def sample_extractive_summarization():
from azure.core.credentials import AzureKeyCredential
from azure.ai.textanalytics import (
TextAnalyticsClient,
ExtractSummaryAction
)
endpoint = os.environ["AZURE_TEXT_ANALYTICS_ENDPOINT"]
key = os.environ["AZURE_TEXT_ANALYTICS_KEY"]
text_analytics_client = TextAnalyticsClient(
endpoint=endpoint,
credential=AzureKeyCredential(key),
)
document = [
"At Microsoft, we have been on a quest to advance AI beyond existing techniques, by taking a more holistic, "
"human-centric approach to learning and understanding. As Chief Technology Officer of Azure AI Cognitive "
"Services, I have been working with a team of amazing scientists and engineers to turn this quest into a "
"reality. In my role, I enjoy a unique perspective in viewing the relationship among three attributes of "
"human cognition: monolingual text (X), audio or visual sensory signals, (Y) and multilingual (Z). At the "
"intersection of all three, there's magic-what we call XYZ-code as illustrated in Figure 1-a joint "
"representation to create more powerful AI that can speak, hear, see, and understand humans better. "
"We believe XYZ-code will enable us to fulfill our long-term vision: cross-domain transfer learning, "
"spanning modalities and languages. The goal is to have pretrained models that can jointly learn "
"representations to support a broad range of downstream AI tasks, much in the way humans do today. "
"Over the past five years, we have achieved human performance on benchmarks in conversational speech "
"recognition, machine translation, conversational question answering, machine reading comprehension, "
"and image captioning. These five breakthroughs provided us with strong signals toward our more ambitious "
"aspiration to produce a leap in AI capabilities, achieving multisensory and multilingual learning that "
"is closer in line with how humans learn and understand. I believe the joint XYZ-code is a foundational "
"component of this aspiration, if grounded with external knowledge sources in the downstream AI tasks."
]
poller = text_analytics_client.begin_analyze_actions(
document,
actions=[
ExtractSummaryAction(),
],
)
document_results = poller.result()
for result in document_results:
extract_summary_result = result[0] # first document, first result
if extract_summary_result.is_error:
print("...Is an error with code '{}' and message '{}'".format(
extract_summary_result.code, extract_summary_result.message
))
else:
print("Summary extracted: \n{}".format(
" ".join([sentence.text for sentence in extract_summary_result.sentences]))
)
def sample_classify_document_multi_categories():
from azure.core.credentials import AzureKeyCredential
from azure.ai.textanalytics import (TextAnalyticsClient,
MultiCategoryClassifyAction)
endpoint = os.environ["AZURE_TEXT_ANALYTICS_ENDPOINT"]
key = os.environ["AZURE_TEXT_ANALYTICS_KEY"]
project_name = os.environ["MULTI_CATEGORY_CLASSIFY_PROJECT_NAME"]
deployed_model_name = os.environ["MULTI_CATEGORY_CLASSIFY_DEPLOYMENT_NAME"]
path_to_sample_document = os.path.abspath(
os.path.join(
os.path.abspath(__file__),
"..",
"./text_samples/custom_classify_sample.txt",
))
text_analytics_client = TextAnalyticsClient(
endpoint=endpoint,
credential=AzureKeyCredential(key),
)
with open(path_to_sample_document, "r") as fd:
document = [fd.read()]
poller = text_analytics_client.begin_analyze_actions(
document,
actions=[
MultiCategoryClassifyAction(project_name=project_name,
deployment_name=deployed_model_name),
],
)
document_results = poller.result()
for doc, classification_results in zip(document, document_results):
for classification_result in classification_results:
if not classification_result.is_error:
classifications = classification_result.classifications
print(
"\nThe movie plot '{}' was classified as the following genres:\n"
.format(doc))
for classification in classifications:
print("'{}' with confidence score {}.".format(
classification.category,
classification.confidence_score))
else:
print(
"Movie plot '{}' has an error with code '{}' and message '{}'"
.format(doc, classification_result.code,
classification_result.message))
def sample_recognize_custom_entities():
from azure.core.credentials import AzureKeyCredential
