v in positive])
elif method == 'community':
c = louvain(G)
commLabels = c.communities
comms = c.to_node_community_map()
return ([(u, v, community_index(G, u, v, commLabels, comms))
for u, v in negative],
[(u, v, community_index(G, u, v, commLabels, comms))
for u, v in positive])
else:
raise NameError('The given method is not supported')
def get_link_pred_auc(graph, pos_test, neg_test):
jc_pos_test_pred = nx.jaccard_coefficient(graph, pos_test)
jc_neg_test_pred = nx.jaccard_coefficient(graph, neg_test)
jc_pos_score = [p for _, _, p in jc_pos_test_pred]
jc_neg_score = [n for _, _, n in jc_neg_test_pred]
jc_all_labels = [1] * len(jc_pos_score) + [0] * len(jc_neg_score)
jc_all_scores = jc_pos_score + jc_neg_score
jc_auc = metrics.roc_auc_score(jc_all_labels, jc_all_scores)
aa_pos_test_pred = nx.resource_allocation_index(graph, pos_test)
aa_neg_test_pred = nx.resource_allocation_index(graph, neg_test)
aa_pos_score = [p for _, _, p in aa_pos_test_pred]
aa_neg_score = [n for _, _, n in aa_neg_test_pred]
aa_all_labels = [1] * len(aa_pos_score) + [0] * len(aa_neg_score)
aa_all_scores = aa_pos_score + aa_neg_score
aa_auc = metrics.roc_auc_score(aa_all_labels, aa_all_scores)
return jc_auc, aa_auc
def get_feature(nonedge, G, df):
#=========common_neigh===========
common_neigh = compute_common_neigh(G, nonedge)
v = get_list_value(common_neigh)
df['common_neigh'] = v
print_output(common_neigh)
#=========jaccard_coefficient===========
jaccard = list(nx.jaccard_coefficient(G, nonedge))
v = get_list_value(jaccard)
df['jaccard'] = v
print_output(jaccard)
resource_alloc = list(nx.resource_allocation_index(G, nonedge))
v = get_list_value(resource_alloc)
df['resource_alloc'] = v
print_output(resource_alloc)
adamic_adar = list(nx.adamic_adar_index(G, nonedge))
v = get_list_value(adamic_adar)
df['adamic_adar'] = v
print_output(adamic_adar)
pref_attach = list(nx.preferential_attachment(G, nonedge))
v = get_list_value(pref_attach)
df['pref_attach'] = v
print_output(pref_attach)
def Link_Precision(Graph):
"""Step1------构造网络"""
G = Graph
# plt.figure(1)
# plt.subplot(211)
# pos = nx.circular_layout(G)
# nx.draw_networkx(G, pos, with_labels=True)
# 对构造的网络删除部分连边
test_set, non_edges_set = delete_link(G)
# plt.subplot(212)
# pos = nx.circular_layout(G)
# nx.draw_networkx(G, pos, with_labels=True)
# plt.show()
"""Step2------对网络缺失边预测得分值"""
# preds = nx.adamic_adar_index(G)
# preds = nx.common_neighbors(G)
# preds = nx.jaccard_coefficient(G)
preds = nx.resource_allocation_index(G)
preds = sorted(preds, key=itemgetter(2), reverse=True) # 根据连边的预测得分值降序排序
"""Step3------AUC，Precision指标的计算"""
auc_result = AUC_Indx(preds, test_set, non_edges_set)
precision_result = Precision_Index(preds, test_set)
"""输出结果"""
print "AUC:", auc_result, "Precision:", precision_result
return auc_result, precision_result
def feature_calculate(g, data, column_names, save_to):
pairs = list(map(lambda x: (x[0], x[1]), data))
jaccard = nx.jaccard_coefficient(g, pairs)
preferential = nx.preferential_attachment(g, pairs)
rai = nx.resource_allocation_index(g, pairs)
# shortest path
total = len(data)
