2021/03/31 - Amazon Comprehend - 9 updated api methods
Changes Support for customer managed KMS encryption of Comprehend custom models
{'ModelKmsKeyId': 'string'}
Creates a new document classifier that you can use to categorize documents. To create a classifier, you provide a set of training documents that labeled with the categories that you want to use. After the classifier is trained you can use it to categorize a set of labeled documents into the categories. For more information, see how-document-classification .
See also: AWS API Documentation
Request Syntax
client.create_document_classifier(
DocumentClassifierName='string',
DataAccessRoleArn='string',
Tags=[
{
'Key': 'string',
'Value': 'string'
},
],
InputDataConfig={
'DataFormat': 'COMPREHEND_CSV'|'AUGMENTED_MANIFEST',
'S3Uri': 'string',
'LabelDelimiter': 'string',
'AugmentedManifests': [
{
'S3Uri': 'string',
'AttributeNames': [
'string',
]
},
]
},
OutputDataConfig={
'S3Uri': 'string',
'KmsKeyId': 'string'
},
ClientRequestToken='string',
LanguageCode='en'|'es'|'fr'|'de'|'it'|'pt'|'ar'|'hi'|'ja'|'ko'|'zh'|'zh-TW',
VolumeKmsKeyId='string',
VpcConfig={
'SecurityGroupIds': [
'string',
],
'Subnets': [
'string',
]
},
Mode='MULTI_CLASS'|'MULTI_LABEL',
ModelKmsKeyId='string'
)
string
[REQUIRED]
The name of the document classifier.
string
[REQUIRED]
The Amazon Resource Name (ARN) of the AWS Identity and Management (IAM) role that grants Amazon Comprehend read access to your input data.
list
Tags to be associated with the document classifier being created. A tag is a key-value pair that adds as a metadata to a resource used by Amazon Comprehend. For example, a tag with "Sales" as the key might be added to a resource to indicate its use by the sales department.
(dict) --
A key-value pair that adds as a metadata to a resource used by Amazon Comprehend. For example, a tag with the key-value pair ‘Department’:’Sales’ might be added to a resource to indicate its use by a particular department.
Key (string) -- [REQUIRED]
The initial part of a key-value pair that forms a tag associated with a given resource. For instance, if you want to show which resources are used by which departments, you might use “Department” as the key portion of the pair, with multiple possible values such as “sales,” “legal,” and “administration.”
Value (string) --
The second part of a key-value pair that forms a tag associated with a given resource. For instance, if you want to show which resources are used by which departments, you might use “Department” as the initial (key) portion of the pair, with a value of “sales” to indicate the sales department.
dict
[REQUIRED]
Specifies the format and location of the input data for the job.
DataFormat (string) --
The format of your training data:
COMPREHEND_CSV : A two-column CSV file, where labels are provided in the first column, and documents are provided in the second. If you use this value, you must provide the S3Uri parameter in your request.
AUGMENTED_MANIFEST : A labeled dataset that is produced by Amazon SageMaker Ground Truth. This file is in JSON lines format. Each line is a complete JSON object that contains a training document and its associated labels. If you use this value, you must provide the AugmentedManifests parameter in your request.
If you don't specify a value, Amazon Comprehend uses COMPREHEND_CSV as the default.
S3Uri (string) --
The Amazon S3 URI for the input data. The S3 bucket must be in the same region as the API endpoint that you are calling. The URI can point to a single input file or it can provide the prefix for a collection of input files.
For example, if you use the URI S3://bucketName/prefix , if the prefix is a single file, Amazon Comprehend uses that file as input. If more than one file begins with the prefix, Amazon Comprehend uses all of them as input.
This parameter is required if you set DataFormat to COMPREHEND_CSV .
LabelDelimiter (string) --
Indicates the delimiter used to separate each label for training a multi-label classifier. The default delimiter between labels is a pipe (|). You can use a different character as a delimiter (if it's an allowed character) by specifying it under Delimiter for labels. If the training documents use a delimiter other than the default or the delimiter you specify, the labels on that line will be combined to make a single unique label, such as LABELLABELLABEL.
AugmentedManifests (list) --
A list of augmented manifest files that provide training data for your custom model. An augmented manifest file is a labeled dataset that is produced by Amazon SageMaker Ground Truth.
This parameter is required if you set DataFormat to AUGMENTED_MANIFEST .
(dict) --
An augmented manifest file that provides training data for your custom model. An augmented manifest file is a labeled dataset that is produced by Amazon SageMaker Ground Truth.
S3Uri (string) -- [REQUIRED]
The Amazon S3 location of the augmented manifest file.
AttributeNames (list) -- [REQUIRED]
The JSON attribute that contains the annotations for your training documents. The number of attribute names that you specify depends on whether your augmented manifest file is the output of a single labeling job or a chained labeling job.
If your file is the output of a single labeling job, specify the LabelAttributeName key that was used when the job was created in Ground Truth.
If your file is the output of a chained labeling job, specify the LabelAttributeName key for one or more jobs in the chain. Each LabelAttributeName key provides the annotations from an individual job.
(string) --
dict
Enables the addition of output results configuration parameters for custom classifier jobs.
S3Uri (string) --
When you use the OutputDataConfig object while creating a custom classifier, you specify the Amazon S3 location where you want to write the confusion matrix. The URI must be in the same region as the API endpoint that you are calling. The location is used as the prefix for the actual location of this output file.
When the custom classifier job is finished, the service creates the output file in a directory specific to the job. The S3Uri field contains the location of the output file, called output.tar.gz . It is a compressed archive that contains the confusion matrix.
KmsKeyId (string) --
ID for the AWS Key Management Service (KMS) key that Amazon Comprehend uses to encrypt the output results from an analysis job. The KmsKeyId can be one of the following formats:
KMS Key ID: "1234abcd-12ab-34cd-56ef-1234567890ab"
Amazon Resource Name (ARN) of a KMS Key: "arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"
KMS Key Alias: "alias/ExampleAlias"
ARN of a KMS Key Alias: "arn:aws:kms:us-west-2:111122223333:alias/ExampleAlias"
string
A unique identifier for the request. If you don't set the client request token, Amazon Comprehend generates one.
This field is autopopulated if not provided.
string
[REQUIRED]
The language of the input documents. You can specify any of the following languages supported by Amazon Comprehend: German ("de"), English ("en"), Spanish ("es"), French ("fr"), Italian ("it"), or Portuguese ("pt"). All documents must be in the same language.
string
ID for the AWS Key Management Service (KMS) key that Amazon Comprehend uses to encrypt data on the storage volume attached to the ML compute instance(s) that process the analysis job. The VolumeKmsKeyId can be either of the following formats:
KMS Key ID: "1234abcd-12ab-34cd-56ef-1234567890ab"
Amazon Resource Name (ARN) of a KMS Key: "arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"
dict
Configuration parameters for an optional private Virtual Private Cloud (VPC) containing the resources you are using for your custom classifier. For more information, see Amazon VPC .
SecurityGroupIds (list) -- [REQUIRED]
The ID number for a security group on an instance of your private VPC. Security groups on your VPC function serve as a virtual firewall to control inbound and outbound traffic and provides security for the resources that you’ll be accessing on the VPC. This ID number is preceded by "sg-", for instance: "sg-03b388029b0a285ea". For more information, see Security Groups for your VPC .
(string) --
Subnets (list) -- [REQUIRED]
The ID for each subnet being used in your private VPC. This subnet is a subset of the a range of IPv4 addresses used by the VPC and is specific to a given availability zone in the VPC’s region. This ID number is preceded by "subnet-", for instance: "subnet-04ccf456919e69055". For more information, see VPCs and Subnets .
(string) --
string
Indicates the mode in which the classifier will be trained. The classifier can be trained in multi-class mode, which identifies one and only one class for each document, or multi-label mode, which identifies one or more labels for each document. In multi-label mode, multiple labels for an individual document are separated by a delimiter. The default delimiter between labels is a pipe (|).
string
ID for the AWS Key Management Service (KMS) key that Amazon Comprehend uses to encrypt trained custom models. The ModelKmsKeyId can be either of the following formats:
KMS Key ID: "1234abcd-12ab-34cd-56ef-1234567890ab"
Amazon Resource Name (ARN) of a KMS Key: "arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"
dict
Response Syntax
{
'DocumentClassifierArn': 'string'
}
Response Structure
(dict) --
DocumentClassifierArn (string) --
The Amazon Resource Name (ARN) that identifies the document classifier.