from azure.ai.textanalytics import (
TextAnalyticsClient,
RecognizeCustomEntitiesAction,
)
endpoint = os.environ["AZURE_TEXT_ANALYTICS_ENDPOINT"]
key = os.environ["AZURE_TEXT_ANALYTICS_KEY"]
project_name = os.environ["CUSTOM_ENTITIES_PROJECT_NAME"]
deployed_model_name = os.environ["CUSTOM_ENTITIES_DEPLOYMENT_NAME"]
path_to_sample_document = os.path.abspath(
os.path.join(
os.path.abspath(__file__),
"..",
"./text_samples/custom_entities_sample.txt",
))
text_analytics_client = TextAnalyticsClient(
endpoint=endpoint,
credential=AzureKeyCredential(key),
)
with open(path_to_sample_document) as fd:
document = [fd.read()]
poller = text_analytics_client.begin_analyze_actions(
document,
actions=[
RecognizeCustomEntitiesAction(project_name=project_name,
deployment_name=deployed_model_name),
],
)
document_results = poller.result()
for result in document_results:
custom_entities_result = result[0] # first document, first result
if not custom_entities_result.is_error:
for entity in custom_entities_result.entities:
print(
"Entity '{}' has category '{}' with confidence score of '{}'"
.format(entity.text, entity.category,
entity.confidence_score))
else:
print("...Is an error with code '{}' and message '{}'".format(
custom_entities_result.code, custom_entities_result.message))
def sample_model_version():
print("--------------Choosing model_version sample--------------")
from azure.core.credentials import AzureKeyCredential
from azure.ai.textanalytics import TextAnalyticsClient, RecognizeEntitiesAction
endpoint = os.environ["AZURE_TEXT_ANALYTICS_ENDPOINT"]
key = os.environ["AZURE_TEXT_ANALYTICS_KEY"]
text_analytics_client = TextAnalyticsClient(
endpoint=endpoint, credential=AzureKeyCredential(key))
documents = [
"I work for Foo Company, and we hired Contoso for our annual founding ceremony. The food \
was amazing and we all can't say enough good words about the quality and the level of service."
]
print("\nSetting model_version='latest' with recognize_entities")
result = text_analytics_client.recognize_entities(documents,
model_version="latest")
result = [review for review in result if not review.is_error]
print("...Results of Recognize Entities:")
for review in result:
for entity in review.entities:
print(
f"......Entity '{entity.text}' has category '{entity.category}'"
)
print(
"\nSetting model_version='latest' with recognize entities action in begin_analyze_actions"
)
poller = text_analytics_client.begin_analyze_actions(
documents, actions=[RecognizeEntitiesAction(model_version="latest")])
print("...Results of Recognize Entities Action:")
document_results = poller.result()
for action_results in document_results:
recognize_entities_result = action_results[0]
if recognize_entities_result.is_error:
print("......Is an error with code '{}' and message '{}'".format(
recognize_entities_result.code,
recognize_entities_result.message))
else:
for entity in recognize_entities_result.entities:
print(
f"......Entity '{entity.text}' has category '{entity.category}'"
)
def analyze(self):
# [START analyze]
from azure.core.credentials import AzureKeyCredential
from azure.ai.textanalytics import (
TextAnalyticsClient,
RecognizeEntitiesAction,
RecognizeLinkedEntitiesAction,
RecognizePiiEntitiesAction,
ExtractKeyPhrasesAction,
AnalyzeSentimentAction,
PiiEntityDomainType,
)
endpoint = os.environ["AZURE_TEXT_ANALYTICS_ENDPOINT"]
key = os.environ["AZURE_TEXT_ANALYTICS_KEY"]
text_analytics_client = TextAnalyticsClient(
endpoint=endpoint,
credential=AzureKeyCredential(key),
)
documents = [
"We went to Contoso Steakhouse located at midtown NYC last week for a dinner party, and we adore the spot! \
They provide marvelous food and they have a great menu. The chief cook happens to be the owner (I think his name is John Doe) \
and he is super nice, coming out of the kitchen and greeted us all. We enjoyed very much dining in the place! \
The Sirloin steak I ordered was tender and juicy, and the place was impeccably clean. You can even pre-order from their \
online menu at www.contososteakhouse.com, call 312-555-0176 or send email to [email protected]! \
The only complaint I have is the food didn't come fast enough. Overall I highly recommend it!"
