Mitigation Retraining¶
This page outlines the operations, endpoints, parameters, and example requests and responses for the Mitigation Retraining.
GET /api/v2/deployments/{deploymentId}/retrainingPolicies/¶
Retrieve a list of deployment retraining policies.
Code samples¶
curl -X GET https://app.datarobot.com/api/v2/deployments/{deploymentId}/retrainingPolicies/ \
-H "Accept: application/json" \
-H "Authorization: Bearer {access-token}"
Parameters
Name | In | Type | Required | Description |
---|---|---|---|---|
offset | query | integer | false | Number of results to skip. |
limit | query | integer | false | At most this many results are returned. The default may change without notice. |
deploymentId | path | string | true | Unique identifier of the deployment. |
Example responses¶
200 Response
{
"count": 0,
"data": [
{
"action": "create_challenger",
"autopilotOptions": {
"blendBestModels": true,
"mode": "auto",
"runLeakageRemovedFeatureList": true,
"scoringCodeOnly": true,
"shapOnlyMode": true
},
"description": "string",
"featureListStrategy": "informative_features",
"id": "string",
"latestRun": {
"challengerId": "string",
"errorMessage": "string",
"finishTime": "2019-08-24T14:15:22Z",
"id": "string",
"modelPackageId": "string",
"projectId": "string",
"registeredModelId": "string",
"startTime": "2019-08-24T14:15:22Z",
"status": "string",
"useCaseId": "string"
},
"modelSelectionStrategy": "autopilot_recommended",
"name": "string",
"projectOptions": {
"cvMethod": "RandomCV",
"holdoutPct": null,
"metric": "Accuracy",
"reps": null,
"validationPct": null,
"validationType": "CV"
},
"projectOptionsStrategy": "same_as_champion",
"timeSeriesOptions": {
"calendarId": "string",
"differencingMethod": "auto",
"exponentiallyWeightedMovingAlpha": 1,
"periodicities": [
{
"timeSteps": 0,
"timeUnit": "MILLISECOND"
}
],
"treatAsExponential": "auto"
},
"trigger": {
"minIntervalBetweenRuns": "string",
"schedule": {
"dayOfMonth": [
"*"
],
"dayOfWeek": [
"*"
],
"hour": [
"*"
],
"minute": [
"*"
],
"month": [
"*"
]
},
"statusDeclinesToFailing": true,
"statusDeclinesToWarning": true,
"statusStillInDecline": true,
"type": "schedule"
}
}
],
"next": "http://example.com",
"previous": "http://example.com",
"totalCount": 0
}
Responses¶
Status | Meaning | Description | Schema |
---|---|---|---|
200 | OK | Retrieve a list of deployment retraining policies. | RetrainingPolicyListResponse |
404 | Not Found | Deployment not found. | None |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
POST /api/v2/deployments/{deploymentId}/retrainingPolicies/¶
Create a deployment retraining policy.
Code samples¶
curl -X POST https://app.datarobot.com/api/v2/deployments/{deploymentId}/retrainingPolicies/ \
-H "Content-Type: application/json" \
-H "Accept: application/json" \
-H "Authorization: Bearer {access-token}" \
-d '{undefined}'
Body parameter¶
{
"action": "create_challenger",
"autopilotOptions": {
"blendBestModels": true,
"mode": "auto",
"runLeakageRemovedFeatureList": true,
"scoringCodeOnly": true,
"shapOnlyMode": true
},
"description": null,
"featureListStrategy": "informative_features",
"modelSelectionStrategy": "autopilot_recommended",
"name": "string",
"projectOptions": {
"cvMethod": "RandomCV",
"holdoutPct": null,
"metric": "Accuracy",
"reps": null,
"validationPct": null,
"validationType": "CV"
},
"projectOptionsStrategy": "same_as_champion",
"timeSeriesOptions": {
"calendarId": "string",
"differencingMethod": "auto",
"exponentiallyWeightedMovingAlpha": 1,
"periodicities": [
{
"timeSteps": 0,
"timeUnit": "MILLISECOND"
}
],
"treatAsExponential": "auto"
},
"trigger": {
"minIntervalBetweenRuns": "string",
"schedule": {
"dayOfMonth": [
"*"
],
"dayOfWeek": [
"*"
],
"hour": [
"*"
],
"minute": [
"*"
],
"month": [
"*"
]
},
"statusDeclinesToFailing": true,
"statusDeclinesToWarning": true,
"statusStillInDecline": true,
"type": "schedule"
}
}
Parameters
Name | In | Type | Required | Description |
---|---|---|---|---|
deploymentId | path | string | true | Unique identifier of the deployment. |
body | body | RetrainingPolicyCreate | false | none |
Example responses¶
200 Response
{
"action": "create_challenger",
"autopilotOptions": {
"blendBestModels": true,
"mode": "auto",
"runLeakageRemovedFeatureList": true,
"scoringCodeOnly": true,
"shapOnlyMode": true
},
"description": "string",
"featureListStrategy": "informative_features",
"id": "string",
"latestRun": {
"challengerId": "string",
"errorMessage": "string",
"finishTime": "2019-08-24T14:15:22Z",
"id": "string",
"modelPackageId": "string",
"projectId": "string",
"registeredModelId": "string",
"startTime": "2019-08-24T14:15:22Z",
"status": "string",
"useCaseId": "string"
},
"modelSelectionStrategy": "autopilot_recommended",
"name": "string",
"projectOptions": {
"cvMethod": "RandomCV",
"holdoutPct": null,
"metric": "Accuracy",
"reps": null,
"validationPct": null,
"validationType": "CV"
},
"projectOptionsStrategy": "same_as_champion",
"timeSeriesOptions": {
"calendarId": "string",
"differencingMethod": "auto",
"exponentiallyWeightedMovingAlpha": 1,
"periodicities": [
{
"timeSteps": 0,
"timeUnit": "MILLISECOND"
}
],
"treatAsExponential": "auto"
},
"trigger": {
"minIntervalBetweenRuns": "string",
"schedule": {
"dayOfMonth": [
"*"
],
"dayOfWeek": [
"*"
],
"hour": [
"*"
],
"minute": [
"*"
],
"month": [
"*"
]
},
"statusDeclinesToFailing": true,
"statusDeclinesToWarning": true,
"statusStillInDecline": true,
"type": "schedule"
}
}
Responses¶
Status | Meaning | Description | Schema |
---|---|---|---|
200 | OK | none | RetrainingPolicyRetrieve |
404 | Not Found | Deployment not found. | None |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
DELETE /api/v2/deployments/{deploymentId}/retrainingPolicies/{retrainingPolicyId}/¶
Delete a deployment retraining policy.
