Amazonka.MachineLearning.Types.Evaluation

Documentation

data Evaluation

Represents the output of GetEvaluation operation.

The content consists of the detailed metadata and data file information and the current status of the Evaluation.

See: newEvaluation smart constructor.

Constructors

Evaluation'

Fields

• computeTime :: Maybe Integer
• createdAt :: Maybe POSIX

  The time that the Evaluation was created. The time is expressed in epoch time.

• createdByIamUser :: Maybe Text

  The AWS user account that invoked the evaluation. The account type can be either an AWS root account or an AWS Identity and Access Management (IAM) user account.

• evaluationDataSourceId :: Maybe Text

  The ID of the DataSource that is used to evaluate the MLModel.

• evaluationId :: Maybe Text

  The ID that is assigned to the Evaluation at creation.

• finishedAt :: Maybe POSIX
• inputDataLocationS3 :: Maybe Text

  The location and name of the data in Amazon Simple Storage Server (Amazon S3) that is used in the evaluation.

• lastUpdatedAt :: Maybe POSIX

  The time of the most recent edit to the Evaluation. The time is expressed in epoch time.

• mLModelId :: Maybe Text

  The ID of the MLModel that is the focus of the evaluation.

• message :: Maybe Text

  A description of the most recent details about evaluating the MLModel.

• name :: Maybe Text

  A user-supplied name or description of the Evaluation.

• performanceMetrics :: Maybe PerformanceMetrics

  Measurements of how well the MLModel performed, using observations referenced by the DataSource. One of the following metrics is returned, based on the type of the MLModel:

  • BinaryAUC: A binary MLModel uses the Area Under the Curve (AUC) technique to measure performance.
  • RegressionRMSE: A regression MLModel uses the Root Mean Square Error (RMSE) technique to measure performance. RMSE measures the difference between predicted and actual values for a single variable.
  • MulticlassAvgFScore: A multiclass MLModel uses the F1 score technique to measure performance.

  For more information about performance metrics, please see the Amazon Machine Learning Developer Guide.

• startedAt :: Maybe POSIX
• status :: Maybe EntityStatus

  The status of the evaluation. This element can have one of the following values:

  • PENDING - Amazon Machine Learning (Amazon ML) submitted a request to evaluate an MLModel.
  • INPROGRESS - The evaluation is underway.
  • FAILED - The request to evaluate an MLModel did not run to completion. It is not usable.
  • COMPLETED - The evaluation process completed successfully.
  • DELETED - The Evaluation is marked as deleted. It is not usable.

Instances

FromJSON Evaluation

Defined in Amazonka.MachineLearning.Types.Evaluation

Methods

parseJSON :: Value -> Parser Evaluation

parseJSONList :: Value -> Parser [Evaluation]

Generic Evaluation

Defined in Amazonka.MachineLearning.Types.Evaluation

Associated Types

type Rep Evaluation :: Type -> Type

Methods

from :: Evaluation -> Rep Evaluation x

to :: Rep Evaluation x -> Evaluation

Read Evaluation

Defined in Amazonka.MachineLearning.Types.Evaluation

Methods

readsPrec :: Int -> ReadS Evaluation

readList :: ReadS [Evaluation]

readPrec :: ReadPrec Evaluation

readListPrec :: ReadPrec [Evaluation]

Show Evaluation

Defined in Amazonka.MachineLearning.Types.Evaluation

Methods

showsPrec :: Int -> Evaluation -> ShowS

show :: Evaluation -> String

showList :: [Evaluation] -> ShowS

NFData Evaluation

Defined in Amazonka.MachineLearning.Types.Evaluation

Methods

rnf :: Evaluation -> ()

Eq Evaluation

Defined in Amazonka.MachineLearning.Types.Evaluation

Methods

(==) :: Evaluation -> Evaluation -> Bool

(/=) :: Evaluation -> Evaluation -> Bool

Hashable Evaluation

Defined in Amazonka.MachineLearning.Types.Evaluation

Methods

hashWithSalt :: Int -> Evaluation -> Int

hash :: Evaluation -> Int

type Rep Evaluation

Defined in Amazonka.MachineLearning.Types.Evaluation

type Rep Evaluation = D1 ('MetaData "Evaluation" "Amazonka.MachineLearning.Types.Evaluation" "amazonka-ml-2.0-A3JLJ63WvmfHxGBBIqhdRA" 'False) (C1 ('MetaCons "Evaluation'" 'PrefixI 'True) (((S1 ('MetaSel ('Just "computeTime") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Integer)) :*: (S1 ('MetaSel ('Just "createdAt") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe POSIX)) :*: S1 ('MetaSel ('Just "createdByIamUser") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Text)))) :*: ((S1 ('MetaSel ('Just "evaluationDataSourceId") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Text)) :*: S1 ('MetaSel ('Just "evaluationId") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Text))) :*: (S1 ('MetaSel ('Just "finishedAt") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe POSIX)) :*: S1 ('MetaSel ('Just "inputDataLocationS3") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Text))))) :*: ((S1 ('MetaSel ('Just "lastUpdatedAt") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe POSIX)) :*: (S1 ('MetaSel ('Just "mLModelId") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Text)) :*: S1 ('MetaSel ('Just "message") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Text)))) :*: ((S1 ('MetaSel ('Just "name") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Text)) :*: S1 ('MetaSel ('Just "performanceMetrics") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe PerformanceMetrics))) :*: (S1 ('MetaSel ('Just "startedAt") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe POSIX)) :*: S1 ('MetaSel ('Just "status") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe EntityStatus)))))))

newEvaluation :: Evaluation

Create a value of Evaluation 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:computeTime:Evaluation', evaluation_computeTime - Undocumented member.

