Amazon Comprehend examples using AWS CLI

The following code examples show you how to perform actions and implement common scenarios by using the AWS Command Line Interface with Amazon Comprehend.

Actions are code excerpts from larger programs and must be run in context. While actions show you how to call individual service functions, you can see actions in context in their related scenarios.

Each example includes a link to the complete source code, where you can find instructions on how to set up and run the code in context.

Topics

Actions

Actions

The following code example shows how to use batch-detect-dominant-language.

AWS CLI

To detect the dominant language of multiple input texts

The following batch-detect-dominant-language example analyzes multiple input texts and returns the dominant language of each. The pre-trained models confidence score is also output for each prediction.


aws comprehend batch-detect-dominant-language \
    --text-list "Physics is the natural science that involves the study of matter and its motion and behavior through space and time, along with related concepts such as energy and force."

Output:


{
    "ResultList": [
        {
            "Index": 0,
            "Languages": [
                {
                    "LanguageCode": "en",
                    "Score": 0.9986501932144165
                }
            ]
        }
    ],
    "ErrorList": []
}

For more information, see Dominant Language in the Amazon Comprehend Developer Guide.

For API details, see BatchDetectDominantLanguage in AWS CLI Command Reference.

The following code example shows how to use batch-detect-entities.

AWS CLI

To detect entities from multiple input texts

The following batch-detect-entities example analyzes multiple input texts and returns the named entities of each. The pre-trained model's confidence score is also output for each prediction.


aws comprehend batch-detect-entities \
    --language-code en \
    --text-list "Dear Jane, Your AnyCompany Financial Services LLC credit card account 1111-XXXX-1111-XXXX has a minimum payment of $24.53 that is due by July 31st." "Please send customer feedback to Sunshine Spa, 123 Main St, Anywhere or to Alice at AnySpa@example.com."

Output:


{
    "ResultList": [
        {
            "Index": 0,
            "Entities": [
                {
                    "Score": 0.9985517859458923,
                    "Type": "PERSON",
                    "Text": "Jane",
                    "BeginOffset": 5,
                    "EndOffset": 9
                },
                {
                    "Score": 0.9767839312553406,
                    "Type": "ORGANIZATION",
                    "Text": "AnyCompany Financial Services, LLC",
                    "BeginOffset": 16,
                    "EndOffset": 50
                },
                {
                    "Score": 0.9856694936752319,
                    "Type": "OTHER",
                    "Text": "1111-XXXX-1111-XXXX",
                    "BeginOffset": 71,
                    "EndOffset": 90
                },
                {
                    "Score": 0.9652159810066223,
                    "Type": "QUANTITY",
                    "Text": ".53",
                    "BeginOffset": 116,
                    "EndOffset": 119
                },
                {
                    "Score": 0.9986667037010193,
                    "Type": "DATE",
                    "Text": "July 31st",
                    "BeginOffset": 135,
                    "EndOffset": 144
                }
            ]
        },
        {
            "Index": 1,
            "Entities": [
                {
                    "Score": 0.720084547996521,
                    "Type": "ORGANIZATION",
                    "Text": "Sunshine Spa",
                    "BeginOffset": 33,
                    "EndOffset": 45
                },
                {
                    "Score": 0.9865870475769043,
                    "Type": "LOCATION",
                    "Text": "123 Main St",
                    "BeginOffset": 47,
                    "EndOffset": 58
                },
                {
                    "Score": 0.5895616412162781,
                    "Type": "LOCATION",
                    "Text": "Anywhere",
                    "BeginOffset": 60,
                    "EndOffset": 68
                },
                {
                    "Score": 0.6809214353561401,
                    "Type": "PERSON",
                    "Text": "Alice",
                    "BeginOffset": 75,
                    "EndOffset": 80
                },
                {
                    "Score": 0.9979087114334106,
                    "Type": "OTHER",
                    "Text": "AnySpa@example.com",
                    "BeginOffset": 84,
                    "EndOffset": 99
                }
            ]
        }
    ],
    "ErrorList": []
}

For more information, see Entities in the Amazon Comprehend Developer Guide.

For API details, see BatchDetectEntities in AWS CLI Command Reference.

The following code example shows how to use batch-detect-key-phrases.

AWS CLI

To detect key phrases of multiple text inputs

The following batch-detect-key-phrases example analyzes multiple input texts and returns the key noun phrases of each. The pre-trained model's confidence score for each prediction is also output.


aws comprehend batch-detect-key-phrases \
    --language-code en \
    --text-list "Hello Zhang Wei, I am John, writing to you about the trip for next Saturday." "Dear Jane, Your AnyCompany Financial Services LLC credit card account 1111-XXXX-1111-XXXX has a minimum payment of $24.53 that is due by July 31st." "Please send customer feedback to Sunshine Spa, 123 Main St, Anywhere or to Alice at AnySpa@example.com."

Output:


{
    "ResultList": [
        {
            "Index": 0,
            "KeyPhrases": [
                {
                    "Score": 0.99700927734375,
                    "Text": "Zhang Wei",
                    "BeginOffset": 6,
                    "EndOffset": 15
                },
                {
                    "Score": 0.9929308891296387,
                    "Text": "John",
                    "BeginOffset": 22,
                    "EndOffset": 26
                },
                {
                    "Score": 0.9997230172157288,
                    "Text": "the trip",
                    "BeginOffset": 49,
                    "EndOffset": 57
                },
                {
                    "Score": 0.9999470114707947,
                    "Text": "next Saturday",
                    "BeginOffset": 62,
                    "EndOffset": 75
                }
            ]
        },
        {
            "Index": 1,
            "KeyPhrases": [
                {
                    "Score": 0.8358274102210999,
                    "Text": "Dear Jane",
                    "BeginOffset": 0,
                    "EndOffset": 9
                },
                {
                    "Score": 0.989359974861145,
                    "Text": "Your AnyCompany Financial Services",
                    "BeginOffset": 11,
                    "EndOffset": 45
                },
                {
                    "Score": 0.8812323808670044,
                    "Text": "LLC credit card account 1111-XXXX-1111-XXXX",
                    "BeginOffset": 47,
                    "EndOffset": 90
                },
                {
                    "Score": 0.9999381899833679,
                    "Text": "a minimum payment",
                    "BeginOffset": 95,
                    "EndOffset": 112
                },
                {
                    "Score": 0.9997439980506897,
                    "Text": ".53",
                    "BeginOffset": 116,
                    "EndOffset": 119
                },
                {
                    "Score": 0.996875524520874,
                    "Text": "July 31st",
                    "BeginOffset": 135,
                    "EndOffset": 144
                }
            ]
        },
        {
            "Index": 2,
            "KeyPhrases": [
                {
                    "Score": 0.9990295767784119,
                    "Text": "customer feedback",
                    "BeginOffset": 12,
                    "EndOffset": 29
                },
                {
                    "Score": 0.9994127750396729,
                    "Text": "Sunshine Spa",
                    "BeginOffset": 33,
                    "EndOffset": 45
                },
                {
                    "Score": 0.9892991185188293,
                    "Text": "123 Main St",
                    "BeginOffset": 47,
                    "EndOffset": 58
                },
                {
                    "Score": 0.9969810843467712,
                    "Text": "Alice",
                    "BeginOffset": 75,
                    "EndOffset": 80
                },
                {
                    "Score": 0.9703696370124817,
                    "Text": "AnySpa@example.com",
                    "BeginOffset": 84,
                    "EndOffset": 99
                }
            ]
        }
    ],
    "ErrorList": []
}

For more information, see Key Phrases in the Amazon Comprehend Developer Guide.

For API details, see BatchDetectKeyPhrases in AWS CLI Command Reference.

The following code example shows how to use batch-detect-sentiment.

AWS CLI

To detect the prevailing sentiment of multiple input texts

The following batch-detect-sentiment example analyzes multiple input texts and returns the prevailing sentiment (POSITIVE, NEUTRAL, MIXED, or NEGATIVE, of each one).


aws comprehend batch-detect-sentiment \
    --text-list "That movie was very boring, I can't believe it was over four hours long." "It is a beautiful day for hiking today." "My meal was okay, I'm excited to try other restaurants." \
    --language-code en

Output:


{
    "ResultList": [
        {
            "Index": 0,
            "Sentiment": "NEGATIVE",
            "SentimentScore": {
                "Positive": 0.00011316669406369328,
                "Negative": 0.9995445609092712,
                "Neutral": 0.00014722718333359808,
                "Mixed": 0.00019498742767609656
            }
        },
        {
            "Index": 1,
            "Sentiment": "POSITIVE",
            "SentimentScore": {
                "Positive": 0.9981263279914856,
                "Negative": 0.00015240783977787942,
                "Neutral": 0.0013876151060685515,
                "Mixed": 0.00033366199932061136
            }
        },
        {
            "Index": 2,
            "Sentiment": "MIXED",
            "SentimentScore": {
                "Positive": 0.15930435061454773,
                "Negative": 0.11471917480230331,
                "Neutral": 0.26897063851356506,
                "Mixed": 0.45700588822364807
            }
        }
    ],
    "ErrorList": []
}

For more information, see Sentiment in the Amazon Comprehend Developer Guide.

For API details, see BatchDetectSentiment in AWS CLI Command Reference.

The following code example shows how to use batch-detect-syntax.

AWS CLI

To inspect the syntax and parts of speech of words in multiple input texts

The following batch-detect-syntax example analyzes the syntax of multiple input texts and returns the different parts of speech. The pre-trained model's confidence score is also output for each prediction.


aws comprehend batch-detect-syntax \
    --text-list "It is a beautiful day." "Can you please pass the salt?" "Please pay the bill before the 31st." \
    --language-code en

Output:


{
    "ResultList": [
        {
            "Index": 0,
            "SyntaxTokens": [
                {
                    "TokenId": 1,
                    "Text": "It",
                    "BeginOffset": 0,
                    "EndOffset": 2,
                    "PartOfSpeech": {
                        "Tag": "PRON",
                        "Score": 0.9999740719795227
                    }
                },
                {
                    "TokenId": 2,
                    "Text": "is",
                    "BeginOffset": 3,
                    "EndOffset": 5,
                    "PartOfSpeech": {
                        "Tag": "VERB",
                        "Score": 0.999937117099762
                    }
                },
                {
                    "TokenId": 3,
                    "Text": "a",
                    "BeginOffset": 6,
                    "EndOffset": 7,
                    "PartOfSpeech": {
                        "Tag": "DET",
                        "Score": 0.9999926686286926
                    }
                },
                {
                    "TokenId": 4,
                    "Text": "beautiful",
                    "BeginOffset": 8,
                    "EndOffset": 17,
                    "PartOfSpeech": {
                        "Tag": "ADJ",
                        "Score": 0.9987891912460327
                    }
                },
                {
                    "TokenId": 5,
                    "Text": "day",
                    "BeginOffset": 18,
                    "EndOffset": 21,
                    "PartOfSpeech": {
                        "Tag": "NOUN",
                        "Score": 0.9999778866767883
                    }
                },
                {
                    "TokenId": 6,
                    "Text": ".",
                    "BeginOffset": 21,
                    "EndOffset": 22,
                    "PartOfSpeech": {
                        "Tag": "PUNCT",
                        "Score": 0.9999974966049194
                    }
                }
            ]
        },
        {
            "Index": 1,
            "SyntaxTokens": [
                {
                    "TokenId": 1,
                    "Text": "Can",
                    "BeginOffset": 0,
                    "EndOffset": 3,
                    "PartOfSpeech": {
                        "Tag": "AUX",
                        "Score": 0.9999770522117615
                    }
                },
                {
                    "TokenId": 2,
                    "Text": "you",
                    "BeginOffset": 4,
                    "EndOffset": 7,
                    "PartOfSpeech": {
                        "Tag": "PRON",
                        "Score": 0.9999986886978149
                    }
                },
                {
                    "TokenId": 3,
                    "Text": "please",
                    "BeginOffset": 8,
                    "EndOffset": 14,
                    "PartOfSpeech": {
                        "Tag": "INTJ",
                        "Score": 0.9681622385978699
                    }
                },
                {
                    "TokenId": 4,
                    "Text": "pass",
                    "BeginOffset": 15,
                    "EndOffset": 19,
                    "PartOfSpeech": {
                        "Tag": "VERB",
                        "Score": 0.9999874830245972
                    }
                },
                {
                    "TokenId": 5,
                    "Text": "the",
                    "BeginOffset": 20,
                    "EndOffset": 23,
                    "PartOfSpeech": {
                        "Tag": "DET",
                        "Score": 0.9999827146530151
                    }
                },
                {
                    "TokenId": 6,
                    "Text": "salt",
                    "BeginOffset": 24,
                    "EndOffset": 28,
                    "PartOfSpeech": {
                        "Tag": "NOUN",
                        "Score": 0.9995040893554688
                    }
                },
                {
                    "TokenId": 7,
                    "Text": "?",
                    "BeginOffset": 28,
                    "EndOffset": 29,
                    "PartOfSpeech": {
                        "Tag": "PUNCT",
                        "Score": 0.999998152256012
                    }
                }
            ]
        },
        {
            "Index": 2,
            "SyntaxTokens": [
                {
                    "TokenId": 1,
                    "Text": "Please",
                    "BeginOffset": 0,
                    "EndOffset": 6,
                    "PartOfSpeech": {
                        "Tag": "INTJ",
                        "Score": 0.9997857809066772
                    }
                },
                {
                    "TokenId": 2,
                    "Text": "pay",
                    "BeginOffset": 7,
                    "EndOffset": 10,
                    "PartOfSpeech": {
                        "Tag": "VERB",
                        "Score": 0.9999252557754517
                    }
                },
                {
                    "TokenId": 3,
                    "Text": "the",
                    "BeginOffset": 11,
                    "EndOffset": 14,
                    "PartOfSpeech": {
                        "Tag": "DET",
                        "Score": 0.9999842643737793
                    }
                },
                {
                    "TokenId": 4,
                    "Text": "bill",
                    "BeginOffset": 15,
                    "EndOffset": 19,
                    "PartOfSpeech": {
                        "Tag": "NOUN",
                        "Score": 0.9999588131904602
                    }
                },
                {
                    "TokenId": 5,
                    "Text": "before",
                    "BeginOffset": 20,
                    "EndOffset": 26,
                    "PartOfSpeech": {
                        "Tag": "ADP",
                        "Score": 0.9958304762840271
                    }
                },
                {
                    "TokenId": 6,
                    "Text": "the",
                    "BeginOffset": 27,
                    "EndOffset": 30,
                    "PartOfSpeech": {
                        "Tag": "DET",
                        "Score": 0.9999947547912598
                    }
                },
                {
                    "TokenId": 7,
                    "Text": "31st",
                    "BeginOffset": 31,
                    "EndOffset": 35,
                    "PartOfSpeech": {
                        "Tag": "NOUN",
                        "Score": 0.9924124479293823
                    }
                },
                {
                    "TokenId": 8,
                    "Text": ".",
                    "BeginOffset": 35,
                    "EndOffset": 36,
                    "PartOfSpeech": {
                        "Tag": "PUNCT",
                        "Score": 0.9999955892562866
                    }
                }
            ]
        }
    ],
    "ErrorList": []
}

For more information, see Syntax Analysis in the Amazon Comprehend Developer Guide.

For API details, see BatchDetectSyntax in AWS CLI Command Reference.

The following code example shows how to use batch-detect-targeted-sentiment.

AWS CLI

To detect the sentiment and each named entity for multiple input texts

The following batch-detect-targeted-sentiment example analyzes multiple input texts and returns the named entities along with the prevailing sentiment attached to each entity. The pre-trained model's confidence score is also output for each prediction.


aws comprehend batch-detect-targeted-sentiment \
    --language-code en \
    --text-list "That movie was really boring, the original was way more entertaining" "The trail is extra beautiful today." "My meal was just okay."

Output:


{
    "ResultList": [
        {
            "Index": 0,
            "Entities": [
                {
                    "DescriptiveMentionIndex": [
                        0
                    ],
                    "Mentions": [
                        {
                            "Score": 0.9999009966850281,
                            "GroupScore": 1.0,
                            "Text": "movie",
                            "Type": "MOVIE",
                            "MentionSentiment": {
                                "Sentiment": "NEGATIVE",
                                "SentimentScore": {
                                    "Positive": 0.13887299597263336,
                                    "Negative": 0.8057460188865662,
                                    "Neutral": 0.05525200068950653,
                                    "Mixed": 0.00012799999967683107
                                }
                            },
                            "BeginOffset": 5,
                            "EndOffset": 10
                        }
                    ]
                },
                {
                    "DescriptiveMentionIndex": [
                        0
                    ],
                    "Mentions": [
                        {
                            "Score": 0.9921110272407532,
                            "GroupScore": 1.0,
                            "Text": "original",
                            "Type": "MOVIE",
                            "MentionSentiment": {
                                "Sentiment": "POSITIVE",
                                "SentimentScore": {
                                    "Positive": 0.9999989867210388,
                                    "Negative": 9.999999974752427e-07,
                                    "Neutral": 0.0,
                                    "Mixed": 0.0
                                }
                            },
                            "BeginOffset": 34,
                            "EndOffset": 42
                        }
                    ]
                }
            ]
        },
        {
            "Index": 1,
            "Entities": [
                {
                    "DescriptiveMentionIndex": [
                        0
                    ],
                    "Mentions": [
                        {
                            "Score": 0.7545599937438965,
                            "GroupScore": 1.0,
                            "Text": "trail",
                            "Type": "OTHER",
                            "MentionSentiment": {
                                "Sentiment": "POSITIVE",
                                "SentimentScore": {
                                    "Positive": 1.0,
                                    "Negative": 0.0,
                                    "Neutral": 0.0,
                                    "Mixed": 0.0
                                }
                            },
                            "BeginOffset": 4,
                            "EndOffset": 9
                        }
                    ]
                },
                {
                    "DescriptiveMentionIndex": [
                        0
                    ],
                    "Mentions": [
                        {
                            "Score": 0.9999960064888,
                            "GroupScore": 1.0,
                            "Text": "today",
                            "Type": "DATE",
                            "MentionSentiment": {
                                "Sentiment": "NEUTRAL",
                                "SentimentScore": {
                                    "Positive": 9.000000318337698e-06,
                                    "Negative": 1.9999999949504854e-06,
                                    "Neutral": 0.9999859929084778,
                                    "Mixed": 3.999999989900971e-06
                                }
                            },
                            "BeginOffset": 29,
                            "EndOffset": 34
                        }
                    ]
                }
            ]
        },
        {
            "Index": 2,
            "Entities": [
                {
                    "DescriptiveMentionIndex": [
                        0
                    ],
                    "Mentions": [
                        {
                            "Score": 0.9999880194664001,
                            "GroupScore": 1.0,
                            "Text": "My",
                            "Type": "PERSON",
                            "MentionSentiment": {
                                "Sentiment": "NEUTRAL",
                                "SentimentScore": {
                                    "Positive": 0.0,
                                    "Negative": 0.0,
                                    "Neutral": 1.0,
                                    "Mixed": 0.0
                                }
                            },
                            "BeginOffset": 0,
                            "EndOffset": 2
                        }
                    ]
                },
                {
                    "DescriptiveMentionIndex": [
                        0
                    ],
                    "Mentions": [
                        {
                            "Score": 0.9995260238647461,
                            "GroupScore": 1.0,
                            "Text": "meal",
                            "Type": "OTHER",
                            "MentionSentiment": {
                                "Sentiment": "NEUTRAL",
                                "SentimentScore": {
                                    "Positive": 0.04695599898695946,
                                    "Negative": 0.003226999891921878,
                                    "Neutral": 0.6091709733009338,
                                    "Mixed": 0.34064599871635437
                                }
                            },
                            "BeginOffset": 3,
                            "EndOffset": 7
                        }
                    ]
                }
            ]
        }
    ],
    "ErrorList": []
}

For more information, see Targeted Sentiment in the Amazon Comprehend Developer Guide.

For API details, see BatchDetectTargetedSentiment in AWS CLI Command Reference.

The following code example shows how to use classify-document.

AWS CLI

To classify document with model-specific endpoint

The following classify-document example classifies a document with an endpoint of a custom model. The model in this example was trained on a dataset containing sms messages labeled as spam or non-spam, or, "ham".


aws comprehend classify-document \
    --endpoint-arn arn:aws:comprehend:us-west-2:111122223333:document-classifier-endpoint/example-classifier-endpoint \
    --text "CONGRATULATIONS! TXT 1235550100 to win $5000"

Output:


{
    "Classes": [
        {
            "Name": "spam",
            "Score": 0.9998599290847778
        },
        {
            "Name": "ham",
            "Score": 0.00014001205272506922
        }
    ]
}

For more information, see Custom Classification in the Amazon Comprehend Developer Guide.

For API details, see ClassifyDocument in AWS CLI Command Reference.

The following code example shows how to use contains-pii-entities.

