Table of Contents
A low-level client representing Amazon Comprehend
Amazon Comprehend is an AWS service for gaining insight into the content of documents. Use these actions to determine the topics contained in your documents, the topics they discuss, the predominant sentiment expressed in them, the predominant language used, and more.
import boto3
client = boto3.client('comprehend')
These are the available methods:
Determines the dominant language of the input text for a batch of documents. For a list of languages that Amazon Comprehend can detect, see Amazon Comprehend Supported Languages .
See also: AWS API Documentation
Request Syntax
response = client.batch_detect_dominant_language(
TextList=[
'string',
]
)
[REQUIRED]
A list containing the text of the input documents. The list can contain a maximum of 25 documents. Each document should contain at least 20 characters and must contain fewer than 5,000 bytes of UTF-8 encoded characters.
{
'ResultList': [
{
'Index': 123,
'Languages': [
{
'LanguageCode': 'string',
'Score': ...
},
]
},
],
'ErrorList': [
{
'Index': 123,
'ErrorCode': 'string',
'ErrorMessage': 'string'
},
]
}
Response Structure
A list of objects containing the results of the operation. The results are sorted in ascending order by the Index field and match the order of the documents in the input list. If all of the documents contain an error, the ResultList is empty.
The result of calling the operation. The operation returns one object for each document that is successfully processed by the operation.
The zero-based index of the document in the input list.
One or more DominantLanguage objects describing the dominant languages in the document.
Returns the code for the dominant language in the input text and the level of confidence that Amazon Comprehend has in the accuracy of the detection.
The RFC 5646 language code for the dominant language. For more information about RFC 5646, see Tags for Identifying Languages on the IETF Tools web site.
The level of confidence that Amazon Comprehend has in the accuracy of the detection.
A list containing one object for each document that contained an error. The results are sorted in ascending order by the Index field and match the order of the documents in the input list. If there are no errors in the batch, the ErrorList is empty.
Describes an error that occurred while processing a document in a batch. The operation returns on BatchItemError object for each document that contained an error.
The zero-based index of the document in the input list.
The numeric error code of the error.
A text description of the error.
Exceptions
Inspects the text of a batch of documents for named entities and returns information about them. For more information about named entities, see how-entities
See also: AWS API Documentation
Request Syntax
response = client.batch_detect_entities(
TextList=[
'string',
],
LanguageCode='en'|'es'|'fr'|'de'|'it'|'pt'|'ar'|'hi'|'ja'|'ko'|'zh'|'zh-TW'
)
[REQUIRED]
A list containing the text of the input documents. The list can contain a maximum of 25 documents. Each document must contain fewer than 5,000 bytes of UTF-8 encoded characters.
[REQUIRED]
The language of the input documents. You can specify any of the primary languages supported by Amazon Comprehend. All documents must be in the same language.
dict
Response Syntax
{
'ResultList': [
{
'Index': 123,
'Entities': [
{
'Score': ...,
'Type': 'PERSON'|'LOCATION'|'ORGANIZATION'|'COMMERCIAL_ITEM'|'EVENT'|'DATE'|'QUANTITY'|'TITLE'|'OTHER',
'Text': 'string',
'BeginOffset': 123,
'EndOffset': 123
},
]
},
],
'ErrorList': [
{
'Index': 123,
'ErrorCode': 'string',
'ErrorMessage': 'string'
},
]
}
Response Structure
(dict) --
ResultList (list) --
A list of objects containing the results of the operation. The results are sorted in ascending order by the Index field and match the order of the documents in the input list. If all of the documents contain an error, the ResultList is empty.
(dict) --
The result of calling the operation. The operation returns one object for each document that is successfully processed by the operation.
Index (integer) --
The zero-based index of the document in the input list.
Entities (list) --
One or more Entity objects, one for each entity detected in the document.
(dict) --
Provides information about an entity.
Score (float) --
The level of confidence that Amazon Comprehend has in the accuracy of the detection.
Type (string) --
The entity's type.
Text (string) --
The text of the entity.
BeginOffset (integer) --
A character offset in the input text that shows where the entity begins (the first character is at position 0). The offset returns the position of each UTF-8 code point in the string. A code point is the abstract character from a particular graphical representation. For example, a multi-byte UTF-8 character maps to a single code point.
EndOffset (integer) --
A character offset in the input text that shows where the entity ends. The offset returns the position of each UTF-8 code point in the string. A code point is the abstract character from a particular graphical representation. For example, a multi-byte UTF-8 character maps to a single code point.
ErrorList (list) --
A list containing one object for each document that contained an error. The results are sorted in ascending order by the Index field and match the order of the documents in the input list. If there are no errors in the batch, the ErrorList is empty.
(dict) --
Describes an error that occurred while processing a document in a batch. The operation returns on BatchItemError object for each document that contained an error.
Index (integer) --
The zero-based index of the document in the input list.
ErrorCode (string) --
The numeric error code of the error.
ErrorMessage (string) --
A text description of the error.
Exceptions
Detects the key noun phrases found in a batch of documents.
See also: AWS API Documentation
Request Syntax
response = client.batch_detect_key_phrases(
TextList=[
'string',
],
LanguageCode='en'|'es'|'fr'|'de'|'it'|'pt'|'ar'|'hi'|'ja'|'ko'|'zh'|'zh-TW'
)
[REQUIRED]
A list containing the text of the input documents. The list can contain a maximum of 25 documents. Each document must contain fewer that 5,000 bytes of UTF-8 encoded characters.
[REQUIRED]
The language of the input documents. You can specify any of the primary languages supported by Amazon Comprehend. All documents must be in the same language.
dict
Response Syntax
{
'ResultList': [
{
'Index': 123,
'KeyPhrases': [
{
'Score': ...,
'Text': 'string',
'BeginOffset': 123,
'EndOffset': 123
},
]
},
],
'ErrorList': [
{
'Index': 123,
'ErrorCode': 'string',
'ErrorMessage': 'string'
},
]
}
Response Structure
(dict) --
ResultList (list) --
A list of objects containing the results of the operation. The results are sorted in ascending order by the Index field and match the order of the documents in the input list. If all of the documents contain an error, the ResultList is empty.
(dict) --
The result of calling the operation. The operation returns one object for each document that is successfully processed by the operation.
Index (integer) --
The zero-based index of the document in the input list.
KeyPhrases (list) --
One or more KeyPhrase objects, one for each key phrase detected in the document.
(dict) --
Describes a key noun phrase.
Score (float) --
The level of confidence that Amazon Comprehend has in the accuracy of the detection.
Text (string) --
The text of a key noun phrase.
BeginOffset (integer) --
A character offset in the input text that shows where the key phrase begins (the first character is at position 0). The offset returns the position of each UTF-8 code point in the string. A code point is the abstract character from a particular graphical representation. For example, a multi-byte UTF-8 character maps to a single code point.
EndOffset (integer) --
A character offset in the input text where the key phrase ends. The offset returns the position of each UTF-8 code point in the string. A code point is the abstract character from a particular graphical representation. For example, a multi-byte UTF-8 character maps to a single code point.
ErrorList (list) --
A list containing one object for each document that contained an error. The results are sorted in ascending order by the Index field and match the order of the documents in the input list. If there are no errors in the batch, the ErrorList is empty.
(dict) --
Describes an error that occurred while processing a document in a batch. The operation returns on BatchItemError object for each document that contained an error.
Index (integer) --
The zero-based index of the document in the input list.
ErrorCode (string) --
The numeric error code of the error.
ErrorMessage (string) --
A text description of the error.
Exceptions
Inspects a batch of documents and returns an inference of the prevailing sentiment, POSITIVE , NEUTRAL , MIXED , or NEGATIVE , in each one.
See also: AWS API Documentation
Request Syntax
response = client.batch_detect_sentiment(
TextList=[
'string',
],
LanguageCode='en'|'es'|'fr'|'de'|'it'|'pt'|'ar'|'hi'|'ja'|'ko'|'zh'|'zh-TW'
)
[REQUIRED]
A list containing the text of the input documents. The list can contain a maximum of 25 documents. Each document must contain fewer that 5,000 bytes of UTF-8 encoded characters.
[REQUIRED]
The language of the input documents. You can specify any of the primary languages supported by Amazon Comprehend. All documents must be in the same language.
dict
Response Syntax
{
'ResultList': [
{
'Index': 123,
'Sentiment': 'POSITIVE'|'NEGATIVE'|'NEUTRAL'|'MIXED',
'SentimentScore': {
'Positive': ...,
'Negative': ...,
'Neutral': ...,
'Mixed': ...
}
},
],
'ErrorList': [
{
'Index': 123,
'ErrorCode': 'string',
'ErrorMessage': 'string'
},
]
}
Response Structure
(dict) --
ResultList (list) --
A list of objects containing the results of the operation. The results are sorted in ascending order by the Index field and match the order of the documents in the input list. If all of the documents contain an error, the ResultList is empty.
(dict) --
The result of calling the operation. The operation returns one object for each document that is successfully processed by the operation.
Index (integer) --
The zero-based index of the document in the input list.
Sentiment (string) --
The sentiment detected in the document.
SentimentScore (dict) --
The level of confidence that Amazon Comprehend has in the accuracy of its sentiment detection.
Positive (float) --
The level of confidence that Amazon Comprehend has in the accuracy of its detection of the POSITIVE sentiment.
Negative (float) --
The level of confidence that Amazon Comprehend has in the accuracy of its detection of the NEGATIVE sentiment.
Neutral (float) --
The level of confidence that Amazon Comprehend has in the accuracy of its detection of the NEUTRAL sentiment.
Mixed (float) --
The level of confidence that Amazon Comprehend has in the accuracy of its detection of the MIXED sentiment.
ErrorList (list) --
A list containing one object for each document that contained an error. The results are sorted in ascending order by the Index field and match the order of the documents in the input list. If there are no errors in the batch, the ErrorList is empty.
(dict) --
Describes an error that occurred while processing a document in a batch. The operation returns on BatchItemError object for each document that contained an error.
Index (integer) --
The zero-based index of the document in the input list.
ErrorCode (string) --
The numeric error code of the error.
ErrorMessage (string) --
A text description of the error.
Exceptions
Inspects the text of a batch of documents for the syntax and part of speech of the words in the document and returns information about them. For more information, see how-syntax .
See also: AWS API Documentation
Request Syntax
response = client.batch_detect_syntax(
TextList=[
'string',
],
LanguageCode='en'|'es'|'fr'|'de'|'it'|'pt'
)
[REQUIRED]
A list containing the text of the input documents. The list can contain a maximum of 25 documents. Each document must contain fewer that 5,000 bytes of UTF-8 encoded characters.
[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.
dict
Response Syntax
{
'ResultList': [
{
'Index': 123,
'SyntaxTokens': [
{
'TokenId': 123,
'Text': 'string',
'BeginOffset': 123,
'EndOffset': 123,
'PartOfSpeech': {
'Tag': 'ADJ'|'ADP'|'ADV'|'AUX'|'CONJ'|'CCONJ'|'DET'|'INTJ'|'NOUN'|'NUM'|'O'|'PART'|'PRON'|'PROPN'|'PUNCT'|'SCONJ'|'SYM'|'VERB',
'Score': ...
}
},
]
},
],
'ErrorList': [
{
'Index': 123,
'ErrorCode': 'string',
'ErrorMessage': 'string'
},
]
}
Response Structure
(dict) --
ResultList (list) --
A list of objects containing the results of the operation. The results are sorted in ascending order by the Index field and match the order of the documents in the input list. If all of the documents contain an error, the ResultList is empty.
(dict) --
The result of calling the operation. The operation returns one object that is successfully processed by the operation.
Index (integer) --
The zero-based index of the document in the input list.
SyntaxTokens (list) --
The syntax tokens for the words in the document, one token for each word.
(dict) --
Represents a work in the input text that was recognized and assigned a part of speech. There is one syntax token record for each word in the source text.
TokenId (integer) --
A unique identifier for a token.
Text (string) --
The word that was recognized in the source text.
BeginOffset (integer) --
The zero-based offset from the beginning of the source text to the first character in the word.
EndOffset (integer) --
The zero-based offset from the beginning of the source text to the last character in the word.
PartOfSpeech (dict) --
Provides the part of speech label and the confidence level that Amazon Comprehend has that the part of speech was correctly identified. For more information, see how-syntax .
Tag (string) --
Identifies the part of speech that the token represents.
Score (float) --
The confidence that Amazon Comprehend has that the part of speech was correctly identified.
ErrorList (list) --
A list containing one object for each document that contained an error. The results are sorted in ascending order by the Index field and match the order of the documents in the input list. If there are no errors in the batch, the ErrorList is empty.
(dict) --
Describes an error that occurred while processing a document in a batch. The operation returns on BatchItemError object for each document that contained an error.
Index (integer) --
The zero-based index of the document in the input list.
ErrorCode (string) --
The numeric error code of the error.
ErrorMessage (string) --
A text description of the error.
Exceptions
Check if an operation can be paginated.
Creates a new document classification request to analyze a single document in real-time, using a previously created and trained custom model and an endpoint.
See also: AWS API Documentation
Request Syntax
response = client.classify_document(
Text='string',
EndpointArn='string'
)
[REQUIRED]
The document text to be analyzed.
[REQUIRED]
The Amazon Resource Number (ARN) of the endpoint.
dict
Response Syntax
{
'Classes': [
{
'Name': 'string',
'Score': ...
},
],
'Labels': [
{
'Name': 'string',
'Score': ...
},
]
}
Response Structure
(dict) --
Classes (list) --
The classes used by the document being analyzed. These are used for multi-class trained models. Individual classes are mutually exclusive and each document is expected to have only a single class assigned to it. For example, an animal can be a dog or a cat, but not both at the same time.
(dict) --
Specifies the class that categorizes the document being analyzed
Name (string) --
The name of the class.
Score (float) --
The confidence score that Amazon Comprehend has this class correctly attributed.
Labels (list) --
The labels used the document being analyzed. These are used for multi-label trained models. Individual labels represent different categories that are related in some manner and are not mutually exclusive. For example, a movie can be just an action movie, or it can be an action movie, a science fiction movie, and a comedy, all at the same time.
(dict) --
Specifies one of the label or labels that categorize the document being analyzed.
Name (string) --
The name of the label.
Score (float) --
The confidence score that Amazon Comprehend has this label correctly attributed.
Exceptions
Analyzes input text for the presence of personally identifiable information (PII) and returns the labels of identified PII entity types such as name, address, bank account number, or phone number.
See also: AWS API Documentation
Request Syntax
response = client.contains_pii_entities(
Text='string',
LanguageCode='en'|'es'|'fr'|'de'|'it'|'pt'|'ar'|'hi'|'ja'|'ko'|'zh'|'zh-TW'
)
[REQUIRED]
Creates a new document classification request to analyze a single document in real-time, returning personally identifiable information (PII) entity labels.
[REQUIRED]
The language of the input documents.
dict
Response Syntax
{
'Labels': [
{
'Name': 'BANK_ACCOUNT_NUMBER'|'BANK_ROUTING'|'CREDIT_DEBIT_NUMBER'|'CREDIT_DEBIT_CVV'|'CREDIT_DEBIT_EXPIRY'|'PIN'|'EMAIL'|'ADDRESS'|'NAME'|'PHONE'|'SSN'|'DATE_TIME'|'PASSPORT_NUMBER'|'DRIVER_ID'|'URL'|'AGE'|'USERNAME'|'PASSWORD'|'AWS_ACCESS_KEY'|'AWS_SECRET_KEY'|'IP_ADDRESS'|'MAC_ADDRESS'|'ALL',
'Score': ...
},
]
}
Response Structure
(dict) --
Labels (list) --
The labels used in the document being analyzed. Individual labels represent personally identifiable information (PII) entity types.
(dict) --
Specifies one of the label or labels that categorize the personally identifiable information (PII) entity being analyzed.