Code samples¶
curl -X DELETE https://app.datarobot.com/api/v2/deployments/{deploymentId}/retrainingPolicies/{retrainingPolicyId}/ \
-H "Authorization: Bearer {access-token}"
Parameters
Name | In | Type | Required | Description |
---|---|---|---|---|
deploymentId | path | string | true | Unique identifier of the deployment. |
retrainingPolicyId | path | string | true | ID of the retraining policy. |
Responses¶
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
GET /api/v2/deployments/{deploymentId}/retrainingPolicies/{retrainingPolicyId}/¶
Retrieve a deployment retraining policy.
Code samples¶
curl -X GET https://app.datarobot.com/api/v2/deployments/{deploymentId}/retrainingPolicies/{retrainingPolicyId}/ \
-H "Accept: application/json" \
-H "Authorization: Bearer {access-token}"
Parameters
Name | In | Type | Required | Description |
---|---|---|---|---|
deploymentId | path | string | true | Unique identifier of the deployment. |
retrainingPolicyId | path | string | true | ID of the retraining policy. |
Example responses¶
200 Response
{
"action": "create_challenger",
"autopilotOptions": {
"blendBestModels": true,
"mode": "auto",
"runLeakageRemovedFeatureList": true,
"scoringCodeOnly": true,
"shapOnlyMode": true
},
"description": "string",
"featureListStrategy": "informative_features",
"id": "string",
"latestRun": {
"challengerId": "string",
"errorMessage": "string",
"finishTime": "2019-08-24T14:15:22Z",
"id": "string",
"modelPackageId": "string",
"projectId": "string",
"registeredModelId": "string",
"startTime": "2019-08-24T14:15:22Z",
"status": "string",
"useCaseId": "string"
},
"modelSelectionStrategy": "autopilot_recommended",
"name": "string",
"projectOptions": {
"cvMethod": "RandomCV",
"holdoutPct": null,
"metric": "Accuracy",
"reps": null,
"validationPct": null,
"validationType": "CV"
},
"projectOptionsStrategy": "same_as_champion",
"timeSeriesOptions": {
"calendarId": "string",
"differencingMethod": "auto",
"exponentiallyWeightedMovingAlpha": 1,
"periodicities": [
{
"timeSteps": 0,
"timeUnit": "MILLISECOND"
}
],
"treatAsExponential": "auto"
},
"trigger": {
"minIntervalBetweenRuns": "string",
"schedule": {
"dayOfMonth": [
"*"
],
"dayOfWeek": [
"*"
],
"hour": [
"*"
],
"minute": [
"*"
],
"month": [
"*"
]
},
"statusDeclinesToFailing": true,
"statusDeclinesToWarning": true,
"statusStillInDecline": true,
"type": "schedule"
}
}
Responses¶
Status | Meaning | Description | Schema |
---|---|---|---|
200 | OK | Retrieve a deployment retraining policy. | RetrainingPolicyRetrieve |
404 | Not Found | Deployment or retraining policy not found. | None |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
PATCH /api/v2/deployments/{deploymentId}/retrainingPolicies/{retrainingPolicyId}/¶
Update a deployment retraining policy.
