sktime: [BUG] `DtwPythonDist` output has randomly permuted rows/columns

Hi,

I tried using DtwPythonDist() to calculate distances between a dataset of time series. It worked well, but I noticed that I get different results every time I run it.

Here’s my code. I run it in my local machine using PyCharm.

dtwpy = DtwPythonDist() dist_mat = dtwpy.transform(data)

I used it with two different datasets: the dataset with all equal lengths, and the dataset with unequal lengths. The DtwPythonDist() behaves the same. If I run it twice, I would get two totally different distance matrices.

Am I missing something? What should I do?

Thank you.

About this issue

  • Original URL
  • State: closed
  • Created 3 years ago
  • Comments: 17

Commits related to this issue

Most upvoted comments

Hi, I’m really sorry for the late reply. I just had the time to try it again with sktime version 0.29.0. It works now; the results don’t permute anymore. Thank you for your help.