Name (string) --
The name of the label.
Score (float) --
The level of confidence that Amazon Comprehend has in the accuracy of the detection.
Exceptions
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
response = 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'
)
[REQUIRED]
The name of the document classifier.
[REQUIRED]
The Amazon Resource Name (ARN) of the AWS Identity and Management (IAM) role that grants Amazon Comprehend read access to your input data.
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.
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.
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.”
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.
[REQUIRED]
Specifies the format and location of the input data for the job.
The format of your training data:
If you don't specify a value, Amazon Comprehend uses COMPREHEND_CSV as the default.
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 .
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.
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 .
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.
The Amazon S3 location of the augmented manifest file.
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.
Enables the addition of output results configuration parameters for custom classifier jobs.
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.
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:
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.
[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.
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:
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 .
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 .
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 .
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:
dict
Response Syntax
{
'DocumentClassifierArn': 'string'
}
Response Structure
(dict) --
DocumentClassifierArn (string) --
The Amazon Resource Name (ARN) that identifies the document classifier.
Exceptions
Creates a model-specific endpoint for synchronous inference for a previously trained custom model
See also: AWS API Documentation
Request Syntax
response = client.create_endpoint(
EndpointName='string',
ModelArn='string',
DesiredInferenceUnits=123,
ClientRequestToken='string',
Tags=[
{
'Key': 'string',
'Value': 'string'
},
],
DataAccessRoleArn='string'
)
[REQUIRED]
This is the descriptive suffix that becomes part of the EndpointArn used for all subsequent requests to this resource.
[REQUIRED]
The Amazon Resource Number (ARN) of the model to which the endpoint will be attached.
[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.
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.
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.
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.
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.”
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
Response Syntax
{
'EndpointArn': 'string'
}
Response Structure
(dict) --
EndpointArn (string) --
The Amazon Resource Number (ARN) of the endpoint being created.
Exceptions
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
response = 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'
)
[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.
[REQUIRED]
The Amazon Resource Name (ARN) of the AWS Identity and Management (IAM) role that grants Amazon Comprehend read access to your input data.
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.
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.
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.”
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.
[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.
The format of your training data:
If you don't specify a value, Amazon Comprehend uses COMPREHEND_CSV as the default.
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).
An entity type within a labeled training dataset that Amazon Comprehend uses to train a custom entity recognizer.
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).
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 .
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.
The S3 location of the CSV file that annotates your training documents.
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.
The S3 location of the CSV file that has the entity list for your custom entity recognizer.
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.
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 .
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.
The Amazon S3 location of the augmented manifest file.
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.
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.
[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.
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:
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 .
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 .
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 .
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
dict
Response Syntax
{
'EntityRecognizerArn': 'string'
}
Response Structure
(dict) --
EntityRecognizerArn (string) --
The Amazon Resource Name (ARN) that identifies the entity recognizer.
Exceptions
Deletes a previously created document classifier
Only those classifiers that are in terminated states (IN_ERROR, TRAINED) will be deleted. If an active inference job is using the model, a ResourceInUseException will be returned.
This is an asynchronous action that puts the classifier into a DELETING state, and it is then removed by a background job. Once removed, the classifier disappears from your account and is no longer available for use.
See also: AWS API Documentation
Request Syntax
response = client.delete_document_classifier(
DocumentClassifierArn='string'
)
[REQUIRED]
The Amazon Resource Name (ARN) that identifies the document classifier.
{}
Response Structure
Exceptions
Deletes a model-specific endpoint for a previously-trained custom model. All endpoints must be deleted in order for the model to be deleted.
See also: AWS API Documentation
Request Syntax
response = client.delete_endpoint(
EndpointArn='string'
)
[REQUIRED]
The Amazon Resource Number (ARN) of the endpoint being deleted.
{}
Response Structure
Exceptions
Deletes an entity recognizer.
Only those recognizers that are in terminated states (IN_ERROR, TRAINED) will be deleted. If an active inference job is using the model, a ResourceInUseException will be returned.
This is an asynchronous action that puts the recognizer into a DELETING state, and it is then removed by a background job. Once removed, the recognizer disappears from your account and is no longer available for use.
See also: AWS API Documentation
Request Syntax
response = client.delete_entity_recognizer(
EntityRecognizerArn='string'
)
[REQUIRED]
The Amazon Resource Name (ARN) that identifies the entity recognizer.
{}
Response Structure
Exceptions
Gets the properties associated with a document classification job. Use this operation to get the status of a classification job.
See also: AWS API Documentation
Request Syntax
response = client.describe_document_classification_job(
JobId='string'
)
[REQUIRED]
The identifier that Amazon Comprehend generated for the job. The operation returns this identifier in its response.
{
'DocumentClassificationJobProperties': {
'JobId': 'string',
'JobName': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED',
'Message': 'string',
'SubmitTime': datetime(2015, 1, 1),
'EndTime': datetime(2015, 1, 1),
'DocumentClassifierArn': 'string',
'InputDataConfig': {
'S3Uri': 'string',
'InputFormat': 'ONE_DOC_PER_FILE'|'ONE_DOC_PER_LINE'
},
'OutputDataConfig': {
'S3Uri': 'string',
'KmsKeyId': 'string'
},
'DataAccessRoleArn': 'string',
'VolumeKmsKeyId': 'string',
'VpcConfig': {
'SecurityGroupIds': [
'string',
],
'Subnets': [
'string',
]
}
}
}
Response Structure
An object that describes the properties associated with the document classification job.
The identifier assigned to the document classification job.
The name that you assigned to the document classification job.
The current status of the document classification job. If the status is FAILED , the Message field shows the reason for the failure.
A description of the status of the job.
The time that the document classification job was submitted for processing.
The time that the document classification job completed.
The Amazon Resource Name (ARN) that identifies the document classifier.
The input data configuration that you supplied when you created the document classification job.
The Amazon S3 URI for the input data. The URI must be in 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 data 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.
Specifies how the text in an input file should be processed:
The output data configuration that you supplied when you created the document classification job.
When you use the OutputDataConfig object with asynchronous operations, you specify the Amazon S3 location where you want to write the output data. 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 the output file.
When the topic detection job is finished, the service creates an 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 ouput of the operation.
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:
The Amazon Resource Name (ARN) of the AWS identity and Access Management (IAM) role that grants Amazon Comprehend read access to your input data.
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:
Configuration parameters for a private Virtual Private Cloud (VPC) containing the resources you are using for your document classification job. For more information, see Amazon VPC .
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 .
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 .
Exceptions
Gets the properties associated with a document classifier.
See also: AWS API Documentation
Request Syntax
response = client.describe_document_classifier(
DocumentClassifierArn='string'
)
[REQUIRED]
The Amazon Resource Name (ARN) that identifies the document classifier. The operation returns this identifier in its response.
{
'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
An object that contains the properties associated with a document classifier.
The Amazon Resource Name (ARN) that identifies the document classifier.
The language code for the language of the documents that the classifier was trained on.
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.
Additional information about the status of the classifier.
The time that the document classifier was submitted for training.
The time that training the document classifier completed.
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.
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.
The input data configuration that you supplied when you created the document classifier for training.
The format of your training data:
If you don't specify a value, Amazon Comprehend uses COMPREHEND_CSV as the default.
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 .
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.
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 .
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.
The Amazon S3 location of the augmented manifest file.
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.
Provides output results configuration parameters for custom classifier jobs.
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.
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:
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.
The number of labels in the input data.
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.
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.
Describes the result metrics for the test data associated with an documentation classifier.
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.
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.
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.
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.
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.
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.
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.
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.
The Amazon Resource Name (ARN) of the AWS Identity and Management (IAM) role that grants Amazon Comprehend read access to your input data.
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:
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 .
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 .
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 .
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.
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:
Exceptions
Gets the properties associated with a dominant language detection job. Use this operation to get the status of a detection job.
See also: AWS API Documentation
Request Syntax
response = client.describe_dominant_language_detection_job(
JobId='string'
)
[REQUIRED]
The identifier that Amazon Comprehend generated for the job. The operation returns this identifier in its response.
{
'DominantLanguageDetectionJobProperties': {
'JobId': 'string',
'JobName': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED',
'Message': 'string',
'SubmitTime': datetime(2015, 1, 1),
'EndTime': datetime(2015, 1, 1),
'InputDataConfig': {
'S3Uri': 'string',
'InputFormat': 'ONE_DOC_PER_FILE'|'ONE_DOC_PER_LINE'
},
'OutputDataConfig': {
'S3Uri': 'string',
'KmsKeyId': 'string'
},
'DataAccessRoleArn': 'string',
'VolumeKmsKeyId': 'string',
'VpcConfig': {
'SecurityGroupIds': [
'string',
],
'Subnets': [
'string',
]
}
}
}
Response Structure
An object that contains the properties associated with a dominant language detection job.
The identifier assigned to the dominant language detection job.
The name that you assigned to the dominant language detection job.
The current status of the dominant language detection job. If the status is FAILED , the Message field shows the reason for the failure.
A description for the status of a job.
The time that the dominant language detection job was submitted for processing.
The time that the dominant language detection job completed.
The input data configuration that you supplied when you created the dominant language detection job.
The Amazon S3 URI for the input data. The URI must be in 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 data 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.
Specifies how the text in an input file should be processed:
The output data configuration that you supplied when you created the dominant language detection job.
When you use the OutputDataConfig object with asynchronous operations, you specify the Amazon S3 location where you want to write the output data. 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 the output file.
When the topic detection job is finished, the service creates an 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 ouput of the operation.
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:
The Amazon Resource Name (ARN) that gives Amazon Comprehend read access to your input data.
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:
Configuration parameters for a private Virtual Private Cloud (VPC) containing the resources you are using for your dominant language detection job. For more information, see Amazon VPC .
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 .
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 .
Exceptions
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
response = client.describe_endpoint(
EndpointArn='string'
)
[REQUIRED]
The Amazon Resource Number (ARN) of the endpoint being described.
{
'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
Describes information associated with the specific endpoint.
The Amazon Resource Number (ARN) of the endpoint.
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.
Specifies a reason for failure in cases of Failed status.
The Amazon Resource Number (ARN) of the model to which the endpoint is attached.
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.
The number of inference units currently used by the model using this endpoint.
The creation date and time of the endpoint.
The date and time that the endpoint was last modified.
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).
Exceptions
Gets the properties associated with an entities detection job. Use this operation to get the status of a detection job.
See also: AWS API Documentation
Request Syntax
response = client.describe_entities_detection_job(
JobId='string'
)
[REQUIRED]
The identifier that Amazon Comprehend generated for the job. The operation returns this identifier in its response.
{
'EntitiesDetectionJobProperties': {
'JobId': 'string',
'JobName': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED',
'Message': 'string',
'SubmitTime': datetime(2015, 1, 1),
'EndTime': datetime(2015, 1, 1),
'EntityRecognizerArn': 'string',
'InputDataConfig': {
'S3Uri': 'string',
'InputFormat': 'ONE_DOC_PER_FILE'|'ONE_DOC_PER_LINE'
},
'OutputDataConfig': {
'S3Uri': 'string',
'KmsKeyId': 'string'
},
'LanguageCode': 'en'|'es'|'fr'|'de'|'it'|'pt'|'ar'|'hi'|'ja'|'ko'|'zh'|'zh-TW',
'DataAccessRoleArn': 'string',
'VolumeKmsKeyId': 'string',
'VpcConfig': {
'SecurityGroupIds': [
'string',
],
'Subnets': [
'string',
]
}
}
}
Response Structure
An object that contains the properties associated with an entities detection job.
The identifier assigned to the entities detection job.
The name that you assigned the entities detection job.
The current status of the entities detection job. If the status is FAILED , the Message field shows the reason for the failure.
A description of the status of a job.
The time that the entities detection job was submitted for processing.
The time that the entities detection job completed
The Amazon Resource Name (ARN) that identifies the entity recognizer.
The input data configuration that you supplied when you created the entities detection job.
The Amazon S3 URI for the input data. The URI must be in 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 data 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.
Specifies how the text in an input file should be processed:
The output data configuration that you supplied when you created the entities detection job.
When you use the OutputDataConfig object with asynchronous operations, you specify the Amazon S3 location where you want to write the output data. 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 the output file.
When the topic detection job is finished, the service creates an 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 ouput of the operation.
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:
The language code of the input documents.
The Amazon Resource Name (ARN) that gives Amazon Comprehend read access to your input data.
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:
Configuration parameters for a private Virtual Private Cloud (VPC) containing the resources you are using for your entity detection job. For more information, see Amazon VPC .
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 .
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 .
Exceptions
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
response = client.describe_entity_recognizer(
EntityRecognizerArn='string'
)
[REQUIRED]
The Amazon Resource Name (ARN) that identifies the entity recognizer.
{
'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
Describes information associated with an entity recognizer.
The Amazon Resource Name (ARN) that identifies the entity recognizer.
The language of the input documents. All documents must be in the same language. Only English ("en") is currently supported.
Provides the status of the entity recognizer.
A description of the status of the recognizer.
The time that the recognizer was submitted for processing.
The time that the recognizer creation completed.
The time that training of the entity recognizer started.
The time that training of the entity recognizer was completed.
The input data properties of an entity recognizer.
The format of your training data:
If you don't specify a value, Amazon Comprehend uses COMPREHEND_CSV as the default.
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).
An entity type within a labeled training dataset that Amazon Comprehend uses to train a custom entity recognizer.
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).
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 .
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.
The S3 location of the CSV file that annotates your training documents.
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.
The S3 location of the CSV file that has the entity list for your custom entity recognizer.
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.
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 .
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.
The Amazon S3 location of the augmented manifest file.
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.
Provides information about an entity recognizer.
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.
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.
Detailed information about the accuracy of an entity recognizer.
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.
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.
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.
Entity types from the metadata of an entity recognizer.
Individual item from the list of entity types in the metadata of an entity recognizer.
Type of entity from the list of entity types in the metadata of an entity recognizer.
Detailed information about the accuracy of the entity recognizer for a specific item on the list of entity types.
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.
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.
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.
Indicates the number of times the given entity type was seen in the training data.
The Amazon Resource Name (ARN) of the AWS Identity and Management (IAM) role that grants Amazon Comprehend read access to your input data.
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:
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 .
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 .
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 .
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:
Exceptions
Gets the status and details of an events detection job.
See also: AWS API Documentation
Request Syntax
response = client.describe_events_detection_job(
JobId='string'
)
[REQUIRED]
The identifier of the events detection job.
{
'EventsDetectionJobProperties': {
'JobId': 'string',
'JobName': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED',
'Message': 'string',
'SubmitTime': datetime(2015, 1, 1),
'EndTime': datetime(2015, 1, 1),
'InputDataConfig': {
'S3Uri': 'string',
'InputFormat': 'ONE_DOC_PER_FILE'|'ONE_DOC_PER_LINE'
},
'OutputDataConfig': {
'S3Uri': 'string',
'KmsKeyId': 'string'
},
'LanguageCode': 'en'|'es'|'fr'|'de'|'it'|'pt'|'ar'|'hi'|'ja'|'ko'|'zh'|'zh-TW',
'DataAccessRoleArn': 'string',
'TargetEventTypes': [
'string',
]
}
}
Response Structure
An object that contains the properties associated with an event detection job.
The identifier assigned to the events detection job.
The name you assigned the events detection job.
The current status of the events detection job.
A description of the status of the events detection job.
The time that the events detection job was submitted for processing.
The time that the events detection job completed.
The input data configuration that you supplied when you created the events detection job.
The Amazon S3 URI for the input data. The URI must be in 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 data 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.
Specifies how the text in an input file should be processed:
The output data configuration that you supplied when you created the events detection job.
When you use the OutputDataConfig object with asynchronous operations, you specify the Amazon S3 location where you want to write the output data. 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 the output file.
