def test_rotate_subscription_key(self, resource_group, location,
text_analytics_account,
text_analytics_account_key):
credential = AzureKeyCredential(text_analytics_account_key)
client = TextAnalyticsClient(text_analytics_account, credential)
docs = [{
"id": "1",
"text": "I will go to the park."
}, {
"id": "2",
"text": "I did not like the hotel we stayed at."
}, {
"id": "3",
"text": "The restaurant had really good food."
}]
response = client.begin_analyze_healthcare(
docs, polling_interval=self._interval()).result()
self.assertIsNotNone(response)
credential.update("xxx") # Make authentication fail
with self.assertRaises(ClientAuthenticationError):
response = client.begin_analyze_healthcare(
docs, polling_interval=self._interval()).result()
credential.update(
text_analytics_account_key) # Authenticate successfully again
response = client.begin_analyze_healthcare(
docs, polling_interval=self._interval()).result()
self.assertIsNotNone(response)
def health_with_cancellation(self):
# [START health_with_cancellation]
from azure.core.credentials import AzureKeyCredential
from azure.ai.textanalytics import TextAnalyticsClient
endpoint = os.environ["AZURE_TEXT_ANALYTICS_ENDPOINT"]
key = os.environ["AZURE_TEXT_ANALYTICS_KEY"]
text_analytics_client = TextAnalyticsClient(
endpoint=endpoint,
credential=AzureKeyCredential(key),
)
documents = [
"RECORD #333582770390100 | MH | 85986313 | | 054351 | 2/14/2001 12:00:00 AM | \
CORONARY ARTERY DISEASE | Signed | DIS | Admission Date: 5/22/2001 \
Report Status: Signed Discharge Date: 4/24/2001 ADMISSION DIAGNOSIS: \
CORONARY ARTERY DISEASE. HISTORY OF PRESENT ILLNESS: \
The patient is a 54-year-old gentleman with a history of progressive angina over the past several months. \
The patient had a cardiac catheterization in July of this year revealing total occlusion of the RCA and \
50% left main disease , with a strong family history of coronary artery disease with a brother dying at \
the age of 52 from a myocardial infarction and another brother who is status post coronary artery bypass grafting. \
The patient had a stress echocardiogram done on July , 2001 , which showed no wall motion abnormalities ,\
but this was a difficult study due to body habitus. The patient went for six minutes with minimal ST depressions \
in the anterior lateral leads , thought due to fatigue and wrist pain , his anginal equivalent. Due to the patient's \
increased symptoms and family history and history left main disease with total occasional of his RCA was referred \
for revascularization with open heart surgery."
]
poller = text_analytics_client.begin_analyze_healthcare(documents)
text_analytics_client.begin_cancel_analyze_healthcare(poller)
poller.wait()
def main(config):
endpoint = config["azure"]["endpoint"]
key = config["azure"]["key"]
print("Endpoint: " + endpoint)
client = TextAnalyticsClient(endpoint=endpoint,
credential=AzureKeyCredential(key),
api_version="v3.1-preview.3")
#documents = [
# {"id":"1", "language":"en" ,"text":"Subject is taking 100mg of ibuprofen twice daily"},
#]
# load sample documents from docs folder
path = os.path.join(os.curdir, 'docs')
reader = sample_reader.SampleReader(path)
documents = reader.process()
poller = client.begin_analyze_healthcare(documents, show_stats=True)
result = poller.result()
docs = [doc for doc in result if not doc.is_error]
print("Results of Healthcare Analysis:")
for idx, doc in enumerate(docs):
for entity in doc.entities:
print("Entity: {}".format(entity.text))
print("...Category: {}".format(entity.category))
print("...Subcategory: {}".format(entity.subcategory))
print("...Offset: {}".format(entity.offset))
print("...Confidence score: {}".format(entity.confidence_score))
if entity.links is not None:
print("...Links:")
for link in entity.links:
print("......ID: {}".format(link.id))
print("......Data source: {}".format(link.data_source))
for relation in doc.relations:
print("Relation:")
