async def test_all_successful_passing_text_document_input(self, client):
docs = [
TextDocumentInput(
id="1",
text="Microsoft was founded by Bill Gates and Paul Allen"),
TextDocumentInput(
id="2",
text="Microsoft fue fundado por Bill Gates y Paul Allen")
]
response = await client.recognize_linked_entities(docs)
for doc in response:
assert len(doc.entities) == 3
for entity in doc.entities:
assert entity.name is not None
assert entity.language is not None
assert entity.data_source_entity_id is not None
assert entity.url is not None
assert entity.data_source is not None
assert entity.matches is not None
for match in entity.matches:
assert match.offset is not None
async def test_mixing_inputs(self, client):
docs = [
{
"id": "1",
"text": "Microsoft was founded by Bill Gates and Paul Allen."
},
TextDocumentInput(
id="2",
text=
"I did not like the hotel we stayed at. It was too expensive."
), u"You cannot mix string input with the above inputs"
]
with self.assertRaises(TypeError):
response = await client.extract_key_phrases(docs)
async def test_all_successful_passing_text_document_input(self, client):
docs = [
TextDocumentInput(id="1", text="My SSN is 859-98-0987."),
TextDocumentInput(id="2", text="Your ABA number - 111000025 - is the first 9 digits in the lower left hand corner of your personal check."),
TextDocumentInput(id="3", text="Is 998.214.865-68 your Brazilian CPF number?")
]
response = await client.recognize_pii_entities(docs, show_stats=True)
self.assertEqual(response[0].entities[0].text, "859-98-0987")
self.assertEqual(response[0].entities[0].category, "USSocialSecurityNumber")
self.assertEqual(response[1].entities[0].text, "111000025")
# self.assertEqual(response[1].entities[0].category, "ABA Routing Number") # Service is currently returning PhoneNumber here
# commenting out brazil cpf, currently service is not returning it
# self.assertEqual(response[2].entities[0].text, "998.214.865-68")
# self.assertEqual(response[2].entities[0].category, "Brazil CPF Number")
for doc in response:
self.assertIsNotNone(doc.id)
self.assertIsNotNone(doc.statistics)
for entity in doc.entities:
self.assertIsNotNone(entity.text)
self.assertIsNotNone(entity.category)
self.assertIsNotNone(entity.offset)
self.assertIsNotNone(entity.confidence_score)
async def test_mixing_inputs(self, client):
docs = [
{
"id": "1",
"text": "Microsoft was founded by Bill Gates and Paul Allen."
},
TextDocumentInput(
id="2",
text=
"I did not like the hotel we stayed at. It was too expensive."
), "You cannot mix string input with the above inputs"
]
with pytest.raises(TypeError):
response = await client.recognize_linked_entities(docs)
async def test_all_successful_passing_text_document_input(self, resource_group, location, text_analytics_account, text_analytics_account_key):
text_analytics = TextAnalyticsClient(text_analytics_account, TextAnalyticsApiKeyCredential(text_analytics_account_key))
docs = [
TextDocumentInput(id="1", text="I should take my cat to the veterinarian"),
TextDocumentInput(id="2", text="Este es un document escrito en Español."),
TextDocumentInput(id="3", text="猫は幸せ"),
TextDocumentInput(id="4", text="Fahrt nach Stuttgart und dann zum Hotel zu Fu.")
]
response = await text_analytics.detect_language(docs)
self.assertEqual(response[0].primary_language.name, "English")
self.assertEqual(response[1].primary_language.name, "Spanish")
self.assertEqual(response[2].primary_language.name, "Japanese")
self.assertEqual(response[3].primary_language.name, "German")
self.assertEqual(response[0].primary_language.iso6391_name, "en")
self.assertEqual(response[1].primary_language.iso6391_name, "es")
self.assertEqual(response[2].primary_language.iso6391_name, "ja")
self.assertEqual(response[3].primary_language.iso6391_name, "de")
for doc in response:
self.assertIsNotNone(doc.primary_language.score)
def test_whole_batch_language_hint_and_obj_input(
self, resource_group, location, text_analytics_account,
text_analytics_account_key):
text_analytics = TextAnalyticsClient(
text_analytics_account,
TextAnalyticsApiKeyCredential(text_analytics_account_key))
def callback(resp):
language_str = "\"language\": \"de\""
language = resp.http_request.body.count(language_str)
self.assertEqual(language, 3)
docs = [
TextDocumentInput(
id="1", text="I should take my cat to the veterinarian."),
TextDocumentInput(id="4",
text="Este es un document escrito en Español."),
TextDocumentInput(id="3", text="猫は幸せ"),
]
response = text_analytics.analyze_sentiment(docs,
language="de",
raw_response_hook=callback)
async def test_whole_batch_language_hint_and_obj_per_item_hints(
self, client):
def callback(resp):
language_str = "\"language\": \"es\""
language = resp.http_request.body.count(language_str)
self.assertEqual(language, 2)
language_str = "\"language\": \"en\""
language = resp.http_request.body.count(language_str)
self.assertEqual(language, 1)
docs = [
TextDocumentInput(id="1",
text="I should take my cat to the veterinarian.",
language="es"),
TextDocumentInput(id="2",
text="Este es un document escrito en Español.",
language="es"),
TextDocumentInput(id="3", text="猫は幸せ"),
]
response = await client.extract_key_phrases(docs,
language="en",
raw_response_hook=callback)
def test_all_successful_passing_text_document_input(self, client):
docs = [
TextDocumentInput(id="1", text="My SSN is 859-98-0987."),
TextDocumentInput(id="2", text="Your ABA number - 111000025 - is the first 9 digits in the lower left hand corner of your personal check."),
TextDocumentInput(id="3", text="Is 998.214.865-68 your Brazilian CPF number?")
