Train a model | Labric | Documentation

curl -X POST https://platform.labric.co/api/v1/ml-models \
     -H "Authorization: Bearer <api_key>" \
     -H "Content-Type: application/json" \
     -d '{
  "target_column": "tensile_strength_mpa",
  "dataset_id": "4e5f6a7b-8c9d-4e0f-a1b2-c3d4e5f6a7b8",
  "description": "Estimates tensile strength of extruded polymer samples from formulation and process parameters.",
  "task_type": "tabular",
  "quality_preset": "high_quality",
  "feature_columns": [
    "polymer_fraction",
    "anneal_temperature_c",
    "extrusion_speed_mm_s"
  ],
  "problem_type": "regression",
  "name": "Tensile strength regressor"
}'

{
  "id": "9f8e7d6c-5b4a-4c3d-9e2f-1a0b9c8d7e6f",
  "name": "Tensile strength regressor",
  "task_type": "tabular",
  "description": "Estimates tensile strength of extruded polymer samples from formulation and process parameters.",
  "target_column": "tensile_strength_mpa",
  "feature_columns": [
    "polymer_fraction",
    "anneal_temperature_c",
    "extrusion_speed_mm_s"
  ],
  "image_columns": null,
  "problem_type": "regression",
  "currently_active": false,
  "status": "pending",
  "version_number": 1,
  "dataset_id": "4e5f6a7b-8c9d-4e0f-a1b2-c3d4e5f6a7b8",
  "quality_preset": "high_quality",
  "error_message": null,
  "training_started_at": null,
  "training_completed_at": null,
  "evaluation_metrics": null
}

Train a new ML model on a dataset, or retrain an existing one.

To train a new model, pass name and omit ml_model_id. To retrain, pass ml_model_id and omit name; the model keeps its name and gains a new version. dataset_id and target_column are always required, and every column must exist in the dataset. Training runs in the background; check its progress with get_ml_model.

Requires an API key with the write scope.

Authentication

AuthorizationBearer

Bearer authentication of the form Bearer <token>, where token is your auth token.

Request

This endpoint expects an object.

target_columnstringRequired

dataset_idstringRequiredformat: "uuid"

descriptionstring or nullOptional

task_typeenum or nullOptional

Allowed values:

quality_presetenumOptionalDefaults to high_quality

Allowed values:

feature_columnslist of strings or nullOptional

image_columnslist of strings or nullOptional

problem_typeenum or nullOptional

Allowed values:

ml_model_idstring or nullOptionalformat: "uuid"

namestring or nullOptional

Response

idstringformat: "uuid"

namestring

task_typestring

descriptionstring or nullOptional

target_columnstring or nullOptional

feature_columnslist of strings or nullOptional

image_columnslist of strings or nullOptional

problem_typestring or nullOptional

currently_activebooleanOptionalDefaults to false

statusstring or nullOptional

version_numberinteger or nullOptional

dataset_idstring or nullOptionalformat: "uuid"

quality_presetstring or nullOptional

error_messagestring or nullOptional

training_started_atdatetime or nullOptional

training_completed_atdatetime or nullOptional

evaluation_metricsmap from strings to any or nullOptional

Errors

400

Bad Request Error

401

Unauthorized Error

403

Forbidden Error

404

Not Found Error

422

Unprocessable Entity Error

500

Internal Server Error

503

Service Unavailable Error