github-mirrors/VictoriaMetrics
1
0
Fork 0
mirror of https://github.com/VictoriaMetrics/VictoriaMetrics.git synced 2024-11-21 14:44:00 +00:00
Code Issues Projects Releases Packages Wiki Activity

docs/vmanomaly - fix 404 img links & remove outdated models (#6460)

Browse source 
### Describe Your Changes

Fix 404 relative img links for v1.13.0 update of vmanomaly docs

### Checklist

The following checks are **mandatory**:

- [x] My change adheres [VictoriaMetrics contributing
guidelines](https://docs.victoriametrics.com/contributing/).
This commit is contained in:
Fred Navruzov 2024-06-11 15:29:11 +02:00 committed by GitHub
parent 1feb5d04d7
commit 9a355c3512
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 11 additions and 15 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
docs/anomaly-detection/Overview.md
View file

@ -88,10 +88,6 @@ Currently, vmanomaly ships with a set of built-in models:
See [statsmodels.org documentation](https://www.statsmodels.org/dev/examples/notebooks/generated/stl_decomposition.html)
for LOESS STD.
1. [**ARIMA**](/anomaly-detection/components/models.html#arima)
Commonly used forecasting model. See [statsmodels.org documentation](https://www.statsmodels.org/stable/generated/statsmodels.tsa.arima.model.ARIMA.html) for ARIMA.
1. [**Rolling Quantile**](/anomaly-detection/components/models.html#rolling-quantile)
A simple moving window of quantiles. Easy to use, easy to understand, but not as powerful as

22
docs/anomaly-detection/components/models.md
View file

@ -135,19 +135,19 @@ Introduced in [1.13.0](/anomaly-detection/CHANGELOG/#1130), `detection_direction
Here's how default (backward-compatible) behavior looks like - anomalies will be tracked in `both` directions (`y > yhat` or `y < yhat`). This is useful when there is no domain expertise to filter the required direction.
<img src="schema_detection_direction=both.webp" width="800px" alt="schema_detection_direction=both"/>
<img src="/anomaly-detection/components/schema_detection_direction=both.webp" width="800px" alt="schema_detection_direction=both"/>
When set to `above_expected`, anomalies are tracked only when `y > yhat`.
*Example metrics*: Error rate, response time, page load time, number of failed transactions - metrics where *lower values are better*, so **higher** values are typically tracked.
<img src="schema_detection_direction=above_expected.webp" width="800px" alt="schema_detection_direction=above_expected"/>
<img src="/anomaly-detection/components/schema_detection_direction=above_expected.webp" width="800px" alt="schema_detection_direction=above_expected"/>
When set to `below_expected`, anomalies are tracked only when `y < yhat`.
*Example metrics*: Service Level Agreement (SLA) compliance, conversion rate, Customer Satisfaction Score (CSAT) - metrics where *higher values are better*, so **lower** values are typically tracked.
<img src="schema_detection_direction=below_expected.webp" width="800px" alt="schema_detection_direction=below_expected"/>
<img src="/anomaly-detection/components/schema_detection_direction=below_expected.webp" width="800px" alt="schema_detection_direction=below_expected"/>
Config with a split example:
@ -193,11 +193,11 @@ Introduced in [v1.13.0](/anomaly-detection/CHANGELOG/#1130), the `min_dev_from_e
Visualizations below demonstrate this concept; the green zone defined as the `[yhat - min_dev_from_expected, yhat + min_dev_from_expected]` range excludes actual data points (`y`) from generating anomaly scores if they fall within that range.
<img src="schema_min_dev_from_expected=0.webp" width="800px" alt="min_dev_from_expected-default"/>
<img src="/anomaly-detection/components/schema_min_dev_from_expected=0.webp" width="800px" alt="min_dev_from_expected-default"/>
<img src="schema_min_dev_from_expected=1.0.webp" width="800px" alt="min_dev_from_expected-small"/>
<img src="/anomaly-detection/components/schema_min_dev_from_expected=1.0.webp" width="800px" alt="min_dev_from_expected-small"/>
<img src="schema_min_dev_from_expected=5.0.webp" width="800px" alt="min_dev_from_expected-big"/>
<img src="/anomaly-detection/components/schema_min_dev_from_expected=5.0.webp" width="800px" alt="min_dev_from_expected-big"/>
## Model types
@ -224,7 +224,7 @@ If during an inference, you got a series having **new labelset** (not present in
**Examples:** [Prophet](#prophet), [Holt-Winters](#holt-winters)
<p></p>
<img alt="vmanomaly-model-type-univariate" src="model-lifecycle-univariate.webp" width="800px"/>
<img alt="vmanomaly-model-type-univariate" src="/anomaly-detection/components/model-lifecycle-univariate.webp" width="800px"/>
### Multivariate Models
@ -239,7 +239,7 @@ If during an inference, you got a **different amount of series** or some series
**Examples:** [IsolationForest](#isolation-forest-multivariate)
<p></p>
<img alt="vmanomaly-model-type-multivariate" src="model-lifecycle-multivariate.webp" width="800px"/>
<img alt="vmanomaly-model-type-multivariate" src="/anomaly-detection/components/model-lifecycle-multivariate.webp" width="800px"/>
### Rolling Models
@ -256,7 +256,7 @@ Such models put **more pressure** on your reader's source, i.e. if your model sh
**Examples:** [RollingQuantile](#rolling-quantile)
<p></p>
<img alt="vmanomaly-model-type-rolling" src="model-type-rolling.webp" width="800px"/>
<img alt="vmanomaly-model-type-rolling" src="/anomaly-detection/components/model-type-rolling.webp" width="800px"/>
### Non-Rolling Models
@ -273,7 +273,7 @@ Produced model instances are **stored in-memory** between consecutive re-fit cal
**Examples:** [Prophet](#prophet)
<p></p>
<img alt="vmanomaly-model-type-non-rolling" src="model-type-non-rolling.webp" width="800px"/>
<img alt="vmanomaly-model-type-non-rolling" src="/anomaly-detection/components/model-type-non-rolling.webp" width="800px"/>
## Built-in Models
@ -312,7 +312,7 @@ Tuning hyperparameters of a model can be tricky and often requires in-depth know
- `n_trials` (int) - How many trials to sample from hyperparameter search space. The higher, the longer it takes but the better the results can be. Defaults to 128.
- `timeout` (float) - How many seconds in total can be spent on each model to tune hyperparameters. The higher, the longer it takes, allowing to test more trials out of defined `n_trials`, but the better the results can be.
<img alt="vmanomaly-autotune-schema" src="autotune.webp" width="800px"/>
<img alt="vmanomaly-autotune-schema" src="/anomaly-detection/components/autotune.webp" width="800px"/>
```yaml
# ...