AWS CLI

To analyze the input text for the presence of PII information

The following contains-pii-entities example analyzes the 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.


aws comprehend contains-pii-entities \
    --language-code en \
    --text "Hello Zhang Wei, I am John. Your AnyCompany Financial Services, LLC credit card
        account 1111-XXXX-1111-XXXX has a minimum payment of $24.53 that is due by July 31st. Based on your autopay settings,
        we will withdraw your payment on the due date from your bank account number XXXXXX1111 with the routing number XXXXX0000.
        Customer feedback for Sunshine Spa, 100 Main St, Anywhere. Send comments to Alice at AnySpa@example.com."

Output:


{
    "Labels": [
        {
            "Name": "NAME",
            "Score": 1.0
        },
        {
            "Name": "EMAIL",
            "Score": 1.0
        },
        {
            "Name": "BANK_ACCOUNT_NUMBER",
            "Score": 0.9995794296264648
        },
        {
            "Name": "BANK_ROUTING",
            "Score": 0.9173126816749573
        },
        {
            "Name": "CREDIT_DEBIT_NUMBER",
            "Score": 1.0
        }
}

For more information, see Personally Identifiable Information (PII) in the Amazon Comprehend Developer Guide.

For API details, see ContainsPiiEntities in AWS CLI Command Reference.

The following code example shows how to use create-dataset.

AWS CLI

To create a flywheel dataset

The following create-dataset example creates a dataset for a flywheel. This dataset will be used as additional training data as specified by the --dataset-type tag.


aws comprehend create-dataset \
    --flywheel-arn arn:aws:comprehend:us-west-2:111122223333:flywheel/flywheel-entity \
    --dataset-name example-dataset \
    --dataset-type "TRAIN" \
    --input-data-config file://inputConfig.json

Contents of file://inputConfig.json:


{
    "DataFormat": "COMPREHEND_CSV",
    "DocumentClassifierInputDataConfig": {
        "S3Uri": "s3://amzn-s3-demo-bucket/training-data.csv"
    }
}

Output:


{
    "DatasetArn": "arn:aws:comprehend:us-west-2:111122223333:flywheel/flywheel-entity/dataset/example-dataset"
}

For more information, see Flywheel Overview in Amazon Comprehend Developer Guide.

For API details, see CreateDataset in AWS CLI Command Reference.

The following code example shows how to use create-document-classifier.

AWS CLI

To create a document classifier to categorize documents

The following create-document-classifier example begins the training process for a document classifier model. The training data file, training.csv, is located at the --input-data-config tag. training.csv is a two column document where the labels, or, classifications are provided in the first column and the documents are provided in the second column.


aws comprehend create-document-classifier \
    --document-classifier-name example-classifier \
    --data-access-arn arn:aws:comprehend:us-west-2:111122223333:pii-entities-detection-job/123456abcdeb0e11022f22a11EXAMPLE \
    --input-data-config "S3Uri=s3://amzn-s3-demo-bucket/" \
    --language-code en

Output:


{
    "DocumentClassifierArn": "arn:aws:comprehend:us-west-2:111122223333:document-classifier/example-classifier"
}

For more information, see Custom Classification in the Amazon Comprehend Developer Guide.

For API details, see CreateDocumentClassifier in AWS CLI Command Reference.

The following code example shows how to use create-endpoint.

AWS CLI

To create an endpoint for a custom model

The following create-endpoint example creates an endpoint for synchronous inference for a previously trained custom model.


aws comprehend create-endpoint \
    --endpoint-name example-classifier-endpoint-1 \
    --model-arn arn:aws:comprehend:us-west-2:111122223333:document-classifier/example-classifier \
    --desired-inference-units 1

Output:


{
    "EndpointArn": "arn:aws:comprehend:us-west-2:111122223333:document-classifier-endpoint/example-classifier-endpoint-1"
}

For more information, see Managing Amazon Comprehend endpoints in the Amazon Comprehend Developer Guide.

For API details, see CreateEndpoint in AWS CLI Command Reference.

The following code example shows how to use create-entity-recognizer.

AWS CLI

To create a custom entity recognizer

The following create-entity-recognizer example begins the training process for a custom entity recognizer model. This example uses a CSV file containing training documents, raw_text.csv, and a CSV entity list, entity_list.csv to train the model. entity-list.csv contains the following columns: text and type.


aws comprehend create-entity-recognizer \
    --recognizer-name example-entity-recognizer
    --data-access-role-arn arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-example-role \
    --input-data-config "EntityTypes=[{Type=DEVICE}],Documents={S3Uri=s3://amzn-s3-demo-bucket/trainingdata/raw_text.csv},EntityList={S3Uri=s3://amzn-s3-demo-bucket/trainingdata/entity_list.csv}"
    --language-code en

Output:


{
    "EntityRecognizerArn": "arn:aws:comprehend:us-west-2:111122223333:example-entity-recognizer/entityrecognizer1"
}

For more information, see Custom entity recognition in the Amazon Comprehend Developer Guide.

For API details, see CreateEntityRecognizer in AWS CLI Command Reference.

The following code example shows how to use create-flywheel.

AWS CLI

To create a flywheel

The following create-flywheel example creates a flywheel to orchestrate the ongoing training of either a document classification or entity recognition model. The flywheel in this example is created to manage an existing trained model specified by the --active-model-arn tag. When the flywheel is created, a data lake is created at the --input-data-lake tag.


aws comprehend create-flywheel \
    --flywheel-name example-flywheel \
    --active-model-arn arn:aws:comprehend:us-west-2:111122223333:document-classifier/example-model/version/1 \
    --data-access-role-arn arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-example-role \
    --data-lake-s3-uri "s3://amzn-s3-demo-bucket"

Output:


{
    "FlywheelArn": "arn:aws:comprehend:us-west-2:111122223333:flywheel/example-flywheel"
}

For more information, see Flywheel Overview in Amazon Comprehend Developer Guide.

For API details, see CreateFlywheel in AWS CLI Command Reference.

The following code example shows how to use delete-document-classifier.

AWS CLI

To delete a custom document classifier

The following delete-document-classifier example deletes a custom document classifier model.


aws comprehend delete-document-classifier \
    --document-classifier-arn arn:aws:comprehend:us-west-2:111122223333:document-classifier/example-classifier-1

This command produces no output.

For more information, see Managing Amazon Comprehend endpoints in the Amazon Comprehend Developer Guide.

For API details, see DeleteDocumentClassifier in AWS CLI Command Reference.

The following code example shows how to use delete-endpoint.

AWS CLI

To delete an endpoint for a custom model

The following delete-endpoint example deletes a model-specific endpoint. All endpoints must be deleted in order for the model to be deleted.


aws comprehend delete-endpoint \
    --endpoint-arn arn:aws:comprehend:us-west-2:111122223333:document-classifier-endpoint/example-classifier-endpoint-1

This command produces no output.

For more information, see Managing Amazon Comprehend endpoints in the Amazon Comprehend Developer Guide.

For API details, see DeleteEndpoint in AWS CLI Command Reference.

The following code example shows how to use delete-entity-recognizer.

AWS CLI

To delete a custom entity recognizer model

The following delete-entity-recognizer example deletes a custom entity recognizer model.


aws comprehend delete-entity-recognizer \
    --entity-recognizer-arn arn:aws:comprehend:us-west-2:111122223333:entity-recognizer/example-entity-recognizer-1

This command produces no output.

For more information, see Managing Amazon Comprehend endpoints in the Amazon Comprehend Developer Guide.

For API details, see DeleteEntityRecognizer in AWS CLI Command Reference.

The following code example shows how to use delete-flywheel.

AWS CLI

To delete a flywheel

The following delete-flywheel example deletes a flywheel. The data lake or the model associated with the flywheel is not deleted.


aws comprehend delete-flywheel \
    --flywheel-arn arn:aws:comprehend:us-west-2:111122223333:flywheel/example-flywheel-1

This command produces no output.

For more information, see Flywheel overview in the Amazon Comprehend Developer Guide.

For API details, see DeleteFlywheel in AWS CLI Command Reference.

The following code example shows how to use delete-resource-policy.

AWS CLI

To delete a resource-based policy

The following delete-resource-policy example deletes a resource-based policy from an Amazon Comprehend resource.


aws comprehend delete-resource-policy \
    --resource-arn arn:aws:comprehend:us-west-2:111122223333:document-classifier/example-classifier-1/version/1

This command produces no output.

For more information, see Copying custom models between AWS accounts in the Amazon Comprehend Developer Guide.

For API details, see DeleteResourcePolicy in AWS CLI Command Reference.

The following code example shows how to use describe-dataset.

AWS CLI

To describe a flywheel dataset

The following describe-dataset example gets the properties of a flywheel dataset.


aws comprehend describe-dataset \
    --dataset-arn arn:aws:comprehend:us-west-2:111122223333:flywheel/flywheel-entity/dataset/example-dataset

Output:


{
    "DatasetProperties": {
        "DatasetArn": "arn:aws:comprehend:us-west-2:111122223333:flywheel/flywheel-entity/dataset/example-dataset",
        "DatasetName": "example-dataset",
        "DatasetType": "TRAIN",
        "DatasetS3Uri": "s3://amzn-s3-demo-bucket/flywheel-entity/schemaVersion=1/12345678A123456Z/datasets/example-dataset/20230616T203710Z/",
        "Status": "CREATING",
        "CreationTime": "2023-06-16T20:37:10.400000+00:00"
    }
}

For more information, see Flywheel Overview in Amazon Comprehend Developer Guide.

For API details, see DescribeDataset in AWS CLI Command Reference.

The following code example shows how to use describe-document-classification-job.

AWS CLI

To describe a document classification job

The following describe-document-classification-job example gets the properties of an asynchronous document classification job.


aws comprehend describe-document-classification-job \
    --job-id 123456abcdeb0e11022f22a11EXAMPLE

Output:


{
    "DocumentClassificationJobProperties": {
        "JobId": "123456abcdeb0e11022f22a11EXAMPLE",
        "JobArn": "arn:aws:comprehend:us-west-2:111122223333:document-classification-job/123456abcdeb0e11022f22a11EXAMPLE",
        "JobName": "exampleclassificationjob",
        "JobStatus": "COMPLETED",
        "SubmitTime": "2023-06-14T17:09:51.788000+00:00",
        "EndTime": "2023-06-14T17:15:58.582000+00:00",
        "DocumentClassifierArn": "arn:aws:comprehend:us-west-2:111122223333:document-classifier/mymodel/version/1",
        "InputDataConfig": {
            "S3Uri": "s3://amzn-s3-demo-bucket/jobdata/",
            "InputFormat": "ONE_DOC_PER_LINE"
        },
        "OutputDataConfig": {
            "S3Uri": "s3://amzn-s3-demo-destination-bucket/testfolder/111122223333-CLN-123456abcdeb0e11022f22a11EXAMPLE/output/output.tar.gz"
        },
        "DataAccessRoleArn": "arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-servicerole"
    }
}

For more information, see Custom Classification in the Amazon Comprehend Developer Guide.

For API details, see DescribeDocumentClassificationJob in AWS CLI Command Reference.

The following code example shows how to use describe-document-classifier.

AWS CLI

To describe a document classifier

The following describe-document-classifier example gets the properties of a custom document classifier model.


aws comprehend describe-document-classifier \
    --document-classifier-arn arn:aws:comprehend:us-west-2:111122223333:document-classifier/example-classifier-1

Output:


{
    "DocumentClassifierProperties": {
        "DocumentClassifierArn": "arn:aws:comprehend:us-west-2:111122223333:document-classifier/example-classifier-1",
        "LanguageCode": "en",
        "Status": "TRAINED",
        "SubmitTime": "2023-06-13T19:04:15.735000+00:00",
        "EndTime": "2023-06-13T19:42:31.752000+00:00",
        "TrainingStartTime": "2023-06-13T19:08:20.114000+00:00",
        "TrainingEndTime": "2023-06-13T19:41:35.080000+00:00",
        "InputDataConfig": {
            "DataFormat": "COMPREHEND_CSV",
            "S3Uri": "s3://amzn-s3-demo-bucket/trainingdata"
        },
        "OutputDataConfig": {},
        "ClassifierMetadata": {
            "NumberOfLabels": 3,
            "NumberOfTrainedDocuments": 5016,
            "NumberOfTestDocuments": 557,
            "EvaluationMetrics": {
                "Accuracy": 0.9856,
                "Precision": 0.9919,
                "Recall": 0.9459,
                "F1Score": 0.9673,
                "MicroPrecision": 0.9856,
                "MicroRecall": 0.9856,
                "MicroF1Score": 0.9856,
                "HammingLoss": 0.0144
            }
        },
        "DataAccessRoleArn": "arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-example-role",
        "Mode": "MULTI_CLASS"
    }
}

For more information, see Creating and managing custom models in the Amazon Comprehend Developer Guide.

For API details, see DescribeDocumentClassifier in AWS CLI Command Reference.

The following code example shows how to use describe-dominant-language-detection-job.

AWS CLI

To describe a dominant language detection detection job.

The following describe-dominant-language-detection-job example gets the properties of an asynchronous dominant language detection job.


aws comprehend describe-dominant-language-detection-job \
    --job-id 123456abcdeb0e11022f22a11EXAMPLE

Output:


{
    "DominantLanguageDetectionJobProperties": {
        "JobId": "123456abcdeb0e11022f22a11EXAMPLE",
        "JobArn": "arn:aws:comprehend:us-west-2:111122223333:dominant-language-detection-job/123456abcdeb0e11022f22a11EXAMPLE",
        "JobName": "languageanalysis1",
        "JobStatus": "IN_PROGRESS",
        "SubmitTime": "2023-06-09T18:10:38.037000+00:00",
        "InputDataConfig": {
            "S3Uri": "s3://amzn-s3-demo-bucket",
            "InputFormat": "ONE_DOC_PER_LINE"
        },
        "OutputDataConfig": {
            "S3Uri": "s3://amzn-s3-demo-destination-bucket/testfolder/111122223333-LANGUAGE-123456abcdeb0e11022f22a11EXAMPLE/output/output.tar.gz"
        },
        "DataAccessRoleArn": "arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-example-role"
    }
}

For more information, see Async analysis for Amazon Comprehend insights in the Amazon Comprehend Developer Guide.

For API details, see DescribeDominantLanguageDetectionJob in AWS CLI Command Reference.

The following code example shows how to use describe-endpoint.

AWS CLI

To describe a specific endpoint

The following describe-endpoint example gets the properties of a model-specific endpoint.


aws comprehend describe-endpoint \
    --endpoint-arn arn:aws:comprehend:us-west-2:111122223333:document-classifier-endpoint/example-classifier-endpoint

Output:


{
    "EndpointProperties": {
        "EndpointArn": "arn:aws:comprehend:us-west-2:111122223333:document-classifier-endpoint/example-classifier-endpoint,
        "Status": "IN_SERVICE",
        "ModelArn": "arn:aws:comprehend:us-west-2:111122223333:document-classifier/exampleclassifier1",
        "DesiredModelArn": "arn:aws:comprehend:us-west-2:111122223333:document-classifier/exampleclassifier1",
        "DesiredInferenceUnits": 1,
        "CurrentInferenceUnits": 1,
        "CreationTime": "2023-06-13T20:32:54.526000+00:00",
        "LastModifiedTime": "2023-06-13T20:32:54.526000+00:00"
    }
}

For more information, see Managing Amazon Comprehend endpoints in the Amazon Comprehend Developer Guide.

For API details, see DescribeEndpoint in AWS CLI Command Reference.

The following code example shows how to use describe-entities-detection-job.

AWS CLI

To describe an entities detection job

The following describe-entities-detection-job example gets the properties of an asynchronous entities detection job.


aws comprehend describe-entities-detection-job \
    --job-id 123456abcdeb0e11022f22a11EXAMPLE

Output:


{
    "EntitiesDetectionJobProperties": {
        "JobId": "123456abcdeb0e11022f22a11EXAMPLE",
        "JobArn": "arn:aws:comprehend:us-west-2:111122223333:entities-detection-job/123456abcdeb0e11022f22a11EXAMPLE",
        "JobName": "example-entity-detector",
        "JobStatus": "COMPLETED",
        "SubmitTime": "2023-06-08T21:30:15.323000+00:00",
        "EndTime": "2023-06-08T21:40:23.509000+00:00",
        "InputDataConfig": {
            "S3Uri": "s3://amzn-s3-demo-bucket/AsyncBatchJobs/",
            "InputFormat": "ONE_DOC_PER_LINE"
        },
        "OutputDataConfig": {
            "S3Uri": "s3://amzn-s3-demo-bucket/thefolder/111122223333-NER-123456abcdeb0e11022f22a11EXAMPLE/output/output.tar.gz"
        },
        "LanguageCode": "en",
        "DataAccessRoleArn": "arn:aws:iam::12345678012:role/service-role/AmazonComprehendServiceRole-example-role"
    }
}

For more information, see Async analysis for Amazon Comprehend insights in the Amazon Comprehend Developer Guide.

For API details, see DescribeEntitiesDetectionJob in AWS CLI Command Reference.

The following code example shows how to use describe-entity-recognizer.

AWS CLI

To describe an entity recognizer

The following describe-entity-recognizer example gets the properties of a custom entity recognizer model.


aws comprehend describe-entity-recognizer \
    entity-recognizer-arn arn:aws:comprehend:us-west-2:111122223333:entity-recognizer/business-recongizer-1/version/1

Output:


{
    "EntityRecognizerProperties": {
        "EntityRecognizerArn": "arn:aws:comprehend:us-west-2:111122223333:entity-recognizer/business-recongizer-1/version/1",
        "LanguageCode": "en",
        "Status": "TRAINED",
        "SubmitTime": "2023-06-14T20:44:59.631000+00:00",
        "EndTime": "2023-06-14T20:59:19.532000+00:00",
        "TrainingStartTime": "2023-06-14T20:48:52.811000+00:00",
        "TrainingEndTime": "2023-06-14T20:58:11.473000+00:00",
        "InputDataConfig": {
            "DataFormat": "COMPREHEND_CSV",
            "EntityTypes": [
                {
                    "Type": "BUSINESS"
                }
            ],
            "Documents": {
                "S3Uri": "s3://amzn-s3-demo-bucket/trainingdata/dataset/",
                "InputFormat": "ONE_DOC_PER_LINE"
            },
            "EntityList": {
                "S3Uri": "s3://amzn-s3-demo-bucket/trainingdata/entity.csv"
            }
        },
        "RecognizerMetadata": {
            "NumberOfTrainedDocuments": 1814,
            "NumberOfTestDocuments": 486,
            "EvaluationMetrics": {
                "Precision": 100.0,
                "Recall": 100.0,
                "F1Score": 100.0
            },
            "EntityTypes": [
                {
                    "Type": "BUSINESS",
                    "EvaluationMetrics": {
                        "Precision": 100.0,
                        "Recall": 100.0,
                        "F1Score": 100.0
                    },
                    "NumberOfTrainMentions": 1520
                }
            ]
        },
        "DataAccessRoleArn": "arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-example-role",
        "VersionName": "1"
    }
}

For more information, see Custom entity recognition in the Amazon Comprehend Developer Guide.

For API details, see DescribeEntityRecognizer in AWS CLI Command Reference.

The following code example shows how to use describe-events-detection-job.

AWS CLI

To describe an events detection job.

The following describe-events-detection-job example gets the properties of an asynchronous events detection job.


aws comprehend describe-events-detection-job \
    --job-id 123456abcdeb0e11022f22a11EXAMPLE

Output:


{
    "EventsDetectionJobProperties": {
        "JobId": "123456abcdeb0e11022f22a11EXAMPLE",
        "JobArn": "arn:aws:comprehend:us-west-2:111122223333:events-detection-job/123456abcdeb0e11022f22a11EXAMPLE",
        "JobName": "events_job_1",
        "JobStatus": "IN_PROGRESS",
        "SubmitTime": "2023-06-12T18:45:56.054000+00:00",
        "InputDataConfig": {
            "S3Uri": "s3://amzn-s3-demo-bucket/EventsData",
            "InputFormat": "ONE_DOC_PER_LINE"
        },
        "OutputDataConfig": {
            "S3Uri": "s3://amzn-s3-demo-destination-bucket/testfolder/111122223333-EVENTS-123456abcdeb0e11022f22a11EXAMPLE/output/"
        },
        "LanguageCode": "en",
        "DataAccessRoleArn": "arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-example-role",
        "TargetEventTypes": [
            "BANKRUPTCY",
            "EMPLOYMENT",
            "CORPORATE_ACQUISITION",
            "CORPORATE_MERGER",
            "INVESTMENT_GENERAL"
        ]
    }
}

For more information, see Async analysis for Amazon Comprehend insights in the Amazon Comprehend Developer Guide.

For API details, see DescribeEventsDetectionJob in AWS CLI Command Reference.

The following code example shows how to use describe-flywheel-iteration.