Code samples¶
curl -X PATCH https://app.datarobot.com/api/v2/deployments/{deploymentId}/retrainingPolicies/{retrainingPolicyId}/ \
-H "Content-Type: application/json" \
-H "Accept: application/json" \
-H "Authorization: Bearer {access-token}" \
-d '{undefined}'
Body parameter¶
{
"action": "create_challenger",
"autopilotOptions": {
"blendBestModels": true,
"mode": "auto",
"runLeakageRemovedFeatureList": true,
"scoringCodeOnly": true,
"shapOnlyMode": true
},
"description": "string",
"featureListStrategy": "informative_features",
"modelSelectionStrategy": "autopilot_recommended",
"name": "string",
"projectOptions": {
"cvMethod": "RandomCV",
"holdoutPct": null,
"metric": "Accuracy",
"reps": null,
"validationPct": null,
"validationType": "CV"
},
"projectOptionsStrategy": "same_as_champion",
"timeSeriesOptions": {
"calendarId": "string",
"differencingMethod": "auto",
"exponentiallyWeightedMovingAlpha": 1,
"periodicities": [
{
"timeSteps": 0,
"timeUnit": "MILLISECOND"
}
],
"treatAsExponential": "auto"
},
"trigger": {
"minIntervalBetweenRuns": "string",
"schedule": {
"dayOfMonth": [
"*"
],
"dayOfWeek": [
"*"
],
"hour": [
"*"
],
"minute": [
"*"
],
"month": [
"*"
]
},
"statusDeclinesToFailing": true,
"statusDeclinesToWarning": true,
"statusStillInDecline": true,
"type": "schedule"
}
}
Parameters
Name | In | Type | Required | Description |
---|---|---|---|---|
deploymentId | path | string | true | Unique identifier of the deployment. |
retrainingPolicyId | path | string | true | ID of the retraining policy. |
body | body | RetrainingPolicyUpdate | false | none |
Example responses¶
200 Response
{
"action": "create_challenger",
"autopilotOptions": {
"blendBestModels": true,
"mode": "auto",
"runLeakageRemovedFeatureList": true,
"scoringCodeOnly": true,
"shapOnlyMode": true
},
"description": "string",
"featureListStrategy": "informative_features",
"id": "string",
"latestRun": {
"challengerId": "string",
"errorMessage": "string",
"finishTime": "2019-08-24T14:15:22Z",
"id": "string",
"modelPackageId": "string",
"projectId": "string",
"registeredModelId": "string",
"startTime": "2019-08-24T14:15:22Z",
"status": "string",
"useCaseId": "string"
},
"modelSelectionStrategy": "autopilot_recommended",
"name": "string",
"projectOptions": {
"cvMethod": "RandomCV",
"holdoutPct": null,
"metric": "Accuracy",
"reps": null,
"validationPct": null,
"validationType": "CV"
},
"projectOptionsStrategy": "same_as_champion",
"timeSeriesOptions": {
"calendarId": "string",
"differencingMethod": "auto",
"exponentiallyWeightedMovingAlpha": 1,
"periodicities": [
{
"timeSteps": 0,
"timeUnit": "MILLISECOND"
}
],
"treatAsExponential": "auto"
},
"trigger": {
"minIntervalBetweenRuns": "string",
"schedule": {
"dayOfMonth": [
"*"
],
"dayOfWeek": [
"*"
],
"hour": [
"*"
],
"minute": [
"*"
],
"month": [
"*"
]
},
"statusDeclinesToFailing": true,
"statusDeclinesToWarning": true,
"statusStillInDecline": true,
"type": "schedule"
}
}
Responses¶
Status | Meaning | Description | Schema |
---|---|---|---|
200 | OK | none | RetrainingPolicyRetrieve |
404 | Not Found | Deployment or retraining policy not found. | None |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
GET /api/v2/deployments/{deploymentId}/retrainingPolicies/{retrainingPolicyId}/runs/¶
Retrieve a list of deployment retraining policy runs.
Code samples¶
curl -X GET https://app.datarobot.com/api/v2/deployments/{deploymentId}/retrainingPolicies/{retrainingPolicyId}/runs/ \
-H "Accept: application/json" \
-H "Authorization: Bearer {access-token}"
Parameters
Name | In | Type | Required | Description |
---|---|---|---|---|
offset | query | integer | false | Number of results to skip. |
limit | query | integer | false | At most this many results are returned. The default may change without notice. |
deploymentId | path | string | true | Unique identifier of the deployment. |
retrainingPolicyId | path | string | true | ID of the retraining policy. |
Example responses¶
200 Response
{
"count": 0,
"data": [
{
"challengerId": "string",
"errorMessage": "string",
"finishTime": "2019-08-24T14:15:22Z",
"id": "string",
"modelPackageId": "string",
"projectId": "string",
"registeredModelId": "string",
"startTime": "2019-08-24T14:15:22Z",
"status": "string",
"useCaseId": "string"
}
],
"next": "http://example.com",
"previous": "http://example.com",
"totalCount": 0
}
Responses¶
Status | Meaning | Description | Schema |
---|---|---|---|
200 | OK | Retrieve a list of deployment retraining policy runs. | RetrainingPolicyRunListResponse |
404 | Not Found | Deployment or retraining policy not found. | None |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
POST /api/v2/deployments/{deploymentId}/retrainingPolicies/{retrainingPolicyId}/runs/¶
Initiate a deployment retraining policy run.
Code samples¶
curl -X POST https://app.datarobot.com/api/v2/deployments/{deploymentId}/retrainingPolicies/{retrainingPolicyId}/runs/ \
-H "Authorization: Bearer {access-token}"
Parameters
Name | In | Type | Required | Description |
---|---|---|---|---|
deploymentId | path | string | true | Unique identifier of the deployment. |
retrainingPolicyId | path | string | true | ID of the retraining policy. |
Responses¶
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
GET /api/v2/deployments/{deploymentId}/retrainingPolicies/{retrainingPolicyId}/runs/{runId}/¶
Retrieve a single deployment retraining policy run.
