eland.ml.MLModel#

class eland.ml.MLModel(es_client: Union[str, List[str], Tuple[str, ...], Elasticsearch], model_id: str)#

A machine learning model managed by Elasticsearch. (See https://www.elastic.co/guide/en/elasticsearch/reference/current/put-inference.html)

These models can be created by Elastic ML, or transformed from supported Python formats such as scikit-learn or xgboost and imported into Elasticsearch.

The methods for this class attempt to mirror standard Python classes.

__init__(es_client: Union[str, List[str], Tuple[str, ...], Elasticsearch], model_id: str)#

Parameters#

es_client: Elasticsearch client argument(s)

  • elasticsearch-py parameters or

  • elasticsearch-py instance

model_id: str

The unique identifier of the trained inference model in Elasticsearch.

Methods

__init__(es_client, model_id)

Parameters es_client: Elasticsearch client argument(s) elasticsearch-py parameters or elasticsearch-py instance

delete_model()

Delete an inference model saved in Elasticsearch

exists_model()

Check if the model already exists in Elasticsearch

export_model()

Export Elastic ML model as sklearn Pipeline.

import_ltr_model(es_client, model_id, model, ...)

Transform and serialize a trained 3rd party model into Elasticsearch.

import_model(es_client, model_id, model, ...)

Transform and serialize a trained 3rd party model into Elasticsearch.

predict(X)

Make a prediction using a trained model stored in Elasticsearch.

Attributes

feature_names

model_type

results_field