]
poller = text_analytics_client.begin_analyze_actions(
documents,
display_name="Sample Text Analysis",
actions=[
RecognizeEntitiesAction(),
RecognizePiiEntitiesAction(domain_filter=PiiEntityDomainType.
PROTECTED_HEALTH_INFORMATION),
ExtractKeyPhrasesAction(),
RecognizeLinkedEntitiesAction(),
AnalyzeSentimentAction()
],
)
result = poller.result()
action_results = [
action_result for action_result in list(result)
if not action_result.is_error
]
first_action_result = action_results[0]
print("Results of Entities Recognition action:")
docs = [
doc for doc in first_action_result.document_results
if not doc.is_error
]
for idx, doc in enumerate(docs):
print("\nDocument text: {}".format(documents[idx]))
for entity in doc.entities:
print("Entity: {}".format(entity.text))
print("...Category: {}".format(entity.category))
print("...Confidence Score: {}".format(
entity.confidence_score))
print("...Offset: {}".format(entity.offset))
print("...Length: {}".format(entity.length))
print("------------------------------------------")
second_action_result = action_results[1]
print("Results of PII Entities Recognition action:")
docs = [
doc for doc in second_action_result.document_results
if not doc.is_error
]
for idx, doc in enumerate(docs):
print("Document text: {}".format(documents[idx]))
print("Document text with redactions: {}".format(
doc.redacted_text))
for entity in doc.entities:
print("Entity: {}".format(entity.text))
print("...Category: {}".format(entity.category))
print("...Confidence Score: {}\n".format(
entity.confidence_score))
print("...Offset: {}".format(entity.offset))
print("...Length: {}".format(entity.length))
print("------------------------------------------")
third_action_result = action_results[2]
print("Results of Key Phrase Extraction action:")
docs = [
doc for doc in third_action_result.document_results
if not doc.is_error
]
for idx, doc in enumerate(docs):
print("Document text: {}\n".format(documents[idx]))
print("Key Phrases: {}\n".format(doc.key_phrases))
print("------------------------------------------")
fourth_action_result = action_results[3]
print("Results of Linked Entities Recognition action:")
docs = [
doc for doc in fourth_action_result.document_results
if not doc.is_error
]
for idx, doc in enumerate(docs):
print("Document text: {}\n".format(documents[idx]))
for linked_entity in doc.entities:
print("Entity name: {}".format(linked_entity.name))
print("...Data source: {}".format(linked_entity.data_source))
print("...Data source language: {}".format(
linked_entity.language))
print("...Data source entity ID: {}".format(
linked_entity.data_source_entity_id))
print("...Data source URL: {}".format(linked_entity.url))
print("...Document matches:")
for match in linked_entity.matches:
print("......Match text: {}".format(match.text))
print(".........Confidence Score: {}".format(
match.confidence_score))
print(".........Offset: {}".format(match.offset))
print(".........Length: {}".format(match.length))
print("------------------------------------------")
fifth_action_result = action_results[4]
print("Results of Sentiment Analysis action:")
docs = [
doc for doc in fifth_action_result.document_results
if not doc.is_error
]
for doc in docs:
print("Overall sentiment: {}".format(doc.sentiment))
print("Scores: positive={}; neutral={}; negative={} \n".format(
doc.confidence_scores.positive,
doc.confidence_scores.neutral,
doc.confidence_scores.negative,
))
print("------------------------------------------")
def sample_analyze_actions():
# [START analyze]
from azure.core.credentials import AzureKeyCredential
from azure.ai.textanalytics import (
TextAnalyticsClient,
RecognizeEntitiesAction,
RecognizeLinkedEntitiesAction,
RecognizePiiEntitiesAction,
ExtractKeyPhrasesAction,
AnalyzeSentimentAction,
)
endpoint = os.environ["AZURE_TEXT_ANALYTICS_ENDPOINT"]
key = os.environ["AZURE_TEXT_ANALYTICS_KEY"]
text_analytics_client = TextAnalyticsClient(
endpoint=endpoint,
credential=AzureKeyCredential(key),
)
documents = [
'We went to Contoso Steakhouse located at midtown NYC last week for a dinner party, and we adore the spot! '
'They provide marvelous food and they have a great menu. The chief cook happens to be the owner (I think his name is John Doe) '
'and he is super nice, coming out of the kitchen and greeted us all.',
'We enjoyed very much dining in the place! '
'The Sirloin steak I ordered was tender and juicy, and the place was impeccably clean. You can even pre-order from their '
'online menu at www.contososteakhouse.com, call 312-555-0176 or send email to [email protected]! '
'The only complaint I have is the food didn\'t come fast enough. Overall I highly recommend it!'