current = 0
for row_data in zip(data, jaccard, preferential, rai):
row = row_data[0]
try:
thisjaccard = row_data[1][2]
except:
thisjaccard = -1
try:
thispreferential = row_data[2][2]
except:
thispreferential = -1
try:
thisrai = row_data[3][2]
except:
thisrai = -1
# pred = row_data[1]
# resource_allocation_index = pred[2]
if current % 1000 == 0:
ut.log("calculating {}/{}...".format(current, total))
path_length = 99999
try:
path = nx.shortest_path(g, row[0], row[1], 'weight')
path_length = len(path)
except:
pass
# shortest path
row.insert(-1, path_length)
# jaccard
row.insert(-1, thisjaccard)
# preferential
row.insert(-1, thispreferential)
# rai
row.insert(-1, thisrai)
current += 1
original_columns_titles = list(column_names)
original_columns_titles.insert(-1, "shortest_path_count")
original_columns_titles.insert(-1, "jaccard")
original_columns_titles.insert(-1, "preferential")
original_columns_titles.insert(-1, "rai")
data.insert(0, original_columns_titles)
ut.write_list_csv(save_to, data)
def sort_edges_by_resource_allocation(graph, edges):
edges_sorted = sorted(list(nx.resource_allocation_index(graph, edges)),
key=lambda l: l[2],
reverse=True,
cmp=compare_with_ties)
return [(row[0], row[1])
for row in edges_sorted], [row[2] for row in edges_sorted]
def link_prediction_with_metrics(subgraph, tuples, df):
jaccard_coefficient_list = list(nx.jaccard_coefficient(subgraph, tuples))
y_test = create_test_data(jaccard_coefficient_list)
print(
f"ROC AUC Score with Jaccard Coefficient: {roc_auc_score(df['link'], y_test)}\n"
f"Average Precision with Jaccard Coefficient: {average_precision_score(df['link'], y_test)}"
)
adamic_adar_list = list(nx.adamic_adar_index(subgraph, tuples))
y_test = create_test_data(adamic_adar_list)
print(
f"ROC AUC Score with Adamic Adar Index: {roc_auc_score(df['link'], y_test)}\n"
f"Average Precision with Adamic Adar Index: {average_precision_score(df['link'], y_test)}"
)
preferential_attachment_list = list(
nx.preferential_attachment(subgraph, tuples))
y_test = create_test_data(preferential_attachment_list)
print(
f"ROC AUC Score with Preferential Attachment: {roc_auc_score(df['link'], y_test)}\n"
f"Average Precision with Preferential Attachment: {average_precision_score(df['link'], y_test)}"
)
resource_allocation_list = list(
nx.resource_allocation_index(subgraph, tuples))
y_test = create_test_data(resource_allocation_list)
print(
f"ROC AUC Score with Resource Allocation Index: {roc_auc_score(df['link'], y_test)}\n"
f"Average Precision with Resource Allocation Index: {average_precision_score(df['link'], y_test)}"
)
def new_connections_predictions():
df = future_connections
df['jaccard_coefficient'] = [
x[2] for x in nx.jaccard_coefficient(G, df.index)
]
df['resource_allocation_index'] = [
x[2] for x in nx.resource_allocation_index(G, df.index)
]
df['preferential_attachment'] = [
x[2] for x in nx.preferential_attachment(G, df.index)
]
df['common_neighbors'] = df.index.map(
lambda ind: len(list(nx.common_neighbors(G, ind[0], ind[1]))))
print('.......we have extracted all the features......')