print("...Source: {}".format(relation.source.text))
print("...Target: {}".format(relation.target.text))
print("...Type: {}".format(relation.relation_type))
print("...Bidirectional: {}".format(relation.is_bidirectional))
print("------------------------------------------")
def analyze_healthcare(self):
# [START analyze_healthcare]
from azure.core.credentials import AzureKeyCredential
from azure.ai.textanalytics import TextAnalyticsClient
endpoint = os.environ["AZURE_TEXT_ANALYTICS_ENDPOINT"]
key = os.environ["AZURE_TEXT_ANALYTICS_KEY"]
text_analytics_client = TextAnalyticsClient(
endpoint=endpoint,
credential=AzureKeyCredential(key),
api_version="v3.1-preview.3")
documents = ["Subject is taking 100mg of ibuprofen twice daily"]
poller = text_analytics_client.begin_analyze_healthcare(
documents, show_stats=True)
result = poller.result()
docs = [doc for doc in result if not doc.is_error]
print("Results of Healthcare Analysis:")
for idx, doc in enumerate(docs):
for entity in doc.entities:
print("Entity: {}".format(entity.text))
print("...Category: {}".format(entity.category))
print("...Subcategory: {}".format(entity.subcategory))
print("...Offset: {}".format(entity.offset))
print("...Confidence score: {}".format(
entity.confidence_score))
if entity.links is not None:
print("...Links:")
for link in entity.links:
print("......ID: {}".format(link.id))
print("......Data source: {}".format(link.data_source))
for relation in doc.relations:
print("Relation:")
print("...Source: {}".format(relation.source.text))
print("...Target: {}".format(relation.target.text))
print("...Type: {}".format(relation.relation_type))
print("...Bidirectional: {}".format(relation.is_bidirectional))
print("------------------------------------------")
def mars(config, argv):
if len(argv) < 4:
print("Invalid inputs")
return
dtStart = datetime.datetime.utcnow()
apiTime=[]
directory = argv[1]
inputFile = argv[2]
outputDir = argv[3]
endpoint = config["azure"]["endpoint"]
key = config["azure"]["key"]
client = TextAnalyticsClient(
endpoint=endpoint,
credential=AzureKeyCredential(key),
api_version="v3.1-preview.3")
# load sample documents from docs folder
path = os.path.join(directory, inputFile)
print("Input File: {}".format(path))
reader = mars_reader.MarsReader(path)
data = reader.process()
print("Documents read: {}".format(len(data)))
# temp take only a small part of total
data = data[100:200]
# --------------------------------------------------------------------
# per Microsoft documentation concerning document size a data limits
# [https://docs.microsoft.com/en-us/azure/cognitive-services/text-analytics/concepts/data-limits?tabs=version-3]
# size of individual document can not exceed 5,120 characters and
# the max number of docs to send per request is 10/1000 web vs container
# to accommodate larger documents and adhere to the request batch size each documents will be sent individually
# with larger documents being broken into multiple sub documents
# Note: Larger documents will utilize an a split at 4500 characters per block adn will seek to
# identify end of current sentence contexts within the same block
# --------------------------------------------------------------------
formatter = mars_formatter.MarsFormatter(limit=4500, noexceed=5100)
for d in data:
print("Document: {} -- processing".format(d["id"]))
batch = formatter.prepare(d)
chunks = []
offset = 0
# save chunking offsets so that positional findings in results can be re-attributed to orig
for item in batch:
chunk = {"id": item["id"], "start": offset, "length": len(item["text"])}
offset += len(item["text"])
chunks.append(chunk)
d["chunks"] = chunks
try:
dtApiStart = datetime.datetime.utcnow()
poller = client.begin_analyze_healthcare(batch, show_stats=True)
result = poller.result()
dtApiEnd = datetime.datetime.utcnow()
ttr = {"record": d["id"], "seconds": (dtApiEnd-dtApiStart).total_seconds()}
apiTime.append(ttr)
rez = []
results = [r for r in result if not r.is_error]
