elasticsearch/docs/reference/ml/df-analytics/apis/put-inference.asciidoc

[role="xpack"]
[testenv="basic"]
[[put-inference]]
=== Create {infer} trained model API
[subs="attributes"]
++++
<titleabbrev>Create {infer} trained model</titleabbrev>
++++

Creates an {infer} trained model.

experimental[]


[[ml-put-inference-request]]
==== {api-request-title}

`PUT _ml/inference/<model_id>`


[[ml-put-inference-prereq]]
==== {api-prereq-title}

If the {es} {security-features} are enabled, you must have the following 
built-in roles and privileges:

* `machine_learning_admin`

For more information, see <<security-privileges>> and <<built-in-roles>>.


[[ml-put-inference-desc]]
==== {api-description-title}

The create {infer} trained model API enables you to supply a trained model that 
is not created by {dfanalytics}. 


[[ml-put-inference-path-params]]
==== {api-path-parms-title}

`<model_id>`::
(Required, string) 
include::{docdir}/ml/ml-shared.asciidoc[tag=model-id]

[role="child_attributes"]
[[ml-put-inference-request-body]]
==== {api-request-body-title}

`compressed_definition`::
(Required, string) 
The compressed (GZipped and Base64 encoded) {infer} definition of the model. 
If `compressed_definition` is specified, then `definition` cannot be specified.

//Begin definition
`definition`::
(Required, object) 
The {infer} definition for the model. If `definition` is specified, then 
`compressed_definition` cannot be specified.
+
.Properties of `definition`
[%collapsible%open]
====
`preprocessors`:::
(Optional, object)
Collection of preprocessors. See <<ml-put-inference-preprocessors>> for the full 
list of available preprocessors.

`trained_model`:::
(Required, object) 
The definition of the trained model. See <<ml-put-inference-trained-model>> for 
details.
====
//End definition

`description`::
(Optional, string) 
A human-readable description of the {infer} trained model.

//Begin inference_config
`inference_config`::
(Required, object)
The default configuration for inference. This can be either a `regression`
or `classification` configuration. It must match the underlying
`definition.trained_model`'s `target_type`.
+
.Properties of `inference_config`
[%collapsible%open]
====
`regression`:::
(Optional, object)
Regression configuration for inference.
+
.Properties of regression inference
[%collapsible%open]
=====
`num_top_feature_importance_values`::::
(Optional, integer)
include::{docdir}/ml/ml-shared.asciidoc[tag=inference-config-regression-num-top-feature-importance-values]

`results_field`::::
(Optional, string)
include::{docdir}/ml/ml-shared.asciidoc[tag=inference-config-regression-results-field]
=====

`classification`:::
(Optional, object)
Classification configuration for inference.
+
.Properties of classification inference
[%collapsible%open]
=====
`num_top_classes`::::
(Optional, integer)
include::{docdir}/ml/ml-shared.asciidoc[tag=inference-config-classification-num-top-classes]

`num_top_feature_importance_values`::::
(Optional, integer)
include::{docdir}/ml/ml-shared.asciidoc[tag=inference-config-classification-num-top-feature-importance-values]

`results_field`::::
(Optional, string)
include::{docdir}/ml/ml-shared.asciidoc[tag=inference-config-classification-results-field]

`top_classes_results_field`::::
(Optional, string)
include::{docdir}/ml/ml-shared.asciidoc[tag=inference-config-classification-top-classes-results-field]
=====
====
//End of inference_config

//Begin input
`input`::
(Required, object) 
The input field names for the model definition.
+
.Properties of `input`
[%collapsible%open]
====
`field_names`:::
(Required, string) 
An array of input field names for the model.
====
//End input

`metadata`::
(Optional, object) 
An object map that contains metadata about the model.

`tags`::
(Optional, string) 
An array of tags to organize the model.

[[ml-put-inference-preprocessors]]
===== {infer-cap} preprocessor definitions

`frequency_encoding`::
(Required, object) 
Defines a frequency encoding for a field.

`frequency_encoding`.`field`:::
(Required, string) 
The field name to encode.

`frequency_encoding`.`feature_name`:::
(Required, string) 
The name of the resulting feature.

`frequency_encoding`.`frequency_map`:::
(Required, object map of string:double) 
Object that maps the field value to the frequency encoded value.

`one_hot_encoding`::
(Required, object) 
Defines a one hot encoding map for a field.

`one_hot_encoding`.`field`:::
(Required, string) 
The field name to encode.

`one_hot_encoding`.`hot_map`:::
(Required, object map of strings) 
String map of "field_value: one_hot_column_name".

`target_mean_encoding`::
(Required, object) 
Defines a target mean encoding for a field.