df_train = df[~pd.isnull(df['Future Connection'])]
df_test = df[pd.isnull(df['Future Connection'])]
features = [
'jaccard_coefficient', 'resource_allocation_index',
'preferential_attachment', 'common_neighbors'
]
X_train = df_train[features]
Y_train = df_train['Future Connection']
X_test = df_test[features]
scaler = MinMaxScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.transform(X_test)
clf = LogisticRegression(solver='liblinear', random_state=14)
clf.fit(X_train_scaled, Y_train)
predictions = np.round(clf.predict_proba(X_test_scaled)[:, 1], 2)
results = pd.Series(data=predictions, index=X_test.index)
results = results.sort_values(ascending=False)
return results
# print (new_connections_predictions())
def extract_features(self, prediction_set=None):
edge_features = defaultdict(dict)
print '{0} | extract_features: res_alloc'.format(str(datetime.now()))
res_alloc = nx.resource_allocation_index(self.G, ebunch=prediction_set)
self.append_features(edge_features,
feature_name='res_alloc',
feature_list=res_alloc)
print '{0} | extract_features: jaccard_coef'.format(str(
datetime.now()))
jaccard_coef = nx.jaccard_coefficient(self.G, ebunch=prediction_set)
self.append_features(edge_features,
feature_name='jaccard_coef',
feature_list=jaccard_coef)
print '{0} | extract_features: adamic_adar'.format(str(datetime.now()))
adamic_adar = nx.adamic_adar_index(self.G, ebunch=prediction_set)
self.append_features(edge_features,
feature_name='adamic_adar',
feature_list=adamic_adar)
print '{0} | extract_features: pref_attachment'.format(
str(datetime.now()))
pref_attachment = nx.preferential_attachment(self.G,
ebunch=prediction_set)
self.append_features(edge_features,
feature_name='pref_attachment',
feature_list=pref_attachment)
# reformat feature dictionary to a dataframe object
df, feature_names = self.feature_dict_to_df(edge_features)
return df, feature_names
def SimilarityMeasures(G):
# resource_allocation_index
preds = nx.resource_allocation_index(G, [(1, 2), (3, 4), (1, 4), (5, 6),
(3, 5)])
for u, v, p in preds:
print('(%d, %d) -> %.8f' % (u, v, p))
print('****************************')
# Common neighours
print(sorted(nx.common_neighbors(G, 1, 2)))
print('****************************')
# jaccard coefficient
preds = nx.jaccard_coefficient(G, [(1, 2), (3, 4), (1, 4), (5, 6), (3, 5)])
for u, v, p in preds:
print('(%d, %d) -> %.8f' % (u, v, p))
print('****************************')
# AdamicAdar
preds = nx.adamic_adar_index(G, [(1, 2), (3, 4), (1, 4), (5, 6), (3, 5)])
for u, v, p in preds:
print('(%d, %d) -> %.8f' % (u, v, p))
print('****************************')
# Preferential Attachment (PA),
preds = nx.preferential_attachment(G, [(1, 2), (3, 4), (1, 4), (5, 6),
(3, 5)])
for u, v, p in preds:
print('(%d, %d) -> %.8f' % (u, v, p))
print('****************************')
def L_P_RA(network):
num_add = 0 # the number of egdes to be added
nodes_pair_without_edge = [] # the pairs of nodes without edges
probability_add = [] # the probabilities of the pairs of nodes to be added
score = 0.0 # the score of each pair of nodes in link prediction model
total_score_without_edge = 0.0 # the sum of scores of pairs of nodes without edge
# calculate the score of each pair of nodes
for i, elei in enumerate(list(network.nodes(), 1)):
for j, elej in enumerate(list(network.nodes(), 1)):
if i >= j:
continue
if not network.has_edge(elei, elej):
try:
pre = nx.resource_allocation_index(network, [(elei, elej)])
for u, v, s in pre:
score = s
except:
continue
total_score_without_edge += score
nodes_pair_without_edge.append((elei, elej, score))
for a, b, c in nodes_pair_without_edge:
probability_add.append(
c / total_score_without_edge
) # calculate the probabilities of edges to be added
# select edges to be added according to probabilities
edges_add = calculate_param.prob_select_distinct(nodes_pair_without_edge,
probability_add, num_add)
for a, b, c in edges_add:
network.add_edge(a, b) # add selected edges
return True
def new_connections_predictions():
future_connections['preferential_attachment'] = [
i[2] for i in nx.preferential_attachment(G, future_connections.index)
]
future_connections['Common Neighbors'] = future_connections.index.map(
lambda x: len(list(nx.common_neighbors(G, x[0], x[1]))))
future_connections['resource_allocation'] = [
i[2] for i in nx.resource_allocation_index(G, future_connections.index)
]
future_connections['jaccard'] = [
i[2] for i in nx.jaccard_coefficient(G, future_connections.index)
]
final_test = future_connections[
future_connections['Future Connection'].isnull() == True]
train = future_connections.dropna()
final_test.drop(['Future Connection'], axis=1, inplace=True)
X = train.drop(['Future Connection'], axis=1)
y = train['Future Connection']
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import roc_auc_score
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=3)
clf = RandomForestClassifier(n_estimators=100,
max_depth=5,
max_features=None,
random_state=0)
ran = clf.fit(X, y)
pred = ran.predict_proba(final_test)
pred1 = [i[1] for i in pred]
final_test['pred'] = pred1
return final_test['pred']
def get_test_features():
features = []
count = 0
print("Generating test data features......")
