ibm_watson.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, iam_apikey=None, iam_access_token=None, iam_url=None, iam_client_id=None, iam_client_secret=None, icp4d_access_token=None, icp4d_url=None, authentication_type=None)[source]¶ Bases:
ibm_cloud_sdk_core.base_service.BaseServiceThe Natural Language Classifier V1 service.
-
default_url= 'https://gateway.watsonplatform.net/natural-language-classifier/api'¶
-
classify(classifier_id, text, **kwargs)[source]¶ Classify a phrase.
Returns label information for the input. The status must be Available before you can use the classifier to classify text.
-
classify_collection(classifier_id, collection, **kwargs)[source]¶ 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
classifier_id (str) – Classifier ID to use.
collection (list[ClassifyInput]) – The submitted phrases.
headers (dict) – A dict containing the request headers
- Returns
A DetailedResponse containing the result, headers and HTTP status code.
- Return type
DetailedResponse
-
create_classifier(metadata, training_data, **kwargs)[source]¶ Create classifier.
Sends data to create and train a classifier and returns information about the new classifier.
- Parameters
metadata (file) – 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. Supported languages are English (en), Arabic (ar), French (fr), German, (de), Italian (it), Japanese (ja), Korean (ko), Brazilian Portuguese (pt), and Spanish (es). :param file training_data: 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/services/natural-language-classifier?topic=natural-language-classifier-using-your-data). :param dict headers: A dict containing the request headers :return: A DetailedResponse containing the result, headers and HTTP status code. :rtype: DetailedResponse
-
list_classifiers(**kwargs)[source]¶ List classifiers.
Returns an empty array if no classifiers are available.
- Parameters
headers (dict) – A dict containing the request headers
- Returns
A DetailedResponse containing the result, headers and HTTP status code.
- Return type
DetailedResponse
-
-
class
Classification(classifier_id=None, url=None, text=None, top_class=None, classes=None)[source]¶ Bases:
objectResponse 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
ClassificationCollection(classifier_id=None, url=None, collection=None)[source]¶ Bases:
objectResponse from the classifier for multiple phrases.
- Attr str classifier_id
(optional) Unique identifier for this classifier.
- Attr str url
(optional) Link to the classifier.
- Attr list[CollectionItem] collection
(optional) An array of classifier responses for
each submitted phrase.
-
class
ClassifiedClass(confidence=None, class_name=None)[source]¶ Bases:
objectClass 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:
objectA 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:
objectList of available classifiers.
- Attr list[Classifier] classifiers
The classifiers available to the user. Returns an
empty array if no classifiers are available.
-
class
ClassifyInput(text)[source]¶ Bases:
objectRequest payload to classify.
- Attr str text
The submitted phrase. The maximum length is 2048 characters.
-
class
CollectionItem(text=None, top_class=None, classes=None)[source]¶ Bases:
objectResponse from the classifier for a phrase in a collection.
- Attr str text
(optional) The submitted phrase. The maximum length is 2048
characters. :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.