182 lines
5.4 KiB
Plaintext
182 lines
5.4 KiB
Plaintext
[role="xpack"]
|
|
[testenv="basic"]
|
|
[[inference-processor]]
|
|
=== {infer-cap} Processor
|
|
|
|
Uses a pre-trained {dfanalytics} model to infer against the data that is being
|
|
ingested in the pipeline.
|
|
|
|
|
|
[[inference-options]]
|
|
.{infer-cap} Options
|
|
[options="header"]
|
|
|======
|
|
| Name | Required | Default | Description
|
|
| `model_id` | yes | - | (String) The ID of the model to load and infer against.
|
|
| `target_field` | no | `ml.inference.<processor_tag>` | (String) Field added to incoming documents to contain results objects.
|
|
| `field_map` | no | If defined the model's default field map | (Object) Maps the document field names to the known field names of the model. This mapping takes precedence over any default mappings provided in the model configuration.
|
|
| `inference_config` | no | The default settings defined in the model | (Object) Contains the inference type and its options. There are two types: <<inference-processor-regression-opt,`regression`>> and <<inference-processor-classification-opt,`classification`>>.
|
|
include::common-options.asciidoc[]
|
|
|======
|
|
|
|
|
|
[source,js]
|
|
--------------------------------------------------
|
|
{
|
|
"inference": {
|
|
"model_id": "flight_delay_regression-1571767128603",
|
|
"target_field": "FlightDelayMin_prediction_infer",
|
|
"field_map": {
|
|
"your_field": "my_field"
|
|
},
|
|
"inference_config": { "regression": {} }
|
|
}
|
|
}
|
|
--------------------------------------------------
|
|
// NOTCONSOLE
|
|
|
|
|
|
[discrete]
|
|
[[inference-processor-regression-opt]]
|
|
==== {regression-cap} configuration options
|
|
|
|
Regression configuration for inference.
|
|
|
|
`results_field`::
|
|
(Optional, string)
|
|
include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-results-field-processor]
|
|
|
|
`num_top_feature_importance_values`::
|
|
(Optional, integer)
|
|
include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-regression-num-top-feature-importance-values]
|
|
|
|
|
|
[discrete]
|
|
[[inference-processor-classification-opt]]
|
|
==== {classification-cap} configuration options
|
|
|
|
Classification configuration for inference.
|
|
|
|
`num_top_classes`::
|
|
(Optional, integer)
|
|
include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-classification-num-top-classes]
|
|
|
|
`num_top_feature_importance_values`::
|
|
(Optional, integer)
|
|
include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-classification-num-top-feature-importance-values]
|
|
|
|
`results_field`::
|
|
(Optional, string)
|
|
include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-results-field-processor]
|
|
|
|
`top_classes_results_field`::
|
|
(Optional, string)
|
|
include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-classification-top-classes-results-field]
|
|
|
|
`prediction_field_type`::
|
|
(Optional, string)
|
|
include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-classification-prediction-field-type]
|
|
|
|
[discrete]
|
|
[[inference-processor-config-example]]
|
|
==== `inference_config` examples
|
|
|
|
[source,js]
|
|
--------------------------------------------------
|
|
{
|
|
"inference_config": {
|
|
"regression": {
|
|
"results_field": "my_regression"
|
|
}
|
|
}
|
|
}
|
|
--------------------------------------------------
|
|
// NOTCONSOLE
|
|
|
|
This configuration specifies a `regression` inference and the results are
|
|
written to the `my_regression` field contained in the `target_field` results
|
|
object.
|
|
|
|
|
|
[source,js]
|
|
--------------------------------------------------
|
|
{
|
|
"inference_config": {
|
|
"classification": {
|
|
"num_top_classes": 2,
|
|
"results_field": "prediction",
|
|
"top_classes_results_field": "probabilities"
|
|
}
|
|
}
|
|
}
|
|
--------------------------------------------------
|
|
// NOTCONSOLE
|
|
|
|
This configuration specifies a `classification` inference. The number of
|
|
categories for which the predicted probabilities are reported is 2
|
|
(`num_top_classes`). The result is written to the `prediction` field and the top
|
|
classes to the `probabilities` field. Both fields are contained in the
|
|
`target_field` results object.
|
|
|
|
|
|
[discrete]
|
|
[[inference-processor-feature-importance]]
|
|
==== {feat-imp-cap} object mapping
|
|
|
|
Update your index mapping of the {feat-imp} result field as you can see below to
|
|
get the full benefit of aggregating and searching for
|
|
{ml-docs}/ml-feature-importance.html[{feat-imp}].
|
|
|
|
[source,js]
|
|
--------------------------------------------------
|
|
"ml.inference.feature_importance": {
|
|
"type": "nested",
|
|
"dynamic": true,
|
|
"properties": {
|
|
"feature_name": {
|
|
"type": "keyword"
|
|
},
|
|
"importance": {
|
|
"type": "double"
|
|
}
|
|
}
|
|
}
|
|
--------------------------------------------------
|
|
// NOTCONSOLE
|
|
|
|
The mapping field name for {feat-imp} is compounded as follows:
|
|
|
|
`<ml.inference.target_field>`.`<inference.tag>`.`feature_importance`
|
|
|
|
If `inference.tag` is not provided in the processor definition, it is not part
|
|
of the field path. The `<ml.inference.target_field>` defaults to `ml.inference`.
|
|
|
|
For example, you provide a tag `foo` in the definition as you can see below:
|
|
|
|
[source,js]
|
|
--------------------------------------------------
|
|
{
|
|
"tag": "foo",
|
|
...
|
|
}
|
|
--------------------------------------------------
|
|
// NOTCONSOLE
|
|
|
|
|
|
The {feat-imp} value is written to the `ml.inference.foo.feature_importance`
|
|
field.
|
|
|
|
You can also specify a target field as follows:
|
|
|
|
[source,js]
|
|
--------------------------------------------------
|
|
{
|
|
"tag": "foo",
|
|
"target_field": "my_field"
|
|
}
|
|
--------------------------------------------------
|
|
// NOTCONSOLE
|
|
|
|
In this case, {feat-imp} is exposed in the
|
|
`my_field.foo.feature_importance` field.
|