continue
l = []
sorted_dict = {}
hour = 0
minute = 0
while hour < 24:
time = str(hour) + ":" + str(minute)
measure = vals[time]
l.append(measure)
hour = hour if minute == 0 else hour + 1
minute = 0 if minute == 30 else 30
sazonal_data[meter] = np.array(l)
total_data += 1
if total_data >= max_data:
break
k = K_means_clustering(
sazonal_data,
list(range(2, 18)),
["k-means", "k-means++"],
["euclidean", "cityblock", "chebyshev", "DTW", "LB_Keogh"],
normalize_by_min=False,
)
# k = K_means_clustering(sazonal_data,list(range(2,3)),['k-means'],['euclidean'],normalize_by_min=False)
k.fit(verbose=True)
k.plot_all(as_time_series=True, key_name=(str(max_data) + "_sg_"))
k.plot_silhouette(key_name=(str(max_data) + "_sg_"))
with open(folder_name + benchmark + '/' + benchmark + '_TRAIN', 'r') as f:
for line in f:
i += 1
floats = [float(x) for x in line.split(',')]
data[i] = np.array(floats[1:len(floats)])
label = floats[0]
expected[i] = label
if label not in clusters_labels:
clusters_labels.append(label)
n_expected_cluster = len(clusters_labels)
diff = 1
min_k = 2 if n_expected_cluster - diff < 2 else n_expected_cluster - diff
max_k = n_expected_cluster + diff
algs = ['k-means']
#dists = ['minkowski_1','minkowski_2','chebyshev','DTW','LB_Keogh','correlation_1_1.5','cort-euclidean']
dists = ['LB_Keogh','correlation_1_1.5','cort-euclidean','DTW']
ks = list(range(min_k,max_k))
normal_by_min = False
k = K_means_clustering(data,expected,[n_expected_cluster],algs,dists,Normalization.by_Z_normalization )
k.fit(verbose=True)
#k.plot_all(as_time_series=True,key_name=benchmark)
#k.plot_validations(benchmark,n_expected_cluster)
#k.plot_real_solution(len(clusters_labels),expected,'k-means','minkowski_1',benchmark)
#k.plot_real_solution(len(clusters_labels),expected,'k-means++','minkowski_2',benchmark)
if (benchmark not in results):
results[benchmark] = {}
results[benchmark][it] = (k.solutions, k.time_clustering, k.expected_indices)