Code samples¶
curl -X GET https://app.datarobot.com/api/v2/deployments/{deploymentId}/retrainingPolicies/{retrainingPolicyId}/runs/{runId}/ \
-H "Accept: application/json" \
-H "Authorization: Bearer {access-token}"
Parameters
Name | In | Type | Required | Description |
---|---|---|---|---|
deploymentId | path | string | true | Unique identifier of the deployment. |
retrainingPolicyId | path | string | true | ID of the retraining policy. |
runId | path | string | true | ID of the retraining policy run. |
Example responses¶
200 Response
{
"challengerId": "string",
"errorMessage": "string",
"finishTime": "2019-08-24T14:15:22Z",
"id": "string",
"modelPackageId": "string",
"projectId": "string",
"registeredModelId": "string",
"startTime": "2019-08-24T14:15:22Z",
"status": "string",
"useCaseId": "string"
}
Responses¶
Status | Meaning | Description | Schema |
---|---|---|---|
200 | OK | Retrieve a single deployment retraining policy run. | RetrainingPolicyRunRetrieve |
404 | Not Found | Deployment or retraining policy not found. | None |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
PATCH /api/v2/deployments/{deploymentId}/retrainingPolicies/{retrainingPolicyId}/runs/{runId}/¶
Update a single deployment retraining policy run.
Code samples¶
curl -X PATCH https://app.datarobot.com/api/v2/deployments/{deploymentId}/retrainingPolicies/{retrainingPolicyId}/runs/{runId}/ \
-H "Content-Type: application/json" \
-H "Accept: application/json" \
-H "Authorization: Bearer {access-token}" \
-d '{undefined}'
Body parameter¶
{
"status": "cancelled"
}
Parameters
Name | In | Type | Required | Description |
---|---|---|---|---|
deploymentId | path | string | true | Unique identifier of the deployment. |
retrainingPolicyId | path | string | true | ID of the retraining policy. |
runId | path | string | true | ID of the retraining policy run. |
body | body | RetrainingPolicyRunUpdate | false | none |
Example responses¶
200 Response
{
"challengerId": "string",
"errorMessage": "string",
"finishTime": "2019-08-24T14:15:22Z",
"id": "string",
"modelPackageId": "string",
"projectId": "string",
"registeredModelId": "string",
"startTime": "2019-08-24T14:15:22Z",
"status": "string",
"useCaseId": "string"
}
Responses¶
Status | Meaning | Description | Schema |
---|---|---|---|
200 | OK | Update a single deployment retraining policy run. | RetrainingPolicyRunRetrieve |
404 | Not Found | Deployment or retraining policy not found. | None |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
GET /api/v2/deployments/{deploymentId}/retrainingSettings/¶
Retrieve deployment retraining settings.
Code samples¶
curl -X GET https://app.datarobot.com/api/v2/deployments/{deploymentId}/retrainingSettings/ \
-H "Accept: application/json" \
-H "Authorization: Bearer {access-token}"
Parameters
Name | In | Type | Required | Description |
---|---|---|---|---|
deploymentId | path | string | true | Unique identifier of the deployment. |
Example responses¶
200 Response
{
"dataset": {
"id": "string",
"name": "string"
},
"predictionEnvironment": {
"id": "string",
"name": "string"
},
"retrainingUser": {
"id": "string",
"username": "string"
}
}
Responses¶
Status | Meaning | Description | Schema |
---|---|---|---|
200 | OK | Retrieve deployment retraining settings. | RetrainingSettingsRetrieve |
404 | Not Found | Deployment not found. | None |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
PATCH /api/v2/deployments/{deploymentId}/retrainingSettings/¶
Update deployment retraining settings.
Code samples¶
curl -X PATCH https://app.datarobot.com/api/v2/deployments/{deploymentId}/retrainingSettings/ \
-H "Content-Type: application/json" \
-H "Authorization: Bearer {access-token}" \
-d '{undefined}'
Body parameter¶
{
"credentialId": "string",
"datasetId": "string",
"predictionEnvironmentId": "string",
"retrainingUserId": "string"
}
Parameters
Name | In | Type | Required | Description |
---|---|---|---|---|
deploymentId | path | string | true | Unique identifier of the deployment. |
body | body | RetrainingSettingsUpdate | false | none |
Responses¶
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
Schemas¶
AutopilotOptions
{
"blendBestModels": true,
"mode": "auto",
"runLeakageRemovedFeatureList": true,
"scoringCodeOnly": true,
"shapOnlyMode": true
}
Options for projects used to build new models.
Properties¶
Name | Type | Required | Restrictions | Description |
---|---|---|---|---|
blendBestModels | boolean | false | Blend best models during Autopilot run. This option is not supported in SHAP-only mode. | |
mode | string | false | The autopilot mode. | |
runLeakageRemovedFeatureList | boolean | false | Run Autopilot on Leakage Removed feature list (if exists). | |
scoringCodeOnly | boolean | false | Keep only models that can be converted to scorable java code during Autopilot run. | |
shapOnlyMode | boolean | false | Include only models with SHAP value support. |
Enumerated Values¶
Property | Value |
---|---|
mode | [auto , comprehensive , quick ] |
Dataset
{
"id": "string",
"name": "string"
}
The dataset that will be used as retraining data.