When the topic detection job is finished, the service creates an 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 ouput of the operation.
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:
The language code of the input documents.
The Amazon Resource Name (ARN) of the AWS Identify and Access Management (IAM) role that grants Amazon Comprehend read access to your input data.
The types of events that are detected by the job.
Exceptions
Gets the properties associated with a key phrases detection job. Use this operation to get the status of a detection job.
See also: AWS API Documentation
Request Syntax
response = client.describe_key_phrases_detection_job(
JobId='string'
)
[REQUIRED]
The identifier that Amazon Comprehend generated for the job. The operation returns this identifier in its response.
{
'KeyPhrasesDetectionJobProperties': {
'JobId': 'string',
'JobName': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED',
'Message': 'string',
'SubmitTime': datetime(2015, 1, 1),
'EndTime': datetime(2015, 1, 1),
'InputDataConfig': {
'S3Uri': 'string',
'InputFormat': 'ONE_DOC_PER_FILE'|'ONE_DOC_PER_LINE'
},
'OutputDataConfig': {
'S3Uri': 'string',
'KmsKeyId': 'string'
},
'LanguageCode': 'en'|'es'|'fr'|'de'|'it'|'pt'|'ar'|'hi'|'ja'|'ko'|'zh'|'zh-TW',
'DataAccessRoleArn': 'string',
'VolumeKmsKeyId': 'string',
'VpcConfig': {
'SecurityGroupIds': [
'string',
],
'Subnets': [
'string',
]
}
}
}
Response Structure
An object that contains the properties associated with a key phrases detection job.
The identifier assigned to the key phrases detection job.
The name that you assigned the key phrases detection job.
The current status of the key phrases detection job. If the status is FAILED , the Message field shows the reason for the failure.
A description of the status of a job.
The time that the key phrases detection job was submitted for processing.
The time that the key phrases detection job completed.
The input data configuration that you supplied when you created the key phrases detection job.
The Amazon S3 URI for the input data. The URI must be in 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 data 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.
Specifies how the text in an input file should be processed:
The output data configuration that you supplied when you created the key phrases detection job.
When you use the OutputDataConfig object with asynchronous operations, you specify the Amazon S3 location where you want to write the output data. 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 the output file.
When the topic detection job is finished, the service creates an 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 ouput of the operation.
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:
The language code of the input documents.
The Amazon Resource Name (ARN) that gives Amazon Comprehend read access to your input data.
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:
Configuration parameters for a private Virtual Private Cloud (VPC) containing the resources you are using for your key phrases detection job. For more information, see Amazon VPC .
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 .
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 .
Exceptions
Gets the properties associated with a PII entities detection job. For example, you can use this operation to get the job status.
See also: AWS API Documentation
Request Syntax
response = client.describe_pii_entities_detection_job(
JobId='string'
)
[REQUIRED]
The identifier that Amazon Comprehend generated for the job. The operation returns this identifier in its response.
{
'PiiEntitiesDetectionJobProperties': {
'JobId': 'string',
'JobName': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED',
'Message': 'string',
'SubmitTime': datetime(2015, 1, 1),
'EndTime': datetime(2015, 1, 1),
'InputDataConfig': {
'S3Uri': 'string',
'InputFormat': 'ONE_DOC_PER_FILE'|'ONE_DOC_PER_LINE'
},
'OutputDataConfig': {
'S3Uri': 'string',
'KmsKeyId': 'string'
},
'RedactionConfig': {
'PiiEntityTypes': [
'BANK_ACCOUNT_NUMBER'|'BANK_ROUTING'|'CREDIT_DEBIT_NUMBER'|'CREDIT_DEBIT_CVV'|'CREDIT_DEBIT_EXPIRY'|'PIN'|'EMAIL'|'ADDRESS'|'NAME'|'PHONE'|'SSN'|'DATE_TIME'|'PASSPORT_NUMBER'|'DRIVER_ID'|'URL'|'AGE'|'USERNAME'|'PASSWORD'|'AWS_ACCESS_KEY'|'AWS_SECRET_KEY'|'IP_ADDRESS'|'MAC_ADDRESS'|'ALL',
],
'MaskMode': 'MASK'|'REPLACE_WITH_PII_ENTITY_TYPE',
'MaskCharacter': 'string'
},
'LanguageCode': 'en'|'es'|'fr'|'de'|'it'|'pt'|'ar'|'hi'|'ja'|'ko'|'zh'|'zh-TW',
'DataAccessRoleArn': 'string',
'Mode': 'ONLY_REDACTION'|'ONLY_OFFSETS'
}
}
Response Structure
Provides information about a PII entities detection job.
The identifier assigned to the PII entities detection job.
The name that you assigned the PII entities detection job.
The current status of the PII entities detection job. If the status is FAILED , the Message field shows the reason for the failure.
A description of the status of a job.
The time that the PII entities detection job was submitted for processing.
The time that the PII entities detection job completed.
The input properties for a PII entities detection job.
The Amazon S3 URI for the input data. The URI must be in 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 data 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.
Specifies how the text in an input file should be processed:
The output data configuration that you supplied when you created the PII entities detection job.
When you use the PiiOutputDataConfig object with asynchronous operations, you specify the Amazon S3 location where you want to write the output data.
ID for the AWS Key Management Service (KMS) key that Amazon Comprehend uses to encrypt the output results from an analysis job.
Provides configuration parameters for PII entity redaction.
This parameter is required if you set the Mode parameter to ONLY_REDACTION . In that case, you must provide a RedactionConfig definition that includes the PiiEntityTypes parameter.
An array of the types of PII entities that Amazon Comprehend detects in the input text for your request.
Specifies whether the PII entity is redacted with the mask character or the entity type.
A character that replaces each character in the redacted PII entity.
The language code of the input documents
The Amazon Resource Name (ARN) that gives Amazon Comprehend read access to your input data.
Specifies whether the output provides the locations (offsets) of PII entities or a file in which PII entities are redacted.
Exceptions
Gets the properties associated with a sentiment detection job. Use this operation to get the status of a detection job.
See also: AWS API Documentation
Request Syntax
response = client.describe_sentiment_detection_job(
JobId='string'
)
[REQUIRED]
The identifier that Amazon Comprehend generated for the job. The operation returns this identifier in its response.
{
'SentimentDetectionJobProperties': {
'JobId': 'string',
'JobName': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED',
'Message': 'string',
'SubmitTime': datetime(2015, 1, 1),
'EndTime': datetime(2015, 1, 1),
'InputDataConfig': {
'S3Uri': 'string',
'InputFormat': 'ONE_DOC_PER_FILE'|'ONE_DOC_PER_LINE'
},
'OutputDataConfig': {
'S3Uri': 'string',
'KmsKeyId': 'string'
},
'LanguageCode': 'en'|'es'|'fr'|'de'|'it'|'pt'|'ar'|'hi'|'ja'|'ko'|'zh'|'zh-TW',
'DataAccessRoleArn': 'string',
'VolumeKmsKeyId': 'string',
'VpcConfig': {
'SecurityGroupIds': [
'string',
],
'Subnets': [
'string',
]
}
}
}
Response Structure
An object that contains the properties associated with a sentiment detection job.
The identifier assigned to the sentiment detection job.
The name that you assigned to the sentiment detection job
The current status of the sentiment detection job. If the status is FAILED , the Messages field shows the reason for the failure.
A description of the status of a job.
The time that the sentiment detection job was submitted for processing.
The time that the sentiment detection job ended.
The input data configuration that you supplied when you created the sentiment detection job.
The Amazon S3 URI for the input data. The URI must be in 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 data 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.
Specifies how the text in an input file should be processed:
The output data configuration that you supplied when you created the sentiment detection job.
When you use the OutputDataConfig object with asynchronous operations, you specify the Amazon S3 location where you want to write the output data. 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 the output file.
When the topic detection job is finished, the service creates an 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 ouput of the operation.
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:
The language code of the input documents.
The Amazon Resource Name (ARN) that gives Amazon Comprehend read access to your input data.
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:
Configuration parameters for a private Virtual Private Cloud (VPC) containing the resources you are using for your sentiment detection job. For more information, see Amazon VPC .
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 .
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 .
Exceptions
Gets the properties associated with a topic detection job. Use this operation to get the status of a detection job.
See also: AWS API Documentation
Request Syntax
response = client.describe_topics_detection_job(
JobId='string'
)
[REQUIRED]
The identifier assigned by the user to the detection job.
{
'TopicsDetectionJobProperties': {
'JobId': 'string',
'JobName': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED',
'Message': 'string',
'SubmitTime': datetime(2015, 1, 1),
'EndTime': datetime(2015, 1, 1),
'InputDataConfig': {
'S3Uri': 'string',
'InputFormat': 'ONE_DOC_PER_FILE'|'ONE_DOC_PER_LINE'
},
'OutputDataConfig': {
'S3Uri': 'string',
'KmsKeyId': 'string'
},
'NumberOfTopics': 123,
'DataAccessRoleArn': 'string',
'VolumeKmsKeyId': 'string',
'VpcConfig': {
'SecurityGroupIds': [
'string',
],
'Subnets': [
'string',
]
}
}
}
Response Structure
The list of properties for the requested job.
The identifier assigned to the topic detection job.
The name of the topic detection job.
The current status of the topic detection job. If the status is Failed , the reason for the failure is shown in the Message field.
A description for the status of a job.
The time that the topic detection job was submitted for processing.
The time that the topic detection job was completed.
The input data configuration supplied when you created the topic detection job.
The Amazon S3 URI for the input data. The URI must be in 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 data 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.
Specifies how the text in an input file should be processed:
The output data configuration supplied when you created the topic detection job.
When you use the OutputDataConfig object with asynchronous operations, you specify the Amazon S3 location where you want to write the output data. 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 the output file.
When the topic detection job is finished, the service creates an 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 ouput of the operation.
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:
The number of topics to detect supplied when you created the topic detection job. The default is 10.
The Amazon Resource Name (ARN) of the AWS Identity and Management (IAM) role that grants Amazon Comprehend read access to your job data.
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:
Configuration parameters for a private Virtual Private Cloud (VPC) containing the resources you are using for your topic detection job. For more information, see Amazon VPC .
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 .
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 .
Exceptions
Determines the dominant language of the input text. For a list of languages that Amazon Comprehend can detect, see Amazon Comprehend Supported Languages .
See also: AWS API Documentation
Request Syntax
response = client.detect_dominant_language(
Text='string'
)
[REQUIRED]
A UTF-8 text string. Each string should contain at least 20 characters and must contain fewer that 5,000 bytes of UTF-8 encoded characters.
{
'Languages': [
{
'LanguageCode': 'string',
'Score': ...
},
]
}
Response Structure
The languages that Amazon Comprehend detected in the input text. For each language, the response returns the RFC 5646 language code and the level of confidence that Amazon Comprehend has in the accuracy of its inference. For more information about RFC 5646, see Tags for Identifying Languages on the IETF Tools web site.
Returns the code for the dominant language in the input text and the level of confidence that Amazon Comprehend has in the accuracy of the detection.
The RFC 5646 language code for the dominant language. For more information about RFC 5646, see Tags for Identifying Languages on the IETF Tools web site.
The level of confidence that Amazon Comprehend has in the accuracy of the detection.
Exceptions
Inspects text for named entities, and returns information about them. For more information, about named entities, see how-entities .
See also: AWS API Documentation
Request Syntax
response = client.detect_entities(
Text='string',
LanguageCode='en'|'es'|'fr'|'de'|'it'|'pt'|'ar'|'hi'|'ja'|'ko'|'zh'|'zh-TW',
EndpointArn='string'
)
[REQUIRED]
A UTF-8 text string. Each string must contain fewer that 5,000 bytes of UTF-8 encoded characters.
The language of the input documents. You can specify any of the primary languages supported by Amazon Comprehend. All documents must be in the same language.
If your request includes the endpoint for a custom entity recognition model, Amazon Comprehend uses the language of your custom model, and it ignores any language code that you specify here.
The Amazon Resource Name of an endpoint that is associated with a custom entity recognition model. Provide an endpoint if you want to detect entities by using your own custom model instead of the default model that is used by Amazon Comprehend.
If you specify an endpoint, Amazon Comprehend uses the language of your custom model, and it ignores any language code that you provide in your request.
dict
Response Syntax
{
'Entities': [
{
'Score': ...,
'Type': 'PERSON'|'LOCATION'|'ORGANIZATION'|'COMMERCIAL_ITEM'|'EVENT'|'DATE'|'QUANTITY'|'TITLE'|'OTHER',
'Text': 'string',
'BeginOffset': 123,
'EndOffset': 123
},
]
}
Response Structure
(dict) --
Entities (list) --
A collection of entities identified in the input text. For each entity, the response provides the entity text, entity type, where the entity text begins and ends, and the level of confidence that Amazon Comprehend has in the detection.
If your request uses a custom entity recognition model, Amazon Comprehend detects the entities that the model is trained to recognize. Otherwise, it detects the default entity types. For a list of default entity types, see how-entities .
(dict) --
Provides information about an entity.
Score (float) --
The level of confidence that Amazon Comprehend has in the accuracy of the detection.
Type (string) --
The entity's type.
Text (string) --
The text of the entity.
BeginOffset (integer) --
A character offset in the input text that shows where the entity begins (the first character is at position 0). The offset returns the position of each UTF-8 code point in the string. A code point is the abstract character from a particular graphical representation. For example, a multi-byte UTF-8 character maps to a single code point.
EndOffset (integer) --
A character offset in the input text that shows where the entity ends. The offset returns the position of each UTF-8 code point in the string. A code point is the abstract character from a particular graphical representation. For example, a multi-byte UTF-8 character maps to a single code point.
Exceptions
Detects the key noun phrases found in the text.
See also: AWS API Documentation
Request Syntax
response = client.detect_key_phrases(
Text='string',
LanguageCode='en'|'es'|'fr'|'de'|'it'|'pt'|'ar'|'hi'|'ja'|'ko'|'zh'|'zh-TW'
)
[REQUIRED]
A UTF-8 text string. Each string must contain fewer that 5,000 bytes of UTF-8 encoded characters.
[REQUIRED]
The language of the input documents. You can specify any of the primary languages supported by Amazon Comprehend. All documents must be in the same language.
dict
Response Syntax
{
'KeyPhrases': [
{
'Score': ...,
'Text': 'string',
'BeginOffset': 123,
'EndOffset': 123
},
]
}
Response Structure
(dict) --
KeyPhrases (list) --
A collection of key phrases that Amazon Comprehend identified in the input text. For each key phrase, the response provides the text of the key phrase, where the key phrase begins and ends, and the level of confidence that Amazon Comprehend has in the accuracy of the detection.
(dict) --
Describes a key noun phrase.
Score (float) --
The level of confidence that Amazon Comprehend has in the accuracy of the detection.
Text (string) --
The text of a key noun phrase.
BeginOffset (integer) --
A character offset in the input text that shows where the key phrase begins (the first character is at position 0). The offset returns the position of each UTF-8 code point in the string. A code point is the abstract character from a particular graphical representation. For example, a multi-byte UTF-8 character maps to a single code point.
EndOffset (integer) --
A character offset in the input text where the key phrase ends. The offset returns the position of each UTF-8 code point in the string. A code point is the abstract character from a particular graphical representation. For example, a multi-byte UTF-8 character maps to a single code point.
Exceptions
Inspects the input text for entities that contain personally identifiable information (PII) and returns information about them.
See also: AWS API Documentation
Request Syntax
response = client.detect_pii_entities(
Text='string',
LanguageCode='en'|'es'|'fr'|'de'|'it'|'pt'|'ar'|'hi'|'ja'|'ko'|'zh'|'zh-TW'
)
[REQUIRED]
A UTF-8 text string. Each string must contain fewer that 5,000 bytes of UTF-8 encoded characters.