]
response = client.recognize_pii_entities(docs, show_stats=True)
assert response[0].entities[0].text == "859-98-0987"
assert response[0].entities[0].category == "USSocialSecurityNumber"
assert response[1].entities[0].text == "111000025"
# assert response[1].entities[0].category == "ABA Routing Number" # Service is currently returning PhoneNumber here
# commenting out brazil cpf, currently service is not returning it
# assert response[2].entities[0].text == "998.214.865-68"
# assert response[2].entities[0].category == "Brazil CPF Number"
for doc in response:
assert doc.id is not None
assert doc.statistics is not None
for entity in doc.entities:
assert entity.text is not None
assert entity.category is not None
assert entity.offset is not None
assert entity.confidence_score is not None
async def test_all_successful_passing_text_document_input(self, client):
docs = [
TextDocumentInput(
id="1",
text="Patient does not suffer from high blood pressure."),
TextDocumentInput(
id="2", text="Prescribed 100mg ibuprofen, taken twice daily."),
]
async with client:
result = await (await client.begin_analyze_healthcare_entities(
docs, polling_interval=self._interval())).result()
self.assertIsNone(result.statistics) # show_stats=False by default
response = []
async for r in result:
response.append(r)
for doc in response:
self.assertIsNotNone(doc.id)
self.assertIsNone(doc.statistics)
self.assertIsNotNone(doc.entities)
self.assertEqual(len(response[0].entities), 2)
entity1 = list(filter(lambda x: x.text == "high",
response[0].entities))[0]
entity2 = list(
filter(lambda x: x.text == "blood pressure",
response[0].entities))[0]
self.assertEqual(len(entity1.related_entities), 1)
related_entity, relation_type = entity1.related_entities.popitem()
self.assertEqual(related_entity, entity2)
self.assertEqual(relation_type, "ValueOfExamination")
self.assertEqual(len(entity2.related_entities), 0)
def test_all_successful_passing_text_document_input(self, client):
docs = [
TextDocumentInput(
id="1",
text="Microsoft was founded by Bill Gates and Paul Allen."),
TextDocumentInput(
id="2",
text=
"I did not like the hotel we stayed at. It was too expensive."
),
TextDocumentInput(
id="3",
text=
"The restaurant had really good food. I recommend you try it."
),
]
response = client.analyze_sentiment(docs)
assert response[0].sentiment == "neutral"
assert response[1].sentiment == "negative"
assert response[2].sentiment == "positive"
for doc in response:
self.validateConfidenceScores(doc.confidence_scores)
assert doc.sentences is not None
assert len(response[0].sentences) == 1
assert response[0].sentences[
0].text == "Microsoft was founded by Bill Gates and Paul Allen."
assert len(response[1].sentences) == 2
assert response[1].sentences[
0].text == "I did not like the hotel we stayed at."
assert response[1].sentences[1].text == "It was too expensive."
assert len(response[2].sentences) == 2
assert response[2].sentences[
0].text == "The restaurant had really good food."
assert response[2].sentences[1].text == "I recommend you try it."
def test_whole_batch_language_hint_and_obj_input(self, client):
def callback(resp):
language_str = "\"language\": \"de\""
language = resp.http_request.body.count(language_str)
self.assertEqual(language, 3)
docs = [
TextDocumentInput(
id="1", text="I should take my cat to the veterinarian."),
TextDocumentInput(id="4",
text="Este es un document escrito en Español."),
TextDocumentInput(id="3", text="猫は幸せ"),
]
response = list(
client.begin_analyze(
docs,
entities_recognition_tasks=[EntitiesRecognitionTask()],
key_phrase_extraction_tasks=[KeyPhraseExtractionTask()],
pii_entities_recognition_tasks=[PiiEntitiesRecognitionTask()],
language="en",
polling_interval=self._interval(),
).result())
task_types = [
"entities_recognition_results", "key_phrase_extraction_results",
"pii_entities_recognition_results"
]
for task_type in task_types:
task_results = getattr(response[0], task_type)
self.assertEqual(len(task_results), 1)
results = task_results[0].results
for r in results:
self.assertFalse(r.is_error)
def test_mixing_inputs(self, client):
docs = [
{
"id": "1",
"text": "Microsoft was founded by Bill Gates and Paul Allen."
