Skip to main content
POST
/
api
/
automl
/
train
Submit an AutoML training job
curl --request POST \
  --url https://api.example.com/api/automl/train \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "name": "<string>",
  "domain": "<string>",
  "owner": "<string>",
  "source_table": "<string>",
  "preset": "balanced",
  "label_column": "<string>",
  "positive_class_value": "<unknown>",
  "feature_columns": [
    "<string>"
  ],
  "group_column": "<string>",
  "action_column": "<string>",
  "reward_column": "<string>",
  "probability_column": "<string>",
  "context_columns": [
    "<string>"
  ],
  "train_split_cutoff": "<string>",
  "time_column": "<string>",
  "hyperparameter_overrides": {},
  "enable_shap": true,
  "experiment_name": "<string>",
  "registered_model_name": "<string>",
  "feature_engineering_job_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "trigger_now": true
}
'
{
  "job_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "name": "<string>",
  "domain": "<string>",
  "owner": "<string>",
  "source_table": "<string>",
  "created_at": "2023-11-07T05:31:56Z",
  "updated_at": "2023-11-07T05:31:56Z",
  "rendered_dag": "<string>",
  "mlflow_run_id": "<string>",
  "mlflow_experiment_name": "<string>",
  "registered_model_name": "<string>",
  "airflow_dag_id": "<string>",
  "airflow_dag_url": "<string>",
  "error_message": "<string>",
  "feature_engineering_job_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a"
}

Documentation Index

Fetch the complete documentation index at: https://docs.nx1cloud.com/llms.txt

Use this file to discover all available pages before exploring further.

Authorizations

​
Authorization
string
header
required

The access token received from the authorization server in the OAuth 2.0 flow.

Body

application/json

Request to train an AutoML model.

Required field presence depends on problem_type; see the matrix in the module docstring. Combinations are enforced by _validate_shape.

​
name
string
required

Human-readable training run name.

​
domain
string
required

Business domain for governance.

​
owner
string
required

Username who owns this run.

​
source_table
string
required

Fully qualified Iceberg training table (catalog.schema.table).

​
problem_type
enum<string>
required

Supervised / unsupervised problem categories.

Available options:
binary_classification,
multiclass_classification,
regression,
ranking,
anomaly_detection,
contextual_bandit
​
algorithm
enum<string>
required

Supported AutoML algorithms.

Available options:
lightgbm_classifier,
lightgbm_regressor,
lightgbm_ranker,
isolation_forest,
vw_classifier,
vw_regressor,
vw_contextual_bandit
​
preset
enum<string>
default:balanced

Tuning presets shared across algorithms.

Available options:
fast,
balanced,
best_quality
​
label_column
string | null
​
positive_class_value
any | null

Value treated as the positive class for binary classification.

​
feature_columns
string[] | null

Override feature columns; if omitted, the DAG infers from the schema.

​
group_column
string | null

Group/query identifier for ranking.

​
action_column
string | null
​
reward_column
string | null
​
probability_column
string | null
​
context_columns
string[] | null
​
train_split_cutoff
string | null

ISO date string. Rows with the time column < cutoff go to train, >= cutoff to test. Optional; default 80/20 random split.

​
time_column
string | null

Column used by train_split_cutoff. Required if cutoff is set.

​
hyperparameter_overrides
Hyperparameter Overrides · object
​
enable_shap
boolean
default:true
​
experiment_name
string | null
​
registered_model_name
string | null
​
feature_engineering_job_id
string<uuid> | null
​
trigger_now
boolean
default:true

Response

Job created with rendered DAG.

A persisted training job.

​
job_id
string<uuid>
required
​
name
string
required
​
domain
string
required
​
owner
string
required
​
source_table
string
required
​
problem_type
enum<string>
required

Supervised / unsupervised problem categories.

Available options:
binary_classification,
multiclass_classification,
regression,
ranking,
anomaly_detection,
contextual_bandit
​
algorithm
enum<string>
required

Supported AutoML algorithms.

Available options:
lightgbm_classifier,
lightgbm_regressor,
lightgbm_ranker,
isolation_forest,
vw_classifier,
vw_regressor,
vw_contextual_bandit
​
preset
enum<string>
required

Tuning presets shared across algorithms.

Available options:
fast,
balanced,
best_quality
​
status
enum<string>
required

Lifecycle of an AutoML training job.

READY — DAG uploaded but not yet triggered. The user opted out of auto-trigger at create time. Manual trigger flips it to QUEUED. QUEUED — DAG triggered, waiting for Airflow to pick it up. RUNNING — Airflow has the run going. COMPLETE/FAILED — terminal.

Available options:
ready,
queued,
running,
complete,
failed
​
created_at
string<date-time>
required
​
updated_at
string<date-time>
required
​
rendered_dag
string | null

The rendered DAG source. Populated on creation.

​
mlflow_run_id
string | null
​
mlflow_experiment_name
string | null
​
registered_model_name
string | null
​
airflow_dag_id
string | null
​
airflow_dag_url
string | null
​
error_message
string | null
​
feature_engineering_job_id
string<uuid> | null