[REQUIRED]
The language of the input documents.
dict
Response Syntax
{
'Entities': [
{
'Score': ...,
'Type': 'BANK_ACCOUNT_NUMBER'|'BANK_ROUTING'|'CREDIT_DEBIT_NUMBER'|'CREDIT_DEBIT_CVV'|'CREDIT_DEBIT_EXPIRY'|'PIN'|'EMAIL'|'ADDRESS'|'NAME'|'PHONE'|'SSN'|'DATE_TIME'|'PASSPORT_NUMBER'|'DRIVER_ID'|'URL'|'AGE'|'USERNAME'|'PASSWORD'|'AWS_ACCESS_KEY'|'AWS_SECRET_KEY'|'IP_ADDRESS'|'MAC_ADDRESS'|'ALL',
'BeginOffset': 123,
'EndOffset': 123
},
]
}
Response Structure
(dict) --
Entities (list) --
A collection of PII entities identified in the input text. For each entity, the response provides the entity type, where the entity text begins and ends, and the level of confidence that Amazon Comprehend has in the detection.
(dict) --
Provides information about a PII entity.
Score (float) --
The level of confidence that Amazon Comprehend has in the accuracy of the detection.
Type (string) --
The entity's type.
BeginOffset (integer) --
A character offset in the input text that shows where the PII entity begins (the first character is at position 0). The offset returns the position of each UTF-8 code point in the string. A code point is the abstract character from a particular graphical representation. For example, a multi-byte UTF-8 character maps to a single code point.
EndOffset (integer) --
A character offset in the input text that shows where the PII entity ends. The offset returns the position of each UTF-8 code point in the string. A code point is the abstract character from a particular graphical representation. For example, a multi-byte UTF-8 character maps to a single code point.
Exceptions
Inspects text and returns an inference of the prevailing sentiment (POSITIVE , NEUTRAL , MIXED , or NEGATIVE ).
See also: AWS API Documentation
Request Syntax
response = client.detect_sentiment(
Text='string',
LanguageCode='en'|'es'|'fr'|'de'|'it'|'pt'|'ar'|'hi'|'ja'|'ko'|'zh'|'zh-TW'
)
[REQUIRED]
A UTF-8 text string. Each string must contain fewer that 5,000 bytes of UTF-8 encoded characters.
[REQUIRED]
The language of the input documents. You can specify any of the primary languages supported by Amazon Comprehend. All documents must be in the same language.
dict
Response Syntax
{
'Sentiment': 'POSITIVE'|'NEGATIVE'|'NEUTRAL'|'MIXED',
'SentimentScore': {
'Positive': ...,
'Negative': ...,
'Neutral': ...,
'Mixed': ...
}
}
Response Structure
(dict) --
Sentiment (string) --
The inferred sentiment that Amazon Comprehend has the highest level of confidence in.
SentimentScore (dict) --
An object that lists the sentiments, and their corresponding confidence levels.
Positive (float) --
The level of confidence that Amazon Comprehend has in the accuracy of its detection of the POSITIVE sentiment.
Negative (float) --
The level of confidence that Amazon Comprehend has in the accuracy of its detection of the NEGATIVE sentiment.
Neutral (float) --
The level of confidence that Amazon Comprehend has in the accuracy of its detection of the NEUTRAL sentiment.
Mixed (float) --
The level of confidence that Amazon Comprehend has in the accuracy of its detection of the MIXED sentiment.
Exceptions
Inspects text for syntax and the part of speech of words in the document. For more information, how-syntax .
See also: AWS API Documentation
Request Syntax
response = client.detect_syntax(
Text='string',
LanguageCode='en'|'es'|'fr'|'de'|'it'|'pt'
)
[REQUIRED]
A UTF-8 string. Each string must contain fewer that 5,000 bytes of UTF encoded characters.
[REQUIRED]
The language code 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").
dict
Response Syntax
{
'SyntaxTokens': [
{
'TokenId': 123,
'Text': 'string',
'BeginOffset': 123,
'EndOffset': 123,
'PartOfSpeech': {
'Tag': 'ADJ'|'ADP'|'ADV'|'AUX'|'CONJ'|'CCONJ'|'DET'|'INTJ'|'NOUN'|'NUM'|'O'|'PART'|'PRON'|'PROPN'|'PUNCT'|'SCONJ'|'SYM'|'VERB',
'Score': ...
}
},
]
}
Response Structure
(dict) --
SyntaxTokens (list) --
A collection of syntax tokens describing the text. For each token, the response provides the text, the token type, where the text begins and ends, and the level of confidence that Amazon Comprehend has that the token is correct. For a list of token types, see how-syntax .
(dict) --
Represents a work in the input text that was recognized and assigned a part of speech. There is one syntax token record for each word in the source text.
TokenId (integer) --
A unique identifier for a token.
Text (string) --
The word that was recognized in the source text.
BeginOffset (integer) --
The zero-based offset from the beginning of the source text to the first character in the word.
EndOffset (integer) --
The zero-based offset from the beginning of the source text to the last character in the word.
PartOfSpeech (dict) --
Provides the part of speech label and the confidence level that Amazon Comprehend has that the part of speech was correctly identified. For more information, see how-syntax .
Tag (string) --
Identifies the part of speech that the token represents.
Score (float) --
The confidence that Amazon Comprehend has that the part of speech was correctly identified.
Exceptions
Generate a presigned url given a client, its method, and arguments
The presigned url
Create a paginator for an operation.
Returns an object that can wait for some condition.
Gets a list of the documentation classification jobs that you have submitted.
See also: AWS API Documentation
Request Syntax
response = client.list_document_classification_jobs(
Filter={
'JobName': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED',
'SubmitTimeBefore': datetime(2015, 1, 1),
'SubmitTimeAfter': datetime(2015, 1, 1)
},
NextToken='string',
MaxResults=123
)
Filters the jobs that are returned. You can filter jobs on their names, status, or the date and time that they were submitted. You can only set one filter at a time.
Filters on the name of the job.
Filters the list based on job status. Returns only jobs with the specified status.
Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted before the specified time. Jobs are returned in ascending order, oldest to newest.
Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted after the specified time. Jobs are returned in descending order, newest to oldest.
dict
Response Syntax
{
'DocumentClassificationJobPropertiesList': [
{
'JobId': 'string',
'JobName': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED',
'Message': 'string',
'SubmitTime': datetime(2015, 1, 1),
'EndTime': datetime(2015, 1, 1),
'DocumentClassifierArn': 'string',
'InputDataConfig': {
'S3Uri': 'string',
'InputFormat': 'ONE_DOC_PER_FILE'|'ONE_DOC_PER_LINE'
},
'OutputDataConfig': {
'S3Uri': 'string',
'KmsKeyId': 'string'
},
'DataAccessRoleArn': 'string',
'VolumeKmsKeyId': 'string',
'VpcConfig': {
'SecurityGroupIds': [
'string',
],
'Subnets': [
'string',
]
}
},
],
'NextToken': 'string'
}
Response Structure
(dict) --
DocumentClassificationJobPropertiesList (list) --
A list containing the properties of each job returned.
(dict) --
Provides information about a document classification job.
JobId (string) --
The identifier assigned to the document classification job.
JobName (string) --
The name that you assigned to the document classification job.
JobStatus (string) --
The current status of the document classification job. If the status is FAILED , the Message field shows the reason for the failure.
Message (string) --
A description of the status of the job.
SubmitTime (datetime) --
The time that the document classification job was submitted for processing.
EndTime (datetime) --
The time that the document classification job completed.
DocumentClassifierArn (string) --
The Amazon Resource Name (ARN) that identifies the document classifier.
InputDataConfig (dict) --
The input data configuration that you supplied when you created the document classification job.
S3Uri (string) --
The Amazon S3 URI for the input data. The URI must be in 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 data 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.
InputFormat (string) --
Specifies how the text in an input file should be processed:
OutputDataConfig (dict) --
The output data configuration that you supplied when you created the document classification job.
S3Uri (string) --
When you use the OutputDataConfig object with asynchronous operations, you specify the Amazon S3 location where you want to write the output data. 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 the output file.
When the topic detection job is finished, the service creates an 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 ouput of the operation.
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:
DataAccessRoleArn (string) --
The Amazon Resource Name (ARN) of the AWS identity and Access 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:
VpcConfig (dict) --
Configuration parameters for a private Virtual Private Cloud (VPC) containing the resources you are using for your document classification job. 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 .
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 .
NextToken (string) --
Identifies the next page of results to return.
Exceptions
Gets a list of the document classifiers that you have created.
See also: AWS API Documentation
Request Syntax
response = 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
)
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.
Filters the list of classifiers based on status.
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.
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.
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:
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.
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:
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:
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 .
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 .
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:
NextToken (string) --
Identifies the next page of results to return.
Exceptions
Gets a list of the dominant language detection jobs that you have submitted.
See also: AWS API Documentation
Request Syntax
response = client.list_dominant_language_detection_jobs(
Filter={
'JobName': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED',
'SubmitTimeBefore': datetime(2015, 1, 1),
'SubmitTimeAfter': datetime(2015, 1, 1)
},
NextToken='string',
MaxResults=123
)
Filters that 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.
Filters on the name of the job.
Filters the list of jobs based on job status. Returns only jobs with the specified status.
Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted before the specified time. Jobs are returned in ascending order, oldest to newest.
Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted after the specified time. Jobs are returned in descending order, newest to oldest.
dict
Response Syntax
{
'DominantLanguageDetectionJobPropertiesList': [
{
'JobId': 'string',
'JobName': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED',
'Message': 'string',
'SubmitTime': datetime(2015, 1, 1),
'EndTime': datetime(2015, 1, 1),
'InputDataConfig': {
'S3Uri': 'string',
'InputFormat': 'ONE_DOC_PER_FILE'|'ONE_DOC_PER_LINE'
},
'OutputDataConfig': {
'S3Uri': 'string',
'KmsKeyId': 'string'
},
'DataAccessRoleArn': 'string',
'VolumeKmsKeyId': 'string',
'VpcConfig': {
'SecurityGroupIds': [
'string',
],
'Subnets': [
'string',
]
}
},
],
'NextToken': 'string'
}
Response Structure
(dict) --
DominantLanguageDetectionJobPropertiesList (list) --
A list containing the properties of each job that is returned.
(dict) --
Provides information about a dominant language detection job.
JobId (string) --
The identifier assigned to the dominant language detection job.
JobName (string) --
The name that you assigned to the dominant language detection job.
JobStatus (string) --
The current status of the dominant language detection job. If the status is FAILED , the Message field shows the reason for the failure.
Message (string) --
A description for the status of a job.
SubmitTime (datetime) --
The time that the dominant language detection job was submitted for processing.
EndTime (datetime) --
The time that the dominant language detection job completed.
InputDataConfig (dict) --
The input data configuration that you supplied when you created the dominant language detection job.
S3Uri (string) --
The Amazon S3 URI for the input data. The URI must be in 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 data 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.
InputFormat (string) --
Specifies how the text in an input file should be processed:
OutputDataConfig (dict) --
The output data configuration that you supplied when you created the dominant language detection job.
S3Uri (string) --
When you use the OutputDataConfig object with asynchronous operations, you specify the Amazon S3 location where you want to write the output data. 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 the output file.
When the topic detection job is finished, the service creates an 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 ouput of the operation.
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:
DataAccessRoleArn (string) --
The Amazon Resource Name (ARN) that gives 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:
VpcConfig (dict) --
Configuration parameters for a private Virtual Private Cloud (VPC) containing the resources you are using for your dominant language detection job. 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 .
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 .
NextToken (string) --
Identifies the next page of results to return.
Exceptions
Gets a list of all existing endpoints that you've created.
See also: AWS API Documentation
Request Syntax
response = 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
)
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.
The Amazon Resource Number (ARN) of the model to which the endpoint is attached.
Specifies the status of the endpoint being returned. Possible values are: Creating, Ready, Updating, Deleting, Failed.
Specifies a date before which the returned endpoint or endpoints were created.
Specifies a date after which the returned endpoint or endpoints were created.
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.
Exceptions
Gets a list of the entity detection jobs that you have submitted.
See also: AWS API Documentation
Request Syntax
response = client.list_entities_detection_jobs(
Filter={
'JobName': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED',
'SubmitTimeBefore': datetime(2015, 1, 1),
'SubmitTimeAfter': datetime(2015, 1, 1)
},
NextToken='string',
MaxResults=123
)
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.
Filters on the name of the job.
Filters the list of jobs based on job status. Returns only jobs with the specified status.
Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted before the specified time. Jobs are returned in ascending order, oldest to newest.
Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted after the specified time. Jobs are returned in descending order, newest to oldest.
dict
Response Syntax
{
'EntitiesDetectionJobPropertiesList': [
{
'JobId': 'string',
'JobName': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED',
'Message': 'string',
'SubmitTime': datetime(2015, 1, 1),
'EndTime': datetime(2015, 1, 1),
'EntityRecognizerArn': 'string',
'InputDataConfig': {
'S3Uri': 'string',
'InputFormat': 'ONE_DOC_PER_FILE'|'ONE_DOC_PER_LINE'
},
'OutputDataConfig': {
'S3Uri': 'string',
'KmsKeyId': 'string'
},
'LanguageCode': 'en'|'es'|'fr'|'de'|'it'|'pt'|'ar'|'hi'|'ja'|'ko'|'zh'|'zh-TW',
'DataAccessRoleArn': 'string',
'VolumeKmsKeyId': 'string',
'VpcConfig': {
'SecurityGroupIds': [
'string',
],
'Subnets': [
'string',
]
}
},
],
'NextToken': 'string'
}
Response Structure
(dict) --
EntitiesDetectionJobPropertiesList (list) --
A list containing the properties of each job that is returned.
(dict) --
Provides information about an entities detection job.
JobId (string) --
The identifier assigned to the entities detection job.
JobName (string) --
The name that you assigned the entities detection job.
JobStatus (string) --
The current status of the entities detection job. If the status is FAILED , the Message field shows the reason for the failure.
Message (string) --
A description of the status of a job.
SubmitTime (datetime) --
The time that the entities detection job was submitted for processing.
EndTime (datetime) --
The time that the entities detection job completed
EntityRecognizerArn (string) --
The Amazon Resource Name (ARN) that identifies the entity recognizer.
InputDataConfig (dict) --
The input data configuration that you supplied when you created the entities detection job.
S3Uri (string) --
The Amazon S3 URI for the input data. The URI must be in 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 data 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.
InputFormat (string) --
Specifies how the text in an input file should be processed:
OutputDataConfig (dict) --
The output data configuration that you supplied when you created the entities detection job.
S3Uri (string) --
When you use the OutputDataConfig object with asynchronous operations, you specify the Amazon S3 location where you want to write the output data. 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 the output file.
When the topic detection job is finished, the service creates an 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 ouput of the operation.
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:
LanguageCode (string) --
The language code of the input documents.
DataAccessRoleArn (string) --
The Amazon Resource Name (ARN) that gives 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:
VpcConfig (dict) --
Configuration parameters for a private Virtual Private Cloud (VPC) containing the resources you are using for your entity detection job. 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 .
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 .
NextToken (string) --
Identifies the next page of results to return.
Exceptions
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
response = 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
)
Filters the list of entities returned. You can filter on Status , SubmitTimeBefore , or SubmitTimeAfter . You can only set one filter at a time.
The status of an entity recognizer.
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.
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.
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:
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.
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:
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 .
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 .
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:
NextToken (string) --
Identifies the next page of results to return.
Exceptions
Gets a list of the events detection jobs that you have submitted.
See also: AWS API Documentation
Request Syntax
response = client.list_events_detection_jobs(
Filter={
'JobName': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED',
'SubmitTimeBefore': datetime(2015, 1, 1),
'SubmitTimeAfter': datetime(2015, 1, 1)
},
NextToken='string',
MaxResults=123
)
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.
Filters on the name of the events detection job.
