holgerteichgraeber / TimeSeriesClustering.jl

Julia implementation of unsupervised learning methods for time series datasets. It provides functionality for clustering and aggregating, detecting motifs, and quantifying similarity between time series datasets.
MIT License
82 stars 22 forks source link

Extreme Days #18

Open holgerteichgraeber opened 5 years ago

holgerteichgraeber commented 5 years ago

Include extreme days:

holgerteichgraeber commented 5 years ago

I'll start on this one to include it in the type system, and then we can see how we go from there to include the different selection methods.

YoungFaithful commented 5 years ago

Extreme Day Result Struct and combined Clust and Extr Result Struct?

holgerteichgraeber commented 5 years ago

@YoungFaithful I have the full extreme day selection with simple, slack-based, feasibility-based selection implemented (feasibility and append). I am holding off with a PR ecause I think I can clean the function a little bit and test it more to run into any bugs that may have slipped through). In case you really want to test it already, let me know, and I'll push something up.

holgerteichgraeber commented 5 years ago

accidentally closed..

YoungFaithful commented 5 years ago

I'd say this addition sounds great. I have a few other things to do first. So I'm sure I won't need it before Thursday next week, but afterwards I think it could be interesting for the continuation of the seasonal storage research.

holgerteichgraeber commented 5 years ago

Great, that gives me a little time to play with it too, even though I'm out for conference next week.