Properties¶
Name | Type | Required | Restrictions | Description |
---|---|---|---|---|
id | string | true | ID of the retraining dataset. | |
name | string | true | Name of the retraining dataset. |
Periodicity
{
"timeSteps": 0,
"timeUnit": "MILLISECOND"
}
Properties¶
Name | Type | Required | Restrictions | Description |
---|---|---|---|---|
timeSteps | integer | true | minimum: 0 |
The number of time steps. |
timeUnit | string | true | The time unit or ROW if windowsBasisUnit is ROW |
Enumerated Values¶
Property | Value |
---|---|
timeUnit | [MILLISECOND , SECOND , MINUTE , HOUR , DAY , WEEK , MONTH , QUARTER , YEAR , ROW ] |
PredictionEnvironment
{
"id": "string",
"name": "string"
}
The prediction environment that will be associated with the challengers created by retraining policies.
Properties¶
Name | Type | Required | Restrictions | Description |
---|---|---|---|---|
id | string | true | ID of the prediction environment. | |
name | string | true | Name of the prediction environment. |
ProjectOptions
{
"cvMethod": "RandomCV",
"holdoutPct": null,
"metric": "Accuracy",
"reps": null,
"validationPct": null,
"validationType": "CV"
}
Options for projects used to build new models.
Properties¶
Name | Type | Required | Restrictions | Description |
---|---|---|---|---|
cvMethod | string | false | The partitioning method for projects used to build new models. | |
holdoutPct | number,null | false | maximum: 98 minimum: 0 |
The percentage of dataset to assign to holdout set in projects used to build new models. |
metric | string,null | false | The model selection metric in projects used to build new models. | |
reps | integer,null | false | maximum: 50 minimum: 2 |
The number of cross validation folds to use for projects used to build new models. |
validationPct | number,null | false | maximum: 99 minimum: 1 |
The percentage of dataset to assign to validation set in projects used to build new models. |
validationType | string | false | The validation type for projects used to build new models. |
Enumerated Values¶
Property | Value |
---|---|
cvMethod | [RandomCV , StratifiedCV ] |
metric | [Accuracy , AUC , Balanced Accuracy , FVE Binomial , Gini Norm , Kolmogorov-Smirnov , LogLoss , Rate@Top5% , Rate@Top10% , TPR , FPR , TNR , PPV , NPV , F1 , MCC , FVE Gamma , FVE Poisson , FVE Tweedie , Gamma Deviance , MAE , MAPE , Poisson Deviance , R Squared , RMSE , RMSLE , Tweedie Deviance , null ] |
validationType | [CV , TVH ] |
RetrainingPolicyCreate
{
"action": "create_challenger",
"autopilotOptions": {
"blendBestModels": true,
"mode": "auto",
"runLeakageRemovedFeatureList": true,
"scoringCodeOnly": true,
"shapOnlyMode": true
},
"description": null,
"featureListStrategy": "informative_features",
"modelSelectionStrategy": "autopilot_recommended",
"name": "string",
"projectOptions": {
"cvMethod": "RandomCV",
"holdoutPct": null,
"metric": "Accuracy",
"reps": null,
"validationPct": null,
"validationType": "CV"
},
"projectOptionsStrategy": "same_as_champion",
"timeSeriesOptions": {
"calendarId": "string",
"differencingMethod": "auto",
"exponentiallyWeightedMovingAlpha": 1,
"periodicities": [
{
"timeSteps": 0,
"timeUnit": "MILLISECOND"
}
],
"treatAsExponential": "auto"
},
"trigger": {
"minIntervalBetweenRuns": "string",
"schedule": {
"dayOfMonth": [
"*"
],
"dayOfWeek": [
"*"
],
"hour": [
"*"
],
"minute": [
"*"
],
"month": [
"*"
]
},
"statusDeclinesToFailing": true,
"statusDeclinesToWarning": true,
"statusStillInDecline": true,
"type": "schedule"
}
}
Properties¶
Name | Type | Required | Restrictions | Description |
---|---|---|---|---|
action | string | false | Configure the action to take on the resultant new model. | |
autopilotOptions | AutopilotOptions | false | Options for projects used to build new models. | |
description | string,null | true | maxLength: 10000 |
Description of the retraining policy. |
featureListStrategy | string | false | Configure the feature list strategy used for modeling. | |
modelSelectionStrategy | string | false | Configure how new model is selected when the retraining policy runs. | |
name | string | true | maxLength: 512 |
Name of the retraining policy. |
projectOptions | ProjectOptions | false | Options for projects used to build new models. | |
projectOptionsStrategy | string | false | Configure the project option strategy used for modeling. | |
timeSeriesOptions | TimeSeriesOptions | false | Time Series project option used to build new models. | |
trigger | Trigger | false | Retraining policy trigger. |
Enumerated Values¶
Property | Value |
---|---|
action | [create_challenger , create_model_package , model_replacement ] |
featureListStrategy | [informative_features , same_as_champion ] |
modelSelectionStrategy | [autopilot_recommended , same_blueprint , same_hyperparameters , custom_job ] |
projectOptionsStrategy | [same_as_champion , override_champion , custom ] |
RetrainingPolicyListResponse
{
"count": 0,
"data": [
{
"action": "create_challenger",
"autopilotOptions": {
"blendBestModels": true,
"mode": "auto",
"runLeakageRemovedFeatureList": true,
"scoringCodeOnly": true,
"shapOnlyMode": true
},
"description": "string",
"featureListStrategy": "informative_features",
"id": "string",
"latestRun": {
"challengerId": "string",
"errorMessage": "string",
"finishTime": "2019-08-24T14:15:22Z",
"id": "string",
"modelPackageId": "string",
"projectId": "string",
"registeredModelId": "string",
"startTime": "2019-08-24T14:15:22Z",
"status": "string",
"useCaseId": "string"