$sel:createdAt:Evaluation', evaluation_createdAt - The time that the Evaluation was created. The time is expressed in epoch time.

$sel:createdByIamUser:Evaluation', evaluation_createdByIamUser - The AWS user account that invoked the evaluation. The account type can be either an AWS root account or an AWS Identity and Access Management (IAM) user account.

$sel:evaluationDataSourceId:Evaluation', evaluation_evaluationDataSourceId - The ID of the DataSource that is used to evaluate the MLModel.

$sel:evaluationId:Evaluation', evaluation_evaluationId - The ID that is assigned to the Evaluation at creation.

$sel:finishedAt:Evaluation', evaluation_finishedAt - Undocumented member.

$sel:inputDataLocationS3:Evaluation', evaluation_inputDataLocationS3 - The location and name of the data in Amazon Simple Storage Server (Amazon S3) that is used in the evaluation.

$sel:lastUpdatedAt:Evaluation', evaluation_lastUpdatedAt - The time of the most recent edit to the Evaluation. The time is expressed in epoch time.

$sel:mLModelId:Evaluation', evaluation_mLModelId - The ID of the MLModel that is the focus of the evaluation.

$sel:message:Evaluation', evaluation_message - A description of the most recent details about evaluating the MLModel.

$sel:name:Evaluation', evaluation_name - A user-supplied name or description of the Evaluation.

$sel:performanceMetrics:Evaluation', evaluation_performanceMetrics - Measurements of how well the MLModel performed, using observations referenced by the DataSource. One of the following metrics is returned, based on the type of the MLModel:

• BinaryAUC: A binary MLModel uses the Area Under the Curve (AUC) technique to measure performance.
• RegressionRMSE: A regression MLModel uses the Root Mean Square Error (RMSE) technique to measure performance. RMSE measures the difference between predicted and actual values for a single variable.
• MulticlassAvgFScore: A multiclass MLModel uses the F1 score technique to measure performance.

For more information about performance metrics, please see the Amazon Machine Learning Developer Guide.

$sel:startedAt:Evaluation', evaluation_startedAt - Undocumented member.

$sel:status:Evaluation', evaluation_status - The status of the evaluation. This element can have one of the following values:

• PENDING - Amazon Machine Learning (Amazon ML) submitted a request to evaluate an MLModel.
• INPROGRESS - The evaluation is underway.
• FAILED - The request to evaluate an MLModel did not run to completion. It is not usable.
• COMPLETED - The evaluation process completed successfully.
• DELETED - The Evaluation is marked as deleted. It is not usable.

evaluation_computeTime :: Lens' Evaluation (Maybe Integer)

Undocumented member.

evaluation_createdAt :: Lens' Evaluation (Maybe UTCTime)

The time that the Evaluation was created. The time is expressed in epoch time.

evaluation_createdByIamUser :: Lens' Evaluation (Maybe Text)

The AWS user account that invoked the evaluation. The account type can be either an AWS root account or an AWS Identity and Access Management (IAM) user account.

evaluation_evaluationDataSourceId :: Lens' Evaluation (Maybe Text)

The ID of the DataSource that is used to evaluate the MLModel.

evaluation_evaluationId :: Lens' Evaluation (Maybe Text)

The ID that is assigned to the Evaluation at creation.

evaluation_finishedAt :: Lens' Evaluation (Maybe UTCTime)

Undocumented member.

evaluation_inputDataLocationS3 :: Lens' Evaluation (Maybe Text)

The location and name of the data in Amazon Simple Storage Server (Amazon S3) that is used in the evaluation.

evaluation_lastUpdatedAt :: Lens' Evaluation (Maybe UTCTime)

The time of the most recent edit to the Evaluation. The time is expressed in epoch time.

evaluation_mLModelId :: Lens' Evaluation (Maybe Text)

The ID of the MLModel that is the focus of the evaluation.

evaluation_message :: Lens' Evaluation (Maybe Text)

A description of the most recent details about evaluating the MLModel.

evaluation_name :: Lens' Evaluation (Maybe Text)

A user-supplied name or description of the Evaluation.

evaluation_performanceMetrics :: Lens' Evaluation (Maybe PerformanceMetrics)

Measurements of how well the MLModel performed, using observations referenced by the DataSource. One of the following metrics is returned, based on the type of the MLModel:

• BinaryAUC: A binary MLModel uses the Area Under the Curve (AUC) technique to measure performance.
• RegressionRMSE: A regression MLModel uses the Root Mean Square Error (RMSE) technique to measure performance. RMSE measures the difference between predicted and actual values for a single variable.
• MulticlassAvgFScore: A multiclass MLModel uses the F1 score technique to measure performance.

For more information about performance metrics, please see the Amazon Machine Learning Developer Guide.

evaluation_startedAt :: Lens' Evaluation (Maybe UTCTime)

Undocumented member.

evaluation_status :: Lens' Evaluation (Maybe EntityStatus)

The status of the evaluation. This element can have one of the following values:

• PENDING - Amazon Machine Learning (Amazon ML) submitted a request to evaluate an MLModel.
• INPROGRESS - The evaluation is underway.
• FAILED - The request to evaluate an MLModel did not run to completion. It is not usable.
• COMPLETED - The evaluation process completed successfully.
• DELETED - The Evaluation is marked as deleted. It is not usable.