Before Width: | Height: | Size: 113 KiB After Width: | Height: | Size: 94 KiB |
BIN
docs/ml/images/ml-data-visualizer-sample.jpg
Normal file
After Width: | Height: | Size: 350 KiB |
Before Width: | Height: | Size: 149 KiB After Width: | Height: | Size: 208 KiB |
BIN
docs/ml/images/ml-settings.jpg
Normal file
After Width: | Height: | Size: 72 KiB |
Before Width: | Height: | Size: 341 KiB After Width: | Height: | Size: 307 KiB |
|
@ -7,42 +7,54 @@
|
|||
|
||||
As datasets increase in size and complexity, the human effort required to
|
||||
inspect dashboards or maintain rules for spotting infrastructure problems,
|
||||
cyber attacks, or business issues becomes impractical. The {xpackml} features
|
||||
cyber attacks, or business issues becomes impractical. The Elastic {ml-features}
|
||||
automatically model the normal behavior of your time series data — learning
|
||||
trends, periodicity, and more — in real time to identify anomalies, streamline
|
||||
root cause analysis, and reduce false positives.
|
||||
|
||||
{xpackml} runs in and scales with {es}, and includes an
|
||||
The {ml-features} run in and scale with {es}, and include an
|
||||
intuitive UI on the {kib} *Machine Learning* page for creating anomaly detection
|
||||
jobs and understanding results.
|
||||
|
||||
You can use the *Job Management* pane to create and manage jobs and their
|
||||
associated {dfeeds}:
|
||||
If you have a basic license, you can use the *Data Visualizer* to learn more
|
||||
about the data that you've stored in {es} and to identify possible fields for
|
||||
{ml} analysis:
|
||||
|
||||
[role="screenshot"]
|
||||
image::ml/images/ml-data-visualizer-sample.jpg[Data Visualizer for sample flight data]
|
||||
|
||||
experimental[] You can also upload a CSV, NDJSON, or log file (up to 100 MB in size).
|
||||
The {ml-features} identify the file format and field mappings. You can then
|
||||
optionally import that data into an {es} index.
|
||||
|
||||
If you have a trial or platinum license, you can <<ml-jobs,create {ml} jobs>>
|
||||
and manage jobs and {dfeeds} from the *Job Management* pane:
|
||||
|
||||
[role="screenshot"]
|
||||
image::ml/images/ml-job-management.jpg[Job Management]
|
||||
|
||||
You can use the *Settings* pane to add scheduled events to calendars and to
|
||||
associate these calendars with your jobs:
|
||||
You can use the *Settings* pane to create and edit
|
||||
{stack-ov}/ml-calendars.html[calendars] and the filters that are used in
|
||||
{stack-ov}/ml-rules.html[custom rules]:
|
||||
|
||||
[role="screenshot"]
|
||||
image::ml/images/ml-calendar-management.jpg[Calendar Management]
|
||||
image::ml/images/ml-settings.jpg[Calendar Management]
|
||||
|
||||
The *Anomaly Explorer* and *Single Metric Viewer* display the results of your
|
||||
{ml} jobs. For example:
|
||||
{ml} jobs. For example:
|
||||
|
||||
[role="screenshot"]
|
||||
image::ml/images/ml-single-metric-viewer.jpg[Single Metric Viewer]
|
||||
|
||||
NOTE: The {xpack} {ml} features in {kib} use pop-ups. You must configure your
|
||||
NOTE: The {kib} {ml-features} use pop-ups. You must configure your
|
||||
web browser so that it does not block pop-up windows or create an exception for
|
||||
your Kibana URL.
|
||||
your {kib} URL.
|
||||
|
||||
For more information about {ml}, see
|
||||
{xpack-ref}/xpack-ml.html[Machine Learning in the Elastic Stack].
|
||||
{stack-ov}/xpack-ml.html[Machine learning in the {stack}].
|
||||
|
||||
--
|
||||
|
||||
include::creating-jobs.asciidoc[]
|
||||
include::job-tips.asciidoc[]
|
||||
//TO-DO: Add info about creating watch
|
||||
|
||||
|
|