/AWS1/CL_SGMCLARIFYINFERENCE00¶
The inference configuration parameter for the model container.
CONSTRUCTOR¶
IMPORTING¶
Optional arguments:¶
iv_featuresattribute TYPE /AWS1/SGMCLARIFYFEATURESATTR /AWS1/SGMCLARIFYFEATURESATTR¶
Provides the JMESPath expression to extract the features from a model container input in JSON Lines format. For example, if
FeaturesAttributeis the JMESPath expression'myfeatures', it extracts a list of features[1,2,3]from request data'{"myfeatures":[1,2,3]}'.
iv_contenttemplate TYPE /AWS1/SGMCLARIFYCONTENTTMPL /AWS1/SGMCLARIFYCONTENTTMPL¶
A template string used to format a JSON record into an acceptable model container input. For example, a
ContentTemplatestring'{"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.
iv_maxrecordcount TYPE /AWS1/SGMCLARIFYMAXRECORDCOUNT /AWS1/SGMCLARIFYMAXRECORDCOUNT¶
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
MaxRecordCountis1, 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.
iv_maxpayloadinmb TYPE /AWS1/SGMCLARIFYMAXPAYLOADINMB /AWS1/SGMCLARIFYMAXPAYLOADINMB¶
The maximum payload size (MB) allowed of a request from the explainer to the model container. Defaults to
6MB.
iv_probabilityindex TYPE /AWS1/SGMCLARIFYPROBABILITYIDX /AWS1/SGMCLARIFYPROBABILITYIDX¶
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', setProbabilityIndexto1to select the probability value0.6.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]"', setProbabilityIndexto1to select the probability values[0.1,0.6,0.3].
iv_labelindex TYPE /AWS1/SGMCLARIFYLABELINDEX /AWS1/SGMCLARIFYLABELINDEX¶
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]"', setLabelIndexto0to select the label headers['cat','dog','fish'].
iv_probabilityattribute TYPE /AWS1/SGMCLARIFYPROBABILITYA00 /AWS1/SGMCLARIFYPROBABILITYA00¶
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 setProbabilityAttributeto'probability'.
iv_labelattribute TYPE /AWS1/SGMCLARIFYLABELATTRIBUTE /AWS1/SGMCLARIFYLABELATTRIBUTE¶
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 setLabelAttributeto'labels'to extract the list of label headers["cat","dog","fish"]
it_labelheaders TYPE /AWS1/CL_SGMCLARIFYLABELHEAD00=>TT_CLARIFYLABELHEADERS TT_CLARIFYLABELHEADERS¶
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
InvokeEndpointAPI. 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.
it_featureheaders TYPE /AWS1/CL_SGMCLARIFYFTHEADERS_W=>TT_CLARIFYFEATUREHEADERS TT_CLARIFYFEATUREHEADERS¶
The names of the features. If provided, these are included in the endpoint response payload to help readability of the
InvokeEndpointoutput. See the Response section under Invoke the endpoint in the Developer Guide for more information.
it_featuretypes TYPE /AWS1/CL_SGMCLARIFYFEATTYPES_W=>TT_CLARIFYFEATURETYPES TT_CLARIFYFEATURETYPES¶
A list of data types of the features (optional). Applicable only to NLP explainability. If provided,
FeatureTypesmust have at least one'text'string (for example,['text']). IfFeatureTypesis 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.
Queryable Attributes¶
FeaturesAttribute¶
Provides the JMESPath expression to extract the features from a model container input in JSON Lines format. For example, if
FeaturesAttributeis the JMESPath expression'myfeatures', it extracts a list of features[1,2,3]from request data'{"myfeatures":[1,2,3]}'.
Accessible with the following methods¶
| Method | Description |
|---|---|
GET_FEATURESATTRIBUTE() |
Getter for FEATURESATTRIBUTE, with configurable default |
ASK_FEATURESATTRIBUTE() |
Getter for FEATURESATTRIBUTE w/ exceptions if field has no v |
HAS_FEATURESATTRIBUTE() |
Determine if FEATURESATTRIBUTE has a value |
ContentTemplate¶
A template string used to format a JSON record into an acceptable model container input. For example, a
ContentTemplatestring'{"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.
Accessible with the following methods¶
| Method | Description |
|---|---|
GET_CONTENTTEMPLATE() |
Getter for CONTENTTEMPLATE, with configurable default |
ASK_CONTENTTEMPLATE() |
Getter for CONTENTTEMPLATE w/ exceptions if field has no val |
HAS_CONTENTTEMPLATE() |
Determine if CONTENTTEMPLATE has a value |
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
MaxRecordCountis1, 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.