Filters the list of jobs based on job status. Returns only jobs with the specified status.
Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted before the specified time. Jobs are returned in ascending order, oldest to newest.
Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted after the specified time. Jobs are returned in descending order, newest to oldest.
dict
Response Syntax
{
'EventsDetectionJobPropertiesList': [
{
'JobId': 'string',
'JobName': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED',
'Message': 'string',
'SubmitTime': datetime(2015, 1, 1),
'EndTime': datetime(2015, 1, 1),
'InputDataConfig': {
'S3Uri': 'string',
'InputFormat': 'ONE_DOC_PER_FILE'|'ONE_DOC_PER_LINE'
},
'OutputDataConfig': {
'S3Uri': 'string',
'KmsKeyId': 'string'
},
'LanguageCode': 'en'|'es'|'fr'|'de'|'it'|'pt'|'ar'|'hi'|'ja'|'ko'|'zh'|'zh-TW',
'DataAccessRoleArn': 'string',
'TargetEventTypes': [
'string',
]
},
],
'NextToken': 'string'
}
Response Structure
(dict) --
EventsDetectionJobPropertiesList (list) --
A list containing the properties of each job that is returned.
(dict) --
Provides information about an events detection job.
JobId (string) --
The identifier assigned to the events detection job.
JobName (string) --
The name you assigned the events detection job.
JobStatus (string) --
The current status of the events detection job.
Message (string) --
A description of the status of the events detection job.
SubmitTime (datetime) --
The time that the events detection job was submitted for processing.
EndTime (datetime) --
The time that the events detection job completed.
InputDataConfig (dict) --
The input data configuration that you supplied when you created the events detection job.
S3Uri (string) --
The Amazon S3 URI for the input data. The URI must be in 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 data 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.
InputFormat (string) --
Specifies how the text in an input file should be processed:
OutputDataConfig (dict) --
The output data configuration that you supplied when you created the events detection job.
S3Uri (string) --
When you use the OutputDataConfig object with asynchronous operations, you specify the Amazon S3 location where you want to write the output data. 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 the output file.
When the topic detection job is finished, the service creates an 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 ouput of the operation.
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:
LanguageCode (string) --
The language code of the input documents.
DataAccessRoleArn (string) --
The Amazon Resource Name (ARN) of the AWS Identify and Access Management (IAM) role that grants Amazon Comprehend read access to your input data.
TargetEventTypes (list) --
The types of events that are detected by the job.
NextToken (string) --
Identifies the next page of results to return.
Exceptions
Get a list of key phrase detection jobs that you have submitted.
See also: AWS API Documentation
Request Syntax
response = client.list_key_phrases_detection_jobs(
Filter={
'JobName': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED',
'SubmitTimeBefore': datetime(2015, 1, 1),
'SubmitTimeAfter': datetime(2015, 1, 1)
},
NextToken='string',
MaxResults=123
)
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.
Filters on the name of the job.
Filters the list of jobs based on job status. Returns only jobs with the specified status.
Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted before the specified time. Jobs are returned in ascending order, oldest to newest.
Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted after the specified time. Jobs are returned in descending order, newest to oldest.
dict
Response Syntax
{
'KeyPhrasesDetectionJobPropertiesList': [
{
'JobId': 'string',
'JobName': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED',
'Message': 'string',
'SubmitTime': datetime(2015, 1, 1),
'EndTime': datetime(2015, 1, 1),
'InputDataConfig': {
'S3Uri': 'string',
'InputFormat': 'ONE_DOC_PER_FILE'|'ONE_DOC_PER_LINE'
},
'OutputDataConfig': {
'S3Uri': 'string',
'KmsKeyId': 'string'
},
'LanguageCode': 'en'|'es'|'fr'|'de'|'it'|'pt'|'ar'|'hi'|'ja'|'ko'|'zh'|'zh-TW',
'DataAccessRoleArn': 'string',
'VolumeKmsKeyId': 'string',
'VpcConfig': {
'SecurityGroupIds': [
'string',
],
'Subnets': [
'string',
]
}
},
],
'NextToken': 'string'
}
Response Structure
(dict) --
KeyPhrasesDetectionJobPropertiesList (list) --
A list containing the properties of each job that is returned.
(dict) --
Provides information about a key phrases detection job.
JobId (string) --
The identifier assigned to the key phrases detection job.
JobName (string) --
The name that you assigned the key phrases detection job.
JobStatus (string) --
The current status of the key phrases detection job. If the status is FAILED , the Message field shows the reason for the failure.
Message (string) --
A description of the status of a job.
SubmitTime (datetime) --
The time that the key phrases detection job was submitted for processing.
EndTime (datetime) --
The time that the key phrases detection job completed.
InputDataConfig (dict) --
The input data configuration that you supplied when you created the key phrases detection job.
S3Uri (string) --
The Amazon S3 URI for the input data. The URI must be in 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 data 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.
InputFormat (string) --
Specifies how the text in an input file should be processed:
OutputDataConfig (dict) --
The output data configuration that you supplied when you created the key phrases detection job.
S3Uri (string) --
When you use the OutputDataConfig object with asynchronous operations, you specify the Amazon S3 location where you want to write the output data. 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 the output file.
When the topic detection job is finished, the service creates an 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 ouput of the operation.
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:
LanguageCode (string) --
The language code of the input documents.
DataAccessRoleArn (string) --
The Amazon Resource Name (ARN) that gives 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:
VpcConfig (dict) --
Configuration parameters for a private Virtual Private Cloud (VPC) containing the resources you are using for your key phrases detection job. 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 .
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 .
NextToken (string) --
Identifies the next page of results to return.
Exceptions
Gets a list of the PII entity detection jobs that you have submitted.
See also: AWS API Documentation
Request Syntax
response = client.list_pii_entities_detection_jobs(
Filter={
'JobName': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED',
'SubmitTimeBefore': datetime(2015, 1, 1),
'SubmitTimeAfter': datetime(2015, 1, 1)
},
NextToken='string',
MaxResults=123
)
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.
Filters on the name of the job.
Filters the list of jobs based on job status. Returns only jobs with the specified status.
Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted before the specified time. Jobs are returned in ascending order, oldest to newest.
Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted after the specified time. Jobs are returned in descending order, newest to oldest.
dict
Response Syntax
{
'PiiEntitiesDetectionJobPropertiesList': [
{
'JobId': 'string',
'JobName': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED',
'Message': 'string',
'SubmitTime': datetime(2015, 1, 1),
'EndTime': datetime(2015, 1, 1),
'InputDataConfig': {
'S3Uri': 'string',
'InputFormat': 'ONE_DOC_PER_FILE'|'ONE_DOC_PER_LINE'
},
'OutputDataConfig': {
'S3Uri': 'string',
'KmsKeyId': 'string'
},
'RedactionConfig': {
'PiiEntityTypes': [
'BANK_ACCOUNT_NUMBER'|'BANK_ROUTING'|'CREDIT_DEBIT_NUMBER'|'CREDIT_DEBIT_CVV'|'CREDIT_DEBIT_EXPIRY'|'PIN'|'EMAIL'|'ADDRESS'|'NAME'|'PHONE'|'SSN'|'DATE_TIME'|'PASSPORT_NUMBER'|'DRIVER_ID'|'URL'|'AGE'|'USERNAME'|'PASSWORD'|'AWS_ACCESS_KEY'|'AWS_SECRET_KEY'|'IP_ADDRESS'|'MAC_ADDRESS'|'ALL',
],
'MaskMode': 'MASK'|'REPLACE_WITH_PII_ENTITY_TYPE',
'MaskCharacter': 'string'
},
'LanguageCode': 'en'|'es'|'fr'|'de'|'it'|'pt'|'ar'|'hi'|'ja'|'ko'|'zh'|'zh-TW',
'DataAccessRoleArn': 'string',
'Mode': 'ONLY_REDACTION'|'ONLY_OFFSETS'
},
],
'NextToken': 'string'
}
Response Structure
(dict) --
PiiEntitiesDetectionJobPropertiesList (list) --
A list containing the properties of each job that is returned.
(dict) --
Provides information about a PII entities detection job.
JobId (string) --
The identifier assigned to the PII entities detection job.
JobName (string) --
The name that you assigned the PII entities detection job.
JobStatus (string) --
The current status of the PII entities detection job. If the status is FAILED , the Message field shows the reason for the failure.
Message (string) --
A description of the status of a job.
SubmitTime (datetime) --
The time that the PII entities detection job was submitted for processing.
EndTime (datetime) --
The time that the PII entities detection job completed.
InputDataConfig (dict) --
The input properties for a PII entities detection job.
S3Uri (string) --
The Amazon S3 URI for the input data. The URI must be in 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 data 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.
InputFormat (string) --
Specifies how the text in an input file should be processed:
OutputDataConfig (dict) --
The output data configuration that you supplied when you created the PII entities detection job.
S3Uri (string) --
When you use the PiiOutputDataConfig object with asynchronous operations, you specify the Amazon S3 location where you want to write the output data.
KmsKeyId (string) --
ID for the AWS Key Management Service (KMS) key that Amazon Comprehend uses to encrypt the output results from an analysis job.
RedactionConfig (dict) --
Provides configuration parameters for PII entity redaction.
This parameter is required if you set the Mode parameter to ONLY_REDACTION . In that case, you must provide a RedactionConfig definition that includes the PiiEntityTypes parameter.
PiiEntityTypes (list) --
An array of the types of PII entities that Amazon Comprehend detects in the input text for your request.
MaskMode (string) --
Specifies whether the PII entity is redacted with the mask character or the entity type.
MaskCharacter (string) --
A character that replaces each character in the redacted PII entity.
LanguageCode (string) --
The language code of the input documents
DataAccessRoleArn (string) --
The Amazon Resource Name (ARN) that gives Amazon Comprehend read access to your input data.
Mode (string) --
Specifies whether the output provides the locations (offsets) of PII entities or a file in which PII entities are redacted.
NextToken (string) --
Identifies the next page of results to return.
Exceptions
Gets a list of sentiment detection jobs that you have submitted.
See also: AWS API Documentation
Request Syntax
response = client.list_sentiment_detection_jobs(
Filter={
'JobName': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED',
'SubmitTimeBefore': datetime(2015, 1, 1),
'SubmitTimeAfter': datetime(2015, 1, 1)
},
NextToken='string',
MaxResults=123
)
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.
Filters on the name of the job.
Filters the list of jobs based on job status. Returns only jobs with the specified status.
Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted before the specified time. Jobs are returned in ascending order, oldest to newest.
Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted after the specified time. Jobs are returned in descending order, newest to oldest.
dict
Response Syntax
{
'SentimentDetectionJobPropertiesList': [
{
'JobId': 'string',
'JobName': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED',
'Message': 'string',
'SubmitTime': datetime(2015, 1, 1),
'EndTime': datetime(2015, 1, 1),
'InputDataConfig': {
'S3Uri': 'string',
'InputFormat': 'ONE_DOC_PER_FILE'|'ONE_DOC_PER_LINE'
},
'OutputDataConfig': {
'S3Uri': 'string',
'KmsKeyId': 'string'
},
'LanguageCode': 'en'|'es'|'fr'|'de'|'it'|'pt'|'ar'|'hi'|'ja'|'ko'|'zh'|'zh-TW',
'DataAccessRoleArn': 'string',
'VolumeKmsKeyId': 'string',
'VpcConfig': {
'SecurityGroupIds': [
'string',
],
'Subnets': [
'string',
]
}
},
],
'NextToken': 'string'
}
Response Structure
(dict) --
SentimentDetectionJobPropertiesList (list) --
A list containing the properties of each job that is returned.
(dict) --
Provides information about a sentiment detection job.
JobId (string) --
The identifier assigned to the sentiment detection job.
JobName (string) --
The name that you assigned to the sentiment detection job
JobStatus (string) --
The current status of the sentiment detection job. If the status is FAILED , the Messages field shows the reason for the failure.
Message (string) --
A description of the status of a job.
SubmitTime (datetime) --
The time that the sentiment detection job was submitted for processing.
EndTime (datetime) --
The time that the sentiment detection job ended.
InputDataConfig (dict) --
The input data configuration that you supplied when you created the sentiment detection job.
S3Uri (string) --
The Amazon S3 URI for the input data. The URI must be in 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 data 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.
InputFormat (string) --
Specifies how the text in an input file should be processed:
OutputDataConfig (dict) --
The output data configuration that you supplied when you created the sentiment detection job.
S3Uri (string) --
When you use the OutputDataConfig object with asynchronous operations, you specify the Amazon S3 location where you want to write the output data. 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 the output file.
When the topic detection job is finished, the service creates an 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 ouput of the operation.
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:
LanguageCode (string) --
The language code of the input documents.
DataAccessRoleArn (string) --
The Amazon Resource Name (ARN) that gives 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:
VpcConfig (dict) --
Configuration parameters for a private Virtual Private Cloud (VPC) containing the resources you are using for your sentiment detection job. 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 .
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 .
NextToken (string) --
Identifies the next page of results to return.
Exceptions
Lists all tags associated with a given Amazon Comprehend resource.
See also: AWS API Documentation
Request Syntax
response = client.list_tags_for_resource(
ResourceArn='string'
)
[REQUIRED]
The Amazon Resource Name (ARN) of the given Amazon Comprehend resource you are querying.
{
'ResourceArn': 'string',
'Tags': [
{
'Key': 'string',
'Value': 'string'
},
]
}
Response Structure
The Amazon Resource Name (ARN) of the given Amazon Comprehend resource you are querying.
Tags associated with the Amazon Comprehend resource being queried. 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.
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.
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.”
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.
Exceptions
Gets a list of the topic detection jobs that you have submitted.
See also: AWS API Documentation
Request Syntax
response = client.list_topics_detection_jobs(
Filter={
'JobName': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED',
'SubmitTimeBefore': datetime(2015, 1, 1),
'SubmitTimeAfter': datetime(2015, 1, 1)
},
NextToken='string',
MaxResults=123
)
Filters the jobs that are returned. Jobs can be filtered on their name, status, or the date and time that they were submitted. You can set only one filter at a time.
Filters the list of topic detection jobs based on job status. Returns only jobs with the specified status.
Filters the list of jobs based on the time that the job was submitted for processing. Only returns jobs submitted before the specified time. Jobs are returned in descending order, newest to oldest.
Filters the list of jobs based on the time that the job was submitted for processing. Only returns jobs submitted after the specified time. Jobs are returned in ascending order, oldest to newest.
dict
Response Syntax
{
'TopicsDetectionJobPropertiesList': [
{
'JobId': 'string',
'JobName': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED',
'Message': 'string',
'SubmitTime': datetime(2015, 1, 1),
'EndTime': datetime(2015, 1, 1),
'InputDataConfig': {
'S3Uri': 'string',
'InputFormat': 'ONE_DOC_PER_FILE'|'ONE_DOC_PER_LINE'
},
'OutputDataConfig': {
'S3Uri': 'string',
'KmsKeyId': 'string'
},
'NumberOfTopics': 123,
'DataAccessRoleArn': 'string',
'VolumeKmsKeyId': 'string',
'VpcConfig': {
'SecurityGroupIds': [
'string',
],
'Subnets': [
'string',
]
}
},
],
'NextToken': 'string'
}
Response Structure
(dict) --
TopicsDetectionJobPropertiesList (list) --
A list containing the properties of each job that is returned.
(dict) --
Provides information about a topic detection job.
JobId (string) --
The identifier assigned to the topic detection job.
JobName (string) --
The name of the topic detection job.
JobStatus (string) --
The current status of the topic detection job. If the status is Failed , the reason for the failure is shown in the Message field.
Message (string) --
A description for the status of a job.
SubmitTime (datetime) --
The time that the topic detection job was submitted for processing.
EndTime (datetime) --
The time that the topic detection job was completed.
InputDataConfig (dict) --
The input data configuration supplied when you created the topic detection job.
