From 6114b6b8bb47b42b905a50cf386fe6d3acdeb26f Mon Sep 17 00:00:00 2001 From: Andrew Maguire Date: Mon, 14 Dec 2020 19:31:52 +0000 Subject: add paragraph in anomalies collector README to ask for feedback (#10363) * add paragraph to ask for feedback * Clean up text Co-authored-by: Joel Hans * add callout for community forums as well * Update collectors/python.d.plugin/anomalies/README.md Co-authored-by: Odysseas Lamtzidis Co-authored-by: Joel Hans Co-authored-by: Odysseas Lamtzidis --- collectors/python.d.plugin/anomalies/README.md | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'collectors') diff --git a/collectors/python.d.plugin/anomalies/README.md b/collectors/python.d.plugin/anomalies/README.md index bfb79d291e..95245a450e 100644 --- a/collectors/python.d.plugin/anomalies/README.md +++ b/collectors/python.d.plugin/anomalies/README.md @@ -7,7 +7,9 @@ custom_edit_url: https://github.com/netdata/netdata/edit/master/collectors/pytho This collector uses the Python [PyOD](https://pyod.readthedocs.io/en/latest/index.html) library to perform unsupervised [anomaly detection](https://en.wikipedia.org/wiki/Anomaly_detection) on your Netdata charts and/or dimensions. -Instead of this collector just _collecting_ data, it also does some computation on the data it collects to return an anomaly probability and anomaly flag for each chart or custom model you define. This computation consists of a **train** function that runs every `train_n_secs` to train the ML models to learn what 'normal' typically looks like on your node. At each iteration there is also a **predict** function that uses the latest trained models and most recent metrics to produce an anomaly probability and anomaly flag for each chart or custom model you define. +Instead of this collector just _collecting_ data, it also does some computation on the data it collects to return an anomaly probability and anomaly flag for each chart or custom model you define. This computation consists of a **train** function that runs every `train_n_secs` to train the ML models to learn what 'normal' typically looks like on your node. At each iteration there is also a **predict** function that uses the latest trained models and most recent metrics to produce an anomaly probability and anomaly flag for each chart or custom model you define. + +**Note**: As this is a somewhat unique collector and involves often subjective concepts like anomalies and anomaly probabilities, we would love to hear any feedback on it from the community. Please let us know on the [community forum](https://community.netdata.cloud/c/agent-development/9) or drop us a note at [analytics-ml-team@netdata.cloud](mailto:analytics-ml-team@netdata.cloud) for any and all feedback, both positive and negative. This sort of feedback is priceless to help us make complex features more useful. ## Charts -- cgit v1.2.3