Amazonka.SageMaker.Types.ClarifyInferenceConfig

Documentation

data ClarifyInferenceConfig

The inference configuration parameter for the model container.

See: newClarifyInferenceConfig smart constructor.

Constructors

ClarifyInferenceConfig'

Fields

• contentTemplate :: Maybe Text

  A template string used to format a JSON record into an acceptable model container input. For example, a ContentTemplate string '{"myfeatures":$features}' will format a list of features [1,2,3] into the record string '{"myfeatures":[1,2,3]}'. Required only when the model container input is in JSON Lines format.

• featureHeaders :: Maybe (NonEmpty Text)

  The names of the features. If provided, these are included in the endpoint response payload to help readability of the InvokeEndpoint output. See the Response section under Invoke the endpoint in the Developer Guide for more information.

• featureTypes :: Maybe (NonEmpty ClarifyFeatureType)

  A list of data types of the features (optional). Applicable only to NLP explainability. If provided, FeatureTypes must have at least one 'text' string (for example, ['text']). If FeatureTypes is not provided, the explainer infers the feature types based on the baseline data. The feature types are included in the endpoint response payload. For additional information see the response section under Invoke the endpoint in the Developer Guide for more information.

• featuresAttribute :: Maybe Text

  Provides the JMESPath expression to extract the features from a model container input in JSON Lines format. For example, if FeaturesAttribute is the JMESPath expression 'myfeatures', it extracts a list of features [1,2,3] from request data '{"myfeatures":[1,2,3]}'.

• labelAttribute :: Maybe Text

  A JMESPath expression used to locate the list of label headers in the model container output.

  Example: If the model container output of a batch request is '{"labels":["cat","dog","fish"],"probability":[0.6,0.3,0.1]}', then set LabelAttribute to 'labels' to extract the list of label headers ["cat","dog","fish"]

• labelHeaders :: Maybe (NonEmpty Text)

  For multiclass classification problems, the label headers are the names of the classes. Otherwise, the label header is the name of the predicted label. These are used to help readability for the output of the InvokeEndpoint API. See the response section under Invoke the endpoint in the Developer Guide for more information. If there are no label headers in the model container output, provide them manually using this parameter.

• labelIndex :: Maybe Natural

  A zero-based index used to extract a label header or list of label headers from model container output in CSV format.

  Example for a multiclass model: If the model container output consists of label headers followed by probabilities: '"[\'cat\',\'dog\',\'fish\']","[0.1,0.6,0.3]"', set LabelIndex to 0 to select the label headers ['cat','dog','fish'].

• maxPayloadInMB :: Maybe Natural

  The maximum payload size (MB) allowed of a request from the explainer to the model container. Defaults to 6 MB.

• maxRecordCount :: Maybe Natural

  The maximum number of records in a request that the model container can process when querying the model container for the predictions of a synthetic dataset. A record is a unit of input data that inference can be made on, for example, a single line in CSV data. If MaxRecordCount is 1, the model container expects one record per request. A value of 2 or greater means that the model expects batch requests, which can reduce overhead and speed up the inferencing process. If this parameter is not provided, the explainer will tune the record count per request according to the model container's capacity at runtime.

• probabilityAttribute :: Maybe Text

  A JMESPath expression used to extract the probability (or score) from the model container output if the model container is in JSON Lines format.

  Example: If the model container output of a single request is '{"predicted_label":1,"probability":0.6}', then set ProbabilityAttribute to 'probability'.

• probabilityIndex :: Maybe Natural

  A zero-based index used to extract a probability value (score) or list from model container output in CSV format. If this value is not provided, the entire model container output will be treated as a probability value (score) or list.

  Example for a single class model: If the model container output consists of a string-formatted prediction label followed by its probability: '1,0.6', set ProbabilityIndex to 1 to select the probability value 0.6.

  Example for a multiclass model: If the model container output consists of a string-formatted prediction label followed by its probability: '"[\'cat\',\'dog\',\'fish\']","[0.1,0.6,0.3]"', set ProbabilityIndex to 1 to select the probability values [0.1,0.6,0.3].