},
"modelSelectionStrategy": "autopilot_recommended",
"name": "string",
"projectOptions": {
"cvMethod": "RandomCV",
"holdoutPct": null,
"metric": "Accuracy",
"reps": null,
"validationPct": null,
"validationType": "CV"
},
"projectOptionsStrategy": "same_as_champion",
"timeSeriesOptions": {
"calendarId": "string",
"differencingMethod": "auto",
"exponentiallyWeightedMovingAlpha": 1,
"periodicities": [
{
"timeSteps": 0,
"timeUnit": "MILLISECOND"
}
],
"treatAsExponential": "auto"
},
"trigger": {
"minIntervalBetweenRuns": "string",
"schedule": {
"dayOfMonth": [
"*"
],
"dayOfWeek": [
"*"
],
"hour": [
"*"
],
"minute": [
"*"
],
"month": [
"*"
]
},
"statusDeclinesToFailing": true,
"statusDeclinesToWarning": true,
"statusStillInDecline": true,
"type": "schedule"
}
}
],
"next": "http://example.com",
"previous": "http://example.com",
"totalCount": 0
}
Properties¶
Name | Type | Required | Restrictions | Description |
---|---|---|---|---|
count | integer | false | Number of items returned on this page. | |
data | [RetrainingPolicyRetrieve] | true | List of retraining policies. | |
next | string,null(uri) | true | URL pointing to the next page (if null, there is no next page). | |
previous | string,null(uri) | true | URL pointing to the previous page (if null, there is no previous page). | |
totalCount | integer | true | The total number of items across all pages. |
RetrainingPolicyRetrieve
{
"action": "create_challenger",
"autopilotOptions": {
"blendBestModels": true,
"mode": "auto",
"runLeakageRemovedFeatureList": true,
"scoringCodeOnly": true,
"shapOnlyMode": true
},
"description": "string",
"featureListStrategy": "informative_features",
"id": "string",
"latestRun": {
"challengerId": "string",
"errorMessage": "string",
"finishTime": "2019-08-24T14:15:22Z",
"id": "string",
"modelPackageId": "string",
"projectId": "string",
"registeredModelId": "string",
"startTime": "2019-08-24T14:15:22Z",
"status": "string",
"useCaseId": "string"
},
"modelSelectionStrategy": "autopilot_recommended",
"name": "string",
"projectOptions": {
"cvMethod": "RandomCV",
"holdoutPct": null,
"metric": "Accuracy",
"reps": null,
"validationPct": null,
"validationType": "CV"
},
"projectOptionsStrategy": "same_as_champion",
"timeSeriesOptions": {
"calendarId": "string",
"differencingMethod": "auto",
"exponentiallyWeightedMovingAlpha": 1,
"periodicities": [
{
"timeSteps": 0,
"timeUnit": "MILLISECOND"
}
],
"treatAsExponential": "auto"
},
"trigger": {
"minIntervalBetweenRuns": "string",
"schedule": {
"dayOfMonth": [
"*"
],
"dayOfWeek": [
"*"
],
"hour": [
"*"
],
"minute": [
"*"
],
"month": [
"*"
]
},
"statusDeclinesToFailing": true,
"statusDeclinesToWarning": true,
"statusStillInDecline": true,
"type": "schedule"
}
}
Properties¶
Name | Type | Required | Restrictions | Description |
---|---|---|---|---|
action | string | true | Configure the action to take on the resultant new model. | |
autopilotOptions | AutopilotOptions | true | Options for projects used to build new models. | |
description | string,null | true | Description of the retraining policy. | |
featureListStrategy | string | false | Configure the feature list strategy used for modeling. | |
id | string | true | ID of the retraining policy. | |
latestRun | RetrainingPolicyRunRetrieve | true | Latest run of the retraining policy. | |
modelSelectionStrategy | string | true | Configure how new model is selected when the retraining policy runs. | |
name | string | true | Name of the retraining policy. | |
projectOptions | ProjectOptions | true | Options for projects used to build new models. | |
projectOptionsStrategy | string | false | Configure the project option strategy used for modeling. | |
timeSeriesOptions | TimeSeriesOptions | false | Time Series project option used to build new models. | |
trigger | Trigger | true | Retraining policy trigger. |
Enumerated Values¶
Property | Value |
---|---|
action | [create_challenger , create_model_package , model_replacement ] |
featureListStrategy | [informative_features , same_as_champion ] |
modelSelectionStrategy | [autopilot_recommended , same_blueprint , same_hyperparameters , custom_job ] |
projectOptionsStrategy | [same_as_champion , override_champion , custom ] |
RetrainingPolicyRunListResponse
{
"count": 0,
"data": [
{
"challengerId": "string",
"errorMessage": "string",
"finishTime": "2019-08-24T14:15:22Z",
"id": "string",
"modelPackageId": "string",
"projectId": "string",
"registeredModelId": "string",
"startTime": "2019-08-24T14:15:22Z",
"status": "string",
"useCaseId": "string"
}
],
"next": "http://example.com",
"previous": "http://example.com",
"totalCount": 0
}
Properties¶
Name | Type | Required | Restrictions | Description |
---|---|---|---|---|
count | integer | false | Number of items returned on this page. | |
data | [RetrainingPolicyRunRetrieve] | true | List of retraining policy runs. | |
next | string,null(uri) | true | URL pointing to the next page (if null, there is no next page). | |
previous | string,null(uri) | true | URL pointing to the previous page (if null, there is no previous page). | |
totalCount | integer | true | The total number of items across all pages. |
RetrainingPolicyRunRetrieve
{
"challengerId": "string",
"errorMessage": "string",
"finishTime": "2019-08-24T14:15:22Z",
"id": "string",
"modelPackageId": "string",
"projectId": "string",
"registeredModelId": "string",
"startTime": "2019-08-24T14:15:22Z",
"status": "string",
"useCaseId": "string"
}
Latest run of the retraining policy.