AWS CLI

To describe a flywheel iteration

The following describe-flywheel-iteration example gets the properties of a flywheel iteration.


aws comprehend describe-flywheel-iteration \
    --flywheel-arn arn:aws:comprehend:us-west-2:111122223333:flywheel/example-flywheel \
    --flywheel-iteration-id 20232222AEXAMPLE

Output:


{
    "FlywheelIterationProperties": {
        "FlywheelArn": "arn:aws:comprehend:us-west-2:111122223333:flywheel/flywheel-entity",
        "FlywheelIterationId": "20232222AEXAMPLE",
        "CreationTime": "2023-06-16T21:10:26.385000+00:00",
        "EndTime": "2023-06-16T23:33:16.827000+00:00",
        "Status": "COMPLETED",
        "Message": "FULL_ITERATION: Flywheel iteration performed all functions successfully.",
        "EvaluatedModelArn": "arn:aws:comprehend:us-west-2:111122223333:document-classifier/example-classifier/version/1",
        "EvaluatedModelMetrics": {
            "AverageF1Score": 0.7742663922375772,
            "AveragePrecision": 0.8287636394041166,
            "AverageRecall": 0.7427084833645399,
            "AverageAccuracy": 0.8795394154118689
        },
        "TrainedModelArn": "arn:aws:comprehend:us-west-2:111122223333:document-classifier/example-classifier/version/Comprehend-Generated-v1-bb52d585",
        "TrainedModelMetrics": {
            "AverageF1Score": 0.9767700253081214,
            "AveragePrecision": 0.9767700253081214,
            "AverageRecall": 0.9767700253081214,
            "AverageAccuracy": 0.9858281665190434
        },
        "EvaluationManifestS3Prefix": "s3://amzn-s3-demo-destination-bucket/flywheel-entity/schemaVersion=1/20230616T200543Z/evaluation/20230616T211026Z/"
    }
}

For more information, see Flywheel overview in the Amazon Comprehend Developer Guide.

For API details, see DescribeFlywheelIteration in AWS CLI Command Reference.

The following code example shows how to use describe-flywheel.

AWS CLI

To describe a flywheel

The following describe-flywheel example gets the properties of a flywheel. In this example, the model associated with the flywheel is a custom classifier model that is trained to classify documents as either spam or nonspam, or, "ham".


aws comprehend describe-flywheel \
    --flywheel-arn arn:aws:comprehend:us-west-2:111122223333:flywheel/example-flywheel

Output:


{
    "FlywheelProperties": {
        "FlywheelArn": "arn:aws:comprehend:us-west-2:111122223333:flywheel/example-flywheel",
        "ActiveModelArn": "arn:aws:comprehend:us-west-2:111122223333:document-classifier/example-model/version/1",
        "DataAccessRoleArn": "arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-example-role",
        "TaskConfig": {
            "LanguageCode": "en",
            "DocumentClassificationConfig": {
                "Mode": "MULTI_CLASS",
                "Labels": [
                    "ham",
                    "spam"
                ]
            }
        },
        "DataLakeS3Uri": "s3://amzn-s3-demo-bucket/example-flywheel/schemaVersion=1/20230616T200543Z/",
        "DataSecurityConfig": {},
        "Status": "ACTIVE",
        "ModelType": "DOCUMENT_CLASSIFIER",
        "CreationTime": "2023-06-16T20:05:43.242000+00:00",
        "LastModifiedTime": "2023-06-16T20:21:43.567000+00:00"
    }
}

For more information, see Flywheel Overview in Amazon Comprehend Developer Guide.

For API details, see DescribeFlywheel in AWS CLI Command Reference.

The following code example shows how to use describe-key-phrases-detection-job.

AWS CLI

To describe a key phrases detection job

The following describe-key-phrases-detection-job example gets the properties of an asynchronous key phrases detection job.


aws comprehend describe-key-phrases-detection-job \
    --job-id 123456abcdeb0e11022f22a11EXAMPLE

Output:


{
    "KeyPhrasesDetectionJobProperties": {
        "JobId": "69aa080c00fc68934a6a98f10EXAMPLE",
        "JobArn": "arn:aws:comprehend:us-west-2:111122223333:key-phrases-detection-job/69aa080c00fc68934a6a98f10EXAMPLE",
        "JobName": "example-key-phrases-detection-job",
        "JobStatus": "COMPLETED",
        "SubmitTime": 1686606439.177,
        "EndTime": 1686606806.157,
        "InputDataConfig": {
            "S3Uri": "s3://dereksbucket1001/EventsData/",
            "InputFormat": "ONE_DOC_PER_LINE"
        },
        "OutputDataConfig": {
            "S3Uri": "s3://dereksbucket1002/testfolder/111122223333-KP-69aa080c00fc68934a6a98f10EXAMPLE/output/output.tar.gz"
        },
        "LanguageCode": "en",
        "DataAccessRoleArn": "arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-testrole"
    }
}

For more information, see Async analysis for Amazon Comprehend insights in the Amazon Comprehend Developer Guide.

For API details, see DescribeKeyPhrasesDetectionJob in AWS CLI Command Reference.

The following code example shows how to use describe-pii-entities-detection-job.

AWS CLI

To describe a PII entities detection job

The following describe-pii-entities-detection-job example gets the properties of an asynchronous pii entities detection job.


aws comprehend describe-pii-entities-detection-job \
    --job-id 123456abcdeb0e11022f22a11EXAMPLE

Output:


{
    "PiiEntitiesDetectionJobProperties": {
        "JobId": "123456abcdeb0e11022f22a11EXAMPLE",
        "JobArn": "arn:aws:comprehend:us-west-2:111122223333:pii-entities-detection-job/123456abcdeb0e11022f22a11EXAMPLE",
        "JobName": "example-pii-entities-job",
        "JobStatus": "IN_PROGRESS",
        "SubmitTime": "2023-06-08T21:30:15.323000+00:00",
        "EndTime": "2023-06-08T21:40:23.509000+00:00",
        "InputDataConfig": {
            "S3Uri": "s3://amzn-s3-demo-bucket/AsyncBatchJobs/",
            "InputFormat": "ONE_DOC_PER_LINE"
        },
        "OutputDataConfig": {
            "S3Uri": "s3://amzn-s3-demo-bucket/thefolder/111122223333-NER-123456abcdeb0e11022f22a11EXAMPLE/output/output.tar.gz"
        },
        "LanguageCode": "en",
        "DataAccessRoleArn": "arn:aws:iam::12345678012:role/service-role/AmazonComprehendServiceRole-example-role"
    }
}

For more information, see Async analysis for Amazon Comprehend insights in the Amazon Comprehend Developer Guide.

For API details, see DescribePiiEntitiesDetectionJob in AWS CLI Command Reference.

The following code example shows how to use describe-resource-policy.

AWS CLI

To describe a resource policy attached to a model

The following describe-resource-policy example gets the properties of a resource-based policy attached to a model.


aws comprehend describe-resource-policy \
    --resource-arn arn:aws:comprehend:us-west-2:111122223333:document-classifier/example-classifier/version/1

Output:


{
    "ResourcePolicy": "{\"Version\":\"2012-10-17\",\"Statement\":[{\"Effect\":\"Allow\",\"Principal\":{\"AWS\":\"arn:aws:iam::444455556666:root\"},\"Action\":\"comprehend:ImportModel\",\"Resource\":\"*\"}]}",
    "CreationTime": "2023-06-19T18:44:26.028000+00:00",
    "LastModifiedTime": "2023-06-19T18:53:02.002000+00:00",
    "PolicyRevisionId": "baa675d069d07afaa2aa3106ae280f61"
}

For more information, see Copying custom models between AWS accounts in the Amazon Comprehend Developer Guide.

For API details, see DescribeResourcePolicy in AWS CLI Command Reference.

The following code example shows how to use describe-sentiment-detection-job.

AWS CLI

To describe a sentiment detection job

The following describe-sentiment-detection-job example gets the properties of an asynchronous sentiment detection job.


aws comprehend describe-sentiment-detection-job \
    --job-id 123456abcdeb0e11022f22a11EXAMPLE

Output:


{
    "SentimentDetectionJobProperties": {
        "JobId": "123456abcdeb0e11022f22a11EXAMPLE",
        "JobArn": "arn:aws:comprehend:us-west-2:111122223333:sentiment-detection-job/123456abcdeb0e11022f22a11EXAMPLE",
        "JobName": "movie_review_analysis",
        "JobStatus": "IN_PROGRESS",
        "SubmitTime": "2023-06-09T23:16:15.956000+00:00",
        "InputDataConfig": {
            "S3Uri": "s3://amzn-s3-demo-bucket/MovieData",
            "InputFormat": "ONE_DOC_PER_LINE"
        },
        "OutputDataConfig": {
            "S3Uri": "s3://amzn-s3-demo-destination-bucket/testfolder/111122223333-TS-123456abcdeb0e11022f22a11EXAMPLE/output/output.tar.gz"
        },
        "LanguageCode": "en",
        "DataAccessRoleArn": "arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-servicerole"
    }
}

For more information, see Async analysis for Amazon Comprehend insights in the Amazon Comprehend Developer Guide.

For API details, see DescribeSentimentDetectionJob in AWS CLI Command Reference.

The following code example shows how to use describe-targeted-sentiment-detection-job.

AWS CLI

To describe a targeted sentiment detection job

The following describe-targeted-sentiment-detection-job example gets the properties of an asynchronous targeted sentiment detection job.


aws comprehend describe-targeted-sentiment-detection-job \
    --job-id 123456abcdeb0e11022f22a11EXAMPLE

Output:


{
    "TargetedSentimentDetectionJobProperties": {
        "JobId": "123456abcdeb0e11022f22a11EXAMPLE",
        "JobArn": "arn:aws:comprehend:us-west-2:111122223333:targeted-sentiment-detection-job/123456abcdeb0e11022f22a11EXAMPLE",
        "JobName": "movie_review_analysis",
        "JobStatus": "IN_PROGRESS",
        "SubmitTime": "2023-06-09T23:16:15.956000+00:00",
        "InputDataConfig": {
            "S3Uri": "s3://amzn-s3-demo-bucket/MovieData",
            "InputFormat": "ONE_DOC_PER_LINE"
        },
        "OutputDataConfig": {
            "S3Uri": "s3://amzn-s3-demo-destination-bucket/testfolder/111122223333-TS-123456abcdeb0e11022f22a11EXAMPLE/output/output.tar.gz"
        },
        "LanguageCode": "en",
        "DataAccessRoleArn": "arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-servicerole"
    }
}

For more information, see Async analysis for Amazon Comprehend insights in the Amazon Comprehend Developer Guide.

For API details, see DescribeTargetedSentimentDetectionJob in AWS CLI Command Reference.

The following code example shows how to use describe-topics-detection-job.

AWS CLI

To describe a topics detection job

The following describe-topics-detection-job example gets the properties of an asynchronous topics detection job.


aws comprehend describe-topics-detection-job \
    --job-id 123456abcdeb0e11022f22a11EXAMPLE

Output:


{
    "TopicsDetectionJobProperties": {
        "JobId": "123456abcdeb0e11022f22a11EXAMPLE",
        "JobArn": "arn:aws:comprehend:us-west-2:111122223333:topics-detection-job/123456abcdeb0e11022f22a11EXAMPLE",
        "JobName": "example_topics_detection",
        "JobStatus": "IN_PROGRESS",
        "SubmitTime": "2023-06-09T18:44:43.414000+00:00",
        "InputDataConfig": {
            "S3Uri": "s3://amzn-s3-demo-bucket",
            "InputFormat": "ONE_DOC_PER_LINE"
        },
        "OutputDataConfig": {
            "S3Uri": "s3://amzn-s3-demo-destination-bucket/testfolder/111122223333-TOPICS-123456abcdeb0e11022f22a11EXAMPLE/output/output.tar.gz"
        },
        "NumberOfTopics": 10,
        "DataAccessRoleArn": "arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-examplerole"
    }
}

For more information, see Async analysis for Amazon Comprehend insights in the Amazon Comprehend Developer Guide.

For API details, see DescribeTopicsDetectionJob in AWS CLI Command Reference.

The following code example shows how to use detect-dominant-language.

AWS CLI

To detect the dominant language of input text

The following detect-dominant-language analyzes the input text and identifies the dominant language. The pre-trained model's confidence score is also output.


aws comprehend detect-dominant-language \
    --text "It is a beautiful day in Seattle."

Output:


{
    "Languages": [
        {
            "LanguageCode": "en",
            "Score": 0.9877256155014038
        }
    ]
}

For more information, see Dominant Language in the Amazon Comprehend Developer Guide.

For API details, see DetectDominantLanguage in AWS CLI Command Reference.

The following code example shows how to use detect-entities.

AWS CLI

To detect named entities in input text

The following detect-entities example analyzes the input text and returns the named entities. The pre-trained model's confidence score is also output for each prediction.


aws comprehend detect-entities \
    --language-code en \
    --text "Hello Zhang Wei, I am John. Your AnyCompany Financial Services, LLC credit card \
    account 1111-XXXX-1111-XXXX has a minimum payment of $24.53 that is due by July 31st. Based on your autopay settings, \
    we will withdraw your payment on the due date from your bank account number XXXXXX1111 with the routing number XXXXX0000. \
    Customer feedback for Sunshine Spa, 123 Main St, Anywhere. Send comments to Alice at AnySpa@example.com."

Output:


{
    "Entities": [
        {
            "Score": 0.9994556307792664,
            "Type": "PERSON",
            "Text": "Zhang Wei",
            "BeginOffset": 6,
            "EndOffset": 15
        },
        {
            "Score": 0.9981022477149963,
            "Type": "PERSON",
            "Text": "John",
            "BeginOffset": 22,
            "EndOffset": 26
        },
        {
            "Score": 0.9986887574195862,
            "Type": "ORGANIZATION",
            "Text": "AnyCompany Financial Services, LLC",
            "BeginOffset": 33,
            "EndOffset": 67
        },
        {
            "Score": 0.9959119558334351,
            "Type": "OTHER",
            "Text": "1111-XXXX-1111-XXXX",
            "BeginOffset": 88,
            "EndOffset": 107
        },
        {
            "Score": 0.9708039164543152,
            "Type": "QUANTITY",
            "Text": ".53",
            "BeginOffset": 133,
            "EndOffset": 136
        },
        {
            "Score": 0.9987268447875977,
            "Type": "DATE",
            "Text": "July 31st",
            "BeginOffset": 152,
            "EndOffset": 161
        },
        {
            "Score": 0.9858865737915039,
            "Type": "OTHER",
            "Text": "XXXXXX1111",
            "BeginOffset": 271,
            "EndOffset": 281
        },
        {
            "Score": 0.9700471758842468,
            "Type": "OTHER",
            "Text": "XXXXX0000",
            "BeginOffset": 306,
            "EndOffset": 315
        },
        {
            "Score": 0.9591118693351746,
            "Type": "ORGANIZATION",
            "Text": "Sunshine Spa",
            "BeginOffset": 340,
            "EndOffset": 352
        },
        {
            "Score": 0.9797496795654297,
            "Type": "LOCATION",
            "Text": "123 Main St",
            "BeginOffset": 354,
            "EndOffset": 365
        },
        {
            "Score": 0.994929313659668,
            "Type": "PERSON",
            "Text": "Alice",
            "BeginOffset": 394,
            "EndOffset": 399
        },
        {
            "Score": 0.9949769377708435,
            "Type": "OTHER",
            "Text": "AnySpa@example.com",
            "BeginOffset": 403,
            "EndOffset": 418
        }
    ]
}

For more information, see Entities in the Amazon Comprehend Developer Guide.

For API details, see DetectEntities in AWS CLI Command Reference.

The following code example shows how to use detect-key-phrases.

AWS CLI

To detect key phrases in input text

The following detect-key-phrases example analyzes the input text and identifies the key noun phrases. The pre-trained model's confidence score is also output for each prediction.


aws comprehend detect-key-phrases \
    --language-code en \
    --text "Hello Zhang Wei, I am John. Your AnyCompany Financial Services, LLC credit card \
        account 1111-XXXX-1111-XXXX has a minimum payment of $24.53 that is due by July 31st. Based on your autopay settings, \
        we will withdraw your payment on the due date from your bank account number XXXXXX1111 with the routing number XXXXX0000. \
        Customer feedback for Sunshine Spa, 123 Main St, Anywhere. Send comments to Alice at AnySpa@example.com."

Output:


{
    "KeyPhrases": [
        {
            "Score": 0.8996376395225525,
            "Text": "Zhang Wei",
            "BeginOffset": 6,
            "EndOffset": 15
        },
        {
            "Score": 0.9992469549179077,
            "Text": "John",
            "BeginOffset": 22,
            "EndOffset": 26
        },
        {
            "Score": 0.988385021686554,
            "Text": "Your AnyCompany Financial Services",
            "BeginOffset": 28,
            "EndOffset": 62
        },
        {
            "Score": 0.8740853071212769,
            "Text": "LLC credit card account 1111-XXXX-1111-XXXX",
            "BeginOffset": 64,
            "EndOffset": 107
        },
        {
            "Score": 0.9999437928199768,
            "Text": "a minimum payment",
            "BeginOffset": 112,
            "EndOffset": 129
        },
        {
            "Score": 0.9998900890350342,
            "Text": ".53",
            "BeginOffset": 133,
            "EndOffset": 136
        },
        {
            "Score": 0.9979453086853027,
            "Text": "July 31st",
            "BeginOffset": 152,
            "EndOffset": 161
        },
        {
            "Score": 0.9983011484146118,
            "Text": "your autopay settings",
            "BeginOffset": 172,
            "EndOffset": 193
        },
        {
            "Score": 0.9996572136878967,
            "Text": "your payment",
            "BeginOffset": 211,
            "EndOffset": 223
        },
        {
            "Score": 0.9995037317276001,
            "Text": "the due date",
            "BeginOffset": 227,
            "EndOffset": 239
        },
        {
            "Score": 0.9702621698379517,
            "Text": "your bank account number XXXXXX1111",
            "BeginOffset": 245,
            "EndOffset": 280
        },
        {
            "Score": 0.9179925918579102,
            "Text": "the routing number XXXXX0000.Customer feedback",
            "BeginOffset": 286,
            "EndOffset": 332
        },
        {
            "Score": 0.9978160858154297,
            "Text": "Sunshine Spa",
            "BeginOffset": 337,
            "EndOffset": 349
        },
        {
            "Score": 0.9706913232803345,
            "Text": "123 Main St",
            "BeginOffset": 351,
            "EndOffset": 362
        },
        {
            "Score": 0.9941995143890381,
            "Text": "comments",
            "BeginOffset": 379,
            "EndOffset": 387
        },
        {
            "Score": 0.9759287238121033,
            "Text": "Alice",
            "BeginOffset": 391,
            "EndOffset": 396
        },
        {
            "Score": 0.8376792669296265,
            "Text": "AnySpa@example.com",
            "BeginOffset": 400,
            "EndOffset": 415
        }
    ]
}

For more information, see Key Phrases in the Amazon Comprehend Developer Guide.

For API details, see DetectKeyPhrases in AWS CLI Command Reference.

The following code example shows how to use detect-pii-entities.

AWS CLI

To detect pii entities in input text

The following detect-pii-entities example analyzes the input text and identifies entities that contain personally identifiable information (PII). The pre-trained model's confidence score is also output for each prediction.


aws comprehend detect-pii-entities \
    --language-code en \
    --text "Hello Zhang Wei, I am John. Your AnyCompany Financial Services, LLC credit card \
        account 1111-XXXX-1111-XXXX has a minimum payment of $24.53 that is due by July 31st. Based on your autopay settings, \
        we will withdraw your payment on the due date from your bank account number XXXXXX1111 with the routing number XXXXX0000. \
        Customer feedback for Sunshine Spa, 123 Main St, Anywhere. Send comments to Alice at AnySpa@example.com."

Output:


{
    "Entities": [
        {
            "Score": 0.9998322129249573,
            "Type": "NAME",
            "BeginOffset": 6,
            "EndOffset": 15
        },
        {
            "Score": 0.9998878240585327,
            "Type": "NAME",
            "BeginOffset": 22,
            "EndOffset": 26
        },
        {
            "Score": 0.9994089603424072,
            "Type": "CREDIT_DEBIT_NUMBER",
            "BeginOffset": 88,
            "EndOffset": 107
        },
        {
            "Score": 0.9999760985374451,
            "Type": "DATE_TIME",
            "BeginOffset": 152,
            "EndOffset": 161
        },
        {
            "Score": 0.9999449253082275,
            "Type": "BANK_ACCOUNT_NUMBER",
            "BeginOffset": 271,
            "EndOffset": 281
        },
        {
            "Score": 0.9999847412109375,
            "Type": "BANK_ROUTING",
            "BeginOffset": 306,
            "EndOffset": 315
        },
        {
            "Score": 0.999925434589386,
            "Type": "ADDRESS",
            "BeginOffset": 354,
            "EndOffset": 365
        },
        {
            "Score": 0.9989161491394043,
            "Type": "NAME",
            "BeginOffset": 394,
            "EndOffset": 399
        },
        {
            "Score": 0.9994171857833862,
            "Type": "EMAIL",
            "BeginOffset": 403,
            "EndOffset": 418
        }
    ]
}

For more information, see Personally Identifiable Information (PII) in the Amazon Comprehend Developer Guide.

