1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
|
# -------------------------------------------------------------------------
# Copyright (c) Microsoft Corporation. All rights reserved.
# Licensed under the MIT License. See License.txt in the project root for
# license information.
# --------------------------------------------------------------------------
"""
FILE: sample_single_label_classify.py
DESCRIPTION:
This sample demonstrates how to classify documents into a single custom category. For example,
movie plot summaries can be categorized into a single movie genre like "Mystery", "Drama", "Thriller",
"Comedy", "Action", etc. Classifying documents is also available as an action type through
the begin_analyze_actions API.
For information on regional support of custom features and how to train a model to
classify your documents, see https://aka.ms/azsdk/textanalytics/customfunctionalities
USAGE:
python sample_single_label_classify.py
Set the environment variables with your own values before running the sample:
1) AZURE_LANGUAGE_ENDPOINT - the endpoint to your Language resource.
2) AZURE_LANGUAGE_KEY - your Language subscription key
3) SINGLE_LABEL_CLASSIFY_PROJECT_NAME - your Language Studio project name
4) SINGLE_LABEL_CLASSIFY_DEPLOYMENT_NAME - your Language Studio deployment name
"""
def sample_classify_document_single_label() -> None:
# [START single_label_classify]
import os
from azure.core.credentials import AzureKeyCredential
from azure.ai.textanalytics import TextAnalyticsClient
endpoint = os.environ["AZURE_LANGUAGE_ENDPOINT"]
key = os.environ["AZURE_LANGUAGE_KEY"]
project_name = os.environ["SINGLE_LABEL_CLASSIFY_PROJECT_NAME"]
deployment_name = os.environ["SINGLE_LABEL_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) as fd:
document = [fd.read()]
poller = text_analytics_client.begin_single_label_classify(
document,
project_name=project_name,
deployment_name=deployment_name
)
document_results = poller.result()
for doc, classification_result in zip(document, document_results):
if classification_result.kind == "CustomDocumentClassification":
classification = classification_result.classifications[0]
print("The document text '{}' was classified as '{}' with confidence score {}.".format(
doc, classification.category, classification.confidence_score)
)
elif classification_result.is_error is True:
print("Document text '{}' has an error with code '{}' and message '{}'".format(
doc, classification_result.error.code, classification_result.error.message
))
# [END single_label_classify]
if __name__ == "__main__":
sample_classify_document_single_label()
|
