def test_ncc_c_2_and_3dim_matches(self):
test = zscore(np.array([
[1, 2, 3, 4, 5],
[0, 10, 4, 5, 7],
[-1, 15, -12, 8, 9],
]), axis=1)
centroids = np.array([[1, 1, 0, 1, 1], [10, 12, 0, 0, 1]])
distances1 = np.empty((3, 2))
distances2 = np.empty((3, 2))
for i in range(3):
for j in range(2):
distances1[i, j] = 1 - _ncc_c(test[i], centroids[j]).max()
for j in range(2):
distances2[:,j] = 1 - _ncc_c_2dim(test, centroids[j]).max(axis=1)
distances3 = (1 - _ncc_c_3dim(test, centroids).max(axis=2)).T
np.testing.assert_array_equal(distances1, distances2)
np.testing.assert_array_equal(distances2, distances3)
def test_ncc_c_2_and_3dim_matches():
test = zscore(np.array([
[1, 2, 3, 4, 5],
[0, 10, 4, 5, 7],
[-1, 15, -12, 8, 9],
]),
axis=1)
centroids = np.array([[1, 1, 0, 1, 1], [10, 12, 0, 0, 1]])
distances1 = np.empty((3, 2))
distances2 = np.empty((3, 2))
for i in range(3):
for j in range(2):
distances1[i, j] = 1 - _ncc_c(test[i], centroids[j]).max()
for j in range(2):
distances2[:, j] = 1 - _ncc_c_2dim(test, centroids[j]).max(axis=1)
distances3 = (1 - _ncc_c_3dim(test, centroids).max(axis=2)).T
assert not (distances1 != distances2).any()
assert not (distances2 != distances3).any()
from kshape.core import kshape, zscore time_series = [[1, 2, 3, 4], [0, 1, 2, 3], [0, 1, 2, 3], [1, 2, 2, 3]] cluster_num = 2 clusters = kshape(zscore(time_series, axis=1), cluster_num)
#def data_plotter(data):
if __name__ == '__main__':
with open(
'C://Users//k_mathin//PycharmProjects//Masters//ciena_trials//Kamal//data//vodafone_data_clusters_filtered.pkl',
'rb') as f:
data_set = pickle.load(f)
data = []
for d in data_set['data']:
data.append(d)
data = np.asarray(data)
#data = data[:,:15]
print(data.shape[0])
label_data = np.asarray(data_set['osid'])
labels, levels = pd.factorize(label_data)
shelves = np.asarray(data_set['shelf'])
cluster_num = levels.shape[0]
print(cluster_num)
clusters = kshape(zscore(data, axis=1), cluster_num)
#clusters = kshape(data,cluster_num)
y_pred = []
for i in range(0, data.shape[0]):
for j in range(0, cluster_num):
if i in clusters[j][1]:
y_pred.append(j)
continue
conf = conf_mat(labels, y_pred)
print(conf_mat(labels, y_pred))
print("done")
def kshape_clusters(arr, cluster_num, ax=1):
from kshape.core import kshape, zscore
clusters = kshape(zscore(arr, ax), cluster_num)
re_arr = apply_clusters(clusters, arr)
return re_arr
from kshape.core import kshape, zscore
time_series = [[1, 2, 3, 4, 5], [0, 1, 2, 3, 4], [3, 2, 1, 0, -1],
[1, 2, 2, 3, 3]]
cluster_num = 2
clusters = kshape(zscore(time_series), cluster_num)
print(clusters)
#%%
causes = pd.read_pickle('data/causes.pkl')
def cluster_show(cluster_rep, cluster_id):
#plt.plot(cluster_rep)
for i in cluster_id:
ev = causes.iloc[i]['id']
temp_In = list(Event(ev, start, end).data[' In'].values)
plt.plot(temp_In)
plt.legend(list(causes.iloc[cluster_id]['cause']))
plt.show()
cluster_num = 6
clusters = kshape(zscore(I_ns, axis=1), cluster_num)
for i in range(cluster_num):
print(causes.iloc[clusters[i][1]], '\n', '----------------------')
cluster_show(clusters[i][0], clusters[i][1])
#%%
import statsmodels.api as sm
dta = sm.datasets.co2.load_pandas().data
# deal with missing values. see issue
dta.co2.interpolate(inplace=True)
id = whole_events[100]
start = 0
end = -1
e = Event(id, start, end)