def kmedoid_clustering(g, r, measure, num_cluster):
all_rdds_df = pd.DataFrame()
for target_one in g:
rdd_list = []
for target_two in g:
rdd_list.append(
RDD.realworld_distance_compare(g, target_one, target_two,
measure, r))
all_rdds_df[target_one] = rdd_list
data = all_rdds_df
np_of_rdds = np.array(data)
kmedoids = KMedoids(n_clusters=num_cluster, random_state=0).fit(np_of_rdds)
cluster_data = kmedoids.labels_
node_list = []
degree_list = []
rad_list = []
# Populate and construct a DataFrame with basic node information
for node in g:
node_list.append(node)
degree_list.append(g.degree(node))
# TODO: Broken
rad_list.append(1)
df = pd.DataFrame({
'node_name': node_list,
'radius': rad_list,
'degree': degree_list,
'cluster': cluster_data
})
return df
def agglomerative_hierarchical_clustering(g, r, measure, num_cluster):
all_rdds_df = pd.DataFrame()
for target_one in g:
rdd_list = []
for target_two in g:
rdd_list.append(
RDD.realworld_distance_compare(g, target_one, target_two,
measure, r))
all_rdds_df[target_one] = rdd_list
data = all_rdds_df
# dend = shc.dendrogram(shc.linkage(data, method='ward'))
cluster = AgglomerativeClustering(n_clusters=num_cluster,
affinity='euclidean',
linkage='ward')
cluster_data = cluster.fit_predict(data)
node_list = []
degree_list = []
rad_list = []
# Populate and construct a DataFrame with basic node information
for node in g:
node_list.append(node)
degree_list.append(g.degree(node))
# TODO: Broken
rad_list.append(1)
df = pd.DataFrame({
'node_name': node_list,
'radius': rad_list,
'degree': degree_list,
'cluster': cluster_data
})
return df