Options
All
  • Public
  • Public/Protected
  • All
Menu

Class NaturalLanguageClassifierV1

IBM Watson™ Natural Language Classifier uses machine learning algorithms to return the top matching predefined classes for short text input. You create and train a classifier to connect predefined classes to example texts so that the service can apply those classes to new inputs. interfaces

API Version: 1.0 See: https://cloud.ibm.com/docs/natural-language-classifier

Hierarchy

  • BaseService
    • NaturalLanguageClassifierV1

Index

Constructors

Properties

Methods

Constructors

constructor

Properties

Static DEFAULT_SERVICE_NAME

DEFAULT_SERVICE_NAME: string = "natural_language_classifier"

Static DEFAULT_SERVICE_URL

DEFAULT_SERVICE_URL: string = "https://api.us-south.natural-language-classifier.watson.cloud.ibm.com"

Methods

classify

  • Classify a phrase.

    Returns label information for the input. The status must be Available before you can use the classifier to classify text.

    Parameters

    Name Type Attribute Description
    params ClassifyParams

    The parameters to send to the service.

    Properties

    Name Type Attributes Description
    classifierId string Classifier ID to use.
    text string The submitted phrase. The maximum length is 2048 characters.
    headers OutgoingHttpHeaders Optional

    Returns Promise<Response<Classification>>

classifyCollection

  • Classify multiple phrases.

    Returns label information for multiple phrases. The status must be Available before you can use the classifier to classify text.

    Note that classifying Japanese texts is a beta feature.

    Parameters

    Name Type Attribute Description
    params ClassifyCollectionParams

    The parameters to send to the service.

    Properties

    Name Type Attributes Description
    classifierId string Classifier ID to use.
    collection ClassifyInput[] The submitted phrases.
    headers OutgoingHttpHeaders Optional

    Returns Promise<Response<ClassificationCollection>>

createClassifier

  • Create classifier.

    Sends data to create and train a classifier and returns information about the new classifier.

    Parameters

    Name Type Attribute Description
    params CreateClassifierParams

    The parameters to send to the service.

    Properties

    Name Type Attributes Description
    trainingData ReadableStream | Buffer Training data in CSV format. Each text value must have at least one class. The data can include up to 3,000 classes and 20,000 records. For details, see [Data preparation](https://cloud.ibm.com/docs/natural-language-classifier?topic=natural-language-classifier-using-your-data).
    trainingMetadata ReadableStream | Buffer Metadata in JSON format. The metadata identifies the language of the data, and an optional name to identify the classifier. Specify the language with the 2-letter primary language code as assigned in ISO standard 639.
    headers OutgoingHttpHeaders Optional

    Returns Promise<Response<Classifier>>

deleteClassifier

getAuthenticator

  • getAuthenticator(): any

  • Get the instance of the authenticator set on the service.

    Returns any

getClassifier

  • Get information about a classifier.

    Returns status and other information about a classifier.

    Parameters

    Name Type Attribute Description
    params GetClassifierParams

    The parameters to send to the service.

    Properties

    Name Type Attributes Description
    classifierId string Classifier ID to query.
    headers OutgoingHttpHeaders Optional

    Returns Promise<Response<Classifier>>

listClassifiers

setEnableGzipCompression

  • setEnableGzipCompression(setting: boolean): void

  • Turn request body compression on or off.

    Parameters

    Name Type Attribute Description
    setting boolean

    Will turn it on if 'true', off if 'false'.

    Returns void

setServiceUrl

  • setServiceUrl(url: string): void

  • Set the service URL to send requests to.

    Parameters

    Name Type Attribute Description
    url string

    The base URL for the service.

    Returns void

Generated using TypeDoc