4
$\begingroup$

Can anyone recommend a library for time series data mining tasks other than predictive modeling and statistical analysis? There seem to be a number for these purposes (e.g., Gretl), but nothing for the tasks of:

  • Classification
  • Clustering
  • Subsequence search
  • Anomaly detection
  • Motif discovery
  • Indexing

I can't be the first person to want to use, e.g., iSAX, but Googling hasn't turned up anything other than a single Java library.

Links to anything that one could interface with C/C++, Python, or Julia are especially welcome, but any help would be appreciated. Assurance that such a library does not exist would be helpful as well, since I would then know it wouldn't be a waste of time to write one...

$\endgroup$
1
$\begingroup$

The machine learning asks that you have listed can be covered by sklearn in python - Classification, clustering , anomaly detection

Indexing can be done with whoosh (again python)

Additionally one can use Pandas in Python (which can do time series data analysis although more of statistical techniques) along with sklearn. I doubt that a single library can do all of time series analysis.

| cite | improve this answer | |
$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.