{'DataAccessRoleArn': 'string'}
Creates a model-specific endpoint for synchronous inference for a previously trained custom model
See also: AWS API Documentation
Request Syntax
client.create_endpoint(
EndpointName='string',
ModelArn='string',
DesiredInferenceUnits=123,
ClientRequestToken='string',
Tags=[
{
'Key': 'string',
'Value': 'string'
},
],
DataAccessRoleArn='string'
)
string
[REQUIRED]
This is the descriptive suffix that becomes part of the EndpointArn used for all subsequent requests to this resource.
string
[REQUIRED]
The Amazon Resource Number (ARN) of the model to which the endpoint will be attached.
integer
[REQUIRED]
The desired number of inference units to be used by the model using this endpoint. Each inference unit represents of a throughput of 100 characters per second.
string
An idempotency token provided by the customer. If this token matches a previous endpoint creation request, Amazon Comprehend will not return a ResourceInUseException .
This field is autopopulated if not provided.
list
Tags associated with the endpoint being created. A tag is a key-value pair that adds metadata to the endpoint. For example, a tag with "Sales" as the key might be added to an endpoint to indicate its use by the sales department.
(dict) --
A key-value pair that adds as a metadata to a resource used by Amazon Comprehend. For example, a tag with the key-value pair ‘Department’:’Sales’ might be added to a resource to indicate its use by a particular department.
Key (string) -- [REQUIRED]
The initial part of a key-value pair that forms a tag associated with a given resource. For instance, if you want to show which resources are used by which departments, you might use “Department” as the key portion of the pair, with multiple possible values such as “sales,” “legal,” and “administration.”
Value (string) --
The second part of a key-value pair that forms a tag associated with a given resource. For instance, if you want to show which resources are used by which departments, you might use “Department” as the initial (key) portion of the pair, with a value of “sales” to indicate the sales department.
string
The Amazon Resource Name (ARN) of the AWS identity and Access Management (IAM) role that grants Amazon Comprehend read access to trained custom models encrypted with a customer managed key (ModelKmsKeyId).
dict
Response Syntax
{
'EndpointArn': 'string'
}
Response Structure
(dict) --
EndpointArn (string) --
The Amazon Resource Number (ARN) of the endpoint being created.
{'ModelKmsKeyId': 'string'}
Creates an entity recognizer using submitted files. After your CreateEntityRecognizer request is submitted, you can check job status using the API.
See also: AWS API Documentation
Request Syntax
client.create_entity_recognizer(
RecognizerName='string',
DataAccessRoleArn='string',
Tags=[
{
'Key': 'string',
'Value': 'string'
},
],
InputDataConfig={
'DataFormat': 'COMPREHEND_CSV'|'AUGMENTED_MANIFEST',
'EntityTypes': [
{
'Type': 'string'
},
],
'Documents': {
'S3Uri': 'string'
},
'Annotations': {
'S3Uri': 'string'
},
'EntityList': {
'S3Uri': 'string'
},
'AugmentedManifests': [
{
'S3Uri': 'string',
'AttributeNames': [
'string',
]
},
]
},
ClientRequestToken='string',
LanguageCode='en'|'es'|'fr'|'de'|'it'|'pt'|'ar'|'hi'|'ja'|'ko'|'zh'|'zh-TW',
VolumeKmsKeyId='string',
VpcConfig={
'SecurityGroupIds': [
'string',
],
'Subnets': [
'string',
]
},
ModelKmsKeyId='string'
)
string
[REQUIRED]
The name given to the newly created recognizer. Recognizer names can be a maximum of 256 characters. Alphanumeric characters, hyphens (-) and underscores (_) are allowed. The name must be unique in the account/region.
string
[REQUIRED]
The Amazon Resource Name (ARN) of the AWS Identity and Management (IAM) role that grants Amazon Comprehend read access to your input data.
list
Tags to be associated with the entity recognizer being created. A tag is a key-value pair that adds as a metadata to a resource used by Amazon Comprehend. For example, a tag with "Sales" as the key might be added to a resource to indicate its use by the sales department.
(dict) --
A key-value pair that adds as a metadata to a resource used by Amazon Comprehend. For example, a tag with the key-value pair ‘Department’:’Sales’ might be added to a resource to indicate its use by a particular department.
Key (string) -- [REQUIRED]
The initial part of a key-value pair that forms a tag associated with a given resource. For instance, if you want to show which resources are used by which departments, you might use “Department” as the key portion of the pair, with multiple possible values such as “sales,” “legal,” and “administration.”
Value (string) --
The second part of a key-value pair that forms a tag associated with a given resource. For instance, if you want to show which resources are used by which departments, you might use “Department” as the initial (key) portion of the pair, with a value of “sales” to indicate the sales department.
dict
[REQUIRED]
Specifies the format and location of the input data. The S3 bucket containing the input data must be located in the same region as the entity recognizer being created.
DataFormat (string) --
The format of your training data:
COMPREHEND_CSV : A CSV file that supplements your training documents. The CSV file contains information about the custom entities that your trained model will detect. The required format of the file depends on whether you are providing annotations or an entity list. If you use this value, you must provide your CSV file by using either the Annotations or EntityList parameters. You must provide your training documents by using the Documents parameter.
AUGMENTED_MANIFEST : A labeled dataset that is produced by Amazon SageMaker Ground Truth. This file is in JSON lines format. Each line is a complete JSON object that contains a training document and its labels. Each label annotates a named entity in the training document. If you use this value, you must provide the AugmentedManifests parameter in your request.
If you don't specify a value, Amazon Comprehend uses COMPREHEND_CSV as the default.
EntityTypes (list) -- [REQUIRED]
The entity types in the labeled training data that Amazon Comprehend uses to train the custom entity recognizer. Any entity types that you don't specify are ignored.
A maximum of 25 entity types can be used at one time to train an entity recognizer. Entity types must not contain the following invalid characters: n (line break), \n (escaped line break), r (carriage return), \r (escaped carriage return), t (tab), \t (escaped tab), space, and , (comma).
(dict) --
An entity type within a labeled training dataset that Amazon Comprehend uses to train a custom entity recognizer.
Type (string) -- [REQUIRED]
An entity type within a labeled training dataset that Amazon Comprehend uses to train a custom entity recognizer.
Entity types must not contain the following invalid characters: n (line break), \n (escaped line break, r (carriage return), \r (escaped carriage return), t (tab), \t (escaped tab), space, and , (comma).
Documents (dict) --
The S3 location of the folder that contains the training documents for your custom entity recognizer.
This parameter is required if you set DataFormat to COMPREHEND_CSV .
S3Uri (string) -- [REQUIRED]
Specifies the Amazon S3 location where the training documents for an entity recognizer are located. The URI must be in the same region as the API endpoint that you are calling.
Annotations (dict) --
The S3 location of the CSV file that annotates your training documents.
S3Uri (string) -- [REQUIRED]
Specifies the Amazon S3 location where the annotations for an entity recognizer are located. The URI must be in the same region as the API endpoint that you are calling.
EntityList (dict) --
The S3 location of the CSV file that has the entity list for your custom entity recognizer.
S3Uri (string) -- [REQUIRED]
Specifies the Amazon S3 location where the entity list is located. The URI must be in the same region as the API endpoint that you are calling.
AugmentedManifests (list) --
A list of augmented manifest files that provide training data for your custom model. An augmented manifest file is a labeled dataset that is produced by Amazon SageMaker Ground Truth.
This parameter is required if you set DataFormat to AUGMENTED_MANIFEST .
(dict) --
An augmented manifest file that provides training data for your custom model. An augmented manifest file is a labeled dataset that is produced by Amazon SageMaker Ground Truth.
S3Uri (string) -- [REQUIRED]
The Amazon S3 location of the augmented manifest file.
AttributeNames (list) -- [REQUIRED]
The JSON attribute that contains the annotations for your training documents. The number of attribute names that you specify depends on whether your augmented manifest file is the output of a single labeling job or a chained labeling job.
If your file is the output of a single labeling job, specify the LabelAttributeName key that was used when the job was created in Ground Truth.
If your file is the output of a chained labeling job, specify the LabelAttributeName key for one or more jobs in the chain. Each LabelAttributeName key provides the annotations from an individual job.
(string) --
string
A unique identifier for the request. If you don't set the client request token, Amazon Comprehend generates one.