},
TextDocumentInput(
id="2",
text=
"I did not like the hotel we stayed at. It was too expensive."
), u"You cannot mix string input with the above inputs"
]
with self.assertRaises(TypeError):
response = client.begin_analyze_healthcare_entities(
docs, polling_interval=self._interval())
async def test_all_successful_passing_text_document_input(
self, resource_group, location, text_analytics_account,
text_analytics_account_key):
text_analytics = TextAnalyticsClient(
text_analytics_account,
TextAnalyticsApiKeyCredential(text_analytics_account_key))
docs = [
TextDocumentInput(id="1", text="My SSN is 555-55-5555."),
TextDocumentInput(
id="2",
text=
"Your ABA number - 111000025 - is the first 9 digits in the lower left hand corner of your personal check."
),
TextDocumentInput(
id="3", text="Is 998.214.865-68 your Brazilian CPF number?")
]
response = await text_analytics.recognize_pii_entities(docs,
show_stats=True)
self.assertEqual(response[0].entities[0].text, "555-55-5555")
self.assertEqual(response[0].entities[0].category,
"U.S. Social Security Number (SSN)")
self.assertEqual(response[1].entities[0].text, "111000025")
# self.assertEqual(response[1].entities[0].category, "ABA Routing Number") # Service is currently returning PhoneNumber here
self.assertEqual(response[2].entities[0].text, "998.214.865-68")
self.assertEqual(response[2].entities[0].category, "Brazil CPF Number")
for doc in response:
self.assertIsNotNone(doc.id)
self.assertIsNotNone(doc.statistics)
for entity in doc.entities:
self.assertIsNotNone(entity.text)
self.assertIsNotNone(entity.category)
self.assertIsNotNone(entity.grapheme_offset)
self.assertIsNotNone(entity.grapheme_length)
self.assertIsNotNone(entity.confidence_score)
async def test_output_same_order_as_input_multiple_tasks(self, client):
docs = [
TextDocumentInput(id="1", text="one"),
TextDocumentInput(id="2", text="two"),
TextDocumentInput(id="3", text="three"),
TextDocumentInput(id="4", text="four"),
TextDocumentInput(id="5", text="five")
]
async with client:
response = await (await client.begin_analyze_batch_actions(
docs,
actions=[
RecognizePiiEntitiesAction(),
ExtractKeyPhrasesAction(),
RecognizePiiEntitiesAction(model_version="bad"),
],
polling_interval=self._interval()
)).result()
action_results = []
async for p in response:
action_results.append(p)
assert len(action_results) == 3
action_result = action_results[0]
assert action_results[0].action_type == AnalyzeBatchActionsType.RECOGNIZE_PII_ENTITIES
assert action_results[1].action_type == AnalyzeBatchActionsType.EXTRACT_KEY_PHRASES
assert action_results[2].is_error
assert all([action_result for action_result in action_results if not action_result.is_error and len(action_result.document_results) == len(docs)])
for action_result in action_results:
if not action_result.is_error:
for idx, doc in enumerate(action_result.document_results):
self.assertEqual(str(idx + 1), doc.id)
def test_all_successful_passing_text_document_input(self, client):
docs = [
TextDocumentInput(id="1",
text="I should take my cat to the veterinarian"),
TextDocumentInput(id="2",
text="Este es un document escrito en Español."),
TextDocumentInput(id="3", text="猫は幸せ"),
TextDocumentInput(
id="4", text="Fahrt nach Stuttgart und dann zum Hotel zu Fu.")
