why the example give very low score?

[mashuai191]

hi Ritesh,
does that mean there is issue in the implementation? then when i run your code with the author's full data, it's getting very slow, while the C++ version completed in 10s, this python version showed 2h+ needed.

Another question is do you know how to decide the threshold for the anomaly score?

Thansk a lot!

Br, Shuai Ma

[prateekiiest]

Hi @mashuai191 , as far as I remember the example notebook has been updated to accommodate a faster version.
let me know if that works. it shows good accuracy for the whole file.

[prateekiiest]

Closing this in favour of https://github.com/ritesh99rakesh/pyMIDAS/blob/master/examples/midas.ipynb