`target_mean_encoding`.`field`:::
(Required, string)
The field name to encode.

`target_mean_encoding`.`feature_name`:::
(Required, string) 
The name of the resulting feature.

`target_mean_encoding`.`target_map`:::
(Required, object map of string:double) 
Object that maps the field value to the target mean value.

`target_mean_encoding`.`default_value`:::
(Required, double) 
The feature value if the field value is not in the `target_map`.

See <<ml-put-inference-preprocessor-example>> for more details.


[[ml-put-inference-trained-model]]
===== {infer-cap} trained model definitions

`tree`::
(Required, object) 
The definition for a binary decision tree.

`tree`.`feature_names`:::
(Required, string)
Features expected by the tree, in their expected order.

`tree`.`tree_structure`:::
(Required, object) 
An array of `tree_node` objects. The nodes must be in ordinal order by their 
`tree_node.node_index` value.

`tree`.`classification_labels`:::
(Optional, string) An array of classification labels (used for 
`classification`).

`tree`.`target_type`:::
(Required, string) 
String indicating the model target type; `regression` or `classification`.

There are two major types of nodes: leaf nodes and not-leaf nodes.

* Leaf nodes only need `node_index` and `leaf_value` defined.
* All other nodes need `split_feature`, `left_child`, `right_child`, 
  `threshold`, `decision_type`, and `default_left` defined.



`tree_node`::
(Required, object) 
The definition of a node in a tree.

`tree_node`.`decision_type`:::
(Optional, string) 
Indicates the positive value (in other words, when to choose the left node) 
decision type. Supported `lt`, `lte`, `gt`, `gte`. Defaults to `lte`.

`tree_node`.`threshold`:::
(Optional, double) 
The decision threshold with which to compare the feature value.

`tree_node`.`left_child`:::
(Optional, integer) 
The index of the left child.

`tree_node`.`right_child`:::
(Optional, integer) 
The index of the right child.

`tree_node`.`default_left`:::
(Optional, boolean) 
Indicates whether to default to the left when the feature is missing. Defaults 
to `true`.

`tree_node`.`split_feature`:::
(Optional, integer) 
The index of the feature value in the feature array.

`tree_node`.`node_index`:::
(Integer) 
The index of the current node.

`tree_node`.`split_gain`:::
(Optional, double) The information gain from the split.

`tree_node`.`leaf_value`:::
(Optional, double) 
The leaf value of the of the node, if the value is a leaf (in other words, no 
children).

`ensemble`::
(Optional, object)
The definition for an ensemble model.

`ensemble`.`feature_names`:::
(Optional, string)
Features expected by the ensemble, in their expected order.

`ensemble`.`trained_models`:::
(Required, object)
An array of `trained_model` objects. Supported trained models are `tree` and 
`ensemble`.

`ensemble`.`classification_labels`:::
(Optional, string) 
An array of classification labels.

`ensemble`.`target_type`:::
(Required, string) 
String indicating the model target type; `regression` or `classification.`

`ensemble`.`aggregate_output`:::
(Required, object) 
An aggregated output object that defines how to aggregate the outputs of the 
`trained_models`. Supported objects are `weighted_mode`, `weighted_sum`, and 
`logistic_regression`.

See <<ml-put-inference-model-example>> for more details.


[[ml-put-inference-aggregated-output]]
===== Aggregated output types

`logistic_regression`::
(Optional, object) 
This `aggregated_output` type works with binary classification (classification 
for values [0, 1]). It multiplies the outputs (in the case of the `ensemble` 
model, the inference model values) by the supplied `weights`. The resulting 
vector is summed and passed to a 
https://en.wikipedia.org/wiki/Sigmoid_function[`sigmoid` function]. The result 
of the `sigmoid` function is considered the probability of class 1 (`P_1`), 
consequently, the probability of class 0 is `1 - P_1`. The class with the 
highest probability (either 0 or 1) is then returned. For more information about 
logistic regression, see 
https://en.wikipedia.org/wiki/Logistic_regression[this wiki article].

`logistic_regression`.`weights`:::
(Required, double) 
The weights to multiply by the input values (the inference values of the trained 
models).

`weighted_sum`::
(Optional, object) 
This `aggregated_output` type works with regression. The weighted sum of the 
input values.

`weighted_sum`.`weights`:::
(Required, double) 
The weights to multiply by the input values (the inference values of the trained 
models).

`weighted_mode`::
(Optional, object) 
This `aggregated_output` type works with regression or classification. It takes 
a weighted vote of the input values. The most common input value (taking the 
weights into account) is returned.

`weighted_mode`.`weights`:::
(Required, double) 
The weights to multiply by the input values (the inference values of the trained 
models).

