Nima Sarajpoor

Actually I didn't resolve the issue. But I couldn't understand whether it is a bug or not. **My main concern is:** Does MatrixProfile find the best matches based on the...

**NOTE: ts_i = ts[i:i+H], where H is the window 24.** My data (accessible via the provided link in the previous post) is a time series with length 8760. the values...

Thanks for the clarification. In fact, I am at the exploration stage, and yes, I am trying to find some sort of repeated patterns. I am trying to see if...

That's correct. I want to cluster many time series together. But the problem with MPDist is that it matches sequences according to their similarity of subsequences regardless of their order...

It seems the link I provided isn't working when I clicked on it. So, here is the name of the paper: The Swiss Army Knife of Time Series Data Mining:...

In fact, I tried DTW and some of its variants. But I wanted to see if MatrixProfile can bring sth new to the picture. I will check out MSMD. So,...

[Update] @tylerwmarrs I tried to use MPDist by getting help from the tutorial. Here is the code: ` MPDist_vecform = pairwise_dist(mydata, window_size=8) MPDist_matform = squareform(MPDist_vecform) ` And, I use Scikit...

Hi tylerwarrs, I was finishing my paper and studying git (for my own sake and github) Recently, I did a pull to change snippets, but after checking out the logs,...

Thanks everyone. Appreciate your input. For now, I will use the BibTeX format provided by @chkoar.

@TimotheeMathieu Thanks a lot for your input. You are right. I might take a look at Agglemorative Clustering in scikit-learn as well and see how the clusters are stored at...