S3Uri (string) --
The Amazon S3 URI for the input data. The URI must be in 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 data 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.
InputFormat (string) --
Specifies how the text in an input file should be processed:
OutputDataConfig (dict) --
The output data configuration supplied when you created the topic detection job.
S3Uri (string) --
When you use the OutputDataConfig object with asynchronous operations, you specify the Amazon S3 location where you want to write the output data. 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 the output file.
When the topic detection job is finished, the service creates an 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 ouput of the operation.
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:
NumberOfTopics (integer) --
The number of topics to detect supplied when you created the topic detection job. The default is 10.
DataAccessRoleArn (string) --
The Amazon Resource Name (ARN) of the AWS Identity and Management (IAM) role that grants Amazon Comprehend read access to your job 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:
VpcConfig (dict) --
Configuration parameters for a private Virtual Private Cloud (VPC) containing the resources you are using for your topic detection job. 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 .
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 .
NextToken (string) --
Identifies the next page of results to return.
Exceptions
Starts an asynchronous document classification job. Use the operation to track the progress of the job.
See also: AWS API Documentation
Request Syntax
response = client.start_document_classification_job(
JobName='string',
DocumentClassifierArn='string',
InputDataConfig={
'S3Uri': 'string',
'InputFormat': 'ONE_DOC_PER_FILE'|'ONE_DOC_PER_LINE'
},
OutputDataConfig={
'S3Uri': 'string',
'KmsKeyId': 'string'
},
DataAccessRoleArn='string',
ClientRequestToken='string',
VolumeKmsKeyId='string',
VpcConfig={
'SecurityGroupIds': [
'string',
],
'Subnets': [
'string',
]
}
)
[REQUIRED]
The Amazon Resource Name (ARN) of the document classifier to use to process the job.
[REQUIRED]
Specifies the format and location of the input data for the job.
The Amazon S3 URI for the input data. The URI must be in 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 data 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.
Specifies how the text in an input file should be processed:
[REQUIRED]
Specifies where to send the output files.
When you use the OutputDataConfig object with asynchronous operations, you specify the Amazon S3 location where you want to write the output data. 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 the output file.
When the topic detection job is finished, the service creates an 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 ouput of the operation.
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:
[REQUIRED]
The Amazon Resource Name (ARN) of the AWS Identity and Access Management (IAM) role that grants Amazon Comprehend read access to your input data.
A unique identifier for the request. If you do not set the client request token, Amazon Comprehend generates one.
This field is autopopulated if not provided.
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:
Configuration parameters for an optional private Virtual Private Cloud (VPC) containing the resources you are using for your document classification job. For more information, see Amazon VPC .
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 .
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 .
dict
Response Syntax
{
'JobId': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED'
}
Response Structure
(dict) --
JobId (string) --
The identifier generated for the job. To get the status of the job, use this identifier with the operation.
JobStatus (string) --
The status of the job:
Exceptions
Starts an asynchronous dominant language detection job for a collection of documents. Use the operation to track the status of a job.
See also: AWS API Documentation
Request Syntax
response = client.start_dominant_language_detection_job(
InputDataConfig={
'S3Uri': 'string',
'InputFormat': 'ONE_DOC_PER_FILE'|'ONE_DOC_PER_LINE'
},
OutputDataConfig={
'S3Uri': 'string',
'KmsKeyId': 'string'
},
DataAccessRoleArn='string',
JobName='string',
ClientRequestToken='string',
VolumeKmsKeyId='string',
VpcConfig={
'SecurityGroupIds': [
'string',
],
'Subnets': [
'string',
]
}
)
[REQUIRED]
Specifies the format and location of the input data for the job.
The Amazon S3 URI for the input data. The URI must be in 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 data 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.
Specifies how the text in an input file should be processed:
[REQUIRED]
Specifies where to send the output files.
When you use the OutputDataConfig object with asynchronous operations, you specify the Amazon S3 location where you want to write the output data. 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 the output file.
When the topic detection job is finished, the service creates an 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 ouput of the operation.
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:
[REQUIRED]
The Amazon Resource Name (ARN) of the AWS Identity and Access Management (IAM) role that grants Amazon Comprehend read access to your input data. For more information, see https://docs.aws.amazon.com/comprehend/latest/dg/access-control-managing-permissions.html#auth-role-permissions .
A unique identifier for the request. If you do not set the client request token, Amazon Comprehend generates one.
This field is autopopulated if not provided.
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:
Configuration parameters for an optional private Virtual Private Cloud (VPC) containing the resources you are using for your dominant language detection job. For more information, see Amazon VPC .
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 .
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 .
dict
Response Syntax
{
'JobId': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED'
}
Response Structure
(dict) --
JobId (string) --
The identifier generated for the job. To get the status of a job, use this identifier with the operation.
JobStatus (string) --
The status of the job.
Exceptions
Starts an asynchronous entity detection job for a collection of documents. Use the operation to track the status of a job.
This API can be used for either standard entity detection or custom entity recognition. In order to be used for custom entity recognition, the optional EntityRecognizerArn must be used in order to provide access to the recognizer being used to detect the custom entity.
See also: AWS API Documentation
Request Syntax
response = client.start_entities_detection_job(
InputDataConfig={
'S3Uri': 'string',
'InputFormat': 'ONE_DOC_PER_FILE'|'ONE_DOC_PER_LINE'
},
OutputDataConfig={
'S3Uri': 'string',
'KmsKeyId': 'string'
},
DataAccessRoleArn='string',
JobName='string',
EntityRecognizerArn='string',
LanguageCode='en'|'es'|'fr'|'de'|'it'|'pt'|'ar'|'hi'|'ja'|'ko'|'zh'|'zh-TW',
ClientRequestToken='string',
VolumeKmsKeyId='string',
VpcConfig={
'SecurityGroupIds': [
'string',
],
'Subnets': [
'string',
]
}
)
[REQUIRED]
Specifies the format and location of the input data for the job.
The Amazon S3 URI for the input data. The URI must be in 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 data 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.
Specifies how the text in an input file should be processed:
[REQUIRED]
Specifies where to send the output files.
When you use the OutputDataConfig object with asynchronous operations, you specify the Amazon S3 location where you want to write the output data. 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 the output file.
When the topic detection job is finished, the service creates an 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 ouput of the operation.
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:
[REQUIRED]
The Amazon Resource Name (ARN) of the AWS Identity and Access Management (IAM) role that grants Amazon Comprehend read access to your input data. For more information, see https://docs.aws.amazon.com/comprehend/latest/dg/access-control-managing-permissions.html#auth-role-permissions .
[REQUIRED]
The language of the input documents. All documents must be in the same language. You can specify any of the languages supported by Amazon Comprehend. If custom entities recognition is used, this parameter is ignored and the language used for training the model is used instead.
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.
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:
Configuration parameters for an optional private Virtual Private Cloud (VPC) containing the resources you are using for your entity detection job. For more information, see Amazon VPC .
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 .
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 .
dict
Response Syntax
{
'JobId': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED'
}
Response Structure
(dict) --
JobId (string) --
The identifier generated for the job. To get the status of job, use this identifier with the operation.
JobStatus (string) --
The status of the job.
Exceptions
Starts an asynchronous event detection job for a collection of documents.
See also: AWS API Documentation
Request Syntax
response = client.start_events_detection_job(
InputDataConfig={
'S3Uri': 'string',
'InputFormat': 'ONE_DOC_PER_FILE'|'ONE_DOC_PER_LINE'
},
OutputDataConfig={
'S3Uri': 'string',
'KmsKeyId': 'string'
},
DataAccessRoleArn='string',
JobName='string',
LanguageCode='en'|'es'|'fr'|'de'|'it'|'pt'|'ar'|'hi'|'ja'|'ko'|'zh'|'zh-TW',
ClientRequestToken='string',
TargetEventTypes=[
'string',
]
)
[REQUIRED]
Specifies the format and location of the input data for the job.
The Amazon S3 URI for the input data. The URI must be in 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 data 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.
Specifies how the text in an input file should be processed:
[REQUIRED]
Specifies where to send the output files.
When you use the OutputDataConfig object with asynchronous operations, you specify the Amazon S3 location where you want to write the output data. 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 the output file.
When the topic detection job is finished, the service creates an 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 ouput of the operation.
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:
[REQUIRED]
The Amazon Resource Name (ARN) of the AWS Identity and Access Management (IAM) role that grants Amazon Comprehend read access to your input data.
[REQUIRED]
The language code of the input documents.
An 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.
[REQUIRED]
The types of events to detect in the input documents.
dict
Response Syntax
{
'JobId': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED'
}
Response Structure
(dict) --
JobId (string) --
An unique identifier for the request. If you don't set the client request token, Amazon Comprehend generates one.
JobStatus (string) --
The status of the events detection job.
Exceptions
Starts an asynchronous key phrase detection job for a collection of documents. Use the operation to track the status of a job.
See also: AWS API Documentation
Request Syntax
response = client.start_key_phrases_detection_job(
InputDataConfig={
'S3Uri': 'string',
'InputFormat': 'ONE_DOC_PER_FILE'|'ONE_DOC_PER_LINE'
},
OutputDataConfig={
'S3Uri': 'string',
'KmsKeyId': 'string'
},
DataAccessRoleArn='string',
JobName='string',
LanguageCode='en'|'es'|'fr'|'de'|'it'|'pt'|'ar'|'hi'|'ja'|'ko'|'zh'|'zh-TW',
ClientRequestToken='string',
VolumeKmsKeyId='string',
VpcConfig={
'SecurityGroupIds': [
'string',
],
'Subnets': [
'string',
]
}
)
[REQUIRED]
Specifies the format and location of the input data for the job.
The Amazon S3 URI for the input data. The URI must be in 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 data 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.
Specifies how the text in an input file should be processed:
[REQUIRED]
Specifies where to send the output files.
When you use the OutputDataConfig object with asynchronous operations, you specify the Amazon S3 location where you want to write the output data. 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 the output file.
When the topic detection job is finished, the service creates an 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 ouput of the operation.
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:
[REQUIRED]
The Amazon Resource Name (ARN) of the AWS Identity and Access Management (IAM) role that grants Amazon Comprehend read access to your input data. For more information, see https://docs.aws.amazon.com/comprehend/latest/dg/access-control-managing-permissions.html#auth-role-permissions .
[REQUIRED]
The language of the input documents. You can specify any of the primary languages supported by Amazon Comprehend. All documents must be in the same language.
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.
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:
Configuration parameters for an optional private Virtual Private Cloud (VPC) containing the resources you are using for your key phrases detection job. For more information, see Amazon VPC .
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 .
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 .
dict
Response Syntax
{
'JobId': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED'
}
Response Structure
(dict) --
JobId (string) --
The identifier generated for the job. To get the status of a job, use this identifier with the operation.
JobStatus (string) --
The status of the job.
Exceptions
Starts an asynchronous PII entity detection job for a collection of documents.
See also: AWS API Documentation
Request Syntax
response = client.start_pii_entities_detection_job(
InputDataConfig={
'S3Uri': 'string',
'InputFormat': 'ONE_DOC_PER_FILE'|'ONE_DOC_PER_LINE'
},
OutputDataConfig={
'S3Uri': 'string',
'KmsKeyId': 'string'
},
Mode='ONLY_REDACTION'|'ONLY_OFFSETS',
RedactionConfig={
'PiiEntityTypes': [
'BANK_ACCOUNT_NUMBER'|'BANK_ROUTING'|'CREDIT_DEBIT_NUMBER'|'CREDIT_DEBIT_CVV'|'CREDIT_DEBIT_EXPIRY'|'PIN'|'EMAIL'|'ADDRESS'|'NAME'|'PHONE'|'SSN'|'DATE_TIME'|'PASSPORT_NUMBER'|'DRIVER_ID'|'URL'|'AGE'|'USERNAME'|'PASSWORD'|'AWS_ACCESS_KEY'|'AWS_SECRET_KEY'|'IP_ADDRESS'|'MAC_ADDRESS'|'ALL',
],
'MaskMode': 'MASK'|'REPLACE_WITH_PII_ENTITY_TYPE',
'MaskCharacter': 'string'
},
DataAccessRoleArn='string',
JobName='string',
LanguageCode='en'|'es'|'fr'|'de'|'it'|'pt'|'ar'|'hi'|'ja'|'ko'|'zh'|'zh-TW',
ClientRequestToken='string'
)
[REQUIRED]
The input properties for a PII entities detection job.
The Amazon S3 URI for the input data. The URI must be in 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 data 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.
Specifies how the text in an input file should be processed:
[REQUIRED]
Provides configuration parameters for the output of PII entity detection jobs.
When you use the OutputDataConfig object with asynchronous operations, you specify the Amazon S3 location where you want to write the output data. 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 the output file.
When the topic detection job is finished, the service creates an 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 ouput of the operation.
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:
[REQUIRED]
Specifies whether the output provides the locations (offsets) of PII entities or a file in which PII entities are redacted.
Provides configuration parameters for PII entity redaction.
This parameter is required if you set the Mode parameter to ONLY_REDACTION . In that case, you must provide a RedactionConfig definition that includes the PiiEntityTypes parameter.
An array of the types of PII entities that Amazon Comprehend detects in the input text for your request.
Specifies whether the PII entity is redacted with the mask character or the entity type.
A character that replaces each character in the redacted PII entity.
[REQUIRED]
The Amazon Resource Name (ARN) of the AWS Identity and Access Management (IAM) role that grants Amazon Comprehend read access to your input data.
[REQUIRED]
The language of the input documents.
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.
dict
Response Syntax
{
'JobId': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED'
}
Response Structure
(dict) --
JobId (string) --
The identifier generated for the job.
JobStatus (string) --
The status of the job.
Exceptions
Starts an asynchronous sentiment detection job for a collection of documents. use the operation to track the status of a job.
See also: AWS API Documentation
Request Syntax
response = client.start_sentiment_detection_job(
InputDataConfig={
'S3Uri': 'string',
'InputFormat': 'ONE_DOC_PER_FILE'|'ONE_DOC_PER_LINE'
},
OutputDataConfig={
'S3Uri': 'string',
'KmsKeyId': 'string'
},
DataAccessRoleArn='string',
JobName='string',
LanguageCode='en'|'es'|'fr'|'de'|'it'|'pt'|'ar'|'hi'|'ja'|'ko'|'zh'|'zh-TW',
ClientRequestToken='string',
VolumeKmsKeyId='string',
VpcConfig={
'SecurityGroupIds': [
'string',
],
'Subnets': [
'string',
]
}
)
[REQUIRED]
Specifies the format and location of the input data for the job.
The Amazon S3 URI for the input data. The URI must be in 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 data 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.
Specifies how the text in an input file should be processed:
[REQUIRED]
Specifies where to send the output files.
When you use the OutputDataConfig object with asynchronous operations, you specify the Amazon S3 location where you want to write the output data. 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 the output file.
When the topic detection job is finished, the service creates an 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 ouput of the operation.
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:
[REQUIRED]
The Amazon Resource Name (ARN) of the AWS Identity and Access Management (IAM) role that grants Amazon Comprehend read access to your input data. For more information, see https://docs.aws.amazon.com/comprehend/latest/dg/access-control-managing-permissions.html#auth-role-permissions .
[REQUIRED]
The language of the input documents. You can specify any of the primary languages supported by Amazon Comprehend. All documents must be in the same language.
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.
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:
Configuration parameters for an optional private Virtual Private Cloud (VPC) containing the resources you are using for your sentiment detection job. For more information, see Amazon VPC .
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 .
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 .
dict
Response Syntax
{
'JobId': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED'
}
Response Structure
(dict) --
JobId (string) --
The identifier generated for the job. To get the status of a job, use this identifier with the operation.
JobStatus (string) --
The status of the job.
Exceptions
Starts an asynchronous topic detection job. Use the DescribeTopicDetectionJob operation to track the status of a job.
