add note with link to guide for using on Pi (#11605)
* add note with link to guide for using on Pi * Update collectors/python.d.plugin/anomalies/README.md Co-authored-by: DShreve2 <david@netdata.cloud> Co-authored-by: DShreve2 <david@netdata.cloud>
Andrew Maguire committed
Dec 20, 2021 at 15:13 UTC
eed062d848b7b0e6074006a04c96afdf3f2ad9b8
1 file changed
+2
-1
collectors/python.d.plugin/anomalies/README.md
+2
-1
@@ -229,6 +229,7 @@ If you would like to go deeper on what exactly the anomalies collector is doing
229
- If you activate this collector on a fresh node, it might take a little while to build up enough data to calculate a realistic and useful model.
230
- Some models like `iforest` can be comparatively expensive (on same n1-standard-2 system above ~2s runtime during predict, ~40s training time, ~50% cpu on both train and predict) so if you would like to use it you might be advised to set a relatively high `update_every` maybe 10, 15 or 30 in `anomalies.conf`.
231
- Setting a higher `train_every_n` and `update_every` is an easy way to devote less resources on the node to anomaly detection. Specifying less charts and a lower `train_n_secs` will also help reduce resources at the expense of covering less charts and maybe a more noisy model if you set `train_n_secs` to be too small for how your node tends to behave.
232
+- If you would like to enable this on a Rasberry Pi, then check out [this guide](https://learn.netdata.cloud/guides/monitor/raspberry-pi-anomaly-detection) which will guide you through first installing LLVM.
233
234
## Useful links and further reading
235
@@ -240,4 +241,4 @@ If you would like to go deeper on what exactly the anomalies collector is doing
241
- Good [blog post](https://www.anodot.com/blog/what-is-anomaly-detection/) from Anodot on time series anomaly detection. Anodot also have some great whitepapers in this space too that some may find useful.
242
- Novelty and outlier detection in the [scikit-learn documentation](https://scikit-learn.org/stable/modules/outlier_detection.html).
243
243
-[]()
\ No newline at end of file
244
+[]()