def test_entities_tostring(analysis):
assert analysis.entities_tostring([
Entity(name="General Motors",
entity_type="ORGANIZATION",
metadata={
"mid": "/m/035nm",
"wikipedia_url":
"http://en.wikipedia.org/wiki/General_Motors"
},
salience=0.33838183,
mentions=["General Motors"]),
Entity(name="jobs",
entity_type="OTHER",
metadata={"wikipedia_url": None},
salience=0.31634554,
mentions=["jobs"])
]) == ('[{name: "General Motors",'
' entity_type: "ORGANIZATION",'
' wikipedia_url: "http://en.wikipedia.org/wiki/General_Motors",'
' metadata: {"mid": "/m/035nm"},'
' salience: 0.33838183,'
' mentions: ["General Motors"]}, '
'{name: "jobs",'
' entity_type: "OTHER",'
' wikipedia_url: None,'
' metadata: {},'
' salience: 0.31634554,'
' mentions: ["jobs"]}]')
assert analysis.entities_tostring([]) == "[]"
def analyze_entities(self):
"""Analyze the entities in the current document.
Finds named entities (currently finds proper names as of August 2016)
in the text, entity types, salience, mentions for each entity, and
other properties.
.. _analyzeEntities: https://cloud.google.com/natural-language/\
reference/rest/v1/documents/analyzeEntities
See `analyzeEntities`_.
:rtype: list
:returns: A list of :class:`~.language.entity.Entity` returned from
the API.
"""
data = {
'document': self._to_dict(),
'encodingType': self.encoding,
}
api_response = self.client._connection.api_request(
method='POST', path='analyzeEntities', data=data)
return [
Entity.from_api_repr(entity) for entity in api_response['entities']
]
def test_constructor(self):
from google.cloud.language.api_responses import EntityResponse
from google.cloud.language.entity import Entity
entity_response = EntityResponse(
entities=[Entity.from_api_repr(self.ENTITY_DICT)],
language='en',
)
self._verify_entity_response(entity_response)
def from_api_repr(cls, payload):
"""Return an entity response from a JSON representation.
:type payload: dict
:param payload: A dictionary representing the response.
:rtype: :class:`~.language.entity.Entity`
:returns: An ``Entity`` object.
"""
return cls(
entities=[Entity.from_api_repr(i) for i in payload['entities']],
language=payload['language'],
)
def analyze_entities(self):
"""Analyze the entities in the current document.
Finds named entities (currently finds proper names as of August 2016)
in the text, entity types, salience, mentions for each entity, and
other properties.
.. _analyzeEntities: https://cloud.google.com/natural-language/\
reference/rest/v1/documents/analyzeEntities
See `analyzeEntities`_.
:rtype: list
:returns: A list of :class:`~.language.entity.Entity` returned from
the API.
"""
data = {
'document': self._to_dict(),
'encodingType': self.encoding,
}
api_response = self.client._connection.api_request(
method='POST', path='analyzeEntities', data=data)
return [Entity.from_api_repr(entity)
for entity in api_response['entities']]
def annotate_text(self,
include_syntax=True,
include_entities=True,
include_sentiment=True):
"""Advanced natural language API: document syntax and other features.
Includes the full functionality of :meth:`analyze_entities` and
:meth:`analyze_sentiment`, enabled by the flags
``include_entities`` and ``include_sentiment`` respectively.
In addition ``include_syntax`` adds a new feature that analyzes
the document for semantic and syntacticinformation.
.. note::
This API is intended for users who are familiar with machine
learning and need in-depth text features to build upon.
.. _annotateText: https://cloud.google.com/natural-language/\
reference/rest/v1/documents/annotateText
See `annotateText`_.
:type include_syntax: bool
:param include_syntax: (Optional) Flag to enable syntax analysis
of the current document.
:type include_entities: bool
:param include_entities: (Optional) Flag to enable entity extraction
from the current document.
:type include_sentiment: bool
:param include_sentiment: (Optional) Flag to enable sentiment
analysis of the current document.
:rtype: :class:`Annotations`
:returns: A tuple of each of the four values returned from the API:
sentences, tokens, sentiment and entities.
"""
features = {}
if include_syntax:
features['extractSyntax'] = True
if include_entities:
features['extractEntities'] = True
if include_sentiment:
features['extractDocumentSentiment'] = True
data = {
'document': self._to_dict(),
'features': features,
'encodingType': self.encoding,
}
api_response = self.client._connection.api_request(method='POST',
path='annotateText',
data=data)
sentences = [
Sentence.from_api_repr(sentence)
for sentence in api_response['sentences']
]
tokens = [
Token.from_api_repr(token) for token in api_response['tokens']
]
sentiment_info = api_response.get('documentSentiment')
if sentiment_info is None:
sentiment = None
else:
sentiment = Sentiment.from_api_repr(sentiment_info)
entities = [
Entity.from_api_repr(entity) for entity in api_response['entities']
]
annotations = Annotations(
sentences=sentences,
tokens=tokens,
sentiment=sentiment,
entities=entities,
)
return annotations
def annotate_text(self, include_syntax=True, include_entities=True,
include_sentiment=True):
"""Advanced natural language API: document syntax and other features.
Includes the full functionality of :meth:`analyze_entities` and
:meth:`analyze_sentiment`, enabled by the flags
``include_entities`` and ``include_sentiment`` respectively.
In addition ``include_syntax`` adds a new feature that analyzes
the document for semantic and syntacticinformation.
.. note::
This API is intended for users who are familiar with machine
learning and need in-depth text features to build upon.
.. _annotateText: https://cloud.google.com/natural-language/\
reference/rest/v1/documents/annotateText
See `annotateText`_.
:type include_syntax: bool
:param include_syntax: (Optional) Flag to enable syntax analysis
of the current document.
:type include_entities: bool
:param include_entities: (Optional) Flag to enable entity extraction
from the current document.
:type include_sentiment: bool
:param include_sentiment: (Optional) Flag to enable sentiment
analysis of the current document.
:rtype: :class:`Annotations`
:returns: A tuple of each of the four values returned from the API:
sentences, tokens, sentiment and entities.
"""
features = {}
if include_syntax:
features['extractSyntax'] = True
if include_entities:
features['extractEntities'] = True
if include_sentiment:
features['extractDocumentSentiment'] = True
data = {
'document': self._to_dict(),
'features': features,
'encodingType': self.encoding,
}
api_response = self.client._connection.api_request(
method='POST', path='annotateText', data=data)
sentences = [Sentence.from_api_repr(sentence)
for sentence in api_response['sentences']]
tokens = [Token.from_api_repr(token)
for token in api_response['tokens']]
sentiment_info = api_response.get('documentSentiment')
if sentiment_info is None:
sentiment = None
else:
sentiment = Sentiment.from_api_repr(sentiment_info)
entities = [Entity.from_api_repr(entity)
for entity in api_response['entities']]
annotations = Annotations(
sentences=sentences,
tokens=tokens,
sentiment=sentiment,
entities=entities,
)
return annotations
