Sebastien Leger
Sebastien Leger
Hi Martin, unfortunately, I don't think queries with "sum of multiple attributes" are supported at this point in loudml. I've seen "scripted" queries in ES however I'm not sure they...
Hi Bruno, it's one of the FAQ I receive on a regular basis. Just "Hit the Like button". You can now Sponsor this feature too, thanks to Github Open Source...
Buckets and scheduled jobs added at run time are not persisted. It’s a limitation in the current version. I will fix this in a future build.
I will patch this one quickly
Hi, Thanks for the logs. So the error is”bucket not found” loudml_1 | ERROR:root:job[42d1a3b9-affa-488b-8f3d-929944e9d613] failed: Bucket not found (name = 'telegraf_autogen_disk') Actual root cause: #148
@sorinmuchi Hi, mv was dropped in 1.5 (the current master branch). We can re-introduce multivariate feature support in a future release. What type of multivariate data problem do you have...
@sorinmuchi thanks a lot for the data centre example. Can we find this data set publicly or privately exchange data? @lephisto Yes it will be back. So I've been cleaning...
Hi Suresh, very cool data set. 1. Anomalies are not flagged in training data. You can exclude let say one year from your training set, and then _evaluate_ the model...
Can you please dump your `config.yml` file?
The annotation_db's main purpose is to log anomalies. The `loudml train` command is trying to query this data in order to exclude abnormal data points from the training set. This...