# dtaidistance！！！優選
from dtaidistance import dtw

# x

query = [1, 1, 2, 3, 2, 0]

# y
template = [0, 1, 1, 2, 3, 2, 1]

dtw.distance(query, template)

1.4142135623730951

s1 = np.array([1, 1, 2, 3, 2, 0], dtype=np.double)
s2 = np.array([0, 1, 1, 2, 3, 2, 1], dtype=np.double)
dtw.distance_fast(s1, s2, use_pruning=True)

1.4142135623730951

print(dtw.distance.__doc__)

from dtaidistance import dtw
s1 = [1, 1, 2, 3, 2, 0]
s2 = [0, 1, 1, 2, 3, 2, 1]
distance, paths = dtw.warping_paths(s1, s2)
print(distance)
print(paths)

from dtaidistance import dtw
from dtaidistance import dtw_visualisation as dtwvis
import random
import numpy as np

s1 = np.array([1, 1, 2, 3, 2, 0], dtype=np.double)
s2 = np.array([0, 1, 1, 2, 3, 2, 1], dtype=np.double)


distance, paths = dtw.warping_paths(s1, s2
                                    #, window=25
                                    #, psi=2
                                   )
print(distance)
best_path = dtw.best_path(paths)# 最短路徑
dtwvis.plot_warpingpaths(s1, s2, paths, best_path)# 制圖

總結

以上是生活随笔為你收集整理的使用dtaidistance实现dtw算法的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。