]
poller = text_analytics_client.begin_analyze_actions(
documents,
display_name="Sample Text Analysis",
actions=[
RecognizeEntitiesAction(),
RecognizePiiEntitiesAction(),
ExtractKeyPhrasesAction(),
RecognizeLinkedEntitiesAction(),
AnalyzeSentimentAction(),
],
)
document_results = poller.result()
for doc, action_results in zip(documents, document_results):
print(f"\nDocument text: {doc}")
recognize_entities_result = action_results[0]
print("...Results of Recognize Entities Action:")
if recognize_entities_result.is_error:
print("...Is an error with code '{}' and message '{}'".format(
recognize_entities_result.code,
recognize_entities_result.message))
else:
for entity in recognize_entities_result.entities:
print(f"......Entity: {entity.text}")
print(f".........Category: {entity.category}")
print(f".........Confidence Score: {entity.confidence_score}")
print(f".........Offset: {entity.offset}")
recognize_pii_entities_result = action_results[1]
print("...Results of Recognize PII Entities action:")
if recognize_pii_entities_result.is_error:
print("...Is an error with code '{}' and message '{}'".format(
recognize_pii_entities_result.code,
recognize_pii_entities_result.message))
else:
for entity in recognize_pii_entities_result.entities:
print(f"......Entity: {entity.text}")
print(f".........Category: {entity.category}")
print(f".........Confidence Score: {entity.confidence_score}")
extract_key_phrases_result = action_results[2]
print("...Results of Extract Key Phrases action:")
if extract_key_phrases_result.is_error:
print("...Is an error with code '{}' and message '{}'".format(
extract_key_phrases_result.code,
extract_key_phrases_result.message))
else:
print(
f"......Key Phrases: {extract_key_phrases_result.key_phrases}")
recognize_linked_entities_result = action_results[3]
print("...Results of Recognize Linked Entities action:")
if recognize_linked_entities_result.is_error:
print("...Is an error with code '{}' and message '{}'".format(
recognize_linked_entities_result.code,
recognize_linked_entities_result.message))
else:
for linked_entity in recognize_linked_entities_result.entities:
print(f"......Entity name: {linked_entity.name}")
print(f".........Data source: {linked_entity.data_source}")
print(
f".........Data source language: {linked_entity.language}")
print(
f".........Data source entity ID: {linked_entity.data_source_entity_id}"
)
print(f".........Data source URL: {linked_entity.url}")
print(".........Document matches:")
for match in linked_entity.matches:
print(f"............Match text: {match.text}")
print(
f"............Confidence Score: {match.confidence_score}"
)
print(f"............Offset: {match.offset}")
print(f"............Length: {match.length}")
analyze_sentiment_result = action_results[4]
print("...Results of Analyze Sentiment action:")
if analyze_sentiment_result.is_error:
print("...Is an error with code '{}' and message '{}'".format(
analyze_sentiment_result.code,
analyze_sentiment_result.message))
else:
print(
f"......Overall sentiment: {analyze_sentiment_result.sentiment}"
)
print(
"......Scores: positive={}; neutral={}; negative={} \n".format(
analyze_sentiment_result.confidence_scores.positive,
analyze_sentiment_result.confidence_scores.neutral,
analyze_sentiment_result.confidence_scores.negative,
))
print("------------------------------------------")
