# Machine Learning API

**URL:** <https://discuss.elastic.co/t/machine-learning-api/99563>\
**Category:** Elasticsearch\
**Tags:** elastic-stack-machine-learning\
**Created:** [September 6, 2017, 10:59am UTC](https://discuss.elastic.co/t/machine-learning-api/99563 "2017-09-06T10:59:16Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![Karni\_Sagi](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/karni_sagi/32/21843_2.png) [@Karni\_Sagi](https://discuss.elastic.co/u/Karni_Sagi)\
**Post date:** [September 6, 2017, 10:59am UTC](https://discuss.elastic.co/t/machine-learning-api/99563/1 "2017-09-06T10:59:17Z")

</div>

I'm new in Elastic stack.  
Looking on the Anomaly Detection in the X-pack package.  
I was wondering if setting up , configuring , ruining and displaying the job result can be **fully** done via API.  
I run across the API reference here :[https://www.elastic.co/guide/en/elasticsearch/reference/current/ml-apis.html](https://www.elastic.co/guide/en/elasticsearch/reference/current/ml-apis.html)  
but before giving it a try I was wondering if everything that could be done though Kibana can also be done via the API.  
For example , Can I fully display the job results in my out visualization when calling the correct API's ?  
To fully draw the results I need to fetch data source along with the anomalous points (including their scores) and the model upper and lower bounds (similar to how Kibana displays it)  
Thanks  
Sagi

---

<div class="post-metadata">

**Author:** ![richcollier](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/richcollier/32/115035_2.png) [@richcollier](https://discuss.elastic.co/u/richcollier)\
**Post date:** [September 6, 2017, 3:06pm UTC](https://discuss.elastic.co/t/machine-learning-api/99563/2 "2017-09-06T15:06:34Z")

</div>

Sagi,

Yes, everything can be fully done via the API.

In addition to using the [results API](https://www.elastic.co/guide/en/x-pack/5.5/ml-api-quickref.html#ml-api-results), all information for ML's results is also stored in Elasticsearch indices (.ml-anomalies-\*) which can be queried with Elasticsearch DSL and therefore can give you even more flexibility.

---

<div class="post-metadata">

**Author:** ![Karni\_Sagi](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/karni_sagi/32/21843_2.png) [@Karni\_Sagi](https://discuss.elastic.co/u/Karni_Sagi)\
**Post date:** [September 6, 2017, 6:35pm UTC](https://discuss.elastic.co/t/machine-learning-api/99563/3 "2017-09-06T18:35:44Z")

</div>

thanks

---

<div class="post-metadata">

**Author:** ![system](https://us1.discourse-cdn.com/elastic/original/3X/1/a/1ac57faf039f6b580b3f104ef42a2a89e41014de.png) [@system](https://discuss.elastic.co/u/system)\
**Post date:** [October 4, 2017, 6:36pm UTC](https://discuss.elastic.co/t/machine-learning-api/99563/4 "2017-10-04T18:36:01Z")

</div>

This topic was automatically closed 28 days after the last reply. New replies are no longer allowed.