for temp_data in test_edges:
if (count % 100 == 0):
print(count)
count += 1
feature = []
try:
preds = nx.resource_allocation_index(G, [temp_data])
for u, v, p in preds:
feature.append(p)
preds = nx.jaccard_coefficient(G, [temp_data])
for u, v, p in preds:
feature.append(p)
except:
print("one error at: "+str(count))
pass
features.append(feature)
print("positive features: "+str(len(features)))
return features
def link_scores(graph, all_dfs, labels, g_undirected):
lst = []
lst2 = []
predictions1 = nx.preferential_attachment(g_undirected,
g_undirected.edges())
[lst.append((u, v, p)) for u, v, p in predictions1]
predictions1 = {(k, v): n for k, v, n in lst}
all_dfs['Preferential_Attachment'] = all_dfs.apply(
lambda x: map_predictions_to_df(predictions1, x), axis=1)
predictions3 = nx.resource_allocation_index(g_undirected,
g_undirected.edges())
try:
[lst2.append((u, v, p)) for u, v, p in predictions3]
predictions3 = {(k, v): n for k, v, n in lst2}
all_dfs['Resource_allocation'] = all_dfs.apply(
lambda x: map_predictions_to_df(predictions3, x), axis=1)
except ZeroDivisionError:
print("ZeroDivisionError: float division by zero")
return all_dfs
def extract_network_based(data):
print("Extracting Network Based Fearure...")
tid1 = data['tid1'].values
tid2 = data['tid2'].values
num_nodes = np.max((tid1.max(), tid2.max())) + 1
G = nx.Graph()
G.add_nodes_from(range(num_nodes))
for u, v in zip(np.concatenate([tid1, tid2]), np.concatenate([tid2,
tid1])):
G.add_edge(u, v)
preds = nx.resource_allocation_index(G, list(zip(tid1, tid2)))
data['nx1'] = [p for (u, v, p) in preds]
preds = nx.jaccard_coefficient(G, list(zip(tid1, tid2)))
data['nx2'] = [p for (u, v, p) in preds]
preds = nx.preferential_attachment(G, list(zip(tid1, tid2)))
data['nx3'] = [p for (u, v, p) in preds]
G.add_node(num_nodes)
for i in range(num_nodes):
G.add_edge(i, num_nodes)
G.add_edge(num_nodes, i)
preds = nx.adamic_adar_index(G, list(zip(tid1, tid2)))
data['nx4'] = [p for (u, v, p) in preds]
return data
def prepare_data_ft():
df = future_connections
# Triadic Measurements return (NodeA, NodeB, coef). use i[2] to access the coef
df['AAI'] = [i[2] for i in nx.adamic_adar_index(G, df.index)]
df['JCI'] = [i[2] for i in nx.jaccard_coefficient(G, df.index)]
df['RA'] = [i[2] for i in nx.resource_allocation_index(G, df.index)]
df['PA'] = [i[2] for i in nx.preferential_attachment(G, df.index)]
return df
def resource_allocation(G, feat, ledge):
feat['R_Allocation'] = 0.0
for i in feat.index.values:
if (G.has_node(feat['Node_1'][i]) and G.has_node(feat['Node_2'][i])):
values = nx.resource_allocation_index(
G, [(feat['Node_1'][i], feat['Node_2'][i])])
for v in values:
feat['R_Allocation'][i] = v[2]
def new_connections_predictions():
# Your Code Here
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.metrics import roc_auc_score
for node in G.nodes():
G.node[node]['community'] = G.node[node]['Department']
preferential_attachment = list(nx.preferential_attachment(G))
df = pd.DataFrame(index=[(x[0], x[1]) for x in preferential_attachment])
df['preferential_attachment'] = [x[2] for x in preferential_attachment]
cn_soundarajan_hopcroft = list(nx.cn_soundarajan_hopcroft(G))
df_cn_soundarajan_hopcroft = pd.DataFrame(
index=[(x[0], x[1]) for x in cn_soundarajan_hopcroft])
df_cn_soundarajan_hopcroft['cn_soundarajan_hopcroft'] = [
x[2] for x in cn_soundarajan_hopcroft
]
df = df.join(df_cn_soundarajan_hopcroft, how='outer')
df['cn_soundarajan_hopcroft'] = df['cn_soundarajan_hopcroft'].fillna(
value=0)
df['resource_allocation_index'] = [
x[2] for x in list(nx.resource_allocation_index(G))
]