This field is autopopulated if not provided.
string
[REQUIRED]
You can specify any of the following languages supported by Amazon Comprehend: English ("en"), Spanish ("es"), French ("fr"), Italian ("it"), German ("de"), or Portuguese ("pt"). All documents must be in the same language.
string
ID for the AWS Key Management Service (KMS) key that Amazon Comprehend uses to encrypt data on the storage volume attached to the ML compute instance(s) that process the analysis job. The VolumeKmsKeyId can be either of the following formats:
KMS Key ID: "1234abcd-12ab-34cd-56ef-1234567890ab"
Amazon Resource Name (ARN) of a KMS Key: "arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"
dict
Configuration parameters for an optional private Virtual Private Cloud (VPC) containing the resources you are using for your custom entity recognizer. For more information, see Amazon VPC .
SecurityGroupIds (list) -- [REQUIRED]
The ID number for a security group on an instance of your private VPC. Security groups on your VPC function serve as a virtual firewall to control inbound and outbound traffic and provides security for the resources that you’ll be accessing on the VPC. This ID number is preceded by "sg-", for instance: "sg-03b388029b0a285ea". For more information, see Security Groups for your VPC .
(string) --
Subnets (list) -- [REQUIRED]
The ID for each subnet being used in your private VPC. This subnet is a subset of the a range of IPv4 addresses used by the VPC and is specific to a given availability zone in the VPC’s region. This ID number is preceded by "subnet-", for instance: "subnet-04ccf456919e69055". For more information, see VPCs and Subnets .
(string) --
string
ID for the AWS Key Management Service (KMS) key that Amazon Comprehend uses to encrypt trained custom models. The ModelKmsKeyId can be either of the following formats
KMS Key ID: "1234abcd-12ab-34cd-56ef-1234567890ab"
Amazon Resource Name (ARN) of a KMS Key: "arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"
dict
Response Syntax
{
'EntityRecognizerArn': 'string'
}
Response Structure
(dict) --
EntityRecognizerArn (string) --
The Amazon Resource Name (ARN) that identifies the entity recognizer.
{'DocumentClassifierProperties': {'ModelKmsKeyId': 'string'}}
Gets the properties associated with a document classifier.
See also: AWS API Documentation
Request Syntax
client.describe_document_classifier(
DocumentClassifierArn='string'
)
string
[REQUIRED]
The Amazon Resource Name (ARN) that identifies the document classifier. The operation returns this identifier in its response.
dict
Response Syntax
{
'DocumentClassifierProperties': {
'DocumentClassifierArn': 'string',
'LanguageCode': 'en'|'es'|'fr'|'de'|'it'|'pt'|'ar'|'hi'|'ja'|'ko'|'zh'|'zh-TW',
'Status': 'SUBMITTED'|'TRAINING'|'DELETING'|'STOP_REQUESTED'|'STOPPED'|'IN_ERROR'|'TRAINED',
'Message': 'string',
'SubmitTime': datetime(2015, 1, 1),
'EndTime': datetime(2015, 1, 1),
'TrainingStartTime': datetime(2015, 1, 1),
'TrainingEndTime': datetime(2015, 1, 1),
'InputDataConfig': {
'DataFormat': 'COMPREHEND_CSV'|'AUGMENTED_MANIFEST',
'S3Uri': 'string',
'LabelDelimiter': 'string',
'AugmentedManifests': [
{
'S3Uri': 'string',
'AttributeNames': [
'string',
]
},
]
},
'OutputDataConfig': {
'S3Uri': 'string',
'KmsKeyId': 'string'
},
'ClassifierMetadata': {
'NumberOfLabels': 123,
'NumberOfTrainedDocuments': 123,
'NumberOfTestDocuments': 123,
'EvaluationMetrics': {
'Accuracy': 123.0,
'Precision': 123.0,
'Recall': 123.0,
'F1Score': 123.0,
'MicroPrecision': 123.0,
'MicroRecall': 123.0,
'MicroF1Score': 123.0,
'HammingLoss': 123.0
}
},
'DataAccessRoleArn': 'string',
'VolumeKmsKeyId': 'string',
'VpcConfig': {
'SecurityGroupIds': [
'string',
],
'Subnets': [
'string',
]
},
'Mode': 'MULTI_CLASS'|'MULTI_LABEL',
'ModelKmsKeyId': 'string'
}
}
Response Structure
(dict) --
DocumentClassifierProperties (dict) --
An object that contains the properties associated with a document classifier.
DocumentClassifierArn (string) --
The Amazon Resource Name (ARN) that identifies the document classifier.
LanguageCode (string) --
The language code for the language of the documents that the classifier was trained on.
Status (string) --
The status of the document classifier. If the status is TRAINED the classifier is ready to use. If the status is FAILED you can see additional information about why the classifier wasn't trained in the Message field.
Message (string) --
Additional information about the status of the classifier.
SubmitTime (datetime) --
The time that the document classifier was submitted for training.
EndTime (datetime) --
The time that training the document classifier completed.
TrainingStartTime (datetime) --
Indicates the time when the training starts on documentation classifiers. You are billed for the time interval between this time and the value of TrainingEndTime.
TrainingEndTime (datetime) --
The time that training of the document classifier was completed. Indicates the time when the training completes on documentation classifiers. You are billed for the time interval between this time and the value of TrainingStartTime.
InputDataConfig (dict) --
The input data configuration that you supplied when you created the document classifier for training.
DataFormat (string) --
The format of your training data:
COMPREHEND_CSV : A two-column CSV file, where labels are provided in the first column, and documents are provided in the second. If you use this value, you must provide the S3Uri parameter in your request.
AUGMENTED_MANIFEST : A labeled dataset that is produced by Amazon SageMaker Ground Truth. This file is in JSON lines format. Each line is a complete JSON object that contains a training document and its associated labels. If you use this value, you must provide the AugmentedManifests parameter in your request.
If you don't specify a value, Amazon Comprehend uses COMPREHEND_CSV as the default.
S3Uri (string) --
The Amazon S3 URI for the input data. The S3 bucket must be in the same region as the API endpoint that you are calling. The URI can point to a single input file or it can provide the prefix for a collection of input files.
For example, if you use the URI S3://bucketName/prefix , if the prefix is a single file, Amazon Comprehend uses that file as input. If more than one file begins with the prefix, Amazon Comprehend uses all of them as input.
This parameter is required if you set DataFormat to COMPREHEND_CSV .
LabelDelimiter (string) --
Indicates the delimiter used to separate each label for training a multi-label classifier. The default delimiter between labels is a pipe (|). You can use a different character as a delimiter (if it's an allowed character) by specifying it under Delimiter for labels. If the training documents use a delimiter other than the default or the delimiter you specify, the labels on that line will be combined to make a single unique label, such as LABELLABELLABEL.
AugmentedManifests (list) --
A list of augmented manifest files that provide training data for your custom model. An augmented manifest file is a labeled dataset that is produced by Amazon SageMaker Ground Truth.
This parameter is required if you set DataFormat to AUGMENTED_MANIFEST .
(dict) --
An augmented manifest file that provides training data for your custom model. An augmented manifest file is a labeled dataset that is produced by Amazon SageMaker Ground Truth.
S3Uri (string) --
The Amazon S3 location of the augmented manifest file.
AttributeNames (list) --
The JSON attribute that contains the annotations for your training documents. The number of attribute names that you specify depends on whether your augmented manifest file is the output of a single labeling job or a chained labeling job.
If your file is the output of a single labeling job, specify the LabelAttributeName key that was used when the job was created in Ground Truth.
If your file is the output of a chained labeling job, specify the LabelAttributeName key for one or more jobs in the chain. Each LabelAttributeName key provides the annotations from an individual job.
(string) --
OutputDataConfig (dict) --
Provides output results configuration parameters for custom classifier jobs.
S3Uri (string) --
When you use the OutputDataConfig object while creating a custom classifier, you specify the Amazon S3 location where you want to write the confusion matrix. The URI must be in the same region as the API endpoint that you are calling. The location is used as the prefix for the actual location of this output file.
When the custom classifier job is finished, the service creates the output file in a directory specific to the job. The S3Uri field contains the location of the output file, called output.tar.gz . It is a compressed archive that contains the confusion matrix.
KmsKeyId (string) --
ID for the AWS Key Management Service (KMS) key that Amazon Comprehend uses to encrypt the output results from an analysis job. The KmsKeyId can be one of the following formats:
KMS Key ID: "1234abcd-12ab-34cd-56ef-1234567890ab"
Amazon Resource Name (ARN) of a KMS Key: "arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"
KMS Key Alias: "alias/ExampleAlias"
ARN of a KMS Key Alias: "arn:aws:kms:us-west-2:111122223333:alias/ExampleAlias"
ClassifierMetadata (dict) --
Information about the document classifier, including the number of documents used for training the classifier, the number of documents used for test the classifier, and an accuracy rating.