See <<ml-put-inference-aggregated-output-example>> for more details.


[[ml-put-inference-example]]
==== {api-examples-title}

[[ml-put-inference-preprocessor-example]]
===== Preprocessor examples

The example below shows a `frequency_encoding` preprocessor object:

[source,js]
----------------------------------
{
   "frequency_encoding":{
      "field":"FlightDelayType",
      "feature_name":"FlightDelayType_frequency",
      "frequency_map":{
         "Carrier Delay":0.6007414737092798,
         "NAS Delay":0.6007414737092798,
         "Weather Delay":0.024573576178086153,
         "Security Delay":0.02476631010889467,
         "No Delay":0.6007414737092798,
         "Late Aircraft Delay":0.6007414737092798
      }
   }
}
----------------------------------
//NOTCONSOLE


The next example shows a `one_hot_encoding` preprocessor object:

[source,js]
----------------------------------
{ 
   "one_hot_encoding":{ 
      "field":"FlightDelayType",
      "hot_map":{ 
         "Carrier Delay":"FlightDelayType_Carrier Delay",
         "NAS Delay":"FlightDelayType_NAS Delay",
         "No Delay":"FlightDelayType_No Delay",
         "Late Aircraft Delay":"FlightDelayType_Late Aircraft Delay"
      }
   }
}
----------------------------------
//NOTCONSOLE


This example shows a `target_mean_encoding` preprocessor object:

[source,js]
----------------------------------
{
   "target_mean_encoding":{
      "field":"FlightDelayType",
      "feature_name":"FlightDelayType_targetmean",
      "target_map":{
         "Carrier Delay":39.97465788139886,
         "NAS Delay":39.97465788139886,
         "Security Delay":203.171206225681,
         "Weather Delay":187.64705882352948,
         "No Delay":39.97465788139886,
         "Late Aircraft Delay":39.97465788139886
      },
      "default_value":158.17995752420433
   }
}
----------------------------------
//NOTCONSOLE


[[ml-put-inference-model-example]]
===== Model examples

The first example shows a `trained_model` object:

[source,js]
----------------------------------
{
   "tree":{
      "feature_names":[
         "DistanceKilometers",
         "FlightTimeMin",
         "FlightDelayType_NAS Delay",
         "Origin_targetmean",
         "DestRegion_targetmean",
         "DestCityName_targetmean",
         "OriginAirportID_targetmean",
         "OriginCityName_frequency",
         "DistanceMiles",
         "FlightDelayType_Late Aircraft Delay"
      ],
      "tree_structure":[
         {
            "decision_type":"lt",
            "threshold":9069.33437193022,
            "split_feature":0,
            "split_gain":4112.094574306927,
            "node_index":0,
            "default_left":true,
            "left_child":1,
            "right_child":2
         },
         ...         
         {
            "node_index":9,
            "leaf_value":-27.68987349695448
         },
         ...
      ],
      "target_type":"regression"
   }
}
----------------------------------
//NOTCONSOLE


The following example shows an `ensemble` model object:

[source,js]
----------------------------------
"ensemble":{
   "feature_names":[
      ...
   ],
   "trained_models":[
      {
         "tree":{
            "feature_names":[],
            "tree_structure":[
               {
                  "decision_type":"lte",
                  "node_index":0,
                  "leaf_value":47.64069875778043,
                  "default_left":false
               }
            ],
            "target_type":"regression"
         }
      },
      ...
   ],
   "aggregate_output":{
      "weighted_sum":{
         "weights":[
            ...
         ]
      }
   },
   "target_type":"regression"
}
----------------------------------
//NOTCONSOLE


[[ml-put-inference-aggregated-output-example]]
===== Aggregated output example

Example of a `logistic_regression` object:

[source,js]
----------------------------------
"aggregate_output" : {
  "logistic_regression" : {
    "weights" : [2.0, 1.0, .5, -1.0, 5.0, 1.0, 1.0]
  }
}
----------------------------------
//NOTCONSOLE


Example of a `weighted_sum` object:

[source,js]
----------------------------------
"aggregate_output" : {
  "weighted_sum" : {
    "weights" : [1.0, -1.0, .5, 1.0, 5.0]
  }
}
----------------------------------
//NOTCONSOLE


Example of a `weighted_mode` object:

[source,js]
----------------------------------
"aggregate_output" : {
  "weighted_mode" : {
    "weights" : [1.0, 1.0, 1.0, 1.0, 1.0]
  }
}
----------------------------------
//NOTCONSOLE


[[ml-put-inference-json-schema]]
===== {infer-cap} JSON schema

For the full JSON schema of model {infer}, 
https://github.com/elastic/ml-json-schemas[click here].