See also: AWS API Documentation
Request Syntax
response = client.start_topics_detection_job(
InputDataConfig={
'S3Uri': 'string',
'InputFormat': 'ONE_DOC_PER_FILE'|'ONE_DOC_PER_LINE'
},
OutputDataConfig={
'S3Uri': 'string',
'KmsKeyId': 'string'
},
DataAccessRoleArn='string',
JobName='string',
NumberOfTopics=123,
ClientRequestToken='string',
VolumeKmsKeyId='string',
VpcConfig={
'SecurityGroupIds': [
'string',
],
'Subnets': [
'string',
]
}
)
[REQUIRED]
Specifies the format and location of the input data for the job.
The Amazon S3 URI for the input data. The URI must be in 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 data 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.
Specifies how the text in an input file should be processed:
[REQUIRED]
Specifies where to send the output files. The output is a compressed archive with two files, topic-terms.csv that lists the terms associated with each topic, and doc-topics.csv that lists the documents associated with each topic
When you use the OutputDataConfig object with asynchronous operations, you specify the Amazon S3 location where you want to write the output data. 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 the output file.
When the topic detection job is finished, the service creates an 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 ouput of the operation.
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:
[REQUIRED]
The Amazon Resource Name (ARN) of the AWS Identity and Access Management (IAM) role that grants Amazon Comprehend read access to your input data. For more information, see https://docs.aws.amazon.com/comprehend/latest/dg/access-control-managing-permissions.html#auth-role-permissions .
A unique identifier for the request. If you do not set the client request token, Amazon Comprehend generates one.
This field is autopopulated if not provided.
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:
Configuration parameters for an optional private Virtual Private Cloud (VPC) containing the resources you are using for your topic detection job. For more information, see Amazon VPC .
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 .
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 .
dict
Response Syntax
{
'JobId': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED'
}
Response Structure
(dict) --
JobId (string) --
The identifier generated for the job. To get the status of the job, use this identifier with the DescribeTopicDetectionJob operation.
JobStatus (string) --
The status of the job:
Exceptions
Stops a dominant language detection job in progress.
If the job state is IN_PROGRESS the job is marked for termination and put into the STOP_REQUESTED state. If the job completes before it can be stopped, it is put into the COMPLETED state; otherwise the job is stopped and put into the STOPPED state.
If the job is in the COMPLETED or FAILED state when you call the StopDominantLanguageDetectionJob operation, the operation returns a 400 Internal Request Exception.
When a job is stopped, any documents already processed are written to the output location.
See also: AWS API Documentation
Request Syntax
response = client.stop_dominant_language_detection_job(
JobId='string'
)
[REQUIRED]
The identifier of the dominant language detection job to stop.
{
'JobId': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED'
}
Response Structure
The identifier of the dominant language detection job to stop.
Either STOP_REQUESTED if the job is currently running, or STOPPED if the job was previously stopped with the StopDominantLanguageDetectionJob operation.
Exceptions
Stops an entities detection job in progress.
If the job state is IN_PROGRESS the job is marked for termination and put into the STOP_REQUESTED state. If the job completes before it can be stopped, it is put into the COMPLETED state; otherwise the job is stopped and put into the STOPPED state.
If the job is in the COMPLETED or FAILED state when you call the StopDominantLanguageDetectionJob operation, the operation returns a 400 Internal Request Exception.
When a job is stopped, any documents already processed are written to the output location.
See also: AWS API Documentation
Request Syntax
response = client.stop_entities_detection_job(
JobId='string'
)
[REQUIRED]
The identifier of the entities detection job to stop.
{
'JobId': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED'
}
Response Structure
The identifier of the entities detection job to stop.
Either STOP_REQUESTED if the job is currently running, or STOPPED if the job was previously stopped with the StopEntitiesDetectionJob operation.
Exceptions
Stops an events detection job in progress.
See also: AWS API Documentation
Request Syntax
response = client.stop_events_detection_job(
JobId='string'
)
[REQUIRED]
The identifier of the events detection job to stop.
{
'JobId': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED'
}
Response Structure
The identifier of the events detection job to stop.
The status of the events detection job.
Exceptions
Stops a key phrases detection job in progress.
If the job state is IN_PROGRESS the job is marked for termination and put into the STOP_REQUESTED state. If the job completes before it can be stopped, it is put into the COMPLETED state; otherwise the job is stopped and put into the STOPPED state.
If the job is in the COMPLETED or FAILED state when you call the StopDominantLanguageDetectionJob operation, the operation returns a 400 Internal Request Exception.
When a job is stopped, any documents already processed are written to the output location.
See also: AWS API Documentation
Request Syntax
response = client.stop_key_phrases_detection_job(
JobId='string'
)
[REQUIRED]
The identifier of the key phrases detection job to stop.
{
'JobId': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED'
}
Response Structure
The identifier of the key phrases detection job to stop.
Either STOP_REQUESTED if the job is currently running, or STOPPED if the job was previously stopped with the StopKeyPhrasesDetectionJob operation.
Exceptions
Stops a PII entities detection job in progress.
See also: AWS API Documentation
Request Syntax
response = client.stop_pii_entities_detection_job(
JobId='string'
)
[REQUIRED]
The identifier of the PII entities detection job to stop.
{
'JobId': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED'
}
Response Structure
The identifier of the PII entities detection job to stop.
The status of the PII entities detection job.
Exceptions
Stops a sentiment detection job in progress.
If the job state is IN_PROGRESS the job is marked for termination and put into the STOP_REQUESTED state. If the job completes before it can be stopped, it is put into the COMPLETED state; otherwise the job is be stopped and put into the STOPPED state.
If the job is in the COMPLETED or FAILED state when you call the StopDominantLanguageDetectionJob operation, the operation returns a 400 Internal Request Exception.
When a job is stopped, any documents already processed are written to the output location.
See also: AWS API Documentation
Request Syntax
response = client.stop_sentiment_detection_job(
JobId='string'
)
[REQUIRED]
The identifier of the sentiment detection job to stop.
{
'JobId': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED'
}
Response Structure
The identifier of the sentiment detection job to stop.
Either STOP_REQUESTED if the job is currently running, or STOPPED if the job was previously stopped with the StopSentimentDetectionJob operation.
Exceptions
Stops a document classifier training job while in progress.
If the training job state is TRAINING , the job is marked for termination and put into the STOP_REQUESTED state. If the training job completes before it can be stopped, it is put into the TRAINED ; otherwise the training job is stopped and put into the STOPPED state and the service sends back an HTTP 200 response with an empty HTTP body.
See also: AWS API Documentation
Request Syntax
response = client.stop_training_document_classifier(
DocumentClassifierArn='string'
)
[REQUIRED]
The Amazon Resource Name (ARN) that identifies the document classifier currently being trained.
{}
Response Structure
Exceptions
Stops an entity recognizer training job while in progress.
If the training job state is TRAINING , the job is marked for termination and put into the STOP_REQUESTED state. If the training job completes before it can be stopped, it is put into the TRAINED ; otherwise the training job is stopped and putted into the STOPPED state and the service sends back an HTTP 200 response with an empty HTTP body.
See also: AWS API Documentation
Request Syntax
response = client.stop_training_entity_recognizer(
EntityRecognizerArn='string'
)
[REQUIRED]
The Amazon Resource Name (ARN) that identifies the entity recognizer currently being trained.
{}
Response Structure
Exceptions
Associates a specific tag with an Amazon Comprehend resource. 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.
See also: AWS API Documentation
Request Syntax
response = client.tag_resource(
ResourceArn='string',
Tags=[
{
'Key': 'string',
'Value': 'string'
},
]
)
[REQUIRED]
The Amazon Resource Name (ARN) of the given Amazon Comprehend resource to which you want to associate the tags.
[REQUIRED]
Tags being associated with a specific Amazon Comprehend resource. There can be a maximum of 50 tags (both existing and pending) associated with a specific resource.
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.
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.”
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
Response Syntax
{}
Response Structure
Exceptions
Removes a specific tag associated with an Amazon Comprehend resource.
See also: AWS API Documentation
Request Syntax
response = client.untag_resource(
ResourceArn='string',
TagKeys=[
'string',
]
)
[REQUIRED]
The Amazon Resource Name (ARN) of the given Amazon Comprehend resource from which you want to remove the tags.
[REQUIRED]
The initial part of a key-value pair that forms a tag being removed from a given resource. For example, a tag with "Sales" as the key might be added to a resource to indicate its use by the sales department. Keys must be unique and cannot be duplicated for a particular resource.
dict
Response Syntax
{}
Response Structure
Exceptions
Updates information about the specified endpoint.
See also: AWS API Documentation
Request Syntax
response = client.update_endpoint(
EndpointArn='string',
DesiredInferenceUnits=123
)
[REQUIRED]
The Amazon Resource Number (ARN) of the endpoint being updated.
[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.
dict
Response Syntax
{}
Response Structure
Exceptions
The available paginators are:
paginator = client.get_paginator('list_document_classification_jobs')
Creates an iterator that will paginate through responses from Comprehend.Client.list_document_classification_jobs().
See also: AWS API Documentation
Request Syntax
response_iterator = paginator.paginate(
Filter={
'JobName': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED',
'SubmitTimeBefore': datetime(2015, 1, 1),
'SubmitTimeAfter': datetime(2015, 1, 1)
},
PaginationConfig={
'MaxItems': 123,
'PageSize': 123,
'StartingToken': 'string'
}
)
Filters the jobs that are returned. You can filter jobs on their names, status, or the date and time that they were submitted. You can only set one filter at a time.
Filters on the name of the job.
Filters the list based on job status. Returns only jobs with the specified status.
Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted before the specified time. Jobs are returned in ascending order, oldest to newest.
Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted after the specified time. Jobs are returned in descending order, newest to oldest.
A dictionary that provides parameters to control pagination.
The total number of items to return. If the total number of items available is more than the value specified in max-items then a NextToken will be provided in the output that you can use to resume pagination.
The size of each page.
A token to specify where to start paginating. This is the NextToken from a previous response.
dict
Response Syntax
{
'DocumentClassificationJobPropertiesList': [
{
'JobId': 'string',
'JobName': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED',
'Message': 'string',
'SubmitTime': datetime(2015, 1, 1),
'EndTime': datetime(2015, 1, 1),
'DocumentClassifierArn': 'string',
'InputDataConfig': {
'S3Uri': 'string',
'InputFormat': 'ONE_DOC_PER_FILE'|'ONE_DOC_PER_LINE'
},
'OutputDataConfig': {
'S3Uri': 'string',
'KmsKeyId': 'string'
},
'DataAccessRoleArn': 'string',
'VolumeKmsKeyId': 'string',
'VpcConfig': {
'SecurityGroupIds': [
'string',
],
'Subnets': [
'string',
]
}
},
],
}
Response Structure
(dict) --
DocumentClassificationJobPropertiesList (list) --
A list containing the properties of each job returned.
(dict) --
Provides information about a document classification job.
JobId (string) --
The identifier assigned to the document classification job.
JobName (string) --
The name that you assigned to the document classification job.
JobStatus (string) --
The current status of the document classification job. If the status is FAILED , the Message field shows the reason for the failure.
Message (string) --
A description of the status of the job.
SubmitTime (datetime) --
The time that the document classification job was submitted for processing.
EndTime (datetime) --
The time that the document classification job completed.
DocumentClassifierArn (string) --
The Amazon Resource Name (ARN) that identifies the document classifier.
InputDataConfig (dict) --
The input data configuration that you supplied when you created the document classification job.
S3Uri (string) --
The Amazon S3 URI for the input data. The URI must be in 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 data 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.
InputFormat (string) --
Specifies how the text in an input file should be processed:
OutputDataConfig (dict) --
The output data configuration that you supplied when you created the document classification job.
S3Uri (string) --
When you use the OutputDataConfig object with asynchronous operations, you specify the Amazon S3 location where you want to write the output data. 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 the output file.
When the topic detection job is finished, the service creates an 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 ouput of the operation.
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:
DataAccessRoleArn (string) --
The Amazon Resource Name (ARN) of the AWS identity and Access 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:
VpcConfig (dict) --
Configuration parameters for a private Virtual Private Cloud (VPC) containing the resources you are using for your document classification job. 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 .
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 .
paginator = client.get_paginator('list_document_classifiers')
Creates an iterator that will paginate through responses from Comprehend.Client.list_document_classifiers().
See also: AWS API Documentation
Request Syntax
response_iterator = paginator.paginate(
Filter={
'Status': 'SUBMITTED'|'TRAINING'|'DELETING'|'STOP_REQUESTED'|'STOPPED'|'IN_ERROR'|'TRAINED',
'SubmitTimeBefore': datetime(2015, 1, 1),
'SubmitTimeAfter': datetime(2015, 1, 1)
},
PaginationConfig={
'MaxItems': 123,
'PageSize': 123,
'StartingToken': 'string'
}
)
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.
Filters the list of classifiers based on status.
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.
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.
A dictionary that provides parameters to control pagination.
The total number of items to return. If the total number of items available is more than the value specified in max-items then a NextToken will be provided in the output that you can use to resume pagination.
The size of each page.
A token to specify where to start paginating. This is the NextToken from a previous response.
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'
},
],
}
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:
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.
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:
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:
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 .
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 .
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:
paginator = client.get_paginator('list_dominant_language_detection_jobs')
Creates an iterator that will paginate through responses from Comprehend.Client.list_dominant_language_detection_jobs().
See also: AWS API Documentation
Request Syntax
response_iterator = paginator.paginate(
Filter={
'JobName': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED',
'SubmitTimeBefore': datetime(2015, 1, 1),
'SubmitTimeAfter': datetime(2015, 1, 1)
},
PaginationConfig={
'MaxItems': 123,
'PageSize': 123,
'StartingToken': 'string'
}
)
Filters that 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.
Filters on the name of the job.
Filters the list of jobs based on job status. Returns only jobs with the specified status.
Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted before the specified time. Jobs are returned in ascending order, oldest to newest.
Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted after the specified time. Jobs are returned in descending order, newest to oldest.
A dictionary that provides parameters to control pagination.
The total number of items to return. If the total number of items available is more than the value specified in max-items then a NextToken will be provided in the output that you can use to resume pagination.
The size of each page.
A token to specify where to start paginating. This is the NextToken from a previous response.
dict
Response Syntax
{
'DominantLanguageDetectionJobPropertiesList': [
{
'JobId': 'string',
'JobName': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED',
'Message': 'string',
'SubmitTime': datetime(2015, 1, 1),
'EndTime': datetime(2015, 1, 1),
'InputDataConfig': {
'S3Uri': 'string',
'InputFormat': 'ONE_DOC_PER_FILE'|'ONE_DOC_PER_LINE'
},
'OutputDataConfig': {
'S3Uri': 'string',
'KmsKeyId': 'string'
},
'DataAccessRoleArn': 'string',
'VolumeKmsKeyId': 'string',
'VpcConfig': {
'SecurityGroupIds': [
'string',
],
'Subnets': [
'string',
]
}
},
],
}
Response Structure
(dict) --
DominantLanguageDetectionJobPropertiesList (list) --
A list containing the properties of each job that is returned.
(dict) --
Provides information about a dominant language detection job.
JobId (string) --
The identifier assigned to the dominant language detection job.
JobName (string) --
The name that you assigned to the dominant language detection job.
JobStatus (string) --
The current status of the dominant language detection job. If the status is FAILED , the Message field shows the reason for the failure.
Message (string) --
A description for the status of a job.
SubmitTime (datetime) --
The time that the dominant language detection job was submitted for processing.
EndTime (datetime) --
The time that the dominant language detection job completed.
InputDataConfig (dict) --
The input data configuration that you supplied when you created the dominant language detection job.
S3Uri (string) --
The Amazon S3 URI for the input data. The URI must be in 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 data 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.