]
response = client.detect_language(docs)
self.assertEqual(response[0].primary_language.name, "English")
self.assertEqual(response[1].primary_language.name, "Spanish")
self.assertEqual(response[2].primary_language.name, "Japanese")
self.assertEqual(response[3].primary_language.name, "German")
self.assertEqual(response[0].primary_language.iso6391_name, "en")
self.assertEqual(response[1].primary_language.iso6391_name, "es")
self.assertEqual(response[2].primary_language.iso6391_name, "ja")
self.assertEqual(response[3].primary_language.iso6391_name, "de")
for doc in response:
self.assertIsNotNone(doc.primary_language.score)
async def test_all_successful_passing_text_document_input(
self, resource_group, location, text_analytics_account,
text_analytics_account_key):
text_analytics = TextAnalyticsClient(
text_analytics_account,
AzureKeyCredential(text_analytics_account_key))
docs = [
TextDocumentInput(
id="1",
text="Microsoft was founded by Bill Gates and Paul Allen",
language="en"),
TextDocumentInput(
id="2",
text="Microsoft fue fundado por Bill Gates y Paul Allen",
language="es")
]
response = await text_analytics.extract_key_phrases(docs)
for phrases in response:
self.assertIn("Paul Allen", phrases.key_phrases)
self.assertIn("Bill Gates", phrases.key_phrases)
self.assertIn("Microsoft", phrases.key_phrases)
self.assertIsNotNone(phrases.id)
def test_all_successful_passing_text_document_input(self, client):
docs = [
TextDocumentInput(id="1", text="Microsoft was founded by Bill Gates and Paul Allen."),
TextDocumentInput(id="2", text="I did not like the hotel we stayed at. It was too expensive."),
TextDocumentInput(id="3", text="The restaurant had really good food. I recommend you try it."),
]
response = client.analyze_sentiment(docs)
self.assertEqual(response[0].sentiment, "neutral")
self.assertEqual(response[1].sentiment, "negative")
self.assertEqual(response[2].sentiment, "positive")
for doc in response:
self.assertIsNotNone(doc.confidence_scores)
self.assertIsNotNone(doc.sentences)
self.assertEqual(len(response[0].sentences), 1)
self.assertEqual(response[0].sentences[0].text, "Microsoft was founded by Bill Gates and Paul Allen.")
self.assertEqual(len(response[1].sentences), 2)
self.assertEqual(response[1].sentences[0].text, "I did not like the hotel we stayed at.")
self.assertEqual(response[1].sentences[1].text, "It was too expensive.")
self.assertEqual(len(response[2].sentences), 2)
self.assertEqual(response[2].sentences[0].text, "The restaurant had really good food.")
self.assertEqual(response[2].sentences[1].text, "I recommend you try it.")
def test_all_successful_passing_text_document_input(self, client):
docs = [
TextDocumentInput(
id="1",
text="Microsoft was founded by Bill Gates and Paul Allen"),
TextDocumentInput(
id="2",
text="Microsoft fue fundado por Bill Gates y Paul Allen")
]
response = client.recognize_linked_entities(docs)
for doc in response:
self.assertEqual(len(doc.entities), 3)
for entity in doc.entities:
self.assertIsNotNone(entity.name)
self.assertIsNotNone(entity.language)
self.assertIsNotNone(entity.data_source_entity_id)
self.assertIsNotNone(entity.url)
self.assertIsNotNone(entity.data_source)
self.assertIsNotNone(entity.matches)
for match in entity.matches:
self.assertIsNotNone(match.offset)
self.assertIsNotNone(match.length)
self.assertNotEqual(match.length, 0)
def test_mixing_inputs(self, client):
docs = [
{"id": "1", "text": "Microsoft was founded by Bill Gates and Paul Allen."},
TextDocumentInput(id="2", text="I did not like the hotel we stayed at. It was too expensive."),
u"You cannot mix string input with the above inputs"
]
with self.assertRaises(TypeError):
response = client.begin_analyze_batch_actions(
docs,
actions=[
RecognizeEntitiesAction(),
ExtractKeyPhrasesAction(),
RecognizePiiEntitiesAction(),
],
polling_interval=self._interval(),
).result()
def test_mixing_inputs(self, resource_group, location,
text_analytics_account, text_analytics_account_key):
text_analytics = TextAnalyticsClient(text_analytics_account,
text_analytics_account_key)
docs = [
{
"id": "1",
"text": "Microsoft was founded by Bill Gates and Paul Allen."
},
TextDocumentInput(
id="2",
text=
"I did not like the hotel we stayed it. It was too expensive."
), u"You cannot mix string input with the above inputs"
]
with self.assertRaises(TypeError):
response = text_analytics.analyze_sentiment(docs)
def test_mixing_inputs(self, client):
docs = [
{
"id": "1",
"text": "Microsoft was founded by Bill Gates and Paul Allen."
},
TextDocumentInput(
id="2",
text=
"I did not like the hotel we stayed at. It was too expensive."
), u"You cannot mix string input with the above inputs"
]
with self.assertRaises(TypeError):
response = client.begin_analyze(
docs,
entities_recognition_tasks=[EntitiesRecognitionTask()],
key_phrase_extraction_tasks=[KeyPhraseExtractionTask()],
pii_entities_recognition_tasks=[PiiEntitiesRecognitionTask()],
polling_interval=self._interval(),
).result()