Instances

FromJSON ClarifyInferenceConfig

Defined in Amazonka.SageMaker.Types.ClarifyInferenceConfig

Methods

parseJSON :: Value -> Parser ClarifyInferenceConfig

parseJSONList :: Value -> Parser [ClarifyInferenceConfig]

ToJSON ClarifyInferenceConfig

Defined in Amazonka.SageMaker.Types.ClarifyInferenceConfig

Methods

toJSON :: ClarifyInferenceConfig -> Value

toEncoding :: ClarifyInferenceConfig -> Encoding

toJSONList :: [ClarifyInferenceConfig] -> Value

toEncodingList :: [ClarifyInferenceConfig] -> Encoding

Generic ClarifyInferenceConfig

Defined in Amazonka.SageMaker.Types.ClarifyInferenceConfig

Associated Types

type Rep ClarifyInferenceConfig :: Type -> Type

Methods

from :: ClarifyInferenceConfig -> Rep ClarifyInferenceConfig x

to :: Rep ClarifyInferenceConfig x -> ClarifyInferenceConfig

Read ClarifyInferenceConfig

Defined in Amazonka.SageMaker.Types.ClarifyInferenceConfig

Methods

readsPrec :: Int -> ReadS ClarifyInferenceConfig

readList :: ReadS [ClarifyInferenceConfig]

readPrec :: ReadPrec ClarifyInferenceConfig

readListPrec :: ReadPrec [ClarifyInferenceConfig]

Show ClarifyInferenceConfig

Defined in Amazonka.SageMaker.Types.ClarifyInferenceConfig

Methods

showsPrec :: Int -> ClarifyInferenceConfig -> ShowS

show :: ClarifyInferenceConfig -> String

showList :: [ClarifyInferenceConfig] -> ShowS

NFData ClarifyInferenceConfig

Defined in Amazonka.SageMaker.Types.ClarifyInferenceConfig

Methods

rnf :: ClarifyInferenceConfig -> ()

Eq ClarifyInferenceConfig

Defined in Amazonka.SageMaker.Types.ClarifyInferenceConfig

Methods

(==) :: ClarifyInferenceConfig -> ClarifyInferenceConfig -> Bool

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

Hashable ClarifyInferenceConfig

Defined in Amazonka.SageMaker.Types.ClarifyInferenceConfig

Methods

hashWithSalt :: Int -> ClarifyInferenceConfig -> Int

hash :: ClarifyInferenceConfig -> Int

type Rep ClarifyInferenceConfig

Defined in Amazonka.SageMaker.Types.ClarifyInferenceConfig

type Rep ClarifyInferenceConfig = D1 ('MetaData "ClarifyInferenceConfig" "Amazonka.SageMaker.Types.ClarifyInferenceConfig" "amazonka-sagemaker-2.0-9SyrKZ4KqhsL1qX9u3ILA3" 'False) (C1 ('MetaCons "ClarifyInferenceConfig'" 'PrefixI 'True) (((S1 ('MetaSel ('Just "contentTemplate") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Text)) :*: S1 ('MetaSel ('Just "featureHeaders") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe (NonEmpty Text)))) :*: (S1 ('MetaSel ('Just "featureTypes") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe (NonEmpty ClarifyFeatureType))) :*: (S1 ('MetaSel ('Just "featuresAttribute") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Text)) :*: S1 ('MetaSel ('Just "labelAttribute") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Text))))) :*: ((S1 ('MetaSel ('Just "labelHeaders") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe (NonEmpty Text))) :*: (S1 ('MetaSel ('Just "labelIndex") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Natural)) :*: S1 ('MetaSel ('Just "maxPayloadInMB") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Natural)))) :*: (S1 ('MetaSel ('Just "maxRecordCount") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Natural)) :*: (S1 ('MetaSel ('Just "probabilityAttribute") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Text)) :*: S1 ('MetaSel ('Just "probabilityIndex") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Natural)))))))

newClarifyInferenceConfig :: ClarifyInferenceConfig

Create a value of ClarifyInferenceConfig 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:

$sel:contentTemplate:ClarifyInferenceConfig', clarifyInferenceConfig_contentTemplate - A template string used to format a JSON record into an acceptable model container input. For example, a ContentTemplate string '{"myfeatures":$features}' will format a list of features [1,2,3] into the record string '{"myfeatures":[1,2,3]}'. Required only when the model container input is in JSON Lines format.