df['jaccard_coefficient'] = [x[2] for x in list(nx.jaccard_coefficient(G))]
df = future_connections.join(df, how='outer')
df_train = df[~pd.isnull(df['Future Connection'])]
df_test = df[pd.isnull(df['Future Connection'])]
features = [
'cn_soundarajan_hopcroft', 'preferential_attachment',
'resource_allocation_index', 'jaccard_coefficient'
]
df_test = df_test[features]
X_train, X_test, y_train, y_test = train_test_split(
df_train[features],
df_train['Future Connection'],
random_state=0,
test_size=0.5)
clf_RF = RandomForestClassifier(max_features=3,
random_state=0,
max_depth=3,
min_samples_leaf=3,
criterion='entropy')
clf_RF.fit(X_train, y_train)
clf_GDBT = GradientBoostingClassifier(learning_rate=0.01,
max_depth=8,
random_state=0,
n_estimators=30)
clf_GDBT.fit(X_train, y_train)
roc_score_forest = roc_auc_score(y_test,
clf_RF.predict_proba(X_test)[:, 1])
roc_score = roc_auc_score(y_test, clf_GDBT.predict_proba(X_test)[:, 1])
print(roc_score_forest)
print(roc_score)
#test_proba = clf_RF.predict_proba(X_test)[:, 1]
preds = pd.Series(data=clf_GDBT.predict_proba(df_test)[:, 1],
index=df_test.index)
return preds # Your Answer Here
def new_connections_predictions():
pref_attach = list(nx.preferential_attachment(G))
df = pd.DataFrame(index=[(x[0], x[1]) for x in pref_attach])
df['pref_attch'] = [x[2] for x in pref_attach]
common_neigh = [(e[0], e[1], len(list(nx.common_neighbors(G, e[0], e[1]))))
for e in nx.non_edges(G)]
df1 = pd.DataFrame(index=[(x[0], x[1]) for x in common_neigh])
df1['common_neigh'] = [x[2] for x in common_neigh]
df = df.join(df1, how='outer')
df['common_neigh'] = df['common_neigh'].fillna(value=0)
del df1
community_common_neigh = list(
nx.cn_soundarajan_hopcroft(G, community='Department'))
df1 = pd.DataFrame(index=[(x[0], x[1]) for x in community_common_neigh])
df1['community_common_neigh'] = [x[2] for x in community_common_neigh]
df = df.join(df1, how='outer')
df['community_common_neigh'] = df['community_common_neigh'].fillna(value=0)
del df1
community_res_alloc = list(
nx.ra_index_soundarajan_hopcroft(G, community='Department'))
df1 = pd.DataFrame(index=[(x[0], x[1]) for x in community_res_alloc])
df1['community_res_alloc'] = [x[2] for x in community_res_alloc]
df = df.join(df1, how='outer')
df['community_res_alloc'] = df['community_res_alloc'].fillna(value=0)
del df1
df['res_alloc'] = [x[2] for x in list(nx.resource_allocation_index(G))]
df['jaccard_coeff'] = [x[2] for x in list(nx.jaccard_coefficient(G))]
features = [
'jaccard_coeff', 'res_alloc', 'pref_attch', 'common_neigh',
'community_common_neigh', 'community_res_alloc'
]
df = future_connections.join(df, how='outer')
df_train = df[~pd.isnull(df['Future Connection'])]
df_test = df[pd.isnull(df['Future Connection'])]
X_train = df_train[features]
X_test = df_test[features]
y_train = df_train['Future Connection']
scalar = MinMaxScaler()
X_train_scaled = scalar.fit_transform(X_train)
X_test_scaled = scalar.fit_transform(X_test)
clf = RandomForestClassifier(n_estimators=100,
n_jobs=-1,
max_depth=10,
random_state=0).fit(X_train_scaled, y_train)
test_proba = clf.predict_proba(X_test_scaled)[:, 1]
predictions = pd.Series(test_proba, X_test.index)
# target = future_connections[pd.isnull(future_connections['Future Connection'])]
# target['proba'] = [predictions[x] for x in target.index]
return predictions
def new_connections_predictions():
# Your Code Here
for n in G.nodes():
G.node[n]['community'] = G.node[n]['Department']
#df = pd.DataFrame(index=[(x[0], x[1]) for x in list(nx.preferential_attachment(G))])
future_connections['common_neighbors'] = [
len(list(nx.common_neighbors(G, x[0], x[1])))