NumberOfLabels (integer) --
The number of labels in the input data.
NumberOfTrainedDocuments (integer) --
The number of documents in the input data that were used to train the classifier. Typically this is 80 to 90 percent of the input documents.
NumberOfTestDocuments (integer) --
The number of documents in the input data that were used to test the classifier. Typically this is 10 to 20 percent of the input documents, up to 10,000 documents.
EvaluationMetrics (dict) --
Describes the result metrics for the test data associated with an documentation classifier.
Accuracy (float) --
The fraction of the labels that were correct recognized. It is computed by dividing the number of labels in the test documents that were correctly recognized by the total number of labels in the test documents.
Precision (float) --
A measure of the usefulness of the classifier results in the test data. High precision means that the classifier returned substantially more relevant results than irrelevant ones.
Recall (float) --
A measure of how complete the classifier results are for the test data. High recall means that the classifier returned most of the relevant results.
F1Score (float) --
A measure of how accurate the classifier results are for the test data. It is derived from the Precision and Recall values. The F1Score is the harmonic average of the two scores. The highest score is 1, and the worst score is 0.
MicroPrecision (float) --
A measure of the usefulness of the recognizer results in the test data. High precision means that the recognizer returned substantially more relevant results than irrelevant ones. Unlike the Precision metric which comes from averaging the precision of all available labels, this is based on the overall score of all precision scores added together.
MicroRecall (float) --
A measure of how complete the classifier results are for the test data. High recall means that the classifier returned most of the relevant results. Specifically, this indicates how many of the correct categories in the text that the model can predict. It is a percentage of correct categories in the text that can found. Instead of averaging the recall scores of all labels (as with Recall), micro Recall is based on the overall score of all recall scores added together.
MicroF1Score (float) --
A measure of how accurate the classifier results are for the test data. It is a combination of the Micro Precision and Micro Recall values. The Micro F1Score is the harmonic mean of the two scores. The highest score is 1, and the worst score is 0.
HammingLoss (float) --
Indicates the fraction of labels that are incorrectly predicted. Also seen as the fraction of wrong labels compared to the total number of labels. Scores closer to zero are better.
DataAccessRoleArn (string) --
The Amazon Resource Name (ARN) of the AWS Identity and Management (IAM) role that grants Amazon Comprehend read access to your input data.
VolumeKmsKeyId (string) --
ID for the AWS Key Management Service (KMS) key that Amazon Comprehend uses to encrypt data on the storage volume attached to the ML compute instance(s) that process the analysis job. The VolumeKmsKeyId can be either of the following formats:
KMS Key ID: "1234abcd-12ab-34cd-56ef-1234567890ab"
Amazon Resource Name (ARN) of a KMS Key: "arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"
VpcConfig (dict) --
Configuration parameters for a private Virtual Private Cloud (VPC) containing the resources you are using for your custom classifier. For more information, see Amazon VPC .
SecurityGroupIds (list) --
The ID number for a security group on an instance of your private VPC. Security groups on your VPC function serve as a virtual firewall to control inbound and outbound traffic and provides security for the resources that you’ll be accessing on the VPC. This ID number is preceded by "sg-", for instance: "sg-03b388029b0a285ea". For more information, see Security Groups for your VPC .
(string) --
Subnets (list) --
The ID for each subnet being used in your private VPC. This subnet is a subset of the a range of IPv4 addresses used by the VPC and is specific to a given availability zone in the VPC’s region. This ID number is preceded by "subnet-", for instance: "subnet-04ccf456919e69055". For more information, see VPCs and Subnets .
(string) --
Mode (string) --
Indicates the mode in which the specific classifier was trained. This also indicates the format of input documents and the format of the confusion matrix. Each classifier can only be trained in one mode and this cannot be changed once the classifier is trained.
ModelKmsKeyId (string) --
ID for the AWS Key Management Service (KMS) key that Amazon Comprehend uses to encrypt trained custom models. The ModelKmsKeyId can be either of the following formats:
KMS Key ID: "1234abcd-12ab-34cd-56ef-1234567890ab"
Amazon Resource Name (ARN) of a KMS Key: "arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"
{'EndpointProperties': {'DataAccessRoleArn': 'string'}}
Gets the properties associated with a specific endpoint. Use this operation to get the status of an endpoint.
See also: AWS API Documentation
Request Syntax
client.describe_endpoint(
EndpointArn='string'
)
string
[REQUIRED]
The Amazon Resource Number (ARN) of the endpoint being described.
dict
Response Syntax
{
'EndpointProperties': {
'EndpointArn': 'string',
'Status': 'CREATING'|'DELETING'|'FAILED'|'IN_SERVICE'|'UPDATING',
'Message': 'string',
'ModelArn': 'string',
'DesiredInferenceUnits': 123,
'CurrentInferenceUnits': 123,
'CreationTime': datetime(2015, 1, 1),
'LastModifiedTime': datetime(2015, 1, 1),
'DataAccessRoleArn': 'string'
}
}
Response Structure
(dict) --
EndpointProperties (dict) --
Describes information associated with the specific endpoint.
EndpointArn (string) --
The Amazon Resource Number (ARN) of the endpoint.
Status (string) --
Specifies the status of the endpoint. Because the endpoint updates and creation are asynchronous, so customers will need to wait for the endpoint to be Ready status before making inference requests.
Message (string) --
Specifies a reason for failure in cases of Failed status.
ModelArn (string) --
The Amazon Resource Number (ARN) of the model to which the endpoint is attached.
DesiredInferenceUnits (integer) --
The desired number of inference units to be used by the model using this endpoint. Each inference unit represents of a throughput of 100 characters per second.
CurrentInferenceUnits (integer) --
The number of inference units currently used by the model using this endpoint.
CreationTime (datetime) --
The creation date and time of the endpoint.
LastModifiedTime (datetime) --
The date and time that the endpoint was last modified.
DataAccessRoleArn (string) --
The Amazon Resource Name (ARN) of the AWS identity and Access Management (IAM) role that grants Amazon Comprehend read access to trained custom models encrypted with a customer managed key (ModelKmsKeyId).
{'EntityRecognizerProperties': {'ModelKmsKeyId': 'string'}}
Provides details about an entity recognizer including status, S3 buckets containing training data, recognizer metadata, metrics, and so on.
See also: AWS API Documentation
Request Syntax
client.describe_entity_recognizer(
EntityRecognizerArn='string'
)
string
[REQUIRED]
The Amazon Resource Name (ARN) that identifies the entity recognizer.
dict
Response Syntax
{
'EntityRecognizerProperties': {
'EntityRecognizerArn': 'string',
'LanguageCode': 'en'|'es'|'fr'|'de'|'it'|'pt'|'ar'|'hi'|'ja'|'ko'|'zh'|'zh-TW',
'Status': 'SUBMITTED'|'TRAINING'|'DELETING'|'STOP_REQUESTED'|'STOPPED'|'IN_ERROR'|'TRAINED',
'Message': 'string',
'SubmitTime': datetime(2015, 1, 1),
'EndTime': datetime(2015, 1, 1),
'TrainingStartTime': datetime(2015, 1, 1),
'TrainingEndTime': datetime(2015, 1, 1),
'InputDataConfig': {
'DataFormat': 'COMPREHEND_CSV'|'AUGMENTED_MANIFEST',
'EntityTypes': [
{
'Type': 'string'
},
],
'Documents': {
'S3Uri': 'string'
},
'Annotations': {
'S3Uri': 'string'
},
'EntityList': {
'S3Uri': 'string'
},
'AugmentedManifests': [
{
'S3Uri': 'string',
'AttributeNames': [
'string',
]
},
]
},
'RecognizerMetadata': {
'NumberOfTrainedDocuments': 123,
'NumberOfTestDocuments': 123,
'EvaluationMetrics': {
'Precision': 123.0,
'Recall': 123.0,
'F1Score': 123.0
},
'EntityTypes': [
{
'Type': 'string',
'EvaluationMetrics': {
'Precision': 123.0,
'Recall': 123.0,
'F1Score': 123.0
},
'NumberOfTrainMentions': 123
},
]
},
'DataAccessRoleArn': 'string',
'VolumeKmsKeyId': 'string',
'VpcConfig': {
'SecurityGroupIds': [
'string',
],
'Subnets': [
'string',
]
},
'ModelKmsKeyId': 'string'
}
}
Response Structure
(dict) --
EntityRecognizerProperties (dict) --
Describes information associated with an entity recognizer.