Properties¶
Name | Type | Required | Restrictions | Description |
---|---|---|---|---|
challengerId | string,null | true | ID of the challenger created from this retraining policy run. | |
errorMessage | string,null | true | Error message of the retraining policy run. | |
finishTime | string,null(date-time) | true | Finish time of the retraining policy run. | |
id | string,null | true | ID of the retraining policy run. | |
modelPackageId | string,null | true | ID of the model package created from this retraining policy run. | |
projectId | string,null | true | ID of the project created from this retraining policy run. | |
registeredModelId | string,null | true | ID of the registered model associated with model package created from this retraining policy run | |
startTime | string,null(date-time) | true | Start time of the retraining policy run. | |
status | string,null | true | Status of the retraining policy run. | |
useCaseId | string,null | false | The ID of the Use Case associated with the model package created from this retraining policy run. |
RetrainingPolicyRunUpdate
{
"status": "cancelled"
}
Properties¶
Name | Type | Required | Restrictions | Description |
---|---|---|---|---|
status | string | true | New status of the retraining policy. |
Enumerated Values¶
Property | Value |
---|---|
status | cancelled |
RetrainingPolicyUpdate
{
"action": "create_challenger",
"autopilotOptions": {
"blendBestModels": true,
"mode": "auto",
"runLeakageRemovedFeatureList": true,
"scoringCodeOnly": true,
"shapOnlyMode": true
},
"description": "string",
"featureListStrategy": "informative_features",
"modelSelectionStrategy": "autopilot_recommended",
"name": "string",
"projectOptions": {
"cvMethod": "RandomCV",
"holdoutPct": null,
"metric": "Accuracy",
"reps": null,
"validationPct": null,
"validationType": "CV"
},
"projectOptionsStrategy": "same_as_champion",
"timeSeriesOptions": {
"calendarId": "string",
"differencingMethod": "auto",
"exponentiallyWeightedMovingAlpha": 1,
"periodicities": [
{
"timeSteps": 0,
"timeUnit": "MILLISECOND"
}
],
"treatAsExponential": "auto"
},
"trigger": {
"minIntervalBetweenRuns": "string",
"schedule": {
"dayOfMonth": [
"*"
],
"dayOfWeek": [
"*"
],
"hour": [
"*"
],
"minute": [
"*"
],
"month": [
"*"
]
},
"statusDeclinesToFailing": true,
"statusDeclinesToWarning": true,
"statusStillInDecline": true,
"type": "schedule"
}
}
Properties¶
Name | Type | Required | Restrictions | Description |
---|---|---|---|---|
action | string | false | Configure the action to take on the resultant new model. | |
autopilotOptions | AutopilotOptions | false | Options for projects used to build new models. | |
description | string,null | false | maxLength: 10000 |
Description of the retraining policy. |
featureListStrategy | string | false | Configure the feature list strategy used for modeling. | |
modelSelectionStrategy | string | false | Configure how new model is selected when the retraining policy runs. | |
name | string | false | maxLength: 512 |
Name of the retraining policy. |
projectOptions | ProjectOptions | false | Options for projects used to build new models. | |
projectOptionsStrategy | string | false | Configure the project option strategy used for modeling. | |
timeSeriesOptions | TimeSeriesOptions | false | Time Series project option used to build new models. | |
trigger | Trigger | false | Retraining policy trigger. |
Enumerated Values¶
Property | Value |
---|---|
action | [create_challenger , create_model_package , model_replacement ] |
featureListStrategy | [informative_features , same_as_champion ] |
modelSelectionStrategy | [autopilot_recommended , same_blueprint , same_hyperparameters , custom_job ] |
projectOptionsStrategy | [same_as_champion , override_champion , custom ] |
RetrainingSettingsRetrieve
{
"dataset": {
"id": "string",
"name": "string"
},
"predictionEnvironment": {
"id": "string",
"name": "string"
},
"retrainingUser": {
"id": "string",
"username": "string"
}
}
Properties¶
Name | Type | Required | Restrictions | Description |
---|---|---|---|---|
dataset | Dataset | true | The dataset that will be used as retraining data. | |
predictionEnvironment | PredictionEnvironment | true | The prediction environment that will be associated with the challengers created by retraining policies. | |
retrainingUser | RetrainingUser | true | The user scheduled retraining will be performed on behalf of. |
RetrainingSettingsUpdate
{
"credentialId": "string",
"datasetId": "string",
"predictionEnvironmentId": "string",
"retrainingUserId": "string"
}
Properties¶
Name | Type | Required | Restrictions | Description |
---|---|---|---|---|
credentialId | string,null | false | ID of the credential used to refresh retraining dataset. | |
datasetId | string,null | false | ID of the retraining dataset. | |
predictionEnvironmentId | string,null | false | ID of the prediction environment to associate with the challengers created by retraining policies. | |
retrainingUserId | string | false | ID of the retraining user. |
RetrainingUser
{
"id": "string",
"username": "string"
}
The user scheduled retraining will be performed on behalf of.