For API details, see DetectPiiEntities in AWS CLI Command Reference.

The following code example shows how to use detect-sentiment.

AWS CLI

To detect the sentiment of an input text

The following detect-sentiment example analyzes the input text and returns an inference of the prevailing sentiment (POSITIVE, NEUTRAL, MIXED, or NEGATIVE).


aws comprehend detect-sentiment \
    --language-code en \
    --text "It is a beautiful day in Seattle"

Output:


{
    "Sentiment": "POSITIVE",
    "SentimentScore": {
        "Positive": 0.9976957440376282,
        "Negative": 9.653854067437351e-05,
        "Neutral": 0.002169104292988777,
        "Mixed": 3.857641786453314e-05
    }
}

For more information, see Sentiment in the Amazon Comprehend Developer Guide

For API details, see DetectSentiment in AWS CLI Command Reference.

The following code example shows how to use detect-syntax.

AWS CLI

To detect the parts of speech in an input text

The following detect-syntax example analyzes the syntax of the input text and returns the different parts of speech. The pre-trained model's confidence score is also output for each prediction.


aws comprehend detect-syntax \
    --language-code en \
    --text "It is a beautiful day in Seattle."

Output:


{
    "SyntaxTokens": [
        {
            "TokenId": 1,
            "Text": "It",
            "BeginOffset": 0,
            "EndOffset": 2,
            "PartOfSpeech": {
                "Tag": "PRON",
                "Score": 0.9999740719795227
            }
        },
        {
            "TokenId": 2,
            "Text": "is",
            "BeginOffset": 3,
            "EndOffset": 5,
            "PartOfSpeech": {
                "Tag": "VERB",
                "Score": 0.999901294708252
            }
        },
        {
            "TokenId": 3,
            "Text": "a",
            "BeginOffset": 6,
            "EndOffset": 7,
            "PartOfSpeech": {
                "Tag": "DET",
                "Score": 0.9999938607215881
            }
        },
        {
            "TokenId": 4,
            "Text": "beautiful",
            "BeginOffset": 8,
            "EndOffset": 17,
            "PartOfSpeech": {
                "Tag": "ADJ",
                "Score": 0.9987351894378662
            }
        },
        {
            "TokenId": 5,
            "Text": "day",
            "BeginOffset": 18,
            "EndOffset": 21,
            "PartOfSpeech": {
                "Tag": "NOUN",
                "Score": 0.9999796748161316
            }
        },
        {
            "TokenId": 6,
            "Text": "in",
            "BeginOffset": 22,
            "EndOffset": 24,
            "PartOfSpeech": {
                "Tag": "ADP",
                "Score": 0.9998047947883606
            }
        },
        {
            "TokenId": 7,
            "Text": "Seattle",
            "BeginOffset": 25,
            "EndOffset": 32,
            "PartOfSpeech": {
                "Tag": "PROPN",
                "Score": 0.9940530061721802
            }
        }
    ]
}

For more information, see Syntax Analysis in the Amazon Comprehend Developer Guide.

For API details, see DetectSyntax in AWS CLI Command Reference.

The following code example shows how to use detect-targeted-sentiment.

AWS CLI

To detect the targeted sentiment of named entities in an input text

The following detect-targeted-sentiment example analyzes the input text and returns the named entities in addition to the targeted sentiment associated with each entity. The pre-trained models confidence score for each prediction is also output.


aws comprehend detect-targeted-sentiment \
    --language-code en \
    --text "I do not enjoy January because it is too cold but August is the perfect temperature"

Output:


{
    "Entities": [
        {
            "DescriptiveMentionIndex": [
                0
            ],
            "Mentions": [
                {
                    "Score": 0.9999979734420776,
                    "GroupScore": 1.0,
                    "Text": "I",
                    "Type": "PERSON",
                    "MentionSentiment": {
                        "Sentiment": "NEUTRAL",
                        "SentimentScore": {
                            "Positive": 0.0,
                            "Negative": 0.0,
                            "Neutral": 1.0,
                            "Mixed": 0.0
                        }
                    },
                    "BeginOffset": 0,
                    "EndOffset": 1
                }
            ]
        },
        {
            "DescriptiveMentionIndex": [
                0
            ],
            "Mentions": [
                {
                    "Score": 0.9638869762420654,
                    "GroupScore": 1.0,
                    "Text": "January",
                    "Type": "DATE",
                    "MentionSentiment": {
                        "Sentiment": "NEGATIVE",
                        "SentimentScore": {
                            "Positive": 0.0031610000878572464,
                            "Negative": 0.9967250227928162,
                            "Neutral": 0.00011100000119768083,
                            "Mixed": 1.9999999949504854e-06
                        }
                    },
                    "BeginOffset": 15,
                    "EndOffset": 22
                }
            ]
        },
        {
            "DescriptiveMentionIndex": [
                0
            ],
            "Mentions": [
                {
                {
                    "Score": 0.9664419889450073,
                    "GroupScore": 1.0,
                    "Text": "August",
                    "Type": "DATE",
                    "MentionSentiment": {
                        "Sentiment": "POSITIVE",
                        "SentimentScore": {
                            "Positive": 0.9999549984931946,
                            "Negative": 3.999999989900971e-06,
                            "Neutral": 4.099999932805076e-05,
                            "Mixed": 0.0
                        }
                    },
                    "BeginOffset": 50,
                    "EndOffset": 56
                }
            ]
        },
        {
            "DescriptiveMentionIndex": [
                0
            ],
            "Mentions": [
                {
                    "Score": 0.9803199768066406,
                    "GroupScore": 1.0,
                    "Text": "temperature",
                    "Type": "ATTRIBUTE",
                    "MentionSentiment": {
                        "Sentiment": "POSITIVE",
                        "SentimentScore": {
                            "Positive": 1.0,
                            "Negative": 0.0,
                            "Neutral": 0.0,
                            "Mixed": 0.0
                        }
                    },
                    "BeginOffset": 77,
                    "EndOffset": 88
                }
            ]
        }
    ]
}

For more information, see Targeted Sentiment in the Amazon Comprehend Developer Guide.

For API details, see DetectTargetedSentiment in AWS CLI Command Reference.

The following code example shows how to use import-model.

AWS CLI

To import a model

The following import-model example imports a model from a different AWS account. The document classifier model in account 444455556666 has a resource-based policy allowing account 111122223333 to import the model.


aws comprehend import-model \
    --source-model-arn arn:aws:comprehend:us-west-2:444455556666:document-classifier/example-classifier

Output:


{
    "ModelArn": "arn:aws:comprehend:us-west-2:111122223333:document-classifier/example-classifier"
}

For more information, see Copying custom models between AWS accounts in the Amazon Comprehend Developer Guide.

For API details, see ImportModel in AWS CLI Command Reference.

The following code example shows how to use list-datasets.

AWS CLI

To list all flywheel datasets

The following list-datasets example lists all datasets associated with a flywheel.


aws comprehend list-datasets \
    --flywheel-arn arn:aws:comprehend:us-west-2:111122223333:flywheel/flywheel-entity

Output:


{
    "DatasetPropertiesList": [
        {
            "DatasetArn": "arn:aws:comprehend:us-west-2:111122223333:flywheel/flywheel-entity/dataset/example-dataset-1",
            "DatasetName": "example-dataset-1",
            "DatasetType": "TRAIN",
            "DatasetS3Uri": "s3://amzn-s3-demo-bucket/flywheel-entity/schemaVersion=1/20230616T200543Z/datasets/example-dataset-1/20230616T203710Z/",
            "Status": "CREATING",
            "CreationTime": "2023-06-16T20:37:10.400000+00:00"
        },
        {
            "DatasetArn": "arn:aws:comprehend:us-west-2:111122223333:flywheel/flywheel-entity/dataset/example-dataset-2",
            "DatasetName": "example-dataset-2",
            "DatasetType": "TRAIN",
            "DatasetS3Uri": "s3://amzn-s3-demo-bucket/flywheel-entity/schemaVersion=1/20230616T200543Z/datasets/example-dataset-2/20230616T200607Z/",
            "Description": "TRAIN Dataset created by Flywheel creation.",
            "Status": "COMPLETED",
            "NumberOfDocuments": 5572,
            "CreationTime": "2023-06-16T20:06:07.722000+00:00"
        }
    ]
}

For more information, see Flywheel Overview in Amazon Comprehend Developer Guide.

For API details, see ListDatasets in AWS CLI Command Reference.

The following code example shows how to use list-document-classification-jobs.

AWS CLI

To list of all document classification jobs

The following list-document-classification-jobs example lists all document classification jobs.


aws comprehend list-document-classification-jobs

Output:


{
    "DocumentClassificationJobPropertiesList": [
        {
            "JobId": "123456abcdeb0e11022f22a11EXAMPLE",
            "JobArn": "arn:aws:comprehend:us-west-2:1234567890101:document-classification-job/123456abcdeb0e11022f22a11EXAMPLE",
            "JobName": "exampleclassificationjob",
            "JobStatus": "COMPLETED",
            "SubmitTime": "2023-06-14T17:09:51.788000+00:00",
            "EndTime": "2023-06-14T17:15:58.582000+00:00",
            "DocumentClassifierArn": "arn:aws:comprehend:us-west-2:1234567890101:document-classifier/mymodel/version/12",
            "InputDataConfig": {
                "S3Uri": "s3://amzn-s3-demo-bucket/jobdata/",
                "InputFormat": "ONE_DOC_PER_LINE"
            },
            "OutputDataConfig": {
                "S3Uri": "s3://amzn-s3-demo-destination-bucket/thefolder/1234567890101-CLN-e758dd56b824aa717ceab551f11749fb/output/output.tar.gz"
            },
            "DataAccessRoleArn": "arn:aws:iam::1234567890101:role/service-role/AmazonComprehendServiceRole-example-role"
        },
        {
            "JobId": "123456abcdeb0e11022f22a1EXAMPLE2",
            "JobArn": "arn:aws:comprehend:us-west-2:1234567890101:document-classification-job/123456abcdeb0e11022f22a1EXAMPLE2",
            "JobName": "exampleclassificationjob2",
            "JobStatus": "COMPLETED",
            "SubmitTime": "2023-06-14T17:22:39.829000+00:00",
            "EndTime": "2023-06-14T17:28:46.107000+00:00",
            "DocumentClassifierArn": "arn:aws:comprehend:us-west-2:1234567890101:document-classifier/mymodel/version/12",
            "InputDataConfig": {
                "S3Uri": "s3://amzn-s3-demo-bucket/jobdata/",
                "InputFormat": "ONE_DOC_PER_LINE"
            },
            "OutputDataConfig": {
                "S3Uri": "s3://amzn-s3-demo-destination-bucket/thefolder/1234567890101-CLN-123456abcdeb0e11022f22a1EXAMPLE2/output/output.tar.gz"
            },
            "DataAccessRoleArn": "arn:aws:iam::1234567890101:role/service-role/AmazonComprehendServiceRole-example-role"
        }
    ]
}

For more information, see Custom Classification in the Amazon Comprehend Developer Guide.

For API details, see ListDocumentClassificationJobs in AWS CLI Command Reference.

The following code example shows how to use list-document-classifier-summaries.

AWS CLI

To list the summaries of all created document classifiers

The following list-document-classifier-summaries example lists all created document classifier summaries.


aws comprehend list-document-classifier-summaries

Output:


{
    "DocumentClassifierSummariesList": [
        {
            "DocumentClassifierName": "example-classifier-1",
            "NumberOfVersions": 1,
            "LatestVersionCreatedAt": "2023-06-13T22:07:59.825000+00:00",
            "LatestVersionName": "1",
            "LatestVersionStatus": "TRAINED"
        },
        {
            "DocumentClassifierName": "example-classifier-2",
            "NumberOfVersions": 2,
            "LatestVersionCreatedAt": "2023-06-13T21:54:59.589000+00:00",
            "LatestVersionName": "2",
            "LatestVersionStatus": "TRAINED"
        }
    ]
}

For more information, see Creating and managing custom models in the Amazon Comprehend Developer Guide.

For API details, see ListDocumentClassifierSummaries in AWS CLI Command Reference.

The following code example shows how to use list-document-classifiers.

AWS CLI

To list of all document classifiers

The following list-document-classifiers example lists all trained and in-training document classifier models.


aws comprehend list-document-classifiers

Output:


{
    "DocumentClassifierPropertiesList": [
        {
            "DocumentClassifierArn": "arn:aws:comprehend:us-west-2:111122223333:document-classifier/exampleclassifier1",
            "LanguageCode": "en",
            "Status": "TRAINED",
            "SubmitTime": "2023-06-13T19:04:15.735000+00:00",
            "EndTime": "2023-06-13T19:42:31.752000+00:00",
            "TrainingStartTime": "2023-06-13T19:08:20.114000+00:00",
            "TrainingEndTime": "2023-06-13T19:41:35.080000+00:00",
            "InputDataConfig": {
                "DataFormat": "COMPREHEND_CSV",
                "S3Uri": "s3://amzn-s3-demo-bucket/trainingdata"
            },
            "OutputDataConfig": {},
            "ClassifierMetadata": {
                "NumberOfLabels": 3,
                "NumberOfTrainedDocuments": 5016,
                "NumberOfTestDocuments": 557,
                "EvaluationMetrics": {
                    "Accuracy": 0.9856,
                    "Precision": 0.9919,
                    "Recall": 0.9459,
                    "F1Score": 0.9673,
                    "MicroPrecision": 0.9856,
                    "MicroRecall": 0.9856,
                    "MicroF1Score": 0.9856,
                    "HammingLoss": 0.0144
                }
            },
            "DataAccessRoleArn": "arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-testorle",
            "Mode": "MULTI_CLASS"
        },
        {
            "DocumentClassifierArn": "arn:aws:comprehend:us-west-2:111122223333:document-classifier/exampleclassifier2",
            "LanguageCode": "en",
            "Status": "TRAINING",
            "SubmitTime": "2023-06-13T21:20:28.690000+00:00",
            "InputDataConfig": {
                "DataFormat": "COMPREHEND_CSV",
                "S3Uri": "s3://amzn-s3-demo-bucket/trainingdata"
            },
            "OutputDataConfig": {},
            "DataAccessRoleArn": "arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-testorle",
            "Mode": "MULTI_CLASS"
        }
    ]
}

For more information, see Creating and managing custom models in the Amazon Comprehend Developer Guide.

For API details, see ListDocumentClassifiers in AWS CLI Command Reference.

The following code example shows how to use list-dominant-language-detection-jobs.

AWS CLI

To list all dominant language detection jobs

The following list-dominant-language-detection-jobs example lists all in-progress and completed asynchronous dominant language detection jobs.


aws comprehend list-dominant-language-detection-jobs

Output:


{
    "DominantLanguageDetectionJobPropertiesList": [
        {
            "JobId": "123456abcdeb0e11022f22a11EXAMPLE",
            "JobArn": "arn:aws:comprehend:us-west-2:111122223333:dominant-language-detection-job/123456abcdeb0e11022f22a11EXAMPLE",
            "JobName": "languageanalysis1",
            "JobStatus": "COMPLETED",
            "SubmitTime": "2023-06-09T18:10:38.037000+00:00",
            "EndTime": "2023-06-09T18:18:45.498000+00:00",
            "InputDataConfig": {
                "S3Uri": "s3://amzn-s3-demo-bucket",
                "InputFormat": "ONE_DOC_PER_LINE"
            },
            "OutputDataConfig": {
                "S3Uri": "s3://amzn-s3-demo-destination-bucket/testfolder/111122223333-LANGUAGE-123456abcdeb0e11022f22a11EXAMPLE/output/output.tar.gz"
            },
            "DataAccessRoleArn": "arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-example-role"
        },
        {
            "JobId": "123456abcdeb0e11022f22a11EXAMPLE",
            "JobArn": "arn:aws:comprehend:us-west-2:111122223333:dominant-language-detection-job/123456abcdeb0e11022f22a11EXAMPLE",
            "JobName": "languageanalysis2",
            "JobStatus": "STOPPED",
            "SubmitTime": "2023-06-09T18:16:33.690000+00:00",
            "EndTime": "2023-06-09T18:24:40.608000+00:00",
            "InputDataConfig": {
                "S3Uri": "s3://amzn-s3-demo-bucket",
                "InputFormat": "ONE_DOC_PER_LINE"
            },
            "OutputDataConfig": {
                "S3Uri": "s3://amzn-s3-demo-destination-bucket/testfolder/111122223333-LANGUAGE-123456abcdeb0e11022f22a11EXAMPLE/output/output.tar.gz"
            },
            "DataAccessRoleArn": "arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-example-role"
        }
    ]
}

For more information, see Async analysis for Amazon Comprehend insights in the Amazon Comprehend Developer Guide.

For API details, see ListDominantLanguageDetectionJobs in AWS CLI Command Reference.

The following code example shows how to use list-endpoints.

AWS CLI

To list of all endpoints

The following list-endpoints example lists all active model-specific endpoints.


aws comprehend list-endpoints

Output:


{
    "EndpointPropertiesList": [
        {
            "EndpointArn": "arn:aws:comprehend:us-west-2:111122223333:document-classifier-endpoint/ExampleClassifierEndpoint",
            "Status": "IN_SERVICE",
            "ModelArn": "arn:aws:comprehend:us-west-2:111122223333:document-classifier/exampleclassifier1",
            "DesiredModelArn": "arn:aws:comprehend:us-west-2:111122223333:document-classifier/exampleclassifier1",
            "DesiredInferenceUnits": 1,
            "CurrentInferenceUnits": 1,
            "CreationTime": "2023-06-13T20:32:54.526000+00:00",
            "LastModifiedTime": "2023-06-13T20:32:54.526000+00:00"
        },
        {
            "EndpointArn": "arn:aws:comprehend:us-west-2:111122223333:document-classifier-endpoint/ExampleClassifierEndpoint2",
            "Status": "IN_SERVICE",
            "ModelArn": "arn:aws:comprehend:us-west-2:111122223333:document-classifier/exampleclassifier2",
            "DesiredModelArn": "arn:aws:comprehend:us-west-2:111122223333:document-classifier/exampleclassifier2",
            "DesiredInferenceUnits": 1,
            "CurrentInferenceUnits": 1,
            "CreationTime": "2023-06-13T20:32:54.526000+00:00",
            "LastModifiedTime": "2023-06-13T20:32:54.526000+00:00"
        }
    ]
}

For more information, see Managing Amazon Comprehend endpoints in the Amazon Comprehend Developer Guide.

For API details, see ListEndpoints in AWS CLI Command Reference.

The following code example shows how to use list-entities-detection-jobs.

AWS CLI

To list all entities detection jobs

The following list-entities-detection-jobs example lists all asynchronous entities detection jobs.


aws comprehend list-entities-detection-jobs

Output:


{
    "EntitiesDetectionJobPropertiesList": [
        {
            "JobId": "468af39c28ab45b83eb0c4ab9EXAMPLE",
            "JobArn": "arn:aws:comprehend:us-west-2:111122223333:entities-detection-job/468af39c28ab45b83eb0c4ab9EXAMPLE",
            "JobName": "example-entities-detection",
            "JobStatus": "COMPLETED",
            "SubmitTime": "2023-06-08T20:57:46.476000+00:00",
            "EndTime": "2023-06-08T21:05:53.718000+00:00",
            "InputDataConfig": {
                "S3Uri": "s3://amzn-s3-demo-bucket/AsyncBatchJobs/",
                "InputFormat": "ONE_DOC_PER_LINE"
            },
            "OutputDataConfig": {
                "S3Uri": "s3://amzn-s3-demo-destination-bucket/thefolder/111122223333-NER-468af39c28ab45b83eb0c4ab9EXAMPLE/output/output.tar.gz"
            },
            "LanguageCode": "en",
            "DataAccessRoleArn": "arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-example-role"
        },
        {
            "JobId": "809691caeaab0e71406f80a28EXAMPLE",
            "JobArn": "arn:aws:comprehend:us-west-2:111122223333:entities-detection-job/809691caeaab0e71406f80a28EXAMPLE",
            "JobName": "example-entities-detection-2",
            "JobStatus": "COMPLETED",
            "SubmitTime": "2023-06-08T21:30:15.323000+00:00",
            "EndTime": "2023-06-08T21:40:23.509000+00:00",
            "InputDataConfig": {
                "S3Uri": "s3://amzn-s3-demo-bucket/AsyncBatchJobs/",
                "InputFormat": "ONE_DOC_PER_LINE"
            },
            "OutputDataConfig": {
                "S3Uri": "s3://amzn-s3-demo-destination-bucket/thefolder/111122223333-NER-809691caeaab0e71406f80a28EXAMPLE/output/output.tar.gz"
            },
            "LanguageCode": "en",
            "DataAccessRoleArn": "arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-example-role"
        },
        {
            "JobId": "e00597c36b448b91d70dea165EXAMPLE",
            "JobArn": "arn:aws:comprehend:us-west-2:111122223333:entities-detection-job/e00597c36b448b91d70dea165EXAMPLE",
            "JobName": "example-entities-detection-3",
            "JobStatus": "STOPPED",
            "SubmitTime": "2023-06-08T22:19:28.528000+00:00",
            "EndTime": "2023-06-08T22:27:33.991000+00:00",
            "InputDataConfig": {
                "S3Uri": "s3://amzn-s3-demo-bucket/AsyncBatchJobs/",
                "InputFormat": "ONE_DOC_PER_LINE"
            },
            "OutputDataConfig": {
                "S3Uri": "s3://amzn-s3-demo-destination-bucket/thefolder/111122223333-NER-e00597c36b448b91d70dea165EXAMPLE/output/output.tar.gz"
            },
            "LanguageCode": "en",
            "DataAccessRoleArn": "arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-example-role"
        }
    ]
}

For more information, see Entities in the Amazon Comprehend Developer Guide.