for x in future_connections.index
]
future_connections['jaccard_coefficient'] = [
list(nx.jaccard_coefficient(G, [x]))[0][2]
for x in future_connections.index
]
future_connections['resource_allocation_index'] = [
list(nx.resource_allocation_index(G, [x]))[0][2]
for x in future_connections.index
]
future_connections['adamic_adar_index'] = [
list(nx.adamic_adar_index(G, [x]))[0][2]
for x in future_connections.index
]
future_connections['preferential_attachment'] = [
list(nx.preferential_attachment(G, [x]))[0][2]
for x in future_connections.index
]
future_connections['cn_soundarajan_hopcroft'] = [
list(nx.cn_soundarajan_hopcroft(G, [x]))[0][2]
for x in future_connections.index
]
#future_connections['ra_soundarajan_hopcroft'] = [list(nx.ra_soundarajan_hopcroft(G, [x]))[0][2] for x in future_connections.index]
future_connections['cn_soundarajan_hopcroft'] = future_connections[
'cn_soundarajan_hopcroft'].fillna(value=0)
#future_connections['ra_soundarajan_hopcroft'] = df['cn_soundarajan_hopcroft'].fillna(value=0)
#future_connections.join(df,how='outer')
features = [
'jaccard_coefficient', 'resource_allocation_index',
'adamic_adar_index', 'preferential_attachment',
'cn_soundarajan_hopcroft'
]
X_train = future_connections.loc[
~pd.isnull(future_connections['Future Connection']), features]
y_train = future_connections.loc[
~pd.isnull(future_connections['Future Connection']),
['Future Connection']]
X_test = future_connections.loc[(
pd.isnull(future_connections['Future Connection'])), features]
classifier = MLPClassifier(hidden_layer_sizes=[10, 5],
solver='lbfgs',
alpha=10)
classifier.fit(X_train, y_train)
y_predicted = classifier.predict_proba(X_test)[:, 1]
return pd.Series(y_predicted, X_test.index) # Your Answer Here
def resource_allocation_index(graph, train_set, test_set):
if not os.path.isfile("./data/resource_allocation_training.csv"):
print("Computing training resource-allocation index")
t0 = clock()
results = []
for i in range(0, len(train_set)):
preds = nx.resource_allocation_index(graph, [(train_set[i][0], train_set[i][1])])
results.append([float(p) for u, v, p in preds])
if i % 5000 == 0:
print(i)
print("Some elements of results:", results[0:5])
with open("./data/resource_allocation_training.csv", 'w') as file:
csv_out = csv.writer(file)
for i in range(0, len(train_set)):
csv_out.writerow(results[i])
if i % 100000 == 0:
print(i)
print(clock() - t0)
if not os.path.isfile("./data/resource_allocation_testing.csv"):
print("Computing testing resource-allocation index")
t0 = clock()
results = []
for i in range(0, len(test_set)):
preds = nx.resource_allocation_index(graph, [(test_set[i][0], test_set[i][1])])
results.append([float(p) for u, v, p in preds])
if i % 5000 == 0:
print(i)
print("Some elements of results:", results[0:5])
with open("./data/resource_allocation_testing.csv", 'w') as file:
csv_out = csv.writer(file)
for i in range(0, len(test_set)):
csv_out.writerow(results[i])
if i % 100000 == 0:
print(i)
print(clock() - t0)
def edge_feature(self, e):
return numpy.array([
math.sqrt(float(len(set(self.G[e[0]]).intersection(self.G[e[1]])))), \
float(abs(nx.clustering(self.G, e[0]) - nx.clustering(self.G, e[1]))), \
float(list(nx.jaccard_coefficient(self.G, [(e[0], e[1])]))[0][2]), \
float(list(nx.resource_allocation_index(self.G, [(e[0], e[1])]))[0][2]),\
float(min(len(self.G[e[0]]), len(self.G[e[1]]))) / float(max(len(self.G[e[0]]), len(self.G[e[1]]))), \
1.0
])
def predict(self, node_pairs):
predictions = resource_allocation_index(self.graph, node_pairs)
return list(predictions)
def __repr__(self):
return self.__str__()
def __str__(self):