Properties¶
Name | Type | Required | Restrictions | Description |
---|---|---|---|---|
id | string | true | ID of the scheduled retraining user. | |
username | string | true | Username of the scheduled retraining user. |
Schedule
{
"dayOfMonth": [
"*"
],
"dayOfWeek": [
"*"
],
"hour": [
"*"
],
"minute": [
"*"
],
"month": [
"*"
]
}
The scheduling information defining how often and when to execute this job to the Job Scheduling service. Optional if enabled = False.
Properties¶
Name | Type | Required | Restrictions | Description |
---|---|---|---|---|
dayOfMonth | [number,string] | true | maxItems: 31 |
The date(s) of the month that the job will run. Allowed values are either [1 ... 31] or ["*"] for all days of the month. This field is additive with dayOfWeek , meaning the job will run both on the date(s) defined in this field and the day specified by dayOfWeek (for example, dates 1st, 2nd, 3rd, plus every Tuesday). If dayOfMonth is set to ["*"] and dayOfWeek is defined, the scheduler will trigger on every day of the month that matches dayOfWeek (for example, Tuesday the 2nd, 9th, 16th, 23rd, 30th). Invalid dates such as February 31st are ignored. |
dayOfWeek | [number,string] | true | maxItems: 7 |
The day(s) of the week that the job will run. Allowed values are [0 .. 6] , where (Sunday=0), or ["*"] , for all days of the week. Strings, either 3-letter abbreviations or the full name of the day, can be used interchangeably (e.g., "sunday", "Sunday", "sun", or "Sun", all map to [0] . This field is additive with dayOfMonth , meaning the job will run both on the date specified by dayOfMonth and the day defined in this field. |
hour | [number,string] | true | maxItems: 24 |
The hour(s) of the day that the job will run. Allowed values are either ["*"] meaning every hour of the day or [0 ... 23] . |
minute | [number,string] | true | maxItems: 60 |
The minute(s) of the day that the job will run. Allowed values are either ["*"] meaning every minute of the day or[0 ... 59] . |
month | [number,string] | true | maxItems: 12 |
The month(s) of the year that the job will run. Allowed values are either [1 ... 12] or ["*"] for all months of the year. Strings, either 3-letter abbreviations or the full name of the month, can be used interchangeably (e.g., "jan" or "october"). Months that are not compatible with dayOfMonth are ignored, for example {"dayOfMonth": [31], "month":["feb"]} . |
TimeSeriesOptions
{
"calendarId": "string",
"differencingMethod": "auto",
"exponentiallyWeightedMovingAlpha": 1,
"periodicities": [
{
"timeSteps": 0,
"timeUnit": "MILLISECOND"
}
],
"treatAsExponential": "auto"
}
Time Series project option used to build new models.
Properties¶
Name | Type | Required | Restrictions | Description |
---|---|---|---|---|
calendarId | string,null | false | The ID of the calendar to be used in this project. | |
differencingMethod | string,null | false | For time series projects only. Used to specify which differencing method to apply if the data is stationary. For classification problems simple and seasonal are not allowed. Parameter periodicities must be specified if seasonal is chosen. Defaults to auto . |
|
exponentiallyWeightedMovingAlpha | number,null | false | maximum: 1 |
Discount factor (alpha) used for exponentially weighted moving features |
periodicities | [Periodicity] | false | A list of periodicities for time series projects only. For classification problems periodicities are not allowed. If this is provided, parameter 'differencing_method' will default to 'seasonal' if not provided or 'auto'. | |
treatAsExponential | string,null | false | For time series projects only. Used to specify whether to treat data as exponential trend and apply transformations like log-transform. For classification problems always is not allowed. Defaults to auto . |
Enumerated Values¶
Property | Value |
---|---|
differencingMethod | [auto , none , simple , seasonal ] |
treatAsExponential | [auto , never , always ] |
Trigger
{
"minIntervalBetweenRuns": "string",
"schedule": {
"dayOfMonth": [
"*"
],
"dayOfWeek": [
"*"
],
"hour": [
"*"
],
"minute": [
"*"
],
"month": [
"*"
]
},
"statusDeclinesToFailing": true,
"statusDeclinesToWarning": true,
"statusStillInDecline": true,
"type": "schedule"
}
Retraining policy trigger.
Properties¶
Name | Type | Required | Restrictions | Description |
---|---|---|---|---|
minIntervalBetweenRuns | string,null | false | Minimal interval between policy runs in ISO 8601 duration string. | |
schedule | Schedule | false | The scheduling information defining how often and when to execute this job to the Job Scheduling service. Optional if enabled = False. | |
statusDeclinesToFailing | boolean | false | Identifies when trigger type is based on deployment a health status, whether the policy will run when health status declines to failing. | |
statusDeclinesToWarning | boolean | false | Identifies when trigger type is based on deployment a health status, whether the policy will run when health status declines to warning. | |
statusStillInDecline | boolean,null | false | Identifies when trigger type is based on deployment a health status, whether the policy will run when health status still in decline. | |
type | string | true | Type of retraining policy trigger. |
Enumerated Values¶
Property | Value |
---|---|
type | [schedule , data_drift_decline , accuracy_decline , custom_job , null ] |