For API details, see ListEntitiesDetectionJobs in AWS CLI Command Reference.

The following code example shows how to use list-entity-recognizer-summaries.

AWS CLI

To list of summaries for all created entity recognizers

The following list-entity-recognizer-summaries example lists all entity recognizer summaries.


aws comprehend list-entity-recognizer-summaries

Output:


{
    "EntityRecognizerSummariesList": [
        {
            "RecognizerName": "entity-recognizer-3",
            "NumberOfVersions": 2,
            "LatestVersionCreatedAt": "2023-06-15T23:15:07.621000+00:00",
            "LatestVersionName": "2",
            "LatestVersionStatus": "STOP_REQUESTED"
        },
        {
            "RecognizerName": "entity-recognizer-2",
            "NumberOfVersions": 1,
            "LatestVersionCreatedAt": "2023-06-14T22:55:27.805000+00:00",
            "LatestVersionName": "2"
            "LatestVersionStatus": "TRAINED"
        },
        {
            "RecognizerName": "entity-recognizer-1",
            "NumberOfVersions": 1,
            "LatestVersionCreatedAt": "2023-06-14T20:44:59.631000+00:00",
            "LatestVersionName": "1",
            "LatestVersionStatus": "TRAINED"
        }
    ]
}

For more information, see Custom entity recognition in the Amazon Comprehend Developer Guide.

For API details, see ListEntityRecognizerSummaries in AWS CLI Command Reference.

The following code example shows how to use list-entity-recognizers.

AWS CLI

To list of all custom entity recognizers

The following list-entity-recognizers example lists all created custom entity recognizers.


aws comprehend list-entity-recognizers

Output:


{
    "EntityRecognizerPropertiesList": [
        {
            "EntityRecognizerArn": "arn:aws:comprehend:us-west-2:111122223333:entity-recognizer/EntityRecognizer/version/1",
            "LanguageCode": "en",
            "Status": "TRAINED",
            "SubmitTime": "2023-06-14T20:44:59.631000+00:00",
            "EndTime": "2023-06-14T20:59:19.532000+00:00",
            "TrainingStartTime": "2023-06-14T20:48:52.811000+00:00",
            "TrainingEndTime": "2023-06-14T20:58:11.473000+00:00",
            "InputDataConfig": {
                "DataFormat": "COMPREHEND_CSV",
                "EntityTypes": [
                    {
                        "Type": "BUSINESS"
                    }
                ],
                "Documents": {
                    "S3Uri": "s3://amzn-s3-demo-bucket/trainingdata/dataset/",
                    "InputFormat": "ONE_DOC_PER_LINE"
                },
                "EntityList": {
                    "S3Uri": "s3://amzn-s3-demo-bucket/trainingdata/entity.csv"
                }
            },
            "RecognizerMetadata": {
                "NumberOfTrainedDocuments": 1814,
                "NumberOfTestDocuments": 486,
                "EvaluationMetrics": {
                    "Precision": 100.0,
                    "Recall": 100.0,
                    "F1Score": 100.0
                },
                "EntityTypes": [
                    {
                        "Type": "BUSINESS",
                        "EvaluationMetrics": {
                            "Precision": 100.0,
                            "Recall": 100.0,
                            "F1Score": 100.0
                        },
                        "NumberOfTrainMentions": 1520
                    }
                ]
            },
            "DataAccessRoleArn": "arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-servicerole",
            "VersionName": "1"
        },
        {
            "EntityRecognizerArn": "arn:aws:comprehend:us-west-2:111122223333:entity-recognizer/entityrecognizer3",
            "LanguageCode": "en",
            "Status": "TRAINED",
            "SubmitTime": "2023-06-14T22:57:51.056000+00:00",
            "EndTime": "2023-06-14T23:14:13.894000+00:00",
            "TrainingStartTime": "2023-06-14T23:01:33.984000+00:00",
            "TrainingEndTime": "2023-06-14T23:13:02.984000+00:00",
            "InputDataConfig": {
                "DataFormat": "COMPREHEND_CSV",
                "EntityTypes": [
                    {
                        "Type": "DEVICE"
                    }
                ],
                "Documents": {
                    "S3Uri": "s3://amzn-s3-demo-bucket/trainingdata/raw_txt.csv",
                    "InputFormat": "ONE_DOC_PER_LINE"
                },
                "EntityList": {
                    "S3Uri": "s3://amzn-s3-demo-bucket/trainingdata/entity_list.csv"
                }
            },
            "RecognizerMetadata": {
                "NumberOfTrainedDocuments": 4616,
                "NumberOfTestDocuments": 3489,
                "EvaluationMetrics": {
                    "Precision": 98.54227405247813,
                    "Recall": 100.0,
                    "F1Score": 99.26578560939794
                },
                "EntityTypes": [
                    {
                        "Type": "DEVICE",
                        "EvaluationMetrics": {
                            "Precision": 98.54227405247813,
                            "Recall": 100.0,
                            "F1Score": 99.26578560939794
                        },
                        "NumberOfTrainMentions": 2764
                    }
                ]
            },
            "DataAccessRoleArn": "arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-servicerole"
        }
    ]
}

For more information, see Custom entity recognition in the Amazon Comprehend Developer Guide.

For API details, see ListEntityRecognizers in AWS CLI Command Reference.

The following code example shows how to use list-events-detection-jobs.

AWS CLI

To list all events detection jobs

The following list-events-detection-jobs example lists all asynchronous events detection jobs.


aws comprehend list-events-detection-jobs

Output:


{
    "EventsDetectionJobPropertiesList": [
        {
            "JobId": "aa9593f9203e84f3ef032ce18EXAMPLE",
            "JobArn": "arn:aws:comprehend:us-west-2:1111222233333:events-detection-job/aa9593f9203e84f3ef032ce18EXAMPLE",
            "JobName": "events_job_1",
            "JobStatus": "COMPLETED",
            "SubmitTime": "2023-06-12T19:14:57.751000+00:00",
            "EndTime": "2023-06-12T19:21:04.962000+00:00",
            "InputDataConfig": {
                "S3Uri": "s3://amzn-s3-demo-source-bucket/EventsData/",
                "InputFormat": "ONE_DOC_PER_LINE"
            },
            "OutputDataConfig": {
                "S3Uri": "s3://amzn-s3-demo-destination-bucket/testfolder/1111222233333-EVENTS-aa9593f9203e84f3ef032ce18EXAMPLE/output/"
            },
            "LanguageCode": "en",
            "DataAccessRoleArn": "arn:aws:iam::1111222233333:role/service-role/AmazonComprehendServiceRole-example-role",
            "TargetEventTypes": [
                "BANKRUPTCY",
                "EMPLOYMENT",
                "CORPORATE_ACQUISITION",
                "CORPORATE_MERGER",
                "INVESTMENT_GENERAL"
            ]
        },
        {
            "JobId": "4a990a2f7e82adfca6e171135EXAMPLE",
            "JobArn": "arn:aws:comprehend:us-west-2:1111222233333:events-detection-job/4a990a2f7e82adfca6e171135EXAMPLE",
            "JobName": "events_job_2",
            "JobStatus": "COMPLETED",
            "SubmitTime": "2023-06-12T19:55:43.702000+00:00",
            "EndTime": "2023-06-12T20:03:49.893000+00:00",
            "InputDataConfig": {
                "S3Uri": "s3://amzn-s3-demo-source-bucket/EventsData/",
                "InputFormat": "ONE_DOC_PER_LINE"
            },
            "OutputDataConfig": {
                "S3Uri": "s3://amzn-s3-demo-destination-bucket/testfolder/1111222233333-EVENTS-4a990a2f7e82adfca6e171135EXAMPLE/output/"
            },
            "LanguageCode": "en",
            "DataAccessRoleArn": "arn:aws:iam::1111222233333:role/service-role/AmazonComprehendServiceRole-example-role",
            "TargetEventTypes": [
                "BANKRUPTCY",
                "EMPLOYMENT",
                "CORPORATE_ACQUISITION",
                "CORPORATE_MERGER",
                "INVESTMENT_GENERAL"
            ]
        }
    ]
}

For more information, see Async analysis for Amazon Comprehend insights in the Amazon Comprehend Developer Guide.

For API details, see ListEventsDetectionJobs in AWS CLI Command Reference.

The following code example shows how to use list-flywheel-iteration-history.

AWS CLI

To list all flywheel iteration history

The following list-flywheel-iteration-history example lists all iterations of a flywheel.


aws comprehend list-flywheel-iteration-history
    --flywheel-arn arn:aws:comprehend:us-west-2:111122223333:flywheel/example-flywheel

Output:


{
    "FlywheelIterationPropertiesList": [
        {
            "FlywheelArn": "arn:aws:comprehend:us-west-2:111122223333:flywheel/example-flywheel",
            "FlywheelIterationId": "20230619TEXAMPLE",
            "CreationTime": "2023-06-19T04:00:32.594000+00:00",
            "EndTime": "2023-06-19T04:00:49.248000+00:00",
            "Status": "COMPLETED",
            "Message": "FULL_ITERATION: Flywheel iteration performed all functions successfully.",
            "EvaluatedModelArn": "arn:aws:comprehend:us-west-2:111122223333:document-classifier/example-classifier/version/1",
            "EvaluatedModelMetrics": {
                "AverageF1Score": 0.7742663922375772,
                "AverageF1Score": 0.9876464664646313,
                "AveragePrecision": 0.9800000253081214,
                "AverageRecall": 0.9445600253081214,
                "AverageAccuracy": 0.9997281665190434
            },
            "EvaluationManifestS3Prefix": "s3://amzn-s3-demo-bucket/example-flywheel/schemaVersion=1/20230619TEXAMPLE/evaluation/20230619TEXAMPLE/"
        },
        {
            "FlywheelArn": "arn:aws:comprehend:us-west-2:111122223333:flywheel/example-flywheel-2",
            "FlywheelIterationId": "20230616TEXAMPLE",
            "CreationTime": "2023-06-16T21:10:26.385000+00:00",
            "EndTime": "2023-06-16T23:33:16.827000+00:00",
            "Status": "COMPLETED",
            "Message": "FULL_ITERATION: Flywheel iteration performed all functions successfully.",
            "EvaluatedModelArn": "arn:aws:comprehend:us-west-2:111122223333:document-classifier/spamvshamclassify/version/1",
            "EvaluatedModelMetrics": {
                "AverageF1Score": 0.7742663922375772,
                "AverageF1Score": 0.9767700253081214,
                "AveragePrecision": 0.9767700253081214,
                "AverageRecall": 0.9767700253081214,
                "AverageAccuracy": 0.9858281665190434
            },
            "EvaluationManifestS3Prefix": "s3://amzn-s3-demo-bucket/example-flywheel-2/schemaVersion=1/20230616TEXAMPLE/evaluation/20230616TEXAMPLE/"
        }
    ]
}

For more information, see Flywheel overview in the Amazon Comprehend Developer Guide.

For API details, see ListFlywheelIterationHistory in AWS CLI Command Reference.

The following code example shows how to use list-flywheels.

AWS CLI

To list all flywheels

The following list-flywheels example lists all created flywheels.


aws comprehend list-flywheels

Output:


{
    "FlywheelSummaryList": [
        {
            "FlywheelArn": "arn:aws:comprehend:us-west-2:111122223333:flywheel/example-flywheel-1",
            "ActiveModelArn": "arn:aws:comprehend:us-west-2:111122223333:document-classifier/exampleclassifier/version/1",
            "DataLakeS3Uri": "s3://amzn-s3-demo-bucket/example-flywheel-1/schemaVersion=1/20230616T200543Z/",
            "Status": "ACTIVE",
            "ModelType": "DOCUMENT_CLASSIFIER",
            "CreationTime": "2023-06-16T20:05:43.242000+00:00",
            "LastModifiedTime": "2023-06-19T04:00:43.027000+00:00",
            "LatestFlywheelIteration": "20230619T040032Z"
        },
        {
            "FlywheelArn": "arn:aws:comprehend:us-west-2:111122223333:flywheel/example-flywheel-2",
            "ActiveModelArn": "arn:aws:comprehend:us-west-2:111122223333:document-classifier/exampleclassifier2/version/1",
            "DataLakeS3Uri": "s3://amzn-s3-demo-bucket/example-flywheel-2/schemaVersion=1/20220616T200543Z/",
            "Status": "ACTIVE",
            "ModelType": "DOCUMENT_CLASSIFIER",
            "CreationTime": "2022-06-16T20:05:43.242000+00:00",
            "LastModifiedTime": "2022-06-19T04:00:43.027000+00:00",
            "LatestFlywheelIteration": "20220619T040032Z"
        }
    ]
}

For more information, see Flywheel overview in the Amazon Comprehend Developer Guide.

For API details, see ListFlywheels in AWS CLI Command Reference.

The following code example shows how to use list-key-phrases-detection-jobs.

AWS CLI

To list all key phrases detection jobs

The following list-key-phrases-detection-jobs example lists all in-progress and completed asynchronous key phrases detection jobs.


aws comprehend list-key-phrases-detection-jobs

Output:


{
    "KeyPhrasesDetectionJobPropertiesList": [
        {
            "JobId": "123456abcdeb0e11022f22a11EXAMPLE",
            "JobArn": "arn:aws:comprehend:us-west-2:111122223333:key-phrases-detection-job/123456abcdeb0e11022f22a11EXAMPLE",
            "JobName": "keyphrasesanalysis1",
            "JobStatus": "COMPLETED",
            "SubmitTime": "2023-06-08T22:31:43.767000+00:00",
            "EndTime": "2023-06-08T22:39:52.565000+00:00",
            "InputDataConfig": {
                "S3Uri": "s3://amzn-s3-demo-source-bucket/AsyncBatchJobs/",
                "InputFormat": "ONE_DOC_PER_LINE"
            },
            "OutputDataConfig": {
                "S3Uri": "s3://amzn-s3-demo-destination-bucket/testfolder/111122223333-KP-123456abcdeb0e11022f22a11EXAMPLE/output/output.tar.gz"
            },
            "LanguageCode": "en",
            "DataAccessRoleArn": "arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-example-role"
        },
        {
            "JobId": "123456abcdeb0e11022f22a33EXAMPLE",
            "JobArn": "arn:aws:comprehend:us-west-2:111122223333:key-phrases-detection-job/123456abcdeb0e11022f22a33EXAMPLE",
            "JobName": "keyphrasesanalysis2",
            "JobStatus": "STOPPED",
            "SubmitTime": "2023-06-08T22:57:52.154000+00:00",
            "EndTime": "2023-06-08T23:05:48.385000+00:00",
            "InputDataConfig": {
                "S3Uri": "s3://amzn-s3-demo-bucket/AsyncBatchJobs/",
                "InputFormat": "ONE_DOC_PER_LINE"
            },
            "OutputDataConfig": {
                "S3Uri": "s3://amzn-s3-demo-destination-bucket/testfolder/111122223333-KP-123456abcdeb0e11022f22a33EXAMPLE/output/output.tar.gz"
            },
            "LanguageCode": "en",
            "DataAccessRoleArn": "arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-example-role"
        },
        {
            "JobId": "123456abcdeb0e11022f22a44EXAMPLE",
            "JobArn": "arn:aws:comprehend:us-west-2:111122223333:key-phrases-detection-job/123456abcdeb0e11022f22a44EXAMPLE",
            "JobName": "keyphrasesanalysis3",
            "JobStatus": "FAILED",
            "Message": "NO_READ_ACCESS_TO_INPUT: The provided data access role does not have proper access to the input data.",
            "SubmitTime": "2023-06-09T16:47:04.029000+00:00",
            "EndTime": "2023-06-09T16:47:18.413000+00:00",
            "InputDataConfig": {
                "S3Uri": "s3://amzn-s3-demo-bucket",
                "InputFormat": "ONE_DOC_PER_LINE"
            },
            "OutputDataConfig": {
                "S3Uri": "s3://amzn-s3-demo-destination-bucket/testfolder/111122223333-KP-123456abcdeb0e11022f22a44EXAMPLE/output/output.tar.gz"
            },
            "LanguageCode": "en",
            "DataAccessRoleArn": "arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-example-role"
        }
    ]
}

For more information, see Async analysis for Amazon Comprehend insights in the Amazon Comprehend Developer Guide.

For API details, see ListKeyPhrasesDetectionJobs in AWS CLI Command Reference.

The following code example shows how to use list-pii-entities-detection-jobs.

AWS CLI

To list all pii entities detection jobs

The following list-pii-entities-detection-jobs example lists all in-progress and completed asynchronous pii detection jobs.


aws comprehend list-pii-entities-detection-jobs

Output:


{
    "PiiEntitiesDetectionJobPropertiesList": [
        {
            "JobId": "6f9db0c42d0c810e814670ee4EXAMPLE",
            "JobArn": "arn:aws:comprehend:us-west-2:111122223333:pii-entities-detection-job/6f9db0c42d0c810e814670ee4EXAMPLE",
            "JobName": "example-pii-detection-job",
            "JobStatus": "COMPLETED",
            "SubmitTime": "2023-06-09T21:02:46.241000+00:00",
            "EndTime": "2023-06-09T21:12:52.602000+00:00",
            "InputDataConfig": {
                "S3Uri": "s3://amzn-s3-demo-bucket/AsyncBatchJobs/",
                "InputFormat": "ONE_DOC_PER_LINE"
            },
            "OutputDataConfig": {
                "S3Uri": "s3://amzn-s3-demo-source-bucket/111122223333-PII-6f9db0c42d0c810e814670ee4EXAMPLE/output/"
            },
            "LanguageCode": "en",
            "DataAccessRoleArn": "arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-example-role",
            "Mode": "ONLY_OFFSETS"
        },
        {
            "JobId": "d927562638cfa739331a99b3cEXAMPLE",
            "JobArn": "arn:aws:comprehend:us-west-2:111122223333:pii-entities-detection-job/d927562638cfa739331a99b3cEXAMPLE",
            "JobName": "example-pii-detection-job-2",
            "JobStatus": "COMPLETED",
            "SubmitTime": "2023-06-09T21:20:58.211000+00:00",
            "EndTime": "2023-06-09T21:31:06.027000+00:00",
            "InputDataConfig": {
                "S3Uri": "s3://amzn-s3-demo-bucket/AsyncBatchJobs/",
                "InputFormat": "ONE_DOC_PER_LINE"
            },
            "OutputDataConfig": {
                "S3Uri": "s3://amzn-s3-demo-destination-bucket/thefolder/111122223333-PII-d927562638cfa739331a99b3cEXAMPLE/output/"
            },
            "LanguageCode": "en",
            "DataAccessRoleArn": "arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-example-role",
            "Mode": "ONLY_OFFSETS"
        }
    ]
}

For more information, see Async analysis for Amazon Comprehend insights in the Amazon Comprehend Developer Guide.

For API details, see ListPiiEntitiesDetectionJobs in AWS CLI Command Reference.

The following code example shows how to use list-sentiment-detection-jobs.

AWS CLI

To list all sentiment detection jobs

The following list-sentiment-detection-jobs example lists all in-progress and completed asynchronous sentiment detection jobs.


aws comprehend list-sentiment-detection-jobs

Output:


{
    "SentimentDetectionJobPropertiesList": [
        {
            "JobId": "123456abcdeb0e11022f22a11EXAMPLE",
            "JobArn": "arn:aws:comprehend:us-west-2:111122223333:sentiment-detection-job/123456abcdeb0e11022f22a11EXAMPLE",
            "JobName": "example-sentiment-detection-job",
            "JobStatus": "IN_PROGRESS",
            "SubmitTime": "2023-06-09T22:42:20.545000+00:00",
            "EndTime": "2023-06-09T22:52:27.416000+00:00",
            "InputDataConfig": {
                "S3Uri": "s3://amzn-s3-demo-bucket/MovieData",
                "InputFormat": "ONE_DOC_PER_LINE"
            },
            "OutputDataConfig": {
                "S3Uri": "s3://amzn-s3-demo-destination-bucket/testfolder/111122223333-TS-123456abcdeb0e11022f22a11EXAMPLE/output/output.tar.gz"
            },
            "LanguageCode": "en",
            "DataAccessRoleArn": "arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-example-role"
        },
        {
            "JobId": "123456abcdeb0e11022f22a1EXAMPLE2",
            "JobArn": "arn:aws:comprehend:us-west-2:111122223333:sentiment-detection-job/123456abcdeb0e11022f22a1EXAMPLE2",
            "JobName": "example-sentiment-detection-job-2",
            "JobStatus": "COMPLETED",
            "SubmitTime": "2023-06-09T23:16:15.956000+00:00",
            "EndTime": "2023-06-09T23:26:00.168000+00:00",
            "InputDataConfig": {
                "S3Uri": "s3://amzn-s3-demo-bucket/MovieData2",
                "InputFormat": "ONE_DOC_PER_LINE"
            },
            "OutputDataConfig": {
                "S3Uri": "s3://amzn-s3-demo-destination-bucket/testfolder/111122223333-TS-123456abcdeb0e11022f22a1EXAMPLE2/output/output.tar.gz"
            },
            "LanguageCode": "en",
            "DataAccessRoleArn": "arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-example-role"
        }
    ]
}

For more information, see Async analysis for Amazon Comprehend insights in the Amazon Comprehend Developer Guide.

