watson_developer_cloud.natural_language_classifier_v1 module

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.

class NaturalLanguageClassifierV1(url='https://gateway.watsonplatform.net/natural-language-classifier/api', username=None, password=None)[source]

Bases: watson_developer_cloud.watson_service.WatsonService

The Natural Language Classifier V1 service.

default_url = 'https://gateway.watsonplatform.net/natural-language-classifier/api'
classify(classifier_id, text)[source]

Returns label information for the input.

The status must be Available before you can use the classifier to classify text. Use Get information about a classifier to retrieve the status.

Parameters:
  • classifier_id (str) – Classifier ID to use.
  • text (str) – The submitted phrase.
Returns:

A dict containing the Classification response.

Return type:

dict

create_classifier(metadata, training_data, metadata_filename=None, training_data_filename=None)[source]

Create classifier.

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

Parameters:
Returns:

A dict containing the Classifier response.

Return type:

dict

delete_classifier(classifier_id)[source]

Delete classifier.

Parameters:classifier_id (str) – Classifier ID to delete.
Return type:None
get_classifier(classifier_id)[source]

Get information about a classifier.

Returns status and other information about a classifier.

Parameters:classifier_id (str) – Classifier ID to query.
Returns:A dict containing the Classifier response.
Return type:dict
list_classifiers()[source]

List classifiers.

Returns an empty array if no classifiers are available.

Returns:A dict containing the ClassifierList response.
Return type:dict
class Classification(classifier_id=None, url=None, text=None, top_class=None, classes=None)[source]

Bases: object

Response from the classifier for a phrase.

Attr str classifier_id:
 (optional) Unique identifier for this classifier.
Attr str url:(optional) Link to the classifier.
Attr str text:(optional) The submitted phrase.
Attr str top_class:
 (optional) The class with the highest confidence.
Attr list[ClassifiedClass] classes:
 (optional) An array of up to ten class-confidence pairs sorted in descending order of confidence.
class ClassifiedClass(confidence=None, class_name=None)[source]

Bases: object

Class and confidence.

Attr float confidence:
 (optional) A decimal percentage that represents the confidence that Watson has in this class. Higher values represent higher confidences.
Attr str class_name:
 (optional) Class label.
class Classifier(url, classifier_id, name=None, status=None, created=None, status_description=None, language=None)[source]

Bases: object

A classifier for natural language phrases.

Attr str name:(optional) User-supplied name for the classifier.
Attr str url:Link to the classifier.
Attr str status:
 (optional) The state of the classifier.
Attr str classifier_id:
 Unique identifier for this classifier.
Attr datetime created:
 (optional) Date and time (UTC) the classifier was created.
Attr str status_description:
 (optional) Additional detail about the status.
Attr str language:
 (optional) The language used for the classifier.
class ClassifierList(classifiers)[source]

Bases: object

List of available classifiers.

Attr list[Classifier] classifiers:
 The classifiers available to the user. Returns an empty array if no classifiers are available.