return 'ResourceAllocation'
def new_connections_predictions():
pref_atch = list(nx.preferential_attachment(G))
new_df = pd.DataFrame(index=[(x[0], x[1]) for x in pref_atch])
new_df["PrefrentialAttachment"] = [x[2] for x in pref_atch]
cn_soundarajan_hopcroft = list(
nx.cn_soundarajan_hopcroft(G, community="Department"))
df_cn_soundarajan_hopcroft = pd.DataFrame(
index=[(x[0], x[1]) for x in cn_soundarajan_hopcroft])
df_cn_soundarajan_hopcroft['CommunityCommonNeighbor'] = [
x[2] for x in cn_soundarajan_hopcroft
]
new_df = new_df.join(df_cn_soundarajan_hopcroft, how='outer')
new_df['CommunityCommonNeighbor'] = new_df[
'CommunityCommonNeighbor'].fillna(value=0)
res_alo = list(nx.resource_allocation_index(G))
df_res_alo = pd.DataFrame(index=[(x[0], x[1]) for x in res_alo])
df_res_alo["ResourceAllocationIndex"] = [x[2] for x in res_alo]
new_df = new_df.join(df_res_alo, how='outer')
new_df['ResourceAllocationIndex'] = new_df[
'ResourceAllocationIndex'].fillna(value=0)
jac_coef = list(nx.jaccard_coefficient(G))
df_jac_coef = pd.DataFrame(index=[(x[0], x[1]) for x in jac_coef])
df_jac_coef["JaccardCoeffiecient"] = [x[2] for x in jac_coef]
new_df = new_df.join(df_jac_coef, how='outer')
new_df['JaccardCoeffiecient'] = new_df['JaccardCoeffiecient'].fillna(
value=0)
new_df = new_df.join(future_connections, how='outer')
train_df = new_df[~new_df["Future Connection"].isnull()]
test_df = new_df[new_df["Future Connection"].isnull()]
features = [
"PrefrentialAttachment", "CommunityCommonNeighbor",
"ResourceAllocationIndex", "JaccardCoeffiecient"
]
X_train = train_df[features]
X_test = test_df[features]
y_train = train_df["Future Connection"]
scaler = MinMaxScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.transform(X_test)
clf = MLPClassifier(hidden_layer_sizes=[10, 5],
alpha=5,
random_state=0,
solver='lbfgs',
verbose=0)
clf.fit(X_train_scaled, y_train)
rslt = clf.predict_proba(X_test_scaled)[:, 1]
final_rslt = pd.Series(rslt, index=X_test.index)
return final_rslt
def resourceAllocation(G, X):
resource_allocation = []
for i in range(X.shape[0]):
try:
coef = [[u, v, p] for u, v, p in nx.resource_allocation_index(
G, [(X[i][0], X[i][1])])][0]
resource_allocation.append(coef[2])
except:
resource_allocation.append(0)
return resource_allocation
def resourceAllocationIndex(self, buyerPairs):
# Sort the allocatio indexes in ascending order.
allocation = nx.resource_allocation_index(self.networkG, buyerPairs)
allocation = [entry for entry in allocation if entry[2] > 1.5]
allocation = list(set(allocation))
#Print allocation indexes
for entry in allocation:
u, v, p = entry
print('Node pair: [', u, ']', '[', v, '] -> ', 'Index = ', p)
def calRA(nodeA, nodeB):
if (UDG.has_node(nodeA) and UDG.has_node(nodeB)):
try:
AA = nx.resource_allocation_index(UDG, [(nodeA, nodeB)])
for u, v, p in AA:
return p
except ZeroDivisionError:
return 0
else:
return 0
def generate_algo(graph, X):
res_alloc_index = np.asarray(list(nx.resource_allocation_index(graph,
X)))[:, 2]
jac_coef = np.asarray(list(nx.jaccard_coefficient(graph, X)))[:, 2]
ad_adar_idx = np.asarray(list(nx.adamic_adar_index(graph, X)))[:, 2]
pref_att = np.asarray(list(nx.preferential_attachment(graph, X)))[:, 2]
#cn_sound_hop=list(nx.cn_soundarajan_hopcroft(graph, X))
#ra_sound_hop =list( nx.ra_index_soundarajan_hopcroft(graph, X))
#within = list(nx.within_inter_cluster(graph, X))
return list(res_alloc_index), list(jac_coef), list(ad_adar_idx), list(
pref_att)
def resourceAllocationIndex(self, buyerPairs):
# Sort the allocatio indexes in ascending order.
print('Computing Similarity Scors using Resource Allocation Index ...')