EntityRecognizerArn (string) --
The Amazon Resource Name (ARN) that identifies the entity recognizer.
LanguageCode (string) --
The language of the input documents. All documents must be in the same language. Only English ("en") is currently supported.
Status (string) --
Provides the status of the entity recognizer.
Message (string) --
A description of the status of the recognizer.
SubmitTime (datetime) --
The time that the recognizer was submitted for processing.
EndTime (datetime) --
The time that the recognizer creation completed.
TrainingStartTime (datetime) --
The time that training of the entity recognizer started.
TrainingEndTime (datetime) --
The time that training of the entity recognizer was completed.
InputDataConfig (dict) --
The input data properties of an entity recognizer.
DataFormat (string) --
The format of your training data:
COMPREHEND_CSV : A CSV file that supplements your training documents. The CSV file contains information about the custom entities that your trained model will detect. The required format of the file depends on whether you are providing annotations or an entity list. If you use this value, you must provide your CSV file by using either the Annotations or EntityList parameters. You must provide your training documents by using the Documents parameter.
AUGMENTED_MANIFEST : A labeled dataset that is produced by Amazon SageMaker Ground Truth. This file is in JSON lines format. Each line is a complete JSON object that contains a training document and its labels. Each label annotates a named entity in the training document. If you use this value, you must provide the AugmentedManifests parameter in your request.
If you don't specify a value, Amazon Comprehend uses COMPREHEND_CSV as the default.
EntityTypes (list) --
The entity types in the labeled training data that Amazon Comprehend uses to train the custom entity recognizer. Any entity types that you don't specify are ignored.
A maximum of 25 entity types can be used at one time to train an entity recognizer. Entity types must not contain the following invalid characters: n (line break), \n (escaped line break), r (carriage return), \r (escaped carriage return), t (tab), \t (escaped tab), space, and , (comma).
(dict) --
An entity type within a labeled training dataset that Amazon Comprehend uses to train a custom entity recognizer.
Type (string) --
An entity type within a labeled training dataset that Amazon Comprehend uses to train a custom entity recognizer.
Entity types must not contain the following invalid characters: n (line break), \n (escaped line break, r (carriage return), \r (escaped carriage return), t (tab), \t (escaped tab), space, and , (comma).
Documents (dict) --
The S3 location of the folder that contains the training documents for your custom entity recognizer.
This parameter is required if you set DataFormat to COMPREHEND_CSV .
S3Uri (string) --
Specifies the Amazon S3 location where the training documents for an entity recognizer are located. The URI must be in the same region as the API endpoint that you are calling.
Annotations (dict) --
The S3 location of the CSV file that annotates your training documents.
S3Uri (string) --
Specifies the Amazon S3 location where the annotations for an entity recognizer are located. The URI must be in the same region as the API endpoint that you are calling.
EntityList (dict) --
The S3 location of the CSV file that has the entity list for your custom entity recognizer.
S3Uri (string) --
Specifies the Amazon S3 location where the entity list is located. The URI must be in the same region as the API endpoint that you are calling.
AugmentedManifests (list) --
A list of augmented manifest files that provide training data for your custom model. An augmented manifest file is a labeled dataset that is produced by Amazon SageMaker Ground Truth.
This parameter is required if you set DataFormat to AUGMENTED_MANIFEST .
(dict) --
An augmented manifest file that provides training data for your custom model. An augmented manifest file is a labeled dataset that is produced by Amazon SageMaker Ground Truth.
S3Uri (string) --
The Amazon S3 location of the augmented manifest file.
AttributeNames (list) --
The JSON attribute that contains the annotations for your training documents. The number of attribute names that you specify depends on whether your augmented manifest file is the output of a single labeling job or a chained labeling job.
If your file is the output of a single labeling job, specify the LabelAttributeName key that was used when the job was created in Ground Truth.
If your file is the output of a chained labeling job, specify the LabelAttributeName key for one or more jobs in the chain. Each LabelAttributeName key provides the annotations from an individual job.
(string) --
RecognizerMetadata (dict) --
Provides information about an entity recognizer.
NumberOfTrainedDocuments (integer) --
The number of documents in the input data that were used to train the entity recognizer. Typically this is 80 to 90 percent of the input documents.
NumberOfTestDocuments (integer) --
The number of documents in the input data that were used to test the entity recognizer. Typically this is 10 to 20 percent of the input documents.
EvaluationMetrics (dict) --
Detailed information about the accuracy of an entity recognizer.
Precision (float) --
A measure of the usefulness of the recognizer results in the test data. High precision means that the recognizer returned substantially more relevant results than irrelevant ones.
Recall (float) --
A measure of how complete the recognizer results are for the test data. High recall means that the recognizer returned most of the relevant results.
F1Score (float) --
A measure of how accurate the recognizer results are for the test data. It is derived from the Precision and Recall values. The F1Score is the harmonic average of the two scores. The highest score is 1, and the worst score is 0.
EntityTypes (list) --
Entity types from the metadata of an entity recognizer.
(dict) --
Individual item from the list of entity types in the metadata of an entity recognizer.
Type (string) --
Type of entity from the list of entity types in the metadata of an entity recognizer.
EvaluationMetrics (dict) --
Detailed information about the accuracy of the entity recognizer for a specific item on the list of entity types.
Precision (float) --
A measure of the usefulness of the recognizer results for a specific entity type in the test data. High precision means that the recognizer returned substantially more relevant results than irrelevant ones.
Recall (float) --
A measure of how complete the recognizer results are for a specific entity type in the test data. High recall means that the recognizer returned most of the relevant results.
F1Score (float) --
A measure of how accurate the recognizer results are for a specific entity type in the test data. It is derived from the Precision and Recall values. The F1Score is the harmonic average of the two scores. The highest score is 1, and the worst score is 0.
NumberOfTrainMentions (integer) --
Indicates the number of times the given entity type was seen in the training data.
DataAccessRoleArn (string) --
The Amazon Resource Name (ARN) of the AWS Identity and Management (IAM) role that grants Amazon Comprehend read access to your input data.
VolumeKmsKeyId (string) --
ID for the AWS Key Management Service (KMS) key that Amazon Comprehend uses to encrypt data on the storage volume attached to the ML compute instance(s) that process the analysis job. The VolumeKmsKeyId can be either of the following formats:
KMS Key ID: "1234abcd-12ab-34cd-56ef-1234567890ab"
Amazon Resource Name (ARN) of a KMS Key: "arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"
VpcConfig (dict) --
Configuration parameters for a private Virtual Private Cloud (VPC) containing the resources you are using for your custom entity recognizer. For more information, see Amazon VPC .
SecurityGroupIds (list) --
The ID number for a security group on an instance of your private VPC. Security groups on your VPC function serve as a virtual firewall to control inbound and outbound traffic and provides security for the resources that you’ll be accessing on the VPC. This ID number is preceded by "sg-", for instance: "sg-03b388029b0a285ea". For more information, see Security Groups for your VPC .
(string) --
Subnets (list) --
The ID for each subnet being used in your private VPC. This subnet is a subset of the a range of IPv4 addresses used by the VPC and is specific to a given availability zone in the VPC’s region. This ID number is preceded by "subnet-", for instance: "subnet-04ccf456919e69055". For more information, see VPCs and Subnets .
(string) --
ModelKmsKeyId (string) --
ID for the AWS Key Management Service (KMS) key that Amazon Comprehend uses to encrypt trained custom models. The ModelKmsKeyId can be either of the following formats:
KMS Key ID: "1234abcd-12ab-34cd-56ef-1234567890ab"
Amazon Resource Name (ARN) of a KMS Key: "arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"
{'DocumentClassifierPropertiesList': {'ModelKmsKeyId': 'string'}}
Gets a list of the document classifiers that you have created.
See also: AWS API Documentation
Request Syntax
client.list_document_classifiers(
Filter={
'Status': 'SUBMITTED'|'TRAINING'|'DELETING'|'STOP_REQUESTED'|'STOPPED'|'IN_ERROR'|'TRAINED',
'SubmitTimeBefore': datetime(2015, 1, 1),
'SubmitTimeAfter': datetime(2015, 1, 1)
},
NextToken='string',
MaxResults=123
)
dict
Filters the jobs that are returned. You can filter jobs on their name, status, or the date and time that they were submitted. You can only set one filter at a time.
