-
Notifications
You must be signed in to change notification settings - Fork 2.7k
/
sample_analyze_custom_documents.py
147 lines (126 loc) · 6.16 KB
/
sample_analyze_custom_documents.py
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
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
# coding: utf-8
# -------------------------------------------------------------------------
# Copyright (c) Microsoft Corporation. All rights reserved.
# Licensed under the MIT License. See License.txt in the project root for
# license information.
# --------------------------------------------------------------------------
"""
FILE: sample_analyze_custom_documents.py
DESCRIPTION:
This sample demonstrates how to analyze a document with a custom
built model. The document must be of the same type as the documents the custom model
was built on. To learn how to build your own models, look at
sample_build_model.py.
The model can be built using the training files found here:
https://aka.ms/azsdk/formrecognizer/sampletrainingfiles
USAGE:
python sample_analyze_custom_documents.py
Set the environment variables with your own values before running the sample:
1) AZURE_FORM_RECOGNIZER_ENDPOINT - the endpoint to your Form Recognizer resource.
2) AZURE_FORM_RECOGNIZER_KEY - your Form Recognizer API key
3) CUSTOM_BUILT_MODEL_ID - the ID of your custom built model
-OR-
CONTAINER_SAS_URL - The shared access signature (SAS) Url of your Azure Blob Storage container with your training files.
A model will be built and used to run the sample.
"""
import os
def analyze_custom_documents(custom_model_id):
path_to_sample_documents = os.path.abspath(
os.path.join(
os.path.abspath(__file__), "..", "..", "./sample_forms/forms/Form_1.jpg"
)
)
# [START analyze_custom_documents]
from azure.core.credentials import AzureKeyCredential
from azure.ai.formrecognizer import DocumentAnalysisClient
endpoint = os.environ["AZURE_FORM_RECOGNIZER_ENDPOINT"]
key = os.environ["AZURE_FORM_RECOGNIZER_KEY"]
model_id = os.getenv("CUSTOM_BUILT_MODEL_ID", custom_model_id)
document_analysis_client = DocumentAnalysisClient(
endpoint=endpoint, credential=AzureKeyCredential(key)
)
# Make sure your document's type is included in the list of document types the custom model can analyze
with open(path_to_sample_documents, "rb") as f:
poller = document_analysis_client.begin_analyze_document(
model_id=model_id, document=f
)
result = poller.result()
for idx, document in enumerate(result.documents):
print(f"--------Analyzing document #{idx + 1}--------")
print(f"Document has type {document.doc_type}")
print(f"Document has document type confidence {document.confidence}")
print(f"Document was analyzed with model with ID {result.model_id}")
for name, field in document.fields.items():
field_value = field.value if field.value else field.content
print(
f"......found field of type '{field.value_type}' with value '{field_value}' and with confidence {field.confidence}"
)
# iterate over tables, lines, and selection marks on each page
for page in result.pages:
print(f"\nLines found on page {page.page_number}")
for line in page.lines:
print(f"...Line '{line.content}'")
for word in page.words:
print(f"...Word '{word.content}' has a confidence of {word.confidence}")
if page.selection_marks:
print(f"\nSelection marks found on page {page.page_number}")
for selection_mark in page.selection_marks:
print(
f"...Selection mark is '{selection_mark.state}' and has a confidence of {selection_mark.confidence}"
)
for i, table in enumerate(result.tables):
print(f"\nTable {i + 1} can be found on page:")
for region in table.bounding_regions:
print(f"...{region.page_number}")
for cell in table.cells:
print(
f"...Cell[{cell.row_index}][{cell.column_index}] has text '{cell.content}'"
)
print("-----------------------------------")
# [END analyze_custom_documents]
if __name__ == "__main__":
import sys
from azure.core.exceptions import HttpResponseError
try:
model_id = None
if os.getenv("CONTAINER_SAS_URL") and not os.getenv("CUSTOM_BUILT_MODEL_ID"):
from azure.core.credentials import AzureKeyCredential
from azure.ai.formrecognizer import (
DocumentModelAdministrationClient,
ModelBuildMode,
)
endpoint = os.getenv("AZURE_FORM_RECOGNIZER_ENDPOINT")
key = os.getenv("AZURE_FORM_RECOGNIZER_KEY")
if not endpoint or not key:
raise ValueError(
"Please provide endpoint and API key to run the samples."
)
document_model_admin_client = DocumentModelAdministrationClient(
endpoint=endpoint, credential=AzureKeyCredential(key)
)
blob_container_sas_url = os.getenv("CONTAINER_SAS_URL")
if blob_container_sas_url is not None:
model = document_model_admin_client.begin_build_document_model(
ModelBuildMode.TEMPLATE, blob_container_url=blob_container_sas_url
).result()
model_id = model.model_id
analyze_custom_documents(model_id)
except HttpResponseError as error:
print(
"For more information about troubleshooting errors, see the following guide: "
"https://aka.ms/azsdk/python/formrecognizer/troubleshooting"
)
# Examples of how to check an HttpResponseError
# Check by error code:
if error.error is not None:
if error.error.code == "InvalidImage":
print(f"Received an invalid image error: {error.error}")
if error.error.code == "InvalidRequest":
print(f"Received an invalid request error: {error.error}")
# Raise the error again after printing it
raise
# If the inner error is None and then it is possible to check the message to get more information:
if "Invalid request".casefold() in error.message.casefold():
print(f"Uh-oh! Seems there was an invalid request: {error}")
# Raise the error again
raise