[
https://issues.apache.org/jira/browse/METRON-562?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15678186#comment-15678186
]
ASF GitHub Bot commented on METRON-562:
---------------------------------------
Github user james-sirota commented on the issue:
https://github.com/apache/incubator-metron/pull/352
+ 1. i got it to work. one point of feedback, though. a lot of telemetry
data distributions tend to be heavy in the tails. not all are normally
distributed. i would augment your Gaussian test data to also include something
from a heavy-tailed distribution of your choice.....
https://docs.scipy.org/doc/numpy/reference/generated/numpy.random.standard_t.html
maybe?
I know your method will work with both because I have experience using it
in production with real data. but i think the tests should reflect it as well.
> Add rudimentary statistical outlier detection
> ---------------------------------------------
>
> Key: METRON-562
> URL: https://issues.apache.org/jira/browse/METRON-562
> Project: Metron
> Issue Type: New Feature
> Reporter: Casey Stella
> Assignee: Casey Stella
> Original Estimate: 48h
> Remaining Estimate: 48h
>
> With the advent of the profiler, we can now capture state. Furthermore, with
> Stellar, we can capture statistical summaries. We should provide rudimentary
> outlier detection functionality in the form of Stellar functions that can
> operate on captured state from the profiler.
> To begin, we should enable simple outlier tests using distance from a central
> measure such as Median Absolute Deviation (see
> http://www.itl.nist.gov/div898/handbook/eda/section3/eda35h.htm).
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