$sel:featureHeaders:ClarifyInferenceConfig', clarifyInferenceConfig_featureHeaders - The names of the features. If provided, these are included in the endpoint response payload to help readability of the InvokeEndpoint output. See the Response section under Invoke the endpoint in the Developer Guide for more information.

$sel:featureTypes:ClarifyInferenceConfig', clarifyInferenceConfig_featureTypes - A list of data types of the features (optional). Applicable only to NLP explainability. If provided, FeatureTypes must have at least one 'text' string (for example, ['text']). If FeatureTypes is not provided, the explainer infers the feature types based on the baseline data. The feature types are included in the endpoint response payload. For additional information see the response section under Invoke the endpoint in the Developer Guide for more information.

$sel:featuresAttribute:ClarifyInferenceConfig', clarifyInferenceConfig_featuresAttribute - Provides the JMESPath expression to extract the features from a model container input in JSON Lines format. For example, if FeaturesAttribute is the JMESPath expression 'myfeatures', it extracts a list of features [1,2,3] from request data '{"myfeatures":[1,2,3]}'.

$sel:labelAttribute:ClarifyInferenceConfig', clarifyInferenceConfig_labelAttribute - A JMESPath expression used to locate the list of label headers in the model container output.

Example: If the model container output of a batch request is '{"labels":["cat","dog","fish"],"probability":[0.6,0.3,0.1]}', then set LabelAttribute to 'labels' to extract the list of label headers ["cat","dog","fish"]

$sel:labelHeaders:ClarifyInferenceConfig', clarifyInferenceConfig_labelHeaders - For multiclass classification problems, the label headers are the names of the classes. Otherwise, the label header is the name of the predicted label. These are used to help readability for the output of the InvokeEndpoint API. See the response section under Invoke the endpoint in the Developer Guide for more information. If there are no label headers in the model container output, provide them manually using this parameter.

$sel:labelIndex:ClarifyInferenceConfig', clarifyInferenceConfig_labelIndex - A zero-based index used to extract a label header or list of label headers from model container output in CSV format.

Example for a multiclass model: If the model container output consists of label headers followed by probabilities: '"[\'cat\',\'dog\',\'fish\']","[0.1,0.6,0.3]"', set LabelIndex to 0 to select the label headers ['cat','dog','fish'].

$sel:maxPayloadInMB:ClarifyInferenceConfig', clarifyInferenceConfig_maxPayloadInMB - The maximum payload size (MB) allowed of a request from the explainer to the model container. Defaults to 6 MB.

$sel:maxRecordCount:ClarifyInferenceConfig', clarifyInferenceConfig_maxRecordCount - The maximum number of records in a request that the model container can process when querying the model container for the predictions of a synthetic dataset. A record is a unit of input data that inference can be made on, for example, a single line in CSV data. If MaxRecordCount is 1, the model container expects one record per request. A value of 2 or greater means that the model expects batch requests, which can reduce overhead and speed up the inferencing process. If this parameter is not provided, the explainer will tune the record count per request according to the model container's capacity at runtime.

$sel:probabilityAttribute:ClarifyInferenceConfig', clarifyInferenceConfig_probabilityAttribute - A JMESPath expression used to extract the probability (or score) from the model container output if the model container is in JSON Lines format.

Example: If the model container output of a single request is '{"predicted_label":1,"probability":0.6}', then set ProbabilityAttribute to 'probability'.

$sel:probabilityIndex:ClarifyInferenceConfig', clarifyInferenceConfig_probabilityIndex - A zero-based index used to extract a probability value (score) or list from model container output in CSV format. If this value is not provided, the entire model container output will be treated as a probability value (score) or list.

Example for a single class model: If the model container output consists of a string-formatted prediction label followed by its probability: '1,0.6', set ProbabilityIndex to 1 to select the probability value 0.6.

