def dbscan(sim_matrix, radius, min_samples, dist_measure, max_radius):
start = datetime.now()
result = DBSCAN(eps=radius,
min_samples=min_samples,
metric='precomputed',
n_jobs=-1).fit(sim_matrix)
end = datetime.now()
getLogger(__name__).info('dbscan running time:{}'.format(end - start))
core_sample_mask = np.zeros_like(result.labels_, dtype=bool)
core_sample_mask[result.core_sample_indices_] = True
labels_cal = result.labels_
# for i in range(0,len(result.labels_)):
# print(TRAIN_KPI[i], core_sample_mask[i], labels_cal[i])
# Number of clusters in labels calculated by DBSCAN, ignoring noise if present
num_clusters = len(set(labels_cal)) - (1 if -1 in labels_cal else 0)
# print('number of clusters: %d' % num_clusters)
getLogger(__name__).info('number of clusters: %d' % num_clusters)
cluster = {}
medoids = []
for cla in range(0, num_clusters):
cluster[cla] = []
# print('class %d: %d' % (cla, labels_cal.tolist().count(cla)))
getLogger(__name__).info('class %d: %d' %
(cla, labels_cal.tolist().count(cla)))
index = [idx for idx, e in enumerate(labels_cal) if e == cla]
for id in index:
cluster[cla].append(TRAIN_KPI[id])
# print(TRAIN_KPI[id])
medoid, min_dist = get_the_medoids(sim_matrix, index)
medoids.append(medoid)
# print(medoid, min_dist)
getLogger(__name__).info(medoid)
getLogger(__name__).info(min_dist)
# assign the 'noisy' curve in DBSCAN and find the real noise.(sim to all the medoids are larger than threshold)
index = [idx for idx, e in enumerate(labels_cal) if e == -1]
cluster[-1] = []
# assign according to the sim to the medoid of each cluster.
for uuid in index:
data_arr = data_dict[TRAIN_KPI[uuid]]
cla, it_dist = assignment(medoids,
data_arr,
dist_category=dist_measure)
cluster[cla].append(TRAIN_KPI[uuid])
labels_cal[uuid] = cla
print('KPI %s belongs to class %d' % (TRAIN_KPI[uuid], cla))
getLogger(__name__).info('KPI %s belongs to class %d' %
(TRAIN_KPI[uuid], cla))
all_kpi.append(TRAIN_KPI[uuid])
all_cla.append(cla)
all_dist.append(it_dist)
dataframe = pd.DataFrame({
'uuid': all_kpi,
'cluster': all_cla,
'dist': all_dist
})
dataframe.to_csv("/home/jialingxiang/NewDTWFrame/SplitKPI/all_dist.csv",
index=False,
sep=',')
# assign method 2: assign according to its nearest clustered curve.
'''
for uuid in index:
cla, new_labels = assign_to_nearest(sim_matrix, uuid, labels_cal)
cluster[cla].append(TRAIN_KPI[uuid])
print('KPI %d belongs to class %d' %(TRAIN_KPI[uuid], cla))
labels_cal = new_labels
'''
# print(cluster)
result = {}
for key in cluster.keys():
# print('class %d: %d' % (key, len(cluster[key])))
getLogger(__name__).info('class %d: %d' % (key, len(cluster[key])))
for value in cluster[key]:
result[value] = key
result_df = pd.DataFrame(list(result.items()), columns=['uuid', 'cluster'])
result_df.to_hdf(EXP_ROOT + 'cluster_result_r%f.hdf' % max_radius,
'/cluster_result',
mode='w',
format='table')
medoids_dict = {}
for i in range(0, len(medoids)):
medoids_dict[i] = medoids[i]
medoids_df = pd.DataFrame(list(medoids_dict.items()),
columns=['cluster', 'medoid'])
medoids_df.to_hdf(EXP_ROOT + 'medoids_r%f.hdf' % max_radius,
'/medoids',
mode='w',
format='table')
return medoids, labels_cal