For API details, see ListSentimentDetectionJobs in AWS CLI Command Reference.

The following code example shows how to use list-tags-for-resource.

AWS CLI

To list tags for resource

The following list-tags-for-resource example lists the tags for an Amazon Comprehend resource.


aws comprehend list-tags-for-resource \
    --resource-arn arn:aws:comprehend:us-west-2:111122223333:document-classifier/example-classifier/version/1

Output:


{
    "ResourceArn": "arn:aws:comprehend:us-west-2:111122223333:document-classifier/example-classifier/version/1",
    "Tags": [
        {
            "Key": "Department",
            "Value": "Finance"
        },
        {
            "Key": "location",
            "Value": "Seattle"
        }
    ]
}

For more information, see Tagging your resources in the Amazon Comprehend Developer Guide.

For API details, see ListTagsForResource in AWS CLI Command Reference.

The following code example shows how to use list-targeted-sentiment-detection-jobs.

AWS CLI

To list all targeted sentiment detection jobs

The following list-targeted-sentiment-detection-jobs example lists all in-progress and completed asynchronous targeted sentiment detection jobs.


aws comprehend list-targeted-sentiment-detection-jobs

Output:


{
    "TargetedSentimentDetectionJobPropertiesList": [
        {
            "JobId": "123456abcdeb0e11022f22a11EXAMPLE",
            "JobArn": "arn:aws:comprehend:us-west-2:111122223333:targeted-sentiment-detection-job/123456abcdeb0e11022f22a11EXAMPLE",
            "JobName": "example-targeted-sentiment-detection-job",
            "JobStatus": "COMPLETED",
            "SubmitTime": "2023-06-09T22:42:20.545000+00:00",
            "EndTime": "2023-06-09T22:52:27.416000+00:00",
            "InputDataConfig": {
                "S3Uri": "s3://amzn-s3-demo-bucket/MovieData",
                "InputFormat": "ONE_DOC_PER_LINE"
            },
            "OutputDataConfig": {
                "S3Uri": "s3://amzn-s3-demo-destination-bucket/testfolder/111122223333-TS-123456abcdeb0e11022f22a11EXAMPLE/output/output.tar.gz"
            },
            "LanguageCode": "en",
            "DataAccessRoleArn": "arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-IOrole"
        },
        {
            "JobId": "123456abcdeb0e11022f22a1EXAMPLE2",
            "JobArn": "arn:aws:comprehend:us-west-2:111122223333:targeted-sentiment-detection-job/123456abcdeb0e11022f22a1EXAMPLE2",
            "JobName": "example-targeted-sentiment-detection-job-2",
            "JobStatus": "COMPLETED",
            "SubmitTime": "2023-06-09T23:16:15.956000+00:00",
            "EndTime": "2023-06-09T23:26:00.168000+00:00",
            "InputDataConfig": {
                "S3Uri": "s3://amzn-s3-demo-bucket/MovieData2",
                "InputFormat": "ONE_DOC_PER_LINE"
            },
            "OutputDataConfig": {
                "S3Uri": "s3://amzn-s3-demo-destination-bucket/testfolder/111122223333-TS-123456abcdeb0e11022f22a1EXAMPLE2/output/output.tar.gz"
            },
            "LanguageCode": "en",
            "DataAccessRoleArn": "arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-example-role"
        }
    ]
}

For more information, see Async analysis for Amazon Comprehend insights in the Amazon Comprehend Developer Guide.

For API details, see ListTargetedSentimentDetectionJobs in AWS CLI Command Reference.

The following code example shows how to use list-topics-detection-jobs.

AWS CLI

To list all topic detection jobs

The following list-topics-detection-jobs example lists all in-progress and completed asynchronous topics detection jobs.


aws comprehend list-topics-detection-jobs

Output:


{
    "TopicsDetectionJobPropertiesList": [
        {
            "JobId": "123456abcdeb0e11022f22a11EXAMPLE",
            "JobArn": "arn:aws:comprehend:us-west-2:111122223333:topics-detection-job/123456abcdeb0e11022f22a11EXAMPLE",
            "JobName" "topic-analysis-1"
            "JobStatus": "IN_PROGRESS",
            "SubmitTime": "2023-06-09T18:40:35.384000+00:00",
            "EndTime": "2023-06-09T18:46:41.936000+00:00",
            "InputDataConfig": {
                "S3Uri": "s3://amzn-s3-demo-bucket",
                "InputFormat": "ONE_DOC_PER_LINE"
            },
            "OutputDataConfig": {
                "S3Uri": "s3://amzn-s3-demo-destination-bucket/thefolder/111122223333-TOPICS-123456abcdeb0e11022f22a11EXAMPLE/output/output.tar.gz"
            },
            "NumberOfTopics": 10,
            "DataAccessRoleArn": "arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-example-role"
        },
        {
            "JobId": "123456abcdeb0e11022f22a1EXAMPLE2",
            "JobArn": "arn:aws:comprehend:us-west-2:111122223333:topics-detection-job/123456abcdeb0e11022f22a1EXAMPLE2",
            "JobName": "topic-analysis-2",
            "JobStatus": "COMPLETED",
            "SubmitTime": "2023-06-09T18:44:43.414000+00:00",
            "EndTime": "2023-06-09T18:50:50.872000+00:00",
            "InputDataConfig": {
                "S3Uri": "s3://amzn-s3-demo-bucket",
                "InputFormat": "ONE_DOC_PER_LINE"
            },
            "OutputDataConfig": {
                "S3Uri": "s3://amzn-s3-demo-destination-bucket/thefolder/111122223333-TOPICS-123456abcdeb0e11022f22a1EXAMPLE2/output/output.tar.gz"
            },
            "NumberOfTopics": 10,
            "DataAccessRoleArn": "arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-example-role"
        },
        {
            "JobId": "123456abcdeb0e11022f22a1EXAMPLE3",
            "JobArn": "arn:aws:comprehend:us-west-2:111122223333:topics-detection-job/123456abcdeb0e11022f22a1EXAMPLE3",
            "JobName": "topic-analysis-2",
            "JobStatus": "IN_PROGRESS",
            "SubmitTime": "2023-06-09T18:50:56.737000+00:00",
            "InputDataConfig": {
                "S3Uri": "s3://amzn-s3-demo-bucket",
                "InputFormat": "ONE_DOC_PER_LINE"
            },
            "OutputDataConfig": {
                "S3Uri": "s3://amzn-s3-demo-destination-bucket/thefolder/111122223333-TOPICS-123456abcdeb0e11022f22a1EXAMPLE3/output/output.tar.gz"
            },
            "NumberOfTopics": 10,
            "DataAccessRoleArn": "arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-example-role"
        }
    ]
}

For more information, see Async analysis for Amazon Comprehend insights in the Amazon Comprehend Developer Guide.

For API details, see ListTopicsDetectionJobs in AWS CLI Command Reference.

The following code example shows how to use put-resource-policy.

AWS CLI

To attach a resource-based policy

The following put-resource-policy example attaches a resource-based policy to a model so that can be imported by another AWS account. The policy is attached to the model in account 111122223333 and allows account 444455556666 import the model.


aws comprehend put-resource-policy \
    --resource-arn arn:aws:comprehend:us-west-2:111122223333:document-classifier/example-classifier/version/1 \
    --resource-policy '{"Version":"2012-10-17",		 	 	 "Statement":[{"Effect":"Allow","Action":"comprehend:ImportModel","Resource":"*","Principal":{"AWS":["arn:aws:iam::444455556666:root"]}}]}'

Ouput:


{
    "PolicyRevisionId": "aaa111d069d07afaa2aa3106aEXAMPLE"
}

For more information, see Copying custom models between AWS accounts in the Amazon Comprehend Developer Guide.

For API details, see PutResourcePolicy in AWS CLI Command Reference.

The following code example shows how to use start-document-classification-job.

AWS CLI

To start document classification job

The following start-document-classification-job example starts a document classification job with a custom model on all of the files at the address specified by the --input-data-config tag. In this example, the input S3 bucket contains SampleSMStext1.txt, SampleSMStext2.txt, and SampleSMStext3.txt. The model was previously trained on document classifications of spam and non-spam, or, "ham", SMS messages. When the job is complete, output.tar.gz is put at the location specified by the --output-data-config tag. output.tar.gz contains predictions.jsonl which lists the classification of each document. The Json output is printed on one line per file, but is formatted here for readability.


aws comprehend start-document-classification-job \
    --job-name exampleclassificationjob \
    --input-data-config "S3Uri=s3://amzn-s3-demo-bucket-INPUT/jobdata/" \
    --output-data-config "S3Uri=s3://amzn-s3-demo-destination-bucket/testfolder/" \
    --data-access-role-arn arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-example-role \
    --document-classifier-arn arn:aws:comprehend:us-west-2:111122223333:document-classifier/mymodel/version/12

Contents of SampleSMStext1.txt:


"CONGRATULATIONS! TXT 2155550100 to win $5000"

Contents of SampleSMStext2.txt:


"Hi, when do you want me to pick you up from practice?"

Contents of SampleSMStext3.txt:


"Plz send bank account # to 2155550100 to claim prize!!"

Output:


{
    "JobId": "e758dd56b824aa717ceab551fEXAMPLE",
    "JobArn": "arn:aws:comprehend:us-west-2:111122223333:document-classification-job/e758dd56b824aa717ceab551fEXAMPLE",
    "JobStatus": "SUBMITTED"
}

Contents of predictions.jsonl:


{"File": "SampleSMSText1.txt", "Line": "0", "Classes": [{"Name": "spam", "Score": 0.9999}, {"Name": "ham", "Score": 0.0001}]}
{"File": "SampleSMStext2.txt", "Line": "0", "Classes": [{"Name": "ham", "Score": 0.9994}, {"Name": "spam", "Score": 0.0006}]}
{"File": "SampleSMSText3.txt", "Line": "0", "Classes": [{"Name": "spam", "Score": 0.9999}, {"Name": "ham", "Score": 0.0001}]}

For more information, see Custom Classification in the Amazon Comprehend Developer Guide.

For API details, see StartDocumentClassificationJob in AWS CLI Command Reference.

The following code example shows how to use start-dominant-language-detection-job.

AWS CLI

To start an asynchronous language detection job

The following start-dominant-language-detection-job example starts an asynchronous language detection job for all of the files located at the address specified by the --input-data-config tag. The S3 bucket in this example contains Sampletext1.txt. When the job is complete, the folder, output, is placed in the location specified by the --output-data-config tag. The folder contains output.txt which contains the dominant language of each of the text files as well as the pre-trained model's confidence score for each prediction.


aws comprehend start-dominant-language-detection-job \
    --job-name example_language_analysis_job \
    --language-code en \
    --input-data-config "S3Uri=s3://amzn-s3-demo-bucket/" \
    --output-data-config "S3Uri=s3://amzn-s3-demo-destination-bucket/testfolder/" \
    --data-access-role-arn arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-example-role \
    --language-code en

Contents of Sampletext1.txt:


"Physics is the natural science that involves the study of matter and its motion and behavior through space and time, along with related concepts such as energy and force."

Output:


{
    "JobId": "123456abcdeb0e11022f22a11EXAMPLE",
    "JobArn": "arn:aws:comprehend:us-west-2:111122223333:dominant-language-detection-job/123456abcdeb0e11022f22a11EXAMPLE",
    "JobStatus": "SUBMITTED"
}

Contents of output.txt:


{"File": "Sampletext1.txt", "Languages": [{"LanguageCode": "en", "Score": 0.9913753867149353}], "Line": 0}

For more information, see Async analysis for Amazon Comprehend insights in the Amazon Comprehend Developer Guide.

For API details, see StartDominantLanguageDetectionJob in AWS CLI Command Reference.

The following code example shows how to use start-entities-detection-job.

AWS CLI

Example 1: To start a standard entity detection job using the pre-trained model

The following start-entities-detection-job example starts an asynchronous entities detection job for all files located at the address specified by the --input-data-config tag. The S3 bucket in this example contains Sampletext1.txt, Sampletext2.txt, and Sampletext3.txt. When the job is complete, the folder, output, is placed in the location specified by the --output-data-config tag. The folder contains output.txt which lists all of the named entities detected within each text file as well as the pre-trained model's confidence score for each prediction. The Json output is printed on one line per input file, but is formatted here for readability.


aws comprehend start-entities-detection-job \
    --job-name entitiestest \
    --language-code en \
    --input-data-config "S3Uri=s3://amzn-s3-demo-bucket/" \
    --output-data-config "S3Uri=s3://amzn-s3-demo-destination-bucket/testfolder/" \
    --data-access-role-arn arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-example-role \
    --language-code en

Contents of Sampletext1.txt:


"Hello Zhang Wei, I am John. Your AnyCompany Financial Services, LLC credit card account 1111-XXXX-1111-XXXX has a minimum payment of $24.53 that is due by July 31st."

Contents of Sampletext2.txt:


"Dear Max, based on your autopay settings for your account example1.org account, we will withdraw your payment on the due date from your bank account number XXXXXX1111 with the routing number XXXXX0000. "

Contents of Sampletext3.txt:


"Jane, please submit any customer feedback from this weekend to AnySpa, 123 Main St, Anywhere and send comments to Alice at AnySpa@example.com."

Output:


{
    "JobId": "123456abcdeb0e11022f22a11EXAMPLE",
    "JobArn": "arn:aws:comprehend:us-west-2:111122223333:entities-detection-job/123456abcdeb0e11022f22a11EXAMPLE",
    "JobStatus": "SUBMITTED"
}

Contents of output.txt with line indents for readability:


{
"Entities": [
    {
    "BeginOffset": 6,
    "EndOffset": 15,
    "Score": 0.9994006636420306,
    "Text": "Zhang Wei",
    "Type": "PERSON"
    },
    {
    "BeginOffset": 22,
    "EndOffset": 26,
    "Score": 0.9976647915128143,
    "Text": "John",
    "Type": "PERSON"
    },
    {
    "BeginOffset": 33,
    "EndOffset": 67,
    "Score": 0.9984608700836206,
    "Text": "AnyCompany Financial Services, LLC",
    "Type": "ORGANIZATION"
    },
    {
    "BeginOffset": 88,
    "EndOffset": 107,
    "Score": 0.9868521019555556,
    "Text": "1111-XXXX-1111-XXXX",
    "Type": "OTHER"
    },
    {
    "BeginOffset": 133,
    "EndOffset": 139,
    "Score": 0.998242565709204,
    "Text": "$24.53",
    "Type": "QUANTITY"
    },
    {
    "BeginOffset": 155,
    "EndOffset": 164,
    "Score": 0.9993039263159287,
    "Text": "July 31st",
    "Type": "DATE"
    }
],
"File": "SampleText1.txt",
"Line": 0
}
{
"Entities": [
    {
    "BeginOffset": 5,
    "EndOffset": 8,
    "Score": 0.9866232147545232,
    "Text": "Max",
    "Type": "PERSON"
    },
    {
    "BeginOffset": 156,
    "EndOffset": 166,
    "Score": 0.9797723450933329,
    "Text": "XXXXXX1111",
    "Type": "OTHER"
    },
    {
    "BeginOffset": 191,
    "EndOffset": 200,
    "Score": 0.9247838572396843,
    "Text": "XXXXX0000",
    "Type": "OTHER"
    }
],
"File": "SampleText2.txt",
"Line": 0
}
{
 "Entities": [
    {
    "Score": 0.9990532994270325,
    "Type": "PERSON",
    "Text": "Jane",
    "BeginOffset": 0,
    "EndOffset": 4
    },
    {
    "Score": 0.9519651532173157,
    "Type": "DATE",
    "Text": "this weekend",
    "BeginOffset": 47,
    "EndOffset": 59
    },
    {
    "Score": 0.5566426515579224,
    "Type": "ORGANIZATION",
    "Text": "AnySpa",
    "BeginOffset": 63,
    "EndOffset": 69
    },
    {
    "Score": 0.8059805631637573,
    "Type": "LOCATION",
    "Text": "123 Main St, Anywhere",
    "BeginOffset": 71,
    "EndOffset": 92
    },
    {
    "Score": 0.998830258846283,
    "Type": "PERSON",
    "Text": "Alice",
    "BeginOffset": 114,
    "EndOffset": 119
    },
    {
    "Score": 0.997818112373352,
    "Type": "OTHER",
    "Text": "AnySpa@example.com",
    "BeginOffset": 123,
    "EndOffset": 138
    }
    ],
    "File": "SampleText3.txt",
    "Line": 0
}

For more information, see Async analysis for Amazon Comprehend insights in the Amazon Comprehend Developer Guide.

Example 2: To start a custom entity detection job

The following start-entities-detection-job example starts an asynchronous custom entities detection job for all files located at the address specified by the --input-data-config tag. In this example, the S3 bucket in this example contains SampleFeedback1.txt, SampleFeedback2.txt, and SampleFeedback3.txt. The entity recognizer model was trained on customer support Feedbacks to recognize device names. When the job is complete, an the folder, output, is put at the location specified by the --output-data-config tag. The folder contains output.txt, which lists all of the named entities detected within each text file as well as the pre-trained model's confidence score for each prediction. The Json output is printed on one line per file, but is formatted here for readability.


aws comprehend start-entities-detection-job \
    --job-name customentitiestest \
    --entity-recognizer-arn "arn:aws:comprehend:us-west-2:111122223333:entity-recognizer/entityrecognizer" \
    --language-code en \
    --input-data-config "S3Uri=s3://amzn-s3-demo-bucket/jobdata/" \
    --output-data-config "S3Uri=s3://amzn-s3-demo-destination-bucket/testfolder/" \
    --data-access-role-arn "arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-IOrole"

Contents of SampleFeedback1.txt:


"I've been on the AnyPhone app have had issues for 24 hours when trying to pay bill. Cannot make payment. Sigh. | Oh man! Lets get that app up and running. DM me, and we can get to work!"

Contents of SampleFeedback2.txt:


"Hi, I have a discrepancy with my new bill. Could we get it sorted out? A rep added stuff I didnt sign up for when I did my AnyPhone 10 upgrade. | We can absolutely get this sorted!"

Contents of SampleFeedback3.txt:


"Is the by 1 get 1 free AnySmartPhone promo still going on? | Hi Christian! It ended yesterday, send us a DM if you have any questions and we can take a look at your options!"

Output:


{
    "JobId": "019ea9edac758806850fa8a79ff83021",
    "JobArn": "arn:aws:comprehend:us-west-2:111122223333:entities-detection-job/019ea9edac758806850fa8a79ff83021",
    "JobStatus": "SUBMITTED"
}

Contents of output.txt with line indents for readability:


{
"Entities": [
    {
    "BeginOffset": 17,
    "EndOffset": 25,
    "Score": 0.9999728210205924,
    "Text": "AnyPhone",
    "Type": "DEVICE"
    }
],
"File": "SampleFeedback1.txt",
"Line": 0
}
{
"Entities": [
    {
    "BeginOffset": 123,
    "EndOffset": 133,
    "Score": 0.9999892116761524,
    "Text": "AnyPhone 10",
    "Type": "DEVICE"
    }
],
"File": "SampleFeedback2.txt",
"Line": 0
}
{
"Entities": [
    {
    "BeginOffset": 23,
    "EndOffset": 35,
    "Score": 0.9999971389852362,
    "Text": "AnySmartPhone",
    "Type": "DEVICE"
    }
],
"File": "SampleFeedback3.txt",
"Line": 0
}

For more information, see Custom entity recognition in the Amazon Comprehend Developer Guide.

For API details, see StartEntitiesDetectionJob in AWS CLI Command Reference.

The following code example shows how to use start-events-detection-job.