Example for a multiclass model: If the model container output consists of a string-formatted prediction label followed by its probability: '"[\'cat\',\'dog\',\'fish\']","[0.1,0.6,0.3]"', set ProbabilityIndex to 1 to select the probability values [0.1,0.6,0.3].

clarifyInferenceConfig_contentTemplate :: Lens' ClarifyInferenceConfig (Maybe Text)

A template string used to format a JSON record into an acceptable model container input. For example, a ContentTemplate string '{"myfeatures":$features}' will format a list of features [1,2,3] into the record string '{"myfeatures":[1,2,3]}'. Required only when the model container input is in JSON Lines format.

clarifyInferenceConfig_featureHeaders :: Lens' ClarifyInferenceConfig (Maybe (NonEmpty Text))

The names of the features. If provided, these are included in the endpoint response payload to help readability of the InvokeEndpoint output. See the Response section under Invoke the endpoint in the Developer Guide for more information.

clarifyInferenceConfig_featureTypes :: Lens' ClarifyInferenceConfig (Maybe (NonEmpty ClarifyFeatureType))

A list of data types of the features (optional). Applicable only to NLP explainability. If provided, FeatureTypes must have at least one 'text' string (for example, ['text']). If FeatureTypes is not provided, the explainer infers the feature types based on the baseline data. The feature types are included in the endpoint response payload. For additional information see the response section under Invoke the endpoint in the Developer Guide for more information.

clarifyInferenceConfig_featuresAttribute :: Lens' ClarifyInferenceConfig (Maybe Text)

Provides the JMESPath expression to extract the features from a model container input in JSON Lines format. For example, if FeaturesAttribute is the JMESPath expression 'myfeatures', it extracts a list of features [1,2,3] from request data '{"myfeatures":[1,2,3]}'.

clarifyInferenceConfig_labelAttribute :: Lens' ClarifyInferenceConfig (Maybe Text)

A JMESPath expression used to locate the list of label headers in the model container output.

Example: If the model container output of a batch request is '{"labels":["cat","dog","fish"],"probability":[0.6,0.3,0.1]}', then set LabelAttribute to 'labels' to extract the list of label headers ["cat","dog","fish"]

clarifyInferenceConfig_labelHeaders :: Lens' ClarifyInferenceConfig (Maybe (NonEmpty Text))

For multiclass classification problems, the label headers are the names of the classes. Otherwise, the label header is the name of the predicted label. These are used to help readability for the output of the InvokeEndpoint API. See the response section under Invoke the endpoint in the Developer Guide for more information. If there are no label headers in the model container output, provide them manually using this parameter.

clarifyInferenceConfig_labelIndex :: Lens' ClarifyInferenceConfig (Maybe Natural)

A zero-based index used to extract a label header or list of label headers from model container output in CSV format.

Example for a multiclass model: If the model container output consists of label headers followed by probabilities: '"[\'cat\',\'dog\',\'fish\']","[0.1,0.6,0.3]"', set LabelIndex to 0 to select the label headers ['cat','dog','fish'].

clarifyInferenceConfig_maxPayloadInMB :: Lens' ClarifyInferenceConfig (Maybe Natural)

The maximum payload size (MB) allowed of a request from the explainer to the model container. Defaults to 6 MB.

clarifyInferenceConfig_maxRecordCount :: Lens' ClarifyInferenceConfig (Maybe Natural)

The maximum number of records in a request that the model container can process when querying the model container for the predictions of a synthetic dataset. A record is a unit of input data that inference can be made on, for example, a single line in CSV data. If MaxRecordCount is 1, the model container expects one record per request. A value of 2 or greater means that the model expects batch requests, which can reduce overhead and speed up the inferencing process. If this parameter is not provided, the explainer will tune the record count per request according to the model container's capacity at runtime.

clarifyInferenceConfig_probabilityAttribute :: Lens' ClarifyInferenceConfig (Maybe Text)

A JMESPath expression used to extract the probability (or score) from the model container output if the model container is in JSON Lines format.

Example: If the model container output of a single request is '{"predicted_label":1,"probability":0.6}', then set ProbabilityAttribute to 'probability'.

clarifyInferenceConfig_probabilityIndex :: Lens' ClarifyInferenceConfig (Maybe Natural)

A zero-based index used to extract a probability value (score) or list from model container output in CSV format. If this value is not provided, the entire model container output will be treated as a probability value (score) or list.

Example for a single class model: If the model container output consists of a string-formatted prediction label followed by its probability: '1,0.6', set ProbabilityIndex to 1 to select the probability value 0.6.

Example for a multiclass model: If the model container output consists of a string-formatted prediction label followed by its probability: '"[\'cat\',\'dog\',\'fish\']","[0.1,0.6,0.3]"', set ProbabilityIndex to 1 to select the probability values [0.1,0.6,0.3].