I have N time series of DIFFERENT lengths with i number of data points in each observation.
I would like to compute the similarity of each time series and generate M number of clusters.
I have tried Jaquard simliarity, and followed the link below
Time Series Similarity : Differing Lengths with R
but am looking for a similar solution in Python here (which I have found https://github.com/slaypni/fastdtw)
The other problem is the NUMBER of features in the dataset (it is not just X & Y). X = Time, but I have 5 vectors for Y.
import numpy as np
from scipy.spatial.distance import euclidean
from fastdtw import fastdtw
x = x
y = y
print(x.shape)
print(y.shape)
distance, path = fastdtw(x, y, dist=euclidean)
print(distance)
Works fine for uneven dimension size, but if I add multiple dimensions it kicks out an error. Should I do some transposing?
Finally, if I can calculate the distance between each pair, what is the best way to cluster them?