import pandas as pd
def DTWDistance(s1, s2, w: float = np.inf):
DTW = {}
w = max(w, abs(len(s1) - len(s2)))
for i in range(-1, len(s1)):
for j in range(-1, len(s2)):
DTW[(i, j)] = float("inf")
DTW[(-1, -1)] = 0
for i in range(len(s1)):
for j in range(max(0, i - w), min(len(s2), i + w)):
dist = (s1[i] - s2[j]) ** 2
DTW[(i, j)] = dist + min(
DTW[(i - 1, j)], DTW[(i, j - 1)], DTW[(i - 1, j - 1)]
)
return sqrt(DTW[len(s1) - 1, len(s2) - 1])
if __name__ == "__main__":
data = np.array(pd.read_csv("data/data1.csv").head(10))[(0, 1, 3, 5, 6, 8), 1:]
print(data)
print(data.shape)
clust = Cluster(data, metric=DTWDistance)
clust.print(2)
clust.dendogram()
def basic_features_extract(data):
return extract_features(data, column_id="id", column_sort="time")
def extract_features_from_TS(Data, y):
extracted_features = basic_features_extract(Data)
impute(extracted_features)
# features_filtered = select_features(extracted_features, y)
features_filtered_direct = extract_relevant_features(
Data, y, column_id="id", column_sort="time"
)
return extracted_features, features_filtered_direct
if __name__ == "__main__":
n_series = 10
n_clust = 4
features = np.concatenate(
[np.loadtxt(f"data/f{i}.csv") for i in range(1, 4)], axis=0
)[:n_series]
features = features[(0, 1, 3, 5, 6, 8), :]
print(f"Data recive : {features.shape}")
clust = Cluster(features)
print("Cluster initialized :)")
lengths = list(map(len, clust.get(n_series)))
plt.plot(list(range(len(lengths))), lengths)
plt.show()
clust.print(n_clust)
clust.dendogram()