Accessible with the following methods¶
| Method | Description |
|---|---|
GET_MAXRECORDCOUNT() |
Getter for MAXRECORDCOUNT, with configurable default |
ASK_MAXRECORDCOUNT() |
Getter for MAXRECORDCOUNT w/ exceptions if field has no valu |
HAS_MAXRECORDCOUNT() |
Determine if MAXRECORDCOUNT has a value |
MaxPayloadInMB¶
The maximum payload size (MB) allowed of a request from the explainer to the model container. Defaults to
6MB.
Accessible with the following methods¶
| Method | Description |
|---|---|
GET_MAXPAYLOADINMB() |
Getter for MAXPAYLOADINMB, with configurable default |
ASK_MAXPAYLOADINMB() |
Getter for MAXPAYLOADINMB w/ exceptions if field has no valu |
HAS_MAXPAYLOADINMB() |
Determine if MAXPAYLOADINMB has a value |
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', setProbabilityIndexto1to select the probability value0.6.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]"', setProbabilityIndexto1to select the probability values[0.1,0.6,0.3].
Accessible with the following methods¶
| Method | Description |
|---|---|
GET_PROBABILITYINDEX() |
Getter for PROBABILITYINDEX, with configurable default |
ASK_PROBABILITYINDEX() |
Getter for PROBABILITYINDEX w/ exceptions if field has no va |
HAS_PROBABILITYINDEX() |
Determine if PROBABILITYINDEX has a value |
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]"', setLabelIndexto0to select the label headers['cat','dog','fish'].
Accessible with the following methods¶
| Method | Description |
|---|---|
GET_LABELINDEX() |
Getter for LABELINDEX, with configurable default |
ASK_LABELINDEX() |
Getter for LABELINDEX w/ exceptions if field has no value |
HAS_LABELINDEX() |
Determine if LABELINDEX has a value |
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 setProbabilityAttributeto'probability'.
Accessible with the following methods¶
| Method | Description |
|---|---|
GET_PROBABILITYATTRIBUTE() |
Getter for PROBABILITYATTRIBUTE, with configurable default |
ASK_PROBABILITYATTRIBUTE() |
Getter for PROBABILITYATTRIBUTE w/ exceptions if field has n |
HAS_PROBABILITYATTRIBUTE() |
Determine if PROBABILITYATTRIBUTE has a value |
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 setLabelAttributeto'labels'to extract the list of label headers["cat","dog","fish"]
Accessible with the following methods¶
| Method | Description |
|---|---|
GET_LABELATTRIBUTE() |
Getter for LABELATTRIBUTE, with configurable default |
ASK_LABELATTRIBUTE() |
Getter for LABELATTRIBUTE w/ exceptions if field has no valu |
HAS_LABELATTRIBUTE() |
Determine if LABELATTRIBUTE has a value |
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
InvokeEndpointAPI. 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.
Accessible with the following methods¶
| Method | Description |
|---|---|
GET_LABELHEADERS() |
Getter for LABELHEADERS, with configurable default |
ASK_LABELHEADERS() |
Getter for LABELHEADERS w/ exceptions if field has no value |
HAS_LABELHEADERS() |
Determine if LABELHEADERS has a value |
FeatureHeaders¶
The names of the features. If provided, these are included in the endpoint response payload to help readability of the
InvokeEndpointoutput. See the Response section under Invoke the endpoint in the Developer Guide for more information.
Accessible with the following methods¶
| Method | Description |
|---|---|
GET_FEATUREHEADERS() |
Getter for FEATUREHEADERS, with configurable default |
ASK_FEATUREHEADERS() |
Getter for FEATUREHEADERS w/ exceptions if field has no valu |
HAS_FEATUREHEADERS() |
Determine if FEATUREHEADERS has a value |
FeatureTypes¶
A list of data types of the features (optional). Applicable only to NLP explainability. If provided,
FeatureTypesmust have at least one'text'string (for example,['text']). IfFeatureTypesis 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.
Accessible with the following methods¶
| Method | Description |
|---|---|
GET_FEATURETYPES() |
Getter for FEATURETYPES, with configurable default |
ASK_FEATURETYPES() |
Getter for FEATURETYPES w/ exceptions if field has no value |
HAS_FEATURETYPES() |
Determine if FEATURETYPES has a value |