AWS CLI

To start an asynchronous events detection job

The following start-events-detection-job example starts an asynchronous events detection job for all files located at the address specified by the --input-data-config tag. Possible target event types include BANKRUPCTY, EMPLOYMENT, CORPORATE_ACQUISITION, INVESTMENT_GENERAL, CORPORATE_MERGER, IPO, RIGHTS_ISSUE, SECONDARY_OFFERING, SHELF_OFFERING, TENDER_OFFERING, and STOCK_SPLIT. The S3 bucket in this example contains SampleText1.txt, SampleText2.txt, and SampleText3.txt. When the job is complete, the folder, output, is placed in the location specified by the --output-data-config tag. The folder contains SampleText1.txt.out, SampleText2.txt.out, and SampleText3.txt.out. The JSON output is printed on one line per file, but is formatted here for readability.


aws comprehend start-events-detection-job \
    --job-name events-detection-1 \
    --input-data-config "S3Uri=s3://amzn-s3-demo-bucket/EventsData" \
    --output-data-config "S3Uri=s3://amzn-s3-demo-destination-bucket/testfolder/" \
    --data-access-role-arn arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-servicerole \
    --language-code en \
    --target-event-types "BANKRUPTCY" "EMPLOYMENT" "CORPORATE_ACQUISITION" "CORPORATE_MERGER" "INVESTMENT_GENERAL"

Contents of SampleText1.txt:


"Company AnyCompany grew by increasing sales and through acquisitions. After purchasing competing firms in 2020, AnyBusiness, a part of the AnyBusinessGroup, gave Jane Does firm a going rate of one cent a gallon or forty-two cents a barrel."

Contents of SampleText2.txt:


"In 2021, AnyCompany officially purchased AnyBusiness for 100 billion dollars, surprising and exciting the shareholders."

Contents of SampleText3.txt:


"In 2022, AnyCompany stock crashed 50. Eventually later that year they filed for bankruptcy."

Output:


{
    "JobId": "123456abcdeb0e11022f22a11EXAMPLE",
    "JobArn": "arn:aws:comprehend:us-west-2:111122223333:events-detection-job/123456abcdeb0e11022f22a11EXAMPLE",
    "JobStatus": "SUBMITTED"
}

Contents of SampleText1.txt.out with line indents for readability:


{
    "Entities": [
        {
        "Mentions": [
            {
            "BeginOffset": 8,
            "EndOffset": 18,
            "Score": 0.99977,
            "Text": "AnyCompany",
            "Type": "ORGANIZATION",
            "GroupScore": 1
            },
            {
            "BeginOffset": 112,
            "EndOffset": 123,
            "Score": 0.999747,
            "Text": "AnyBusiness",
            "Type": "ORGANIZATION",
            "GroupScore": 0.979826
            },
            {
            "BeginOffset": 171,
            "EndOffset": 175,
            "Score": 0.999615,
            "Text": "firm",
            "Type": "ORGANIZATION",
            "GroupScore": 0.871647
            }
        ]
        },
        {
        "Mentions": [
            {
            "BeginOffset": 97,
            "EndOffset": 102,
            "Score": 0.987687,
            "Text": "firms",
            "Type": "ORGANIZATION",
            "GroupScore": 1
            }
        ]
        },
        {
        "Mentions": [
            {
            "BeginOffset": 103,
            "EndOffset": 110,
            "Score": 0.999458,
            "Text": "in 2020",
            "Type": "DATE",
            "GroupScore": 1
            }
        ]
        },
        {
        "Mentions": [
            {
            "BeginOffset": 160,
            "EndOffset": 168,
            "Score": 0.999649,
            "Text": "John Doe",
            "Type": "PERSON",
            "GroupScore": 1
            }
        ]
        }
    ],
    "Events": [
        {
        "Type": "CORPORATE_ACQUISITION",
        "Arguments": [
            {
            "EntityIndex": 0,
            "Role": "INVESTOR",
            "Score": 0.99977
            }
        ],
        "Triggers": [
            {
            "BeginOffset": 56,
            "EndOffset": 68,
            "Score": 0.999967,
            "Text": "acquisitions",
            "Type": "CORPORATE_ACQUISITION",
            "GroupScore": 1
            }
        ]
        },
        {
        "Type": "CORPORATE_ACQUISITION",
        "Arguments": [
            {
            "EntityIndex": 1,
            "Role": "INVESTEE",
            "Score": 0.987687
            },
            {
            "EntityIndex": 2,
            "Role": "DATE",
            "Score": 0.999458
            },
            {
            "EntityIndex": 3,
            "Role": "INVESTOR",
            "Score": 0.999649
            }
        ],
        "Triggers": [
            {
            "BeginOffset": 76,
            "EndOffset": 86,
            "Score": 0.999973,
            "Text": "purchasing",
            "Type": "CORPORATE_ACQUISITION",
            "GroupScore": 1
            }
        ]
        }
    ],
    "File": "SampleText1.txt",
    "Line": 0
}

Contents of SampleText2.txt.out:


{
    "Entities": [
        {
        "Mentions": [
            {
            "BeginOffset": 0,
            "EndOffset": 7,
            "Score": 0.999473,
            "Text": "In 2021",
            "Type": "DATE",
            "GroupScore": 1
            }
        ]
        },
        {
        "Mentions": [
            {
            "BeginOffset": 9,
            "EndOffset": 19,
            "Score": 0.999636,
            "Text": "AnyCompany",
            "Type": "ORGANIZATION",
            "GroupScore": 1
            }
        ]
        },
        {
        "Mentions": [
            {
            "BeginOffset": 45,
            "EndOffset": 56,
            "Score": 0.999712,
            "Text": "AnyBusiness",
            "Type": "ORGANIZATION",
            "GroupScore": 1
            }
        ]
        },
        {
        "Mentions": [
            {
            "BeginOffset": 61,
            "EndOffset": 80,
            "Score": 0.998886,
            "Text": "100 billion dollars",
            "Type": "MONETARY_VALUE",
            "GroupScore": 1
            }
        ]
        }
    ],
    "Events": [
        {
        "Type": "CORPORATE_ACQUISITION",
        "Arguments": [
            {
            "EntityIndex": 3,
            "Role": "AMOUNT",
            "Score": 0.998886
            },
            {
            "EntityIndex": 2,
            "Role": "INVESTEE",
            "Score": 0.999712
            },
            {
            "EntityIndex": 0,
            "Role": "DATE",
            "Score": 0.999473
            },
            {
            "EntityIndex": 1,
            "Role": "INVESTOR",
            "Score": 0.999636
            }
        ],
        "Triggers": [
            {
            "BeginOffset": 31,
            "EndOffset": 40,
            "Score": 0.99995,
            "Text": "purchased",
            "Type": "CORPORATE_ACQUISITION",
            "GroupScore": 1
            }
        ]
        }
    ],
    "File": "SampleText2.txt",
    "Line": 0
}

Contents of SampleText3.txt.out:


{
    "Entities": [
        {
        "Mentions": [
            {
            "BeginOffset": 9,
            "EndOffset": 19,
            "Score": 0.999774,
            "Text": "AnyCompany",
            "Type": "ORGANIZATION",
            "GroupScore": 1
            },
            {
            "BeginOffset": 66,
            "EndOffset": 70,
            "Score": 0.995717,
            "Text": "they",
            "Type": "ORGANIZATION",
            "GroupScore": 0.997626
            }
        ]
        },
        {
        "Mentions": [
            {
            "BeginOffset": 50,
            "EndOffset": 65,
            "Score": 0.999656,
            "Text": "later that year",
            "Type": "DATE",
            "GroupScore": 1
            }
        ]
        }
    ],
    "Events": [
        {
        "Type": "BANKRUPTCY",
        "Arguments": [
            {
            "EntityIndex": 1,
            "Role": "DATE",
            "Score": 0.999656
            },
            {
            "EntityIndex": 0,
            "Role": "FILER",
            "Score": 0.995717
            }
        ],
        "Triggers": [
            {
            "BeginOffset": 81,
            "EndOffset": 91,
            "Score": 0.999936,
            "Text": "bankruptcy",
            "Type": "BANKRUPTCY",
            "GroupScore": 1
            }
        ]
        }
    ],
    "File": "SampleText3.txt",
    "Line": 0
}

For more information, see Async analysis for Amazon Comprehend insights in the Amazon Comprehend Developer Guide.

For API details, see StartEventsDetectionJob in AWS CLI Command Reference.

The following code example shows how to use start-flywheel-iteration.

AWS CLI

To start a flywheel iteration

The following start-flywheel-iteration example starts a flywheel iteration. This operation uses any new datasets in the flywheel to train a new model version.


aws comprehend start-flywheel-iteration \
    --flywheel-arn arn:aws:comprehend:us-west-2:111122223333:flywheel/example-flywheel

Output:


{
    "FlywheelArn": "arn:aws:comprehend:us-west-2:111122223333:flywheel/example-flywheel",
    "FlywheelIterationId": "12345123TEXAMPLE"
}

For more information, see Flywheel overview in the Amazon Comprehend Developer Guide.

For API details, see StartFlywheelIteration in AWS CLI Command Reference.

The following code example shows how to use start-key-phrases-detection-job.

AWS CLI

To start a key phrases detection job

The following start-key-phrases-detection-job example starts an asynchronous key phrases detection job for all files located at the address specified by the --input-data-config tag. The S3 bucket in this example contains Sampletext1.txt, Sampletext2.txt, and Sampletext3.txt. When the job is completed, the folder, output, is placed in the location specified by the --output-data-config tag. The folder contains the file output.txt which contains all the key phrases detected within each text file and the pre-trained model's confidence score for each prediction. The Json output is printed on one line per file, but is formatted here for readability.


aws comprehend start-key-phrases-detection-job \
    --job-name keyphrasesanalysistest1 \
    --language-code en \
    --input-data-config "S3Uri=s3://amzn-s3-demo-bucket/" \
    --output-data-config "S3Uri=s3://amzn-s3-demo-destination-bucket/testfolder/" \
    --data-access-role-arn "arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-example-role" \
    --language-code en

Contents of Sampletext1.txt:


"Hello Zhang Wei, I am John. Your AnyCompany Financial Services, LLC credit card account 1111-XXXX-1111-XXXX has a minimum payment of $24.53 that is due by July 31st."

Contents of Sampletext2.txt:


"Dear Max, based on your autopay settings for your account Internet.org account, we will withdraw your payment on the due date from your bank account number XXXXXX1111 with the routing number XXXXX0000. "

Contents of Sampletext3.txt:


"Jane, please submit any customer feedback from this weekend to Sunshine Spa, 123 Main St, Anywhere and send comments to Alice at AnySpa@example.com."

Output:


{
    "JobId": "123456abcdeb0e11022f22a11EXAMPLE",
    "JobArn": "arn:aws:comprehend:us-west-2:111122223333:key-phrases-detection-job/123456abcdeb0e11022f22a11EXAMPLE",
    "JobStatus": "SUBMITTED"
}

Contents of output.txt with line indents for readibility:


{
    "File": "SampleText1.txt",
    "KeyPhrases": [
        {
        "BeginOffset": 6,
        "EndOffset": 15,
        "Score": 0.9748965572679326,
        "Text": "Zhang Wei"
        },
        {
        "BeginOffset": 22,
        "EndOffset": 26,
        "Score": 0.9997344722354619,
        "Text": "John"
        },
        {
        "BeginOffset": 28,
        "EndOffset": 62,
        "Score": 0.9843791074032948,
        "Text": "Your AnyCompany Financial Services"
        },
        {
        "BeginOffset": 64,
        "EndOffset": 107,
        "Score": 0.8976122401721824,
        "Text": "LLC credit card account 1111-XXXX-1111-XXXX"
        },
        {
        "BeginOffset": 112,
        "EndOffset": 129,
        "Score": 0.9999612982629748,
        "Text": "a minimum payment"
        },
        {
        "BeginOffset": 133,
        "EndOffset": 139,
        "Score": 0.99975728947036,
        "Text": "$24.53"
        },
        {
        "BeginOffset": 155,
        "EndOffset": 164,
        "Score": 0.9940866241449973,
        "Text": "July 31st"
        }
    ],
    "Line": 0
    }
    {
    "File": "SampleText2.txt",
    "KeyPhrases": [
        {
        "BeginOffset": 0,
        "EndOffset": 8,
        "Score": 0.9974021100118472,
        "Text": "Dear Max"
        },
        {
        "BeginOffset": 19,
        "EndOffset": 40,
        "Score": 0.9961120519515884,
        "Text": "your autopay settings"
        },
        {
        "BeginOffset": 45,
        "EndOffset": 78,
        "Score": 0.9980620070116009,
        "Text": "your account Internet.org account"
        },
        {
        "BeginOffset": 97,
        "EndOffset": 109,
        "Score": 0.999919660140754,
        "Text": "your payment"
        },
        {
        "BeginOffset": 113,
        "EndOffset": 125,
        "Score": 0.9998370719754205,
        "Text": "the due date"
        },
        {
        "BeginOffset": 131,
        "EndOffset": 166,
        "Score": 0.9955068678502509,
        "Text": "your bank account number XXXXXX1111"
        },
        {
        "BeginOffset": 172,
        "EndOffset": 200,
        "Score": 0.8653433315829526,
        "Text": "the routing number XXXXX0000"
        }
    ],
    "Line": 0
    }
    {
    "File": "SampleText3.txt",
    "KeyPhrases": [
        {
        "BeginOffset": 0,
        "EndOffset": 4,
        "Score": 0.9142947833681668,
        "Text": "Jane"
        },
        {
        "BeginOffset": 20,
        "EndOffset": 41,
        "Score": 0.9984325676596763,
        "Text": "any customer feedback"
        },
        {
        "BeginOffset": 47,
        "EndOffset": 59,
        "Score": 0.9998782448150636,
        "Text": "this weekend"
        },
        {
        "BeginOffset": 63,
        "EndOffset": 75,
        "Score": 0.99866741830757,
        "Text": "Sunshine Spa"
        },
        {
        "BeginOffset": 77,
        "EndOffset": 88,
        "Score": 0.9695803485466054,
        "Text": "123 Main St"
        },
        {
        "BeginOffset": 108,
        "EndOffset": 116,
        "Score": 0.9997065928550928,
        "Text": "comments"
        },
        {
        "BeginOffset": 120,
        "EndOffset": 125,
        "Score": 0.9993466833825161,
        "Text": "Alice"
        },
        {
        "BeginOffset": 129,
        "EndOffset": 144,
        "Score": 0.9654563612885667,
        "Text": "AnySpa@example.com"
        }
    ],
    "Line": 0
}

For more information, see Async analysis for Amazon Comprehend insights in the Amazon Comprehend Developer Guide.

For API details, see StartKeyPhrasesDetectionJob in AWS CLI Command Reference.

The following code example shows how to use start-pii-entities-detection-job.

AWS CLI

To start an asynchronous PII detection job

The following start-pii-entities-detection-job example starts an asynchronous personal identifiable information (PII) entities detection job for all files located at the address specified by the --input-data-config tag. The S3 bucket in this example contains Sampletext1.txt, Sampletext2.txt, and Sampletext3.txt. When the job is complete, the folder, output, is placed in the location specified by the --output-data-config tag. The folder contains SampleText1.txt.out, SampleText2.txt.out, and SampleText3.txt.out which list the named entities within each text file. The Json output is printed on one line per file, but is formatted here for readability.


aws comprehend start-pii-entities-detection-job \
    --job-name entities_test \
    --language-code en \
    --input-data-config "S3Uri=s3://amzn-s3-demo-bucket/" \
    --output-data-config "S3Uri=s3://amzn-s3-demo-destination-bucket/testfolder/" \
    --data-access-role-arn arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-example-role \
    --language-code en \
    --mode ONLY_OFFSETS

Contents of Sampletext1.txt:


"Hello Zhang Wei, I am John. Your AnyCompany Financial Services, LLC credit card account 1111-XXXX-1111-XXXX has a minimum payment of $24.53 that is due by July 31st."

Contents of Sampletext2.txt:


"Dear Max, based on your autopay settings for your account Internet.org account, we will withdraw your payment on the due date from your bank account number XXXXXX1111 with the routing number XXXXX0000. "

Contents of Sampletext3.txt:


"Jane, please submit any customer feedback from this weekend to Sunshine Spa, 123 Main St, Anywhere and send comments to Alice at AnySpa@example.com."

Output:


{
    "JobId": "123456abcdeb0e11022f22a11EXAMPLE",
    "JobArn": "arn:aws:comprehend:us-west-2:111122223333:pii-entities-detection-job/123456abcdeb0e11022f22a11EXAMPLE",
    "JobStatus": "SUBMITTED"
}

Contents of SampleText1.txt.out with line indents for readability:


{
    "Entities": [
        {
        "BeginOffset": 6,
        "EndOffset": 15,
        "Type": "NAME",
        "Score": 0.9998490510222595
        },
        {
        "BeginOffset": 22,
        "EndOffset": 26,
        "Type": "NAME",
        "Score": 0.9998937958019426
        },
        {
        "BeginOffset": 88,
        "EndOffset": 107,
        "Type": "CREDIT_DEBIT_NUMBER",
        "Score": 0.9554297245278491
        },
        {
        "BeginOffset": 155,
        "EndOffset": 164,
        "Type": "DATE_TIME",
        "Score": 0.9999720462925257
        }
    ],
    "File": "SampleText1.txt",
    "Line": 0
}

Contents of SampleText2.txt.out with line indents for readability:


{
    "Entities": [
        {
        "BeginOffset": 5,
        "EndOffset": 8,
        "Type": "NAME",
        "Score": 0.9994390774924007
        },
        {
        "BeginOffset": 58,
        "EndOffset": 70,
        "Type": "URL",
        "Score": 0.9999958276922101
        },
        {
        "BeginOffset": 156,
        "EndOffset": 166,
        "Type": "BANK_ACCOUNT_NUMBER",
        "Score": 0.9999721058045592
        },
        {
        "BeginOffset": 191,
        "EndOffset": 200,
        "Type": "BANK_ROUTING",
        "Score": 0.9998968945989909
        }
    ],
    "File": "SampleText2.txt",
    "Line": 0
}

Contents of SampleText3.txt.out with line indents for readability:


{
    "Entities": [
        {
        "BeginOffset": 0,
        "EndOffset": 4,
        "Type": "NAME",
        "Score": 0.999949934606805
        },
        {
        "BeginOffset": 77,
        "EndOffset": 88,
        "Type": "ADDRESS",
        "Score": 0.9999035300466904
        },
        {
        "BeginOffset": 120,
        "EndOffset": 125,
        "Type": "NAME",
        "Score": 0.9998203838716296
        },
        {
        "BeginOffset": 129,
        "EndOffset": 144,
        "Type": "EMAIL",
        "Score": 0.9998313473105228
        }
    ],
    "File": "SampleText3.txt",
    "Line": 0
}

For more information, see Async analysis for Amazon Comprehend insights in the Amazon Comprehend Developer Guide.

For API details, see StartPiiEntitiesDetectionJob in AWS CLI Command Reference.

The following code example shows how to use start-sentiment-detection-job.

AWS CLI

To start an asynchronous sentiment analysis job

The following start-sentiment-detection-job example starts an asynchronous sentiment analysis detection job for all files located at the address specified by the --input-data-config tag. The S3 bucket folder in this example contains SampleMovieReview1.txt, SampleMovieReview2.txt, and SampleMovieReview3.txt. When the job is complete, the folder, output, is placed at the location specified by the --output-data-config tag. The folder contains the file, output.txt, which contains the prevailing sentiments for each text file and the pre-trained model's confidence score for each prediction. The Json output is printed on one line per file, but is formatted here for readability.


aws comprehend start-sentiment-detection-job \
    --job-name example-sentiment-detection-job \
    --language-code en \
    --input-data-config "S3Uri=s3://amzn-s3-demo-bucket/MovieData" \
    --output-data-config "S3Uri=s3://amzn-s3-demo-destination-bucket/testfolder/" \
    --data-access-role-arn arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-example-role

Contents of SampleMovieReview1.txt:


"The film, AnyMovie2, is fairly predictable and just okay."

Contents of SampleMovieReview2.txt:


"AnyMovie2 is the essential sci-fi film that I grew up watching when I was a kid. I highly recommend this movie."

Contents of SampleMovieReview3.txt:


"Don't get fooled by the 'awards' for AnyMovie2. All parts of the film were poorly stolen from other modern directors."

Output:


{
    "JobId": "0b5001e25f62ebb40631a9a1a7fde7b3",
    "JobArn": "arn:aws:comprehend:us-west-2:111122223333:sentiment-detection-job/0b5001e25f62ebb40631a9a1a7fde7b3",
    "JobStatus": "SUBMITTED"
}

Contents of output.txt with line of indents for readability:


{
    "File": "SampleMovieReview1.txt",
        "Line": 0,
        "Sentiment": "MIXED",
        "SentimentScore": {
            "Mixed": 0.6591159105300903,
            "Negative": 0.26492202281951904,
            "Neutral": 0.035430654883384705,
            "Positive": 0.04053137078881264
            }
        }
    {
    "File": "SampleMovieReview2.txt",
        "Line": 0,
        "Sentiment": "POSITIVE",
        "SentimentScore": {
            "Mixed": 0.000008718466233403888,
            "Negative": 0.00006134175055194646,
            "Neutral": 0.0002941041602753103,
            "Positive": 0.9996358156204224
            }
        }
    {
    "File": "SampleMovieReview3.txt",
        "Line": 0,
        "Sentiment": "NEGATIVE",
        "SentimentScore": {
            "Mixed": 0.004146667663007975,
            "Negative": 0.9645107984542847,
            "Neutral": 0.016559595242142677,
            "Positive": 0.014782938174903393
        }
    }
}

For more information, see Async analysis for Amazon Comprehend insights in the Amazon Comprehend Developer Guide.

