OpenSearch/docs/reference/ml/df-analytics/apis/explain-dfanalytics.asciidoc

[role="xpack"]
[testenv="platinum"]
[[explain-dfanalytics]]
=== Explain {dfanalytics} API

[subs="attributes"]
++++
<titleabbrev>Explain {dfanalytics} API</titleabbrev>
++++

Explains a {dataframe-analytics-config}.

experimental[]


[[ml-explain-dfanalytics-request]]
==== {api-request-title}

`GET _ml/data_frame/analytics/_explain` +

`POST _ml/data_frame/analytics/_explain` +

`GET _ml/data_frame/analytics/<data_frame_analytics_id>/_explain` +

`POST _ml/data_frame/analytics/<data_frame_analytics_id>/_explain`


[[ml-explain-dfanalytics-prereq]]
==== {api-prereq-title}

* You must have `monitor_ml` privilege to use this API. For more
information, see <<security-privileges>> and <<built-in-roles>>.


[[ml-explain-dfanalytics-desc]]
==== {api-description-title}

This API provides explanations for a {dataframe-analytics-config} that either 
exists already or one that has not been created yet.
The following explanations are provided:

* which fields are included or not in the analysis and why,
* how much memory is estimated to be required. The estimate can be used when 
  deciding the appropriate value for `model_memory_limit` setting later on,

about either an existing {dfanalytics-job} or one that has not been created yet.


[[ml-explain-dfanalytics-path-params]]
==== {api-path-parms-title}

`<data_frame_analytics_id>`::
(Optional, string)
include::{docdir}/ml/ml-shared.asciidoc[tag=job-id-data-frame-analytics]


[[ml-explain-dfanalytics-request-body]]
==== {api-request-body-title}

`data_frame_analytics_config`::
  (Optional, object) Intended configuration of {dfanalytics-job}. Note that `id` 
  and `dest` don't need to be provided in the context of this API.


[[ml-explain-dfanalytics-results]]
==== {api-response-body-title}

The API returns a response that contains the following:

`field_selection`::
(array)
include::{docdir}/ml/ml-shared.asciidoc[tag=field-selection]

`memory_estimation`::
(object) 
include::{docdir}/ml/ml-shared.asciidoc[tag=memory-estimation]


[[ml-explain-dfanalytics-example]]
==== {api-examples-title}

[source,console]
--------------------------------------------------
POST _ml/data_frame/analytics/_explain
{
  "data_frame_analytics_config": {
    "source": {
      "index": "houses_sold_last_10_yrs"
    },
    "analysis": {
      "regression": {
        "dependent_variable": "price"
      }
    }
  }
}
--------------------------------------------------
// TEST[skip:TBD]


The API returns the following results:

[source,console-result]
----
{
  "field_selection": [
    {
      "field": "number_of_bedrooms",
      "mappings_types": ["integer"],
      "is_included": true,
      "is_required": false,
      "feature_type": "numerical"
    },
    {
      "field": "postcode",
      "mappings_types": ["text"],
      "is_included": false,
      "is_required": false,
      "reason": "[postcode.keyword] is preferred because it is aggregatable"
    },
    {
      "field": "postcode.keyword",
      "mappings_types": ["keyword"],
      "is_included": true,
      "is_required": false,
      "feature_type": "categorical"
    },
    {
      "field": "price",
      "mappings_types": ["float"],
      "is_included": true,
      "is_required": true,
      "feature_type": "numerical"
    }
  ],
  "memory_estimation": {
    "expected_memory_without_disk": "128MB",
    "expected_memory_with_disk": "32MB"
  }
}
----