detect anomalies on sequential data about banpei HOT 2 CLOSED

thanks very much for your reply.

from banpei.

Sorry for my late reply.
Hotelling method can be used like below.

import banpei 
model   = banpei.Hotelling()
results = model.detect(data, 0.01)  

The input 'data' must be one-dimensional array-like object containing a sequence of values.
The second argument '0.01' is threshold, meaning that we judge that an event occurring at less than 1% is abnormal.

In general, hotelling theory is not suitable for detecting abnormality of time series data. It is suitable for outlier detection. And, it imposes a strong restriction that data follows a normal distribution.

I do not know what you want to do, but if you think that it is suitable for what you want to do, try using it.

from banpei.