For API details, see StartSentimentDetectionJob in AWS CLI Command Reference.

The following code example shows how to use start-targeted-sentiment-detection-job.

AWS CLI

To start an asynchronous targeted sentiment analysis job

The following start-targeted-sentiment-detection-job example starts an asynchronous targeted sentiment analysis detection job for all files located at the address specified by the --input-data-config tag. The S3 bucket folder in this example contains SampleMovieReview1.txt, SampleMovieReview2.txt, and SampleMovieReview3.txt. When the job is complete, output.tar.gz is placed at the location specified by the --output-data-config tag. output.tar.gz contains the files SampleMovieReview1.txt.out, SampleMovieReview2.txt.out, and SampleMovieReview3.txt.out, which each contain all of the named entities and associated sentiments for a single input text file.


aws comprehend start-targeted-sentiment-detection-job \
    --job-name targeted_movie_review_analysis1 \
    --language-code en \
    --input-data-config "S3Uri=s3://amzn-s3-demo-bucket/MovieData" \
    --output-data-config "S3Uri=s3://amzn-s3-demo-destination-bucket/testfolder/" \
    --data-access-role-arn arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-example-role

Contents of SampleMovieReview1.txt:


"The film, AnyMovie, is fairly predictable and just okay."

Contents of SampleMovieReview2.txt:


"AnyMovie is the essential sci-fi film that I grew up watching when I was a kid. I highly recommend this movie."

Contents of SampleMovieReview3.txt:


"Don't get fooled by the 'awards' for AnyMovie. All parts of the film were poorly stolen from other modern directors."

Output:


{
    "JobId": "0b5001e25f62ebb40631a9a1a7fde7b3",
    "JobArn": "arn:aws:comprehend:us-west-2:111122223333:targeted-sentiment-detection-job/0b5001e25f62ebb40631a9a1a7fde7b3",
    "JobStatus": "SUBMITTED"
}

Contents of SampleMovieReview1.txt.out with line indents for readability:


{
    "Entities": [
        {
        "DescriptiveMentionIndex": [
            0
        ],
        "Mentions": [
            {
            "BeginOffset": 4,
            "EndOffset": 8,
            "Score": 0.994972,
            "GroupScore": 1,
            "Text": "film",
            "Type": "MOVIE",
            "MentionSentiment": {
                "Sentiment": "NEUTRAL",
                "SentimentScore": {
                "Mixed": 0,
                "Negative": 0,
                "Neutral": 1,
                "Positive": 0
                }
            }
            }
        ]
        },
        {
        "DescriptiveMentionIndex": [
            0
        ],
        "Mentions": [
            {
            "BeginOffset": 10,
            "EndOffset": 18,
            "Score": 0.631368,
            "GroupScore": 1,
            "Text": "AnyMovie",
            "Type": "ORGANIZATION",
            "MentionSentiment": {
                "Sentiment": "POSITIVE",
                "SentimentScore": {
                "Mixed": 0.001729,
                "Negative": 0.000001,
                "Neutral": 0.000318,
                "Positive": 0.997952
                }
            }
            }
        ]
        }
    ],
    "File": "SampleMovieReview1.txt",
    "Line": 0
}

Contents of SampleMovieReview2.txt.out line indents for readability:


{
    "Entities": [
        {
        "DescriptiveMentionIndex": [
            0
        ],
        "Mentions": [
            {
            "BeginOffset": 0,
            "EndOffset": 8,
            "Score": 0.854024,
            "GroupScore": 1,
            "Text": "AnyMovie",
            "Type": "MOVIE",
            "MentionSentiment": {
                "Sentiment": "POSITIVE",
                "SentimentScore": {
                "Mixed": 0,
                "Negative": 0,
                "Neutral": 0.000007,
                "Positive": 0.999993
                }
            }
            },
            {
            "BeginOffset": 104,
            "EndOffset": 109,
            "Score": 0.999129,
            "GroupScore": 0.502937,
            "Text": "movie",
            "Type": "MOVIE",
            "MentionSentiment": {
                "Sentiment": "POSITIVE",
                "SentimentScore": {
                "Mixed": 0,
                "Negative": 0,
                "Neutral": 0,
                "Positive": 1
                }
            }
            },
            {
            "BeginOffset": 33,
            "EndOffset": 37,
            "Score": 0.999823,
            "GroupScore": 0.999252,
            "Text": "film",
            "Type": "MOVIE",
            "MentionSentiment": {
                "Sentiment": "POSITIVE",
                "SentimentScore": {
                "Mixed": 0,
                "Negative": 0,
                "Neutral": 0.000001,
                "Positive": 0.999999
                }
            }
            }
        ]
        },
        {
        "DescriptiveMentionIndex": [
            0,
            1,
            2
        ],
        "Mentions": [
            {
            "BeginOffset": 43,
            "EndOffset": 44,
            "Score": 0.999997,
            "GroupScore": 1,
            "Text": "I",
            "Type": "PERSON",
            "MentionSentiment": {
                "Sentiment": "NEUTRAL",
                "SentimentScore": {
                "Mixed": 0,
                "Negative": 0,
                "Neutral": 1,
                "Positive": 0
                }
            }
            },
            {
            "BeginOffset": 80,
            "EndOffset": 81,
            "Score": 0.999996,
            "GroupScore": 0.52523,
            "Text": "I",
            "Type": "PERSON",
            "MentionSentiment": {
                "Sentiment": "NEUTRAL",
                "SentimentScore": {
                "Mixed": 0,
                "Negative": 0,
                "Neutral": 1,
                "Positive": 0
                }
            }
            },
            {
            "BeginOffset": 67,
            "EndOffset": 68,
            "Score": 0.999994,
            "GroupScore": 0.999499,
            "Text": "I",
            "Type": "PERSON",
            "MentionSentiment": {
                "Sentiment": "NEUTRAL",
                "SentimentScore": {
                "Mixed": 0,
                "Negative": 0,
                "Neutral": 1,
                "Positive": 0
                }
            }
            }
        ]
        },
        {
        "DescriptiveMentionIndex": [
            0
        ],
        "Mentions": [
            {
            "BeginOffset": 75,
            "EndOffset": 78,
            "Score": 0.999978,
            "GroupScore": 1,
            "Text": "kid",
            "Type": "PERSON",
            "MentionSentiment": {
                "Sentiment": "NEUTRAL",
                "SentimentScore": {
                "Mixed": 0,
                "Negative": 0,
                "Neutral": 1,
                "Positive": 0
                }
            }
            }
        ]
        }
    ],
    "File": "SampleMovieReview2.txt",
    "Line": 0
}

Contents of SampleMovieReview3.txt.out with line indents for readibility:


{
    "Entities": [
        {
        "DescriptiveMentionIndex": [
            1
        ],
        "Mentions": [
            {
            "BeginOffset": 64,
            "EndOffset": 68,
            "Score": 0.992953,
            "GroupScore": 0.999814,
            "Text": "film",
            "Type": "MOVIE",
            "MentionSentiment": {
                "Sentiment": "NEUTRAL",
                "SentimentScore": {
                "Mixed": 0.000004,
                "Negative": 0.010425,
                "Neutral": 0.989543,
                "Positive": 0.000027
                }
            }
            },
            {
            "BeginOffset": 37,
            "EndOffset": 45,
            "Score": 0.999782,
            "GroupScore": 1,
            "Text": "AnyMovie",
            "Type": "ORGANIZATION",
            "MentionSentiment": {
                "Sentiment": "POSITIVE",
                "SentimentScore": {
                "Mixed": 0.000095,
                "Negative": 0.039847,
                "Neutral": 0.000673,
                "Positive": 0.959384
                }
            }
            }
        ]
        },
        {
        "DescriptiveMentionIndex": [
            0
        ],
        "Mentions": [
            {
            "BeginOffset": 47,
            "EndOffset": 50,
            "Score": 0.999991,
            "GroupScore": 1,
            "Text": "All",
            "Type": "QUANTITY",
            "MentionSentiment": {
                "Sentiment": "NEUTRAL",
                "SentimentScore": {
                "Mixed": 0.000001,
                "Negative": 0.000001,
                "Neutral": 0.999998,
                "Positive": 0
                }
            }
            }
        ]
        },
        {
        "DescriptiveMentionIndex": [
            0
        ],
        "Mentions": [
            {
            "BeginOffset": 106,
            "EndOffset": 115,
            "Score": 0.542083,
            "GroupScore": 1,
            "Text": "directors",
            "Type": "PERSON",
            "MentionSentiment": {
                "Sentiment": "NEUTRAL",
                "SentimentScore": {
                "Mixed": 0,
                "Negative": 0,
                "Neutral": 1,
                "Positive": 0
                }
            }
            }
        ]
        }
    ],
    "File": "SampleMovieReview3.txt",
    "Line": 0
}

For more information, see Async analysis for Amazon Comprehend insights in the Amazon Comprehend Developer Guide.

For API details, see StartTargetedSentimentDetectionJob in AWS CLI Command Reference.

The following code example shows how to use start-topics-detection-job.

AWS CLI

To start a topics detection analysis job

The following start-topics-detection-job example starts an asynchronous topics detection job for all files located at the address specified by the --input-data-config tag. When the job is complete, the folder, output, is placed at the location specified by the --ouput-data-config tag. output contains topic-terms.csv and doc-topics.csv. The first output file, topic-terms.csv, is a list of topics in the collection. For each topic, the list includes, by default, the top terms by topic according to their weight. The second file, doc-topics.csv, lists the documents associated with a topic and the proportion of the document that is concerned with the topic.


aws comprehend start-topics-detection-job \
    --job-name example_topics_detection_job \
    --language-code en \
    --input-data-config "S3Uri=s3://amzn-s3-demo-bucket/" \
    --output-data-config "S3Uri=s3://amzn-s3-demo-destination-bucket/testfolder/" \
    --data-access-role-arn arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-example-role \
    --language-code en

Output:


{
    "JobId": "123456abcdeb0e11022f22a11EXAMPLE",
    "JobArn": "arn:aws:comprehend:us-west-2:111122223333:key-phrases-detection-job/123456abcdeb0e11022f22a11EXAMPLE",
    "JobStatus": "SUBMITTED"
}

For more information, see Topic Modeling in the Amazon Comprehend Developer Guide.

For API details, see StartTopicsDetectionJob in AWS CLI Command Reference.

The following code example shows how to use stop-dominant-language-detection-job.

AWS CLI

To stop an asynchronous dominant language detection job

The following stop-dominant-language-detection-job example stops an in-progress, asynchronous dominant language detection job. If the current 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.


aws comprehend stop-dominant-language-detection-job \
    --job-id 123456abcdeb0e11022f22a11EXAMPLE

Output:


{
    "JobId": "123456abcdeb0e11022f22a11EXAMPLE,
    "JobStatus": "STOP_REQUESTED"
}

For more information, see Async analysis for Amazon Comprehend insights in the Amazon Comprehend Developer Guide.

For API details, see StopDominantLanguageDetectionJob in AWS CLI Command Reference.

The following code example shows how to use stop-entities-detection-job.

AWS CLI

To stop an asynchronous entities detection job

The following stop-entities-detection-job example stops an in-progress, asynchronous entities detection job. If the current 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.


aws comprehend stop-entities-detection-job \
    --job-id 123456abcdeb0e11022f22a11EXAMPLE

Output:


{
    "JobId": "123456abcdeb0e11022f22a11EXAMPLE,
    "JobStatus": "STOP_REQUESTED"
}

For more information, see Async analysis for Amazon Comprehend insights in the Amazon Comprehend Developer Guide.

For API details, see StopEntitiesDetectionJob in AWS CLI Command Reference.

The following code example shows how to use stop-events-detection-job.

AWS CLI

To stop an asynchronous events detection job

The following stop-events-detection-job example stops an in-progress, asynchronous events detection job. If the current 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.


aws comprehend stop-events-detection-job \
    --job-id 123456abcdeb0e11022f22a11EXAMPLE

Output:


{
    "JobId": "123456abcdeb0e11022f22a11EXAMPLE,
    "JobStatus": "STOP_REQUESTED"
}

For more information, see Async analysis for Amazon Comprehend insights in the Amazon Comprehend Developer Guide.

For API details, see StopEventsDetectionJob in AWS CLI Command Reference.

The following code example shows how to use stop-key-phrases-detection-job.

AWS CLI

To stop an asynchronous key phrases detection job

The following stop-key-phrases-detection-job example stops an in-progress, asynchronous key phrases detection job. If the current 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.


aws comprehend stop-key-phrases-detection-job \
    --job-id 123456abcdeb0e11022f22a11EXAMPLE

Output:


{
    "JobId": "123456abcdeb0e11022f22a11EXAMPLE,
    "JobStatus": "STOP_REQUESTED"
}

For more information, see Async analysis for Amazon Comprehend insights in the Amazon Comprehend Developer Guide.

For API details, see StopKeyPhrasesDetectionJob in AWS CLI Command Reference.

The following code example shows how to use stop-pii-entities-detection-job.

AWS CLI

To stop an asynchronous pii entities detection job

The following stop-pii-entities-detection-job example stops an in-progress, asynchronous pii entities detection job. If the current 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.


aws comprehend stop-pii-entities-detection-job \
    --job-id 123456abcdeb0e11022f22a11EXAMPLE

Output:


{
    "JobId": "123456abcdeb0e11022f22a11EXAMPLE,
    "JobStatus": "STOP_REQUESTED"
}

For more information, see Async analysis for Amazon Comprehend insights in the Amazon Comprehend Developer Guide.

For API details, see StopPiiEntitiesDetectionJob in AWS CLI Command Reference.

The following code example shows how to use stop-sentiment-detection-job.

AWS CLI

To stop an asynchronous sentiment detection job

The following stop-sentiment-detection-job example stops an in-progress, asynchronous sentiment detection job. If the current 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.


aws comprehend stop-sentiment-detection-job \
    --job-id 123456abcdeb0e11022f22a11EXAMPLE

Output:


{
    "JobId": "123456abcdeb0e11022f22a11EXAMPLE,
    "JobStatus": "STOP_REQUESTED"
}

For more information, see Async analysis for Amazon Comprehend insights in the Amazon Comprehend Developer Guide.

For API details, see StopSentimentDetectionJob in AWS CLI Command Reference.

The following code example shows how to use stop-targeted-sentiment-detection-job.

AWS CLI

To stop an asynchronous targeted sentiment detection job

The following stop-targeted-sentiment-detection-job example stops an in-progress, asynchronous targeted sentiment detection job. If the current 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.


aws comprehend stop-targeted-sentiment-detection-job \
    --job-id 123456abcdeb0e11022f22a11EXAMPLE

Output:


{
    "JobId": "123456abcdeb0e11022f22a11EXAMPLE,
    "JobStatus": "STOP_REQUESTED"
}

For more information, see Async analysis for Amazon Comprehend insights in the Amazon Comprehend Developer Guide.

For API details, see StopTargetedSentimentDetectionJob in AWS CLI Command Reference.

The following code example shows how to use stop-training-document-classifier.

AWS CLI

To stop the training of a document classifier model

The following stop-training-document-classifier example stops the training of a document classifier model while in-progress.


aws comprehend stop-training-document-classifier
    --document-classifier-arn arn:aws:comprehend:us-west-2:111122223333:document-classifier/example-classifier

This command produces no output.

For more information, see Creating and managing custom models in the Amazon Comprehend Developer Guide.

For API details, see StopTrainingDocumentClassifier in AWS CLI Command Reference.

The following code example shows how to use stop-training-entity-recognizer.

AWS CLI

To stop the training of an entity recognizer model

The following stop-training-entity-recognizer example stops the training of an entity recognizer model while in-progress.


aws comprehend stop-training-entity-recognizer
    --entity-recognizer-arn "arn:aws:comprehend:us-west-2:111122223333:entity-recognizer/examplerecognizer1"

This command produces no output.

For more information, see Creating and managing custom models in the Amazon Comprehend Developer Guide.

For API details, see StopTrainingEntityRecognizer in AWS CLI Command Reference.

The following code example shows how to use tag-resource.

AWS CLI

Example 1: To tag a resource

The following tag-resource example adds a single tag to an Amazon Comprehend resource.


aws comprehend tag-resource \
    --resource-arn arn:aws:comprehend:us-west-2:111122223333:document-classifier/example-classifier/version/1 \
    --tags Key=Location,Value=Seattle

This command has no output.

For more information, see Tagging your resources in the Amazon Comprehend Developer Guide.

Example 2: To add multiple tags to a resource

The following tag-resource example adds multiple tags to an Amazon Comprehend resource.


aws comprehend tag-resource \
    --resource-arn "arn:aws:comprehend:us-west-2:111122223333:document-classifier/example-classifier/version/1" \
    --tags Key=location,Value=Seattle Key=Department,Value=Finance

This command has no output.

For more information, see Tagging your resources in the Amazon Comprehend Developer Guide.

For API details, see TagResource in AWS CLI Command Reference.

The following code example shows how to use untag-resource.

AWS CLI

Example 1: To remove a single tag from a resource

The following untag-resource example removes a single tag from an Amazon Comprehend resource.


aws comprehend untag-resource \
    --resource-arn arn:aws:comprehend:us-west-2:111122223333:document-classifier/example-classifier/version/1
    --tag-keys Location

This command produces no output.

For more information, see Tagging your resources in the Amazon Comprehend Developer Guide.

Example 2: To remove multiple tags from a resource

The following untag-resource example removes multiple tags from an Amazon Comprehend resource.


aws comprehend untag-resource \
    --resource-arn arn:aws:comprehend:us-west-2:111122223333:document-classifier/example-classifier/version/1
    --tag-keys Location Department

This command produces no output.

For more information, see Tagging your resources in the Amazon Comprehend Developer Guide.

For API details, see UntagResource in AWS CLI Command Reference.

The following code example shows how to use update-endpoint.

AWS CLI

Example 1: To update an endpoint's inference units

The following update-endpoint example updates information about an endpoint. In this example, the number of inference units is increased.


aws comprehend update-endpoint \
    --endpoint-arn arn:aws:comprehend:us-west-2:111122223333:document-classifier-endpoint/example-classifier-endpoint
    --desired-inference-units 2

This command produces no output.

For more information, see Managing Amazon Comprehend endpoints in the Amazon Comprehend Developer Guide.

Example 2: To update an endpoint's actie model

The following update-endpoint example updates information about an endpoint. In this example, the active model is changed.


aws comprehend update-endpoint \
    --endpoint-arn arn:aws:comprehend:us-west-2:111122223333:document-classifier-endpoint/example-classifier-endpoint
    --active-model-arn arn:aws:comprehend:us-west-2:111122223333:document-classifier/example-classifier-new

This command produces no output.

For more information, see Managing Amazon Comprehend endpoints in the Amazon Comprehend Developer Guide.

For API details, see UpdateEndpoint in AWS CLI Command Reference.

The following code example shows how to use update-flywheel.

AWS CLI

To update a flywheel configuration

The following update-flywheel example updates a flywheel configuration. In this example, the active model for the flywheel is updated.


aws comprehend update-flywheel \
    --flywheel-arn arn:aws:comprehend:us-west-2:111122223333:flywheel/example-flywheel-1 \
    --active-model-arn arn:aws:comprehend:us-west-2:111122223333:document-classifier/example-classifier/version/new-example-classifier-model

Output:


{
    "FlywheelProperties": {
        "FlywheelArn": "arn:aws:comprehend:us-west-2:111122223333:flywheel/flywheel-entity",
        "ActiveModelArn": "arn:aws:comprehend:us-west-2:111122223333:document-classifier/example-classifier/version/new-example-classifier-model",
        "DataAccessRoleArn": "arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-example-role",
        "TaskConfig": {
            "LanguageCode": "en",
            "DocumentClassificationConfig": {
                "Mode": "MULTI_CLASS"
            }
        },
        "DataLakeS3Uri": "s3://amzn-s3-demo-bucket/flywheel-entity/schemaVersion=1/20230616T200543Z/",
        "DataSecurityConfig": {},
        "Status": "ACTIVE",
        "ModelType": "DOCUMENT_CLASSIFIER",
        "CreationTime": "2023-06-16T20:05:43.242000+00:00",
        "LastModifiedTime": "2023-06-19T04:00:43.027000+00:00",
        "LatestFlywheelIteration": "20230619T040032Z"
    }
}

For more information, see Flywheel overview in the Amazon Comprehend Developer Guide.

For API details, see UpdateFlywheel in AWS CLI Command Reference.

Warning Javascript is disabled or is unavailable in your browser.

To use the Amazon Web Services Documentation, Javascript must be enabled. Please refer to your browser's Help pages for instructions.

Document Conventions

Amazon Cognito Identity Provider

Amazon Comprehend Medical