Inference bucket aggregation
editInference bucket aggregation
editA parent pipeline aggregation which loads a pre-trained model and performs inference on the collated result fields from the parent bucket aggregation.
To use the inference bucket aggregation, you need to have the same security privileges that are required for using the get trained models API.
Syntax
editA inference
aggregation looks like this in isolation:
{ "inference": { "model_id": "a_model_for_inference", "inference_config": { "regression_config": { "num_top_feature_importance_values": 2 } }, "buckets_path": { "avg_cost": "avg_agg", "max_cost": "max_agg" } } }
The unique identifier or alias for the trained model. |
|
The optional inference config which overrides the model’s default settings |
|
Map the value of |
Table 63. inference
Parameters
Parameter Name | Description | Required | Default Value |
---|---|---|---|
|
The ID or alias for the trained model. |
Required |
- |
|
Contains the inference type and its options. There are two types: |
Optional |
- |
|
Defines the paths to the input aggregations and maps the aggregation names to the field names expected by the model.
See |
Required |
- |
Configuration options for inference models
editThe inference_config
setting is optional and usually isn’t required as the
pre-trained models come equipped with sensible defaults. In the context of
aggregations some options can be overridden for each of the two types of model.
Configuration options for regression models
edit-
num_top_feature_importance_values
- (Optional, integer) Specifies the maximum number of feature importance values per document. By default, it is zero and no feature importance calculation occurs.
Configuration options for classification models
edit-
num_top_classes
- (Optional, integer) Specifies the number of top class predictions to return. Defaults to 0.
-
num_top_feature_importance_values
- (Optional, integer) Specifies the maximum number of feature importance values per document. Defaults to 0 which means no feature importance calculation occurs.
-
prediction_field_type
-
(Optional, string)
Specifies the type of the predicted field to write.
Valid values are:
string
,number
,boolean
. Whenboolean
is provided1.0
is transformed totrue
and0.0
tofalse
.
Example
editThe following snippet aggregates a web log by client_ip
and extracts a number
of features via metric and bucket sub-aggregations as input to the inference
aggregation configured with a model trained to identify suspicious client IPs:
resp = client.search( index="kibana_sample_data_logs", size=0, aggs={ "client_ip": { "composite": { "sources": [ { "client_ip": { "terms": { "field": "clientip" } } } ] }, "aggs": { "url_dc": { "cardinality": { "field": "url.keyword" } }, "bytes_sum": { "sum": { "field": "bytes" } }, "geo_src_dc": { "cardinality": { "field": "geo.src" } }, "geo_dest_dc": { "cardinality": { "field": "geo.dest" } }, "responses_total": { "value_count": { "field": "timestamp" } }, "success": { "filter": { "term": { "response": "200" } } }, "error404": { "filter": { "term": { "response": "404" } } }, "error503": { "filter": { "term": { "response": "503" } } }, "malicious_client_ip": { "inference": { "model_id": "malicious_clients_model", "buckets_path": { "response_count": "responses_total", "url_dc": "url_dc", "bytes_sum": "bytes_sum", "geo_src_dc": "geo_src_dc", "geo_dest_dc": "geo_dest_dc", "success": "success._count", "error404": "error404._count", "error503": "error503._count" } } } } } }, ) print(resp)
response = client.search( index: 'kibana_sample_data_logs', body: { size: 0, aggregations: { client_ip: { composite: { sources: [ { client_ip: { terms: { field: 'clientip' } } } ] }, aggregations: { url_dc: { cardinality: { field: 'url.keyword' } }, bytes_sum: { sum: { field: 'bytes' } }, geo_src_dc: { cardinality: { field: 'geo.src' } }, geo_dest_dc: { cardinality: { field: 'geo.dest' } }, responses_total: { value_count: { field: 'timestamp' } }, success: { filter: { term: { response: '200' } } }, "error404": { filter: { term: { response: '404' } } }, "error503": { filter: { term: { response: '503' } } }, malicious_client_ip: { inference: { model_id: 'malicious_clients_model', buckets_path: { response_count: 'responses_total', url_dc: 'url_dc', bytes_sum: 'bytes_sum', geo_src_dc: 'geo_src_dc', geo_dest_dc: 'geo_dest_dc', success: 'success._count', "error404": 'error404._count', "error503": 'error503._count' } } } } } } } ) puts response
const response = await client.search({ index: "kibana_sample_data_logs", size: 0, aggs: { client_ip: { composite: { sources: [ { client_ip: { terms: { field: "clientip", }, }, }, ], }, aggs: { url_dc: { cardinality: { field: "url.keyword", }, }, bytes_sum: { sum: { field: "bytes", }, }, geo_src_dc: { cardinality: { field: "geo.src", }, }, geo_dest_dc: { cardinality: { field: "geo.dest", }, }, responses_total: { value_count: { field: "timestamp", }, }, success: { filter: { term: { response: "200", }, }, }, error404: { filter: { term: { response: "404", }, }, }, error503: { filter: { term: { response: "503", }, }, }, malicious_client_ip: { inference: { model_id: "malicious_clients_model", buckets_path: { response_count: "responses_total", url_dc: "url_dc", bytes_sum: "bytes_sum", geo_src_dc: "geo_src_dc", geo_dest_dc: "geo_dest_dc", success: "success._count", error404: "error404._count", error503: "error503._count", }, }, }, }, }, }, }); console.log(response);
GET kibana_sample_data_logs/_search { "size": 0, "aggs": { "client_ip": { "composite": { "sources": [ { "client_ip": { "terms": { "field": "clientip" } } } ] }, "aggs": { "url_dc": { "cardinality": { "field": "url.keyword" } }, "bytes_sum": { "sum": { "field": "bytes" } }, "geo_src_dc": { "cardinality": { "field": "geo.src" } }, "geo_dest_dc": { "cardinality": { "field": "geo.dest" } }, "responses_total": { "value_count": { "field": "timestamp" } }, "success": { "filter": { "term": { "response": "200" } } }, "error404": { "filter": { "term": { "response": "404" } } }, "error503": { "filter": { "term": { "response": "503" } } }, "malicious_client_ip": { "inference": { "model_id": "malicious_clients_model", "buckets_path": { "response_count": "responses_total", "url_dc": "url_dc", "bytes_sum": "bytes_sum", "geo_src_dc": "geo_src_dc", "geo_dest_dc": "geo_dest_dc", "success": "success._count", "error404": "error404._count", "error503": "error503._count" } } } } } } }