InputFormat (string) --
Specifies how the text in an input file should be processed:
OutputDataConfig (dict) --
The output data configuration that you supplied when you created the dominant language detection job.
S3Uri (string) --
When you use the OutputDataConfig object with asynchronous operations, you specify the Amazon S3 location where you want to write the output data. 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 the output file.
When the topic detection job is finished, the service creates an 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 ouput of the operation.
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:
DataAccessRoleArn (string) --
The Amazon Resource Name (ARN) that gives 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:
VpcConfig (dict) --
Configuration parameters for a private Virtual Private Cloud (VPC) containing the resources you are using for your dominant language detection job. 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 .
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 .
paginator = client.get_paginator('list_entities_detection_jobs')
Creates an iterator that will paginate through responses from Comprehend.Client.list_entities_detection_jobs().
See also: AWS API Documentation
Request Syntax
response_iterator = paginator.paginate(
Filter={
'JobName': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED',
'SubmitTimeBefore': datetime(2015, 1, 1),
'SubmitTimeAfter': datetime(2015, 1, 1)
},
PaginationConfig={
'MaxItems': 123,
'PageSize': 123,
'StartingToken': 'string'
}
)
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.
Filters on the name of the job.
Filters the list of jobs based on job status. Returns only jobs with the specified status.
Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted before the specified time. Jobs are returned in ascending order, oldest to newest.
Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted after the specified time. Jobs are returned in descending order, newest to oldest.
A dictionary that provides parameters to control pagination.
The total number of items to return. If the total number of items available is more than the value specified in max-items then a NextToken will be provided in the output that you can use to resume pagination.
The size of each page.
A token to specify where to start paginating. This is the NextToken from a previous response.
dict
Response Syntax
{
'EntitiesDetectionJobPropertiesList': [
{
'JobId': 'string',
'JobName': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED',
'Message': 'string',
'SubmitTime': datetime(2015, 1, 1),
'EndTime': datetime(2015, 1, 1),
'EntityRecognizerArn': 'string',
'InputDataConfig': {
'S3Uri': 'string',
'InputFormat': 'ONE_DOC_PER_FILE'|'ONE_DOC_PER_LINE'
},
'OutputDataConfig': {
'S3Uri': 'string',
'KmsKeyId': 'string'
},
'LanguageCode': 'en'|'es'|'fr'|'de'|'it'|'pt'|'ar'|'hi'|'ja'|'ko'|'zh'|'zh-TW',
'DataAccessRoleArn': 'string',
'VolumeKmsKeyId': 'string',
'VpcConfig': {
'SecurityGroupIds': [
'string',
],
'Subnets': [
'string',
]
}
},
],
}
Response Structure
(dict) --
EntitiesDetectionJobPropertiesList (list) --
A list containing the properties of each job that is returned.
(dict) --
Provides information about an entities detection job.
JobId (string) --
The identifier assigned to the entities detection job.
JobName (string) --
The name that you assigned the entities detection job.
JobStatus (string) --
The current status of the entities detection job. If the status is FAILED , the Message field shows the reason for the failure.
Message (string) --
A description of the status of a job.
SubmitTime (datetime) --
The time that the entities detection job was submitted for processing.
EndTime (datetime) --
The time that the entities detection job completed
EntityRecognizerArn (string) --
The Amazon Resource Name (ARN) that identifies the entity recognizer.
InputDataConfig (dict) --
The input data configuration that you supplied when you created the entities detection job.
S3Uri (string) --
The Amazon S3 URI for the input data. The URI must be in 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 data 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.
InputFormat (string) --
Specifies how the text in an input file should be processed:
OutputDataConfig (dict) --
The output data configuration that you supplied when you created the entities detection job.
S3Uri (string) --
When you use the OutputDataConfig object with asynchronous operations, you specify the Amazon S3 location where you want to write the output data. 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 the output file.
When the topic detection job is finished, the service creates an 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 ouput of the operation.
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:
LanguageCode (string) --
The language code of the input documents.
DataAccessRoleArn (string) --
The Amazon Resource Name (ARN) that gives 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:
VpcConfig (dict) --
Configuration parameters for a private Virtual Private Cloud (VPC) containing the resources you are using for your entity detection job. 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 .
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 .
paginator = client.get_paginator('list_entity_recognizers')
Creates an iterator that will paginate through responses from Comprehend.Client.list_entity_recognizers().
See also: AWS API Documentation
Request Syntax
response_iterator = paginator.paginate(
Filter={
'Status': 'SUBMITTED'|'TRAINING'|'DELETING'|'STOP_REQUESTED'|'STOPPED'|'IN_ERROR'|'TRAINED',
'SubmitTimeBefore': datetime(2015, 1, 1),
'SubmitTimeAfter': datetime(2015, 1, 1)
},
PaginationConfig={
'MaxItems': 123,
'PageSize': 123,
'StartingToken': 'string'
}
)
Filters the list of entities returned. You can filter on Status , SubmitTimeBefore , or SubmitTimeAfter . You can only set one filter at a time.
The status of an entity recognizer.
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.
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.
A dictionary that provides parameters to control pagination.
The total number of items to return. If the total number of items available is more than the value specified in max-items then a NextToken will be provided in the output that you can use to resume pagination.
The size of each page.
A token to specify where to start paginating. This is the NextToken from a previous response.
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'
},
],
}
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:
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.
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:
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 .
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 .
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:
paginator = client.get_paginator('list_key_phrases_detection_jobs')
Creates an iterator that will paginate through responses from Comprehend.Client.list_key_phrases_detection_jobs().
See also: AWS API Documentation
Request Syntax
response_iterator = paginator.paginate(
Filter={
'JobName': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED',
'SubmitTimeBefore': datetime(2015, 1, 1),
'SubmitTimeAfter': datetime(2015, 1, 1)
},
PaginationConfig={
'MaxItems': 123,
'PageSize': 123,
'StartingToken': 'string'
}
)
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.
Filters on the name of the job.
Filters the list of jobs based on job status. Returns only jobs with the specified status.
Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted before the specified time. Jobs are returned in ascending order, oldest to newest.
Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted after the specified time. Jobs are returned in descending order, newest to oldest.
A dictionary that provides parameters to control pagination.
The total number of items to return. If the total number of items available is more than the value specified in max-items then a NextToken will be provided in the output that you can use to resume pagination.
The size of each page.
A token to specify where to start paginating. This is the NextToken from a previous response.
dict
Response Syntax
{
'KeyPhrasesDetectionJobPropertiesList': [
{
'JobId': 'string',
'JobName': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED',
'Message': 'string',
'SubmitTime': datetime(2015, 1, 1),
'EndTime': datetime(2015, 1, 1),
'InputDataConfig': {
'S3Uri': 'string',
'InputFormat': 'ONE_DOC_PER_FILE'|'ONE_DOC_PER_LINE'
},
'OutputDataConfig': {
'S3Uri': 'string',
'KmsKeyId': 'string'
},
'LanguageCode': 'en'|'es'|'fr'|'de'|'it'|'pt'|'ar'|'hi'|'ja'|'ko'|'zh'|'zh-TW',
'DataAccessRoleArn': 'string',
'VolumeKmsKeyId': 'string',
'VpcConfig': {
'SecurityGroupIds': [
'string',
],
'Subnets': [
'string',
]
}
},
],
}
Response Structure
(dict) --
KeyPhrasesDetectionJobPropertiesList (list) --
A list containing the properties of each job that is returned.
(dict) --
Provides information about a key phrases detection job.
JobId (string) --
The identifier assigned to the key phrases detection job.
JobName (string) --
The name that you assigned the key phrases detection job.
JobStatus (string) --
The current status of the key phrases detection job. If the status is FAILED , the Message field shows the reason for the failure.
Message (string) --
A description of the status of a job.
SubmitTime (datetime) --
The time that the key phrases detection job was submitted for processing.
EndTime (datetime) --
The time that the key phrases detection job completed.
InputDataConfig (dict) --
The input data configuration that you supplied when you created the key phrases detection job.
S3Uri (string) --
The Amazon S3 URI for the input data. The URI must be in 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 data 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.
InputFormat (string) --
Specifies how the text in an input file should be processed:
OutputDataConfig (dict) --
The output data configuration that you supplied when you created the key phrases detection job.
S3Uri (string) --
When you use the OutputDataConfig object with asynchronous operations, you specify the Amazon S3 location where you want to write the output data. 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 the output file.
When the topic detection job is finished, the service creates an 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 ouput of the operation.
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:
LanguageCode (string) --
The language code of the input documents.
DataAccessRoleArn (string) --
The Amazon Resource Name (ARN) that gives 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:
VpcConfig (dict) --
Configuration parameters for a private Virtual Private Cloud (VPC) containing the resources you are using for your key phrases detection job. 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 .
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 .
paginator = client.get_paginator('list_sentiment_detection_jobs')
Creates an iterator that will paginate through responses from Comprehend.Client.list_sentiment_detection_jobs().
See also: AWS API Documentation
Request Syntax
response_iterator = paginator.paginate(
Filter={
'JobName': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED',
'SubmitTimeBefore': datetime(2015, 1, 1),
'SubmitTimeAfter': datetime(2015, 1, 1)
},
PaginationConfig={
'MaxItems': 123,
'PageSize': 123,
'StartingToken': 'string'
}
)
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.
Filters on the name of the job.
Filters the list of jobs based on job status. Returns only jobs with the specified status.
Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted before the specified time. Jobs are returned in ascending order, oldest to newest.
Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted after the specified time. Jobs are returned in descending order, newest to oldest.
A dictionary that provides parameters to control pagination.
The total number of items to return. If the total number of items available is more than the value specified in max-items then a NextToken will be provided in the output that you can use to resume pagination.
The size of each page.
A token to specify where to start paginating. This is the NextToken from a previous response.
dict
Response Syntax
{
'SentimentDetectionJobPropertiesList': [
{
'JobId': 'string',
'JobName': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED',
'Message': 'string',
'SubmitTime': datetime(2015, 1, 1),
'EndTime': datetime(2015, 1, 1),
'InputDataConfig': {
'S3Uri': 'string',
'InputFormat': 'ONE_DOC_PER_FILE'|'ONE_DOC_PER_LINE'
},
'OutputDataConfig': {
'S3Uri': 'string',
'KmsKeyId': 'string'
},
'LanguageCode': 'en'|'es'|'fr'|'de'|'it'|'pt'|'ar'|'hi'|'ja'|'ko'|'zh'|'zh-TW',
'DataAccessRoleArn': 'string',
'VolumeKmsKeyId': 'string',
'VpcConfig': {
'SecurityGroupIds': [
'string',
],
'Subnets': [
'string',
]
}
},
],
}
Response Structure
(dict) --
SentimentDetectionJobPropertiesList (list) --
A list containing the properties of each job that is returned.
(dict) --
Provides information about a sentiment detection job.
JobId (string) --
The identifier assigned to the sentiment detection job.
JobName (string) --
The name that you assigned to the sentiment detection job
JobStatus (string) --
The current status of the sentiment detection job. If the status is FAILED , the Messages field shows the reason for the failure.
Message (string) --
A description of the status of a job.
SubmitTime (datetime) --
The time that the sentiment detection job was submitted for processing.
EndTime (datetime) --
The time that the sentiment detection job ended.
InputDataConfig (dict) --
The input data configuration that you supplied when you created the sentiment detection job.
S3Uri (string) --
The Amazon S3 URI for the input data. The URI must be in 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 data 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.
InputFormat (string) --
Specifies how the text in an input file should be processed:
OutputDataConfig (dict) --
The output data configuration that you supplied when you created the sentiment detection job.
S3Uri (string) --
When you use the OutputDataConfig object with asynchronous operations, you specify the Amazon S3 location where you want to write the output data. 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 the output file.
When the topic detection job is finished, the service creates an 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 ouput of the operation.
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:
LanguageCode (string) --
The language code of the input documents.
DataAccessRoleArn (string) --
The Amazon Resource Name (ARN) that gives 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:
VpcConfig (dict) --
Configuration parameters for a private Virtual Private Cloud (VPC) containing the resources you are using for your sentiment detection job. 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 .
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 .
paginator = client.get_paginator('list_topics_detection_jobs')
Creates an iterator that will paginate through responses from Comprehend.Client.list_topics_detection_jobs().
See also: AWS API Documentation
Request Syntax
response_iterator = paginator.paginate(
Filter={
'JobName': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED',
'SubmitTimeBefore': datetime(2015, 1, 1),
'SubmitTimeAfter': datetime(2015, 1, 1)
},
PaginationConfig={
'MaxItems': 123,
'PageSize': 123,
'StartingToken': 'string'
}
)
Filters the jobs that are returned. Jobs can be filtered on their name, status, or the date and time that they were submitted. You can set only one filter at a time.
Filters the list of topic detection jobs based on job status. Returns only jobs with the specified status.
Filters the list of jobs based on the time that the job was submitted for processing. Only returns jobs submitted before the specified time. Jobs are returned in descending order, newest to oldest.
Filters the list of jobs based on the time that the job was submitted for processing. Only returns jobs submitted after the specified time. Jobs are returned in ascending order, oldest to newest.
A dictionary that provides parameters to control pagination.
The total number of items to return. If the total number of items available is more than the value specified in max-items then a NextToken will be provided in the output that you can use to resume pagination.
The size of each page.
A token to specify where to start paginating. This is the NextToken from a previous response.
dict
Response Syntax
{
'TopicsDetectionJobPropertiesList': [
{
'JobId': 'string',
'JobName': 'string',
'JobStatus': 'SUBMITTED'|'IN_PROGRESS'|'COMPLETED'|'FAILED'|'STOP_REQUESTED'|'STOPPED',
'Message': 'string',
'SubmitTime': datetime(2015, 1, 1),
'EndTime': datetime(2015, 1, 1),
'InputDataConfig': {
'S3Uri': 'string',
'InputFormat': 'ONE_DOC_PER_FILE'|'ONE_DOC_PER_LINE'
},
'OutputDataConfig': {
'S3Uri': 'string',
'KmsKeyId': 'string'
},
'NumberOfTopics': 123,
'DataAccessRoleArn': 'string',
'VolumeKmsKeyId': 'string',
'VpcConfig': {
'SecurityGroupIds': [
'string',
],
'Subnets': [
'string',
]
}
},
],
}
Response Structure
(dict) --
TopicsDetectionJobPropertiesList (list) --
A list containing the properties of each job that is returned.
(dict) --
Provides information about a topic detection job.
JobId (string) --
The identifier assigned to the topic detection job.
JobName (string) --
The name of the topic detection job.
JobStatus (string) --
The current status of the topic detection job. If the status is Failed , the reason for the failure is shown in the Message field.
Message (string) --
A description for the status of a job.
SubmitTime (datetime) --
The time that the topic detection job was submitted for processing.
EndTime (datetime) --
The time that the topic detection job was completed.
InputDataConfig (dict) --
The input data configuration supplied when you created the topic detection job.
S3Uri (string) --
The Amazon S3 URI for the input data. The URI must be in 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 data 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.
InputFormat (string) --
Specifies how the text in an input file should be processed:
OutputDataConfig (dict) --
The output data configuration supplied when you created the topic detection job.
S3Uri (string) --
When you use the OutputDataConfig object with asynchronous operations, you specify the Amazon S3 location where you want to write the output data. 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 the output file.
When the topic detection job is finished, the service creates an 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 ouput of the operation.
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:
NumberOfTopics (integer) --
The number of topics to detect supplied when you created the topic detection job. The default is 10.
DataAccessRoleArn (string) --
The Amazon Resource Name (ARN) of the AWS Identity and Management (IAM) role that grants Amazon Comprehend read access to your job 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:
VpcConfig (dict) --
Configuration parameters for a private Virtual Private Cloud (VPC) containing the resources you are using for your topic detection job. 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 .
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 .