Status (string) --
Filters the list of classifiers based on status.
SubmitTimeBefore (datetime) --
Filters the list of classifiers based on the time that the classifier was submitted for processing. Returns only classifiers submitted before the specified time. Classifiers are returned in ascending order, oldest to newest.
SubmitTimeAfter (datetime) --
Filters the list of classifiers based on the time that the classifier was submitted for processing. Returns only classifiers submitted after the specified time. Classifiers are returned in descending order, newest to oldest.
string
Identifies the next page of results to return.
integer
The maximum number of results to return in each page. The default is 100.
dict
Response Syntax
{
'DocumentClassifierPropertiesList': [
{
'DocumentClassifierArn': 'string',
'LanguageCode': 'en'|'es'|'fr'|'de'|'it'|'pt'|'ar'|'hi'|'ja'|'ko'|'zh'|'zh-TW',
'Status': 'SUBMITTED'|'TRAINING'|'DELETING'|'STOP_REQUESTED'|'STOPPED'|'IN_ERROR'|'TRAINED',
'Message': 'string',
'SubmitTime': datetime(2015, 1, 1),
'EndTime': datetime(2015, 1, 1),
'TrainingStartTime': datetime(2015, 1, 1),
'TrainingEndTime': datetime(2015, 1, 1),
'InputDataConfig': {
'DataFormat': 'COMPREHEND_CSV'|'AUGMENTED_MANIFEST',
'S3Uri': 'string',
'LabelDelimiter': 'string',
'AugmentedManifests': [
{
'S3Uri': 'string',
'AttributeNames': [
'string',
]
},
]
},
'OutputDataConfig': {
'S3Uri': 'string',
'KmsKeyId': 'string'
},
'ClassifierMetadata': {
'NumberOfLabels': 123,
'NumberOfTrainedDocuments': 123,
'NumberOfTestDocuments': 123,
'EvaluationMetrics': {
'Accuracy': 123.0,
'Precision': 123.0,
'Recall': 123.0,
'F1Score': 123.0,
'MicroPrecision': 123.0,
'MicroRecall': 123.0,
'MicroF1Score': 123.0,
'HammingLoss': 123.0
}
},
'DataAccessRoleArn': 'string',
'VolumeKmsKeyId': 'string',
'VpcConfig': {
'SecurityGroupIds': [
'string',
],
'Subnets': [
'string',
]
},
'Mode': 'MULTI_CLASS'|'MULTI_LABEL',
'ModelKmsKeyId': 'string'
},
],
'NextToken': 'string'
}
Response Structure
(dict) --
DocumentClassifierPropertiesList (list) --
A list containing the properties of each job returned.
(dict) --
Provides information about a document classifier.
DocumentClassifierArn (string) --
The Amazon Resource Name (ARN) that identifies the document classifier.
LanguageCode (string) --
The language code for the language of the documents that the classifier was trained on.
Status (string) --
The status of the document classifier. If the status is TRAINED the classifier is ready to use. If the status is FAILED you can see additional information about why the classifier wasn't trained in the Message field.
Message (string) --
Additional information about the status of the classifier.
SubmitTime (datetime) --
The time that the document classifier was submitted for training.
EndTime (datetime) --
The time that training the document classifier completed.
TrainingStartTime (datetime) --
Indicates the time when the training starts on documentation classifiers. You are billed for the time interval between this time and the value of TrainingEndTime.
TrainingEndTime (datetime) --
The time that training of the document classifier was completed. Indicates the time when the training completes on documentation classifiers. You are billed for the time interval between this time and the value of TrainingStartTime.
InputDataConfig (dict) --
The input data configuration that you supplied when you created the document classifier for training.
DataFormat (string) --
The format of your training data:
COMPREHEND_CSV : A two-column CSV file, where labels are provided in the first column, and documents are provided in the second. If you use this value, you must provide the S3Uri parameter in your request.
AUGMENTED_MANIFEST : A labeled dataset that is produced by Amazon SageMaker Ground Truth. This file is in JSON lines format. Each line is a complete JSON object that contains a training document and its associated labels. If you use this value, you must provide the AugmentedManifests parameter in your request.
If you don't specify a value, Amazon Comprehend uses COMPREHEND_CSV as the default.
S3Uri (string) --
The Amazon S3 URI for the input data. The S3 bucket must be in the same region as the API endpoint that you are calling. The URI can point to a single input file or it can provide the prefix for a collection of input files.
For example, if you use the URI S3://bucketName/prefix , if the prefix is a single file, Amazon Comprehend uses that file as input. If more than one file begins with the prefix, Amazon Comprehend uses all of them as input.
This parameter is required if you set DataFormat to COMPREHEND_CSV .
LabelDelimiter (string) --
Indicates the delimiter used to separate each label for training a multi-label classifier. The default delimiter between labels is a pipe (|). You can use a different character as a delimiter (if it's an allowed character) by specifying it under Delimiter for labels. If the training documents use a delimiter other than the default or the delimiter you specify, the labels on that line will be combined to make a single unique label, such as LABELLABELLABEL.
AugmentedManifests (list) --
A list of augmented manifest files that provide training data for your custom model. An augmented manifest file is a labeled dataset that is produced by Amazon SageMaker Ground Truth.
This parameter is required if you set DataFormat to AUGMENTED_MANIFEST .
(dict) --
An augmented manifest file that provides training data for your custom model. An augmented manifest file is a labeled dataset that is produced by Amazon SageMaker Ground Truth.
S3Uri (string) --
The Amazon S3 location of the augmented manifest file.
AttributeNames (list) --
The JSON attribute that contains the annotations for your training documents. The number of attribute names that you specify depends on whether your augmented manifest file is the output of a single labeling job or a chained labeling job.
If your file is the output of a single labeling job, specify the LabelAttributeName key that was used when the job was created in Ground Truth.
If your file is the output of a chained labeling job, specify the LabelAttributeName key for one or more jobs in the chain. Each LabelAttributeName key provides the annotations from an individual job.
(string) --
OutputDataConfig (dict) --
Provides output results configuration parameters for custom classifier jobs.
S3Uri (string) --
When you use the OutputDataConfig object while creating a custom classifier, you specify the Amazon S3 location where you want to write the confusion matrix. The URI must be in the same region as the API endpoint that you are calling. The location is used as the prefix for the actual location of this output file.
When the custom classifier job is finished, the service creates the output file in a directory specific to the job. The S3Uri field contains the location of the output file, called output.tar.gz . It is a compressed archive that contains the confusion matrix.
KmsKeyId (string) --
ID for the AWS Key Management Service (KMS) key that Amazon Comprehend uses to encrypt the output results from an analysis job. The KmsKeyId can be one of the following formats:
KMS Key ID: "1234abcd-12ab-34cd-56ef-1234567890ab"
Amazon Resource Name (ARN) of a KMS Key: "arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"
KMS Key Alias: "alias/ExampleAlias"
ARN of a KMS Key Alias: "arn:aws:kms:us-west-2:111122223333:alias/ExampleAlias"
ClassifierMetadata (dict) --
Information about the document classifier, including the number of documents used for training the classifier, the number of documents used for test the classifier, and an accuracy rating.
NumberOfLabels (integer) --
The number of labels in the input data.
NumberOfTrainedDocuments (integer) --
The number of documents in the input data that were used to train the classifier. Typically this is 80 to 90 percent of the input documents.
NumberOfTestDocuments (integer) --
The number of documents in the input data that were used to test the classifier. Typically this is 10 to 20 percent of the input documents, up to 10,000 documents.
EvaluationMetrics (dict) --
Describes the result metrics for the test data associated with an documentation classifier.
Accuracy (float) --
The fraction of the labels that were correct recognized. It is computed by dividing the number of labels in the test documents that were correctly recognized by the total number of labels in the test documents.
Precision (float) --
A measure of the usefulness of the classifier results in the test data. High precision means that the classifier returned substantially more relevant results than irrelevant ones.
Recall (float) --
A measure of how complete the classifier results are for the test data. High recall means that the classifier returned most of the relevant results.
F1Score (float) --
A measure of how accurate the classifier results are for the test data. It is derived from the Precision and Recall values. The F1Score is the harmonic average of the two scores. The highest score is 1, and the worst score is 0.
MicroPrecision (float) --
A measure of the usefulness of the recognizer results in the test data. High precision means that the recognizer returned substantially more relevant results than irrelevant ones. Unlike the Precision metric which comes from averaging the precision of all available labels, this is based on the overall score of all precision scores added together.