for idx, r in enumerate(results):
rezd = {"id": r.id}
entities = []
relations = []
for entity in r.entities:
e = {
"entity": entity.text,
"category": entity.category,
"subcategory": entity.subcategory,
"offset": entity.offset,
"score": entity.confidence_score,
"links": [],
}
if entity.links is not None:
links=[]
for link in entity.links:
l = {"id": link.id, "source": link.data_source}
links.append(l)
e["links"] = links
entities.append(e)
for relation in r.relations:
r = {
"source": relation.source.text,
"target": relation.target.text,
"type": relation.relation_type,
"is_bidirectional": relation.is_bidirectional
}
relations.append(r)
rezd["entities"] = entities
rezd["relations"] = relations
rez.append(rezd)
d["results"] = rez
d["error"] = False
except:
d["error"] = True
finally:
print("Document: {} --- complete".format(d["id"]))
dt = datetime.datetime.utcnow()
print("Process complete, Total run time {} seconds".format((dt-dtStart).total_seconds()))
eo = datetime.datetime(1970, 1, 1)
epoch = (dt - eo).total_seconds()
outputFile = os.path.join(directory, outputDir, "output_{}.json".format(epoch))
print("Writing output file [{}].".format(outputFile))
with open(outputFile, 'w+') as out:
json.dump(data, out)
apiMetricsFile = os.path.join(directory, outputDir, "metrics_{}.json".format(epoch))
with open(apiMetricsFile, 'w+') as out:
json.dump(apiTime, out)
def main(config):
endpoint = config["azure"]["endpoint"]
key = config["azure"]["key"]
print("Endpoint: " + endpoint)
client = TextAnalyticsClient(
endpoint=endpoint,
credential=AzureKeyCredential(key),
api_version="v3.1-preview.3")
# load sample documents from docs folder
path = os.path.join(os.curdir, 'docs')
reader = sample_reader.SampleReader(path)
data = reader.process()
print("Documents [{}]".format(len(data)))
# --------------------------------------------------------------------
# per Microsoft documentation concerning document size a data limits
# [https://docs.microsoft.com/en-us/azure/cognitive-services/text-analytics/concepts/data-limits?tabs=version-3]
# size of individual document can not exceed 5,120 characters and
# the max number of docs to send per request is 10/1000 web vs container
# to accommodate larger documents and adhere to the request batch size each documents will be sent individually
# with larger documents being broken into multiple sub documents
# Note: Larger documents will utilize an a split at 4000 characters per block adn will seek to
# identify end of current sentence contexts within the same block
# --------------------------------------------------------------------
formatter = sample_formatter.SampleFormatter(limit=4000, noexceed=5100)
for document in data:
print("Document:{} Size:{}".format(document["name"], len(document["text"])))
batch = formatter.prepare(document=document)
for item in batch:
print("Id:{} Size:{}".format(item["id"], len(item["text"])))
print("Processing batch with MS Text Analytics..")
poller = client.begin_analyze_healthcare(batch, show_stats=True)
result = poller.result()
print("Results of Healthcare Analysis:")
rez = []
docs = [doc for doc in result if not doc.is_error]
for idx, doc in enumerate(docs):
rezd = {"id": doc.id}
entities=[]
relations=[]
for entity in doc.entities:
e = {
"entity": entity.text,
"category": entity.category,
"subcategory": entity.subcategory,
"offset": entity.offset,
"score": entity.confidence_score,
}
entities.append(e)
for relation in doc.relations:
r = {
"source": relation.source.text,
"target": relation.target.text,
"type": relation.relation_type,
"is_bidirectional": relation.is_bidirectional
}
relations.append(r)
rezd["entities"] = entities
rezd["relations"] = relations
rez.append(rezd)
document["results"] = rez
# write output
outputFile = os.path.join(os.path.dirname(os.path.abspath(__file__)), "dumps", "out.json")
print("Writing output file [{}].".format(outputFile))
with open(outputFile, 'w+') as out:
json.dump(data, out)
