| Copyright | (c) 2013-2021 Brendan Hay |
|---|---|
| License | Mozilla Public License, v. 2.0. |
| Maintainer | Brendan Hay <brendan.g.hay+amazonka@gmail.com> |
| Stability | auto-generated |
| Portability | non-portable (GHC extensions) |
| Safe Haskell | None |
Amazonka.Personalize.CreateSolution
Description
Creates the configuration for training a model. A trained model is known
as a solution. After the configuration is created, you train the model
(create a solution) by calling the CreateSolutionVersion operation.
Every time you call CreateSolutionVersion, a new version of the
solution is created.
After creating a solution version, you check its accuracy by calling GetSolutionMetrics. When you are satisfied with the version, you deploy it using CreateCampaign. The campaign provides recommendations to a client through the GetRecommendations API.
To train a model, Amazon Personalize requires training data and a
recipe. The training data comes from the dataset group that you provide
in the request. A recipe specifies the training algorithm and a feature
transformation. You can specify one of the predefined recipes provided
by Amazon Personalize. Alternatively, you can specify performAutoML
and Amazon Personalize will analyze your data and select the optimum
USER_PERSONALIZATION recipe for you.
Amazon Personalize doesn't support configuring the hpoObjective for
solution hyperparameter optimization at this time.
Status
A solution can be in one of the following states:
- CREATE PENDING > CREATE IN_PROGRESS > ACTIVE -or- CREATE FAILED
- DELETE PENDING > DELETE IN_PROGRESS
To get the status of the solution, call DescribeSolution. Wait until the
status shows as ACTIVE before calling CreateSolutionVersion.
Related APIs
- ListSolutions
- CreateSolutionVersion
- DescribeSolution
- DeleteSolution
- ListSolutionVersions
- DescribeSolutionVersion
Synopsis
- data CreateSolution = CreateSolution' {}
- newCreateSolution :: Text -> Text -> CreateSolution
- createSolution_performAutoML :: Lens' CreateSolution (Maybe Bool)
- createSolution_recipeArn :: Lens' CreateSolution (Maybe Text)
- createSolution_eventType :: Lens' CreateSolution (Maybe Text)
- createSolution_solutionConfig :: Lens' CreateSolution (Maybe SolutionConfig)
- createSolution_performHPO :: Lens' CreateSolution (Maybe Bool)
- createSolution_name :: Lens' CreateSolution Text
- createSolution_datasetGroupArn :: Lens' CreateSolution Text
- data CreateSolutionResponse = CreateSolutionResponse' {
- solutionArn :: Maybe Text
- httpStatus :: Int
- newCreateSolutionResponse :: Int -> CreateSolutionResponse
- createSolutionResponse_solutionArn :: Lens' CreateSolutionResponse (Maybe Text)
- createSolutionResponse_httpStatus :: Lens' CreateSolutionResponse Int
Creating a Request
data CreateSolution Source #
See: newCreateSolution smart constructor.
Constructors
| CreateSolution' | |
Fields
| |
Instances
Arguments
| :: Text | |
| -> Text | |
| -> CreateSolution |
Create a value of CreateSolution with all optional fields omitted.
Use generic-lens or optics to modify other optional fields.
The following record fields are available, with the corresponding lenses provided for backwards compatibility:
$sel:performAutoML:CreateSolution', createSolution_performAutoML - Whether to perform automated machine learning (AutoML). The default is
false. For this case, you must specify recipeArn.
When set to true, Amazon Personalize analyzes your training data and
selects the optimal USER_PERSONALIZATION recipe and hyperparameters. In
this case, you must omit recipeArn. Amazon Personalize determines the
optimal recipe by running tests with different values for the
hyperparameters. AutoML lengthens the training process as compared to
selecting a specific recipe.
$sel:recipeArn:CreateSolution', createSolution_recipeArn - The ARN of the recipe to use for model training. Only specified when
performAutoML is false.
$sel:eventType:CreateSolution', createSolution_eventType - When your have multiple event types (using an EVENT_TYPE schema
field), this parameter specifies which event type (for example,
'click' or 'like') is used for training the model.
If you do not provide an eventType, Amazon Personalize will use all
interactions for training with equal weight regardless of type.
$sel:solutionConfig:CreateSolution', createSolution_solutionConfig - The configuration to use with the solution. When performAutoML is set
to true, Amazon Personalize only evaluates the autoMLConfig section of
the solution configuration.
Amazon Personalize doesn't support configuring the hpoObjective at
this time.
$sel:performHPO:CreateSolution', createSolution_performHPO - Whether to perform hyperparameter optimization (HPO) on the specified or
selected recipe. The default is false.
When performing AutoML, this parameter is always true and you should
not set it to false.
$sel:name:CreateSolution', createSolution_name - The name for the solution.
$sel:datasetGroupArn:CreateSolution', createSolution_datasetGroupArn - The Amazon Resource Name (ARN) of the dataset group that provides the
training data.
Request Lenses
createSolution_performAutoML :: Lens' CreateSolution (Maybe Bool) Source #
Whether to perform automated machine learning (AutoML). The default is
false. For this case, you must specify recipeArn.
When set to true, Amazon Personalize analyzes your training data and
selects the optimal USER_PERSONALIZATION recipe and hyperparameters. In
this case, you must omit recipeArn. Amazon Personalize determines the
optimal recipe by running tests with different values for the
hyperparameters. AutoML lengthens the training process as compared to
selecting a specific recipe.
createSolution_recipeArn :: Lens' CreateSolution (Maybe Text) Source #
The ARN of the recipe to use for model training. Only specified when
performAutoML is false.
createSolution_eventType :: Lens' CreateSolution (Maybe Text) Source #
When your have multiple event types (using an EVENT_TYPE schema
field), this parameter specifies which event type (for example,
'click' or 'like') is used for training the model.
If you do not provide an eventType, Amazon Personalize will use all
interactions for training with equal weight regardless of type.
createSolution_solutionConfig :: Lens' CreateSolution (Maybe SolutionConfig) Source #
The configuration to use with the solution. When performAutoML is set
to true, Amazon Personalize only evaluates the autoMLConfig section of
the solution configuration.
Amazon Personalize doesn't support configuring the hpoObjective at
this time.
createSolution_performHPO :: Lens' CreateSolution (Maybe Bool) Source #
Whether to perform hyperparameter optimization (HPO) on the specified or
selected recipe. The default is false.
When performing AutoML, this parameter is always true and you should
not set it to false.
createSolution_name :: Lens' CreateSolution Text Source #
The name for the solution.
createSolution_datasetGroupArn :: Lens' CreateSolution Text Source #
The Amazon Resource Name (ARN) of the dataset group that provides the training data.
Destructuring the Response
data CreateSolutionResponse Source #
See: newCreateSolutionResponse smart constructor.
Constructors
| CreateSolutionResponse' | |
Fields
| |
Instances
newCreateSolutionResponse Source #
Create a value of CreateSolutionResponse with all optional fields omitted.
Use generic-lens or optics to modify other optional fields.
The following record fields are available, with the corresponding lenses provided for backwards compatibility:
$sel:solutionArn:CreateSolutionResponse', createSolutionResponse_solutionArn - The ARN of the solution.
$sel:httpStatus:CreateSolutionResponse', createSolutionResponse_httpStatus - The response's http status code.
Response Lenses
createSolutionResponse_solutionArn :: Lens' CreateSolutionResponse (Maybe Text) Source #
The ARN of the solution.
createSolutionResponse_httpStatus :: Lens' CreateSolutionResponse Int Source #
The response's http status code.