MicroRecall (float) --
A measure of how complete the classifier results are for the test data. High recall means that the classifier returned most of the relevant results. Specifically, this indicates how many of the correct categories in the text that the model can predict. It is a percentage of correct categories in the text that can found. Instead of averaging the recall scores of all labels (as with Recall), micro Recall is based on the overall score of all recall scores added together.
MicroF1Score (float) --
A measure of how accurate the classifier results are for the test data. It is a combination of the Micro Precision and Micro Recall values. The Micro F1Score is the harmonic mean of the two scores. The highest score is 1, and the worst score is 0.
HammingLoss (float) --
Indicates the fraction of labels that are incorrectly predicted. Also seen as the fraction of wrong labels compared to the total number of labels. Scores closer to zero are better.
DataAccessRoleArn (string) --
The Amazon Resource Name (ARN) of the AWS Identity and Management (IAM) role that grants Amazon Comprehend read access to your input data.
VolumeKmsKeyId (string) --
ID for the AWS Key Management Service (KMS) key that Amazon Comprehend uses to encrypt data on the storage volume attached to the ML compute instance(s) that process the analysis job. The VolumeKmsKeyId can be either of the following formats:
KMS Key ID: "1234abcd-12ab-34cd-56ef-1234567890ab"
Amazon Resource Name (ARN) of a KMS Key: "arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"
VpcConfig (dict) --
Configuration parameters for a private Virtual Private Cloud (VPC) containing the resources you are using for your custom classifier. For more information, see Amazon VPC .
SecurityGroupIds (list) --
The ID number for a security group on an instance of your private VPC. Security groups on your VPC function serve as a virtual firewall to control inbound and outbound traffic and provides security for the resources that you’ll be accessing on the VPC. This ID number is preceded by "sg-", for instance: "sg-03b388029b0a285ea". For more information, see Security Groups for your VPC .
(string) --
Subnets (list) --
The ID for each subnet being used in your private VPC. This subnet is a subset of the a range of IPv4 addresses used by the VPC and is specific to a given availability zone in the VPC’s region. This ID number is preceded by "subnet-", for instance: "subnet-04ccf456919e69055". For more information, see VPCs and Subnets .
(string) --
Mode (string) --
Indicates the mode in which the specific classifier was trained. This also indicates the format of input documents and the format of the confusion matrix. Each classifier can only be trained in one mode and this cannot be changed once the classifier is trained.
ModelKmsKeyId (string) --
ID for the AWS Key Management Service (KMS) key that Amazon Comprehend uses to encrypt trained custom models. The ModelKmsKeyId can be either of the following formats:
KMS Key ID: "1234abcd-12ab-34cd-56ef-1234567890ab"
Amazon Resource Name (ARN) of a KMS Key: "arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"
NextToken (string) --
Identifies the next page of results to return.
{'EndpointPropertiesList': {'DataAccessRoleArn': 'string'}}
Gets a list of all existing endpoints that you've created.
See also: AWS API Documentation
Request Syntax
client.list_endpoints(
Filter={
'ModelArn': 'string',
'Status': 'CREATING'|'DELETING'|'FAILED'|'IN_SERVICE'|'UPDATING',
'CreationTimeBefore': datetime(2015, 1, 1),
'CreationTimeAfter': datetime(2015, 1, 1)
},
NextToken='string',
MaxResults=123
)
dict
Filters the endpoints that are returned. You can filter endpoints on their name, model, status, or the date and time that they were created. You can only set one filter at a time.
ModelArn (string) --
The Amazon Resource Number (ARN) of the model to which the endpoint is attached.
Status (string) --
Specifies the status of the endpoint being returned. Possible values are: Creating, Ready, Updating, Deleting, Failed.
CreationTimeBefore (datetime) --
Specifies a date before which the returned endpoint or endpoints were created.
CreationTimeAfter (datetime) --
Specifies a date after which the returned endpoint or endpoints were created.
string
Identifies the next page of results to return.
integer
The maximum number of results to return in each page. The default is 100.
dict
Response Syntax
{
'EndpointPropertiesList': [
{
'EndpointArn': 'string',
'Status': 'CREATING'|'DELETING'|'FAILED'|'IN_SERVICE'|'UPDATING',
'Message': 'string',
'ModelArn': 'string',
'DesiredInferenceUnits': 123,
'CurrentInferenceUnits': 123,
'CreationTime': datetime(2015, 1, 1),
'LastModifiedTime': datetime(2015, 1, 1),
'DataAccessRoleArn': 'string'
},
],
'NextToken': 'string'
}
Response Structure
(dict) --
EndpointPropertiesList (list) --
Displays a list of endpoint properties being retrieved by the service in response to the request.
(dict) --
Specifies information about the specified endpoint.
EndpointArn (string) --
The Amazon Resource Number (ARN) of the endpoint.
Status (string) --
Specifies the status of the endpoint. Because the endpoint updates and creation are asynchronous, so customers will need to wait for the endpoint to be Ready status before making inference requests.
Message (string) --
Specifies a reason for failure in cases of Failed status.
ModelArn (string) --
The Amazon Resource Number (ARN) of the model to which the endpoint is attached.
DesiredInferenceUnits (integer) --
The desired number of inference units to be used by the model using this endpoint. Each inference unit represents of a throughput of 100 characters per second.
CurrentInferenceUnits (integer) --
The number of inference units currently used by the model using this endpoint.
CreationTime (datetime) --
The creation date and time of the endpoint.
LastModifiedTime (datetime) --
The date and time that the endpoint was last modified.
DataAccessRoleArn (string) --
The Amazon Resource Name (ARN) of the AWS identity and Access Management (IAM) role that grants Amazon Comprehend read access to trained custom models encrypted with a customer managed key (ModelKmsKeyId).
NextToken (string) --
Identifies the next page of results to return.
{'EntityRecognizerPropertiesList': {'ModelKmsKeyId': 'string'}}
Gets a list of the properties of all entity recognizers that you created, including recognizers currently in training. Allows you to filter the list of recognizers based on criteria such as status and submission time. This call returns up to 500 entity recognizers in the list, with a default number of 100 recognizers in the list.
The results of this list are not in any particular order. Please get the list and sort locally if needed.
See also: AWS API Documentation
Request Syntax
client.list_entity_recognizers(
Filter={
'Status': 'SUBMITTED'|'TRAINING'|'DELETING'|'STOP_REQUESTED'|'STOPPED'|'IN_ERROR'|'TRAINED',
'SubmitTimeBefore': datetime(2015, 1, 1),
'SubmitTimeAfter': datetime(2015, 1, 1)
},
NextToken='string',
MaxResults=123
)
dict
Filters the list of entities returned. You can filter on Status , SubmitTimeBefore , or SubmitTimeAfter . You can only set one filter at a time.
Status (string) --
The status of an entity recognizer.
SubmitTimeBefore (datetime) --
Filters the list of entities based on the time that the list was submitted for processing. Returns only jobs submitted before the specified time. Jobs are returned in descending order, newest to oldest.
SubmitTimeAfter (datetime) --
Filters the list of entities based on the time that the list was submitted for processing. Returns only jobs submitted after the specified time. Jobs are returned in ascending order, oldest to newest.
string
Identifies the next page of results to return.
integer
The maximum number of results to return on each page. The default is 100.
dict
Response Syntax
{
'EntityRecognizerPropertiesList': [
{
'EntityRecognizerArn': 'string',
'LanguageCode': 'en'|'es'|'fr'|'de'|'it'|'pt'|'ar'|'hi'|'ja'|'ko'|'zh'|'zh-TW',
'Status': 'SUBMITTED'|'TRAINING'|'DELETING'|'STOP_REQUESTED'|'STOPPED'|'IN_ERROR'|'TRAINED',
'Message': 'string',
'SubmitTime': datetime(2015, 1, 1),
'EndTime': datetime(2015, 1, 1),
'TrainingStartTime': datetime(2015, 1, 1),
'TrainingEndTime': datetime(2015, 1, 1),
'InputDataConfig': {
'DataFormat': 'COMPREHEND_CSV'|'AUGMENTED_MANIFEST',
'EntityTypes': [
{
'Type': 'string'
},
],
'Documents': {
'S3Uri': 'string'
},
'Annotations': {
'S3Uri': 'string'
},
'EntityList': {
'S3Uri': 'string'
},
'AugmentedManifests': [
{
'S3Uri': 'string',
'AttributeNames': [
'string',
]
},
]
},
'RecognizerMetadata': {
'NumberOfTrainedDocuments': 123,
'NumberOfTestDocuments': 123,
'EvaluationMetrics': {
'Precision': 123.0,
'Recall': 123.0,
'F1Score': 123.0
},
'EntityTypes': [
{
'Type': 'string',
'EvaluationMetrics': {
'Precision': 123.0,
'Recall': 123.0,
'F1Score': 123.0
},
'NumberOfTrainMentions': 123
},
]
},
'DataAccessRoleArn': 'string',
'VolumeKmsKeyId': 'string',
'VpcConfig': {
'SecurityGroupIds': [
'string',
],
'Subnets': [
'string',
]
},
'ModelKmsKeyId': 'string'
},
],
'NextToken': 'string'
}
Response Structure
(dict) --
EntityRecognizerPropertiesList (list) --
The list of properties of an entity recognizer.