allocation = nx.resource_allocation_index(self.networkG, buyerPairs)
allocation = [entry for entry in allocation if entry[2] > self.threshold]
allocation = list(set(allocation))
print('Computation Done!')
print('\n')
return(list(set(allocation)))
def prob_in_net(n, m, graphs_test, train_edges_0, test_edges_0, matrixes,
M_test):
feature_train = []
feature_test = []
feature_train_1 = []
feature_test_1 = []
pred_prob = []
pred = []
roc_auc = []
roc_avg = 0
truth_test = []
for i in range(k_net):
#jaccard_coefficient
feature_train.append(
nx.resource_allocation_index(graphs_test[i], train_edges_0))
feature_test.append(
nx.resource_allocation_index(graphs_test[i], test_edges_0))
A2 = M_test[i] * M_test[i]
A3 = A2 * M_test[i]
Lp_matrix = A2 + (0.001 * A3)
(features_train,
truth_train) = similarity_Features(Lp_matrix, matrixes[i],
train_edges_0)
(features_test, truth) = similarity_Features(Lp_matrix, matrixes[i],
test_edges_0)
truth_test.append(truth)
LR = LogisticRegression(class_weight='balanced')
LR.fit(features_train, truth_train)
pred.append(LR.predict(features_test))
x = LR.predict_proba(features_test)[:, 1]
pred_prob.append(x)
fpr, tpr, thrshold = metrics.roc_curve(truth, pred[i])
roc = metrics.auc(fpr, tpr)
roc_auc.append(roc)
print('Net', i, roc)
roc_avg += roc
roc_auc.append(roc_avg / k_net)
return (roc_auc, matrix, pred_prob, truth_test)
def sort_edges_by_resource_allocation(graph, edges):
edges_sorted = sorted(list(nx.resource_allocation_index(
graph, edges)), key=lambda l: l[2], reverse=True, cmp=compare_with_ties)
return [(row[0], row[1]) for row in edges_sorted], [row[2] for row in edges_sorted]
def link_prediction(G, query_nodes, target_nodes, n_edges, start_dist, alg = "ra"):
"""Selects a random set of links between based on the scores calculated by
a standard link-prediction algorithm from networkx library
Parameters
----------
G : Networkx graph
The graph from which the team will be selected.
query : list
The set of nodes from which random walker starts.
target : list
The set of nodes from where the random walker ends.
n_edges : integer
the number of links to be added
start_dist: list
The starting distribution over the query set
alg: string
A string describing the link-prediction algorithm to be used
Returns
-------
links : list
The set of links that reduce the absorbing RW centrality
ac_scores: list
The set of scores of adding the links
"""
assert alg in ["ra", "pa", "jaccard", "aa"], "alg must be one of [\"ra\", \"pa\", \"jaccard\", \"aa\"]."
H = G.copy()
query_set_size = len(query_nodes)
map_query_to_org = dict(zip(query_nodes, range(query_set_size)))
P = csc_matrix(nx.google_matrix(H, alpha=1))
P_abs = P[list(query_nodes),:][:,list(query_nodes)]
F = compute_fundamental(P_abs)
row_sums = start_dist.dot(F.sum())[0,0]
candidates = list(product(query_nodes, target_nodes))
eligible = [candidates[i] for i in range(len(candidates))
if H.has_edge(candidates[i][0], candidates[i][1]) == False]
links_to_add = []
if alg == 'ra':
preds = nx.resource_allocation_index(H, eligible)
elif alg == 'jaccard':
preds = nx.jaccard_coefficient(H, eligible)
elif alg == 'aa':
preds = nx.adamic_adar_index(H, eligible)
elif alg == 'pa':
preds = nx.preferential_attachment(H, eligible)
for u,v,p in preds:
links_to_add.append((u,v,p))
links_to_add.sort(key=lambda x: x[2], reverse = True)
ac_scores = []
ac_scores.append(row_sums)
i = 0
while i < n_edges:
F_updated = update_fundamental_mat(F, H, map_query_to_org, links_to_add[i][0])
H.add_edge(links_to_add[i][0], links_to_add[i][1])
abs_cen = start_dist.dot(F_updated.sum(axis = 1))[0,0]
F = F_updated
ac_scores.append(abs_cen)
i += 1
return links_to_add, ac_scores