algorithm for detecting a limit of time-series numbers

[geekguy]

Is there a well known and proven algorithm to find the limit of a set of points, which are time based metrics? I'm looking for an existing implementation, in order not to try and invent something which already exists.

This is what I have in mind:

Run over the numeric values of a series
1. Calculate L which is the top limit, and E, where 2*E is the convergent stripe around L.
- E is configurable
- Most points, P percentage, except of anomalies/noise, are below the top line of L+E.
- P is configurable, ranging at 90-95-99% range.
- A Linear line around the last X points (Linear Regression) has a minor slope of +/-S
- X and S are configurable

The algo uses a stored state of a previous maximum limit - max-L.
- In case L which was calculated in (a) is lower than max-L, it is considered a local max which is discarded
- If L is greater than max-L then it is considered a new max limit and stored as the new max-L

[swelteringwellies]

@ Drift Hunters zz0.ku4iybxkhgg zz Yes — what you’re describing is not a new problem. It’s basically a combination of well-known techniques:

1. Percentile / quantile estimation
   Your “L where P% of points are below L+E” is essentially a high percentile (e.g. 95th, 99th percentile).
   Instead of inventing L, you can compute:

L = quantile(data, P)

This is standard and implemented everywhere (NumPy, SciPy, pandas, Apache Commons Math, etc.).
zz0.s1fvsu6bydz z