(dict) --
Describes information about an entity recognizer.
EntityRecognizerArn (string) --
The Amazon Resource Name (ARN) that identifies the entity recognizer.
LanguageCode (string) --
The language of the input documents. All documents must be in the same language. Only English ("en") is currently supported.
Status (string) --
Provides the status of the entity recognizer.
Message (string) --
A description of the status of the recognizer.
SubmitTime (datetime) --
The time that the recognizer was submitted for processing.
EndTime (datetime) --
The time that the recognizer creation completed.
TrainingStartTime (datetime) --
The time that training of the entity recognizer started.
TrainingEndTime (datetime) --
The time that training of the entity recognizer was completed.
InputDataConfig (dict) --
The input data properties of an entity recognizer.
DataFormat (string) --
The format of your training data:
COMPREHEND_CSV : A CSV file that supplements your training documents. The CSV file contains information about the custom entities that your trained model will detect. The required format of the file depends on whether you are providing annotations or an entity list. If you use this value, you must provide your CSV file by using either the Annotations or EntityList parameters. You must provide your training documents by using the Documents parameter.
AUGMENTED_MANIFEST : A labeled dataset that is produced by Amazon SageMaker Ground Truth. This file is in JSON lines format. Each line is a complete JSON object that contains a training document and its labels. Each label annotates a named entity in the training document. If you use this value, you must provide the AugmentedManifests parameter in your request.
If you don't specify a value, Amazon Comprehend uses COMPREHEND_CSV as the default.
EntityTypes (list) --
The entity types in the labeled training data that Amazon Comprehend uses to train the custom entity recognizer. Any entity types that you don't specify are ignored.
A maximum of 25 entity types can be used at one time to train an entity recognizer. Entity types must not contain the following invalid characters: n (line break), \n (escaped line break), r (carriage return), \r (escaped carriage return), t (tab), \t (escaped tab), space, and , (comma).
(dict) --
An entity type within a labeled training dataset that Amazon Comprehend uses to train a custom entity recognizer.
Type (string) --
An entity type within a labeled training dataset that Amazon Comprehend uses to train a custom entity recognizer.
Entity types must not contain the following invalid characters: n (line break), \n (escaped line break, r (carriage return), \r (escaped carriage return), t (tab), \t (escaped tab), space, and , (comma).
Documents (dict) --
The S3 location of the folder that contains the training documents for your custom entity recognizer.
This parameter is required if you set DataFormat to COMPREHEND_CSV .
S3Uri (string) --
Specifies the Amazon S3 location where the training documents for an entity recognizer are located. The URI must be in the same region as the API endpoint that you are calling.
Annotations (dict) --
The S3 location of the CSV file that annotates your training documents.
S3Uri (string) --
Specifies the Amazon S3 location where the annotations for an entity recognizer are located. The URI must be in the same region as the API endpoint that you are calling.
EntityList (dict) --
The S3 location of the CSV file that has the entity list for your custom entity recognizer.
S3Uri (string) --
Specifies the Amazon S3 location where the entity list is located. The URI must be in the same region as the API endpoint that you are calling.
AugmentedManifests (list) --
A list of augmented manifest files that provide training data for your custom model. An augmented manifest file is a labeled dataset that is produced by Amazon SageMaker Ground Truth.
This parameter is required if you set DataFormat to AUGMENTED_MANIFEST .
(dict) --
An augmented manifest file that provides training data for your custom model. An augmented manifest file is a labeled dataset that is produced by Amazon SageMaker Ground Truth.
S3Uri (string) --
The Amazon S3 location of the augmented manifest file.
AttributeNames (list) --
The JSON attribute that contains the annotations for your training documents. The number of attribute names that you specify depends on whether your augmented manifest file is the output of a single labeling job or a chained labeling job.
If your file is the output of a single labeling job, specify the LabelAttributeName key that was used when the job was created in Ground Truth.
If your file is the output of a chained labeling job, specify the LabelAttributeName key for one or more jobs in the chain. Each LabelAttributeName key provides the annotations from an individual job.
(string) --
RecognizerMetadata (dict) --
Provides information about an entity recognizer.
NumberOfTrainedDocuments (integer) --
The number of documents in the input data that were used to train the entity recognizer. Typically this is 80 to 90 percent of the input documents.
NumberOfTestDocuments (integer) --
The number of documents in the input data that were used to test the entity recognizer. Typically this is 10 to 20 percent of the input documents.
EvaluationMetrics (dict) --
Detailed information about the accuracy of an entity recognizer.
Precision (float) --
A measure of the usefulness of the recognizer results in the test data. High precision means that the recognizer returned substantially more relevant results than irrelevant ones.
Recall (float) --
A measure of how complete the recognizer results are for the test data. High recall means that the recognizer returned most of the relevant results.
F1Score (float) --
A measure of how accurate the recognizer results are for the test data. It is derived from the Precision and Recall values. The F1Score is the harmonic average of the two scores. The highest score is 1, and the worst score is 0.
EntityTypes (list) --
Entity types from the metadata of an entity recognizer.
(dict) --
Individual item from the list of entity types in the metadata of an entity recognizer.
Type (string) --
Type of entity from the list of entity types in the metadata of an entity recognizer.
EvaluationMetrics (dict) --
Detailed information about the accuracy of the entity recognizer for a specific item on the list of entity types.
Precision (float) --
A measure of the usefulness of the recognizer results for a specific entity type in the test data. High precision means that the recognizer returned substantially more relevant results than irrelevant ones.
Recall (float) --
A measure of how complete the recognizer results are for a specific entity type in the test data. High recall means that the recognizer returned most of the relevant results.
F1Score (float) --
A measure of how accurate the recognizer results are for a specific entity type in the test data. It is derived from the Precision and Recall values. The F1Score is the harmonic average of the two scores. The highest score is 1, and the worst score is 0.
NumberOfTrainMentions (integer) --
Indicates the number of times the given entity type was seen in the training data.
DataAccessRoleArn (string) --
The Amazon Resource Name (ARN) of the AWS Identity and Management (IAM) role that grants Amazon Comprehend read access to your input data.
VolumeKmsKeyId (string) --
ID for the AWS Key Management Service (KMS) key that Amazon Comprehend uses to encrypt data on the storage volume attached to the ML compute instance(s) that process the analysis job. The VolumeKmsKeyId can be either of the following formats:
KMS Key ID: "1234abcd-12ab-34cd-56ef-1234567890ab"
Amazon Resource Name (ARN) of a KMS Key: "arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"
VpcConfig (dict) --
Configuration parameters for a private Virtual Private Cloud (VPC) containing the resources you are using for your custom entity recognizer. For more information, see Amazon VPC .
SecurityGroupIds (list) --
The ID number for a security group on an instance of your private VPC. Security groups on your VPC function serve as a virtual firewall to control inbound and outbound traffic and provides security for the resources that you’ll be accessing on the VPC. This ID number is preceded by "sg-", for instance: "sg-03b388029b0a285ea". For more information, see Security Groups for your VPC .
(string) --
Subnets (list) --
The ID for each subnet being used in your private VPC. This subnet is a subset of the a range of IPv4 addresses used by the VPC and is specific to a given availability zone in the VPC’s region. This ID number is preceded by "subnet-", for instance: "subnet-04ccf456919e69055". For more information, see VPCs and Subnets .
(string) --
ModelKmsKeyId (string) --
ID for the AWS Key Management Service (KMS) key that Amazon Comprehend uses to encrypt trained custom models. The ModelKmsKeyId can be either of the following formats:
KMS Key ID: "1234abcd-12ab-34cd-56ef-1234567890ab"
Amazon Resource Name (ARN) of a KMS Key: "arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"
NextToken (string) --
Identifies the next page of results to return.