Spaces:
Sleeping
Sleeping
Commit
•
7dda936
0
Parent(s):
Duplicate from langdonholmes/piilo
Browse filesCo-authored-by: Langdon Holmes <[email protected]>
- .gitattributes +34 -0
- .gitignore +1 -0
- LICENSE +202 -0
- Pipfile +22 -0
- Pipfile.lock +0 -0
- README.md +26 -0
- analyzer.py +141 -0
- anonymizer.py +140 -0
- app.py +160 -0
- data/ascii_names.parquet +3 -0
- names_database.py +35 -0
- requirements.txt +0 -0
.gitattributes
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
29 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
30 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
31 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
32 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
__pycache__/*
|
LICENSE
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
Apache License
|
3 |
+
Version 2.0, January 2004
|
4 |
+
http://www.apache.org/licenses/
|
5 |
+
|
6 |
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
7 |
+
|
8 |
+
1. Definitions.
|
9 |
+
|
10 |
+
"License" shall mean the terms and conditions for use, reproduction,
|
11 |
+
and distribution as defined by Sections 1 through 9 of this document.
|
12 |
+
|
13 |
+
"Licensor" shall mean the copyright owner or entity authorized by
|
14 |
+
the copyright owner that is granting the License.
|
15 |
+
|
16 |
+
"Legal Entity" shall mean the union of the acting entity and all
|
17 |
+
other entities that control, are controlled by, or are under common
|
18 |
+
control with that entity. For the purposes of this definition,
|
19 |
+
"control" means (i) the power, direct or indirect, to cause the
|
20 |
+
direction or management of such entity, whether by contract or
|
21 |
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
22 |
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
23 |
+
|
24 |
+
"You" (or "Your") shall mean an individual or Legal Entity
|
25 |
+
exercising permissions granted by this License.
|
26 |
+
|
27 |
+
"Source" form shall mean the preferred form for making modifications,
|
28 |
+
including but not limited to software source code, documentation
|
29 |
+
source, and configuration files.
|
30 |
+
|
31 |
+
"Object" form shall mean any form resulting from mechanical
|
32 |
+
transformation or translation of a Source form, including but
|
33 |
+
not limited to compiled object code, generated documentation,
|
34 |
+
and conversions to other media types.
|
35 |
+
|
36 |
+
"Work" shall mean the work of authorship, whether in Source or
|
37 |
+
Object form, made available under the License, as indicated by a
|
38 |
+
copyright notice that is included in or attached to the work
|
39 |
+
(an example is provided in the Appendix below).
|
40 |
+
|
41 |
+
"Derivative Works" shall mean any work, whether in Source or Object
|
42 |
+
form, that is based on (or derived from) the Work and for which the
|
43 |
+
editorial revisions, annotations, elaborations, or other modifications
|
44 |
+
represent, as a whole, an original work of authorship. For the purposes
|
45 |
+
of this License, Derivative Works shall not include works that remain
|
46 |
+
separable from, or merely link (or bind by name) to the interfaces of,
|
47 |
+
the Work and Derivative Works thereof.
|
48 |
+
|
49 |
+
"Contribution" shall mean any work of authorship, including
|
50 |
+
the original version of the Work and any modifications or additions
|
51 |
+
to that Work or Derivative Works thereof, that is intentionally
|
52 |
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
53 |
+
or by an individual or Legal Entity authorized to submit on behalf of
|
54 |
+
the copyright owner. For the purposes of this definition, "submitted"
|
55 |
+
means any form of electronic, verbal, or written communication sent
|
56 |
+
to the Licensor or its representatives, including but not limited to
|
57 |
+
communication on electronic mailing lists, source code control systems,
|
58 |
+
and issue tracking systems that are managed by, or on behalf of, the
|
59 |
+
Licensor for the purpose of discussing and improving the Work, but
|
60 |
+
excluding communication that is conspicuously marked or otherwise
|
61 |
+
designated in writing by the copyright owner as "Not a Contribution."
|
62 |
+
|
63 |
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
64 |
+
on behalf of whom a Contribution has been received by Licensor and
|
65 |
+
subsequently incorporated within the Work.
|
66 |
+
|
67 |
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
68 |
+
this License, each Contributor hereby grants to You a perpetual,
|
69 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
70 |
+
copyright license to reproduce, prepare Derivative Works of,
|
71 |
+
publicly display, publicly perform, sublicense, and distribute the
|
72 |
+
Work and such Derivative Works in Source or Object form.
|
73 |
+
|
74 |
+
3. Grant of Patent License. Subject to the terms and conditions of
|
75 |
+
this License, each Contributor hereby grants to You a perpetual,
|
76 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
77 |
+
(except as stated in this section) patent license to make, have made,
|
78 |
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
79 |
+
where such license applies only to those patent claims licensable
|
80 |
+
by such Contributor that are necessarily infringed by their
|
81 |
+
Contribution(s) alone or by combination of their Contribution(s)
|
82 |
+
with the Work to which such Contribution(s) was submitted. If You
|
83 |
+
institute patent litigation against any entity (including a
|
84 |
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
85 |
+
or a Contribution incorporated within the Work constitutes direct
|
86 |
+
or contributory patent infringement, then any patent licenses
|
87 |
+
granted to You under this License for that Work shall terminate
|
88 |
+
as of the date such litigation is filed.
|
89 |
+
|
90 |
+
4. Redistribution. You may reproduce and distribute copies of the
|
91 |
+
Work or Derivative Works thereof in any medium, with or without
|
92 |
+
modifications, and in Source or Object form, provided that You
|
93 |
+
meet the following conditions:
|
94 |
+
|
95 |
+
(a) You must give any other recipients of the Work or
|
96 |
+
Derivative Works a copy of this License; and
|
97 |
+
|
98 |
+
(b) You must cause any modified files to carry prominent notices
|
99 |
+
stating that You changed the files; and
|
100 |
+
|
101 |
+
(c) You must retain, in the Source form of any Derivative Works
|
102 |
+
that You distribute, all copyright, patent, trademark, and
|
103 |
+
attribution notices from the Source form of the Work,
|
104 |
+
excluding those notices that do not pertain to any part of
|
105 |
+
the Derivative Works; and
|
106 |
+
|
107 |
+
(d) If the Work includes a "NOTICE" text file as part of its
|
108 |
+
distribution, then any Derivative Works that You distribute must
|
109 |
+
include a readable copy of the attribution notices contained
|
110 |
+
within such NOTICE file, excluding those notices that do not
|
111 |
+
pertain to any part of the Derivative Works, in at least one
|
112 |
+
of the following places: within a NOTICE text file distributed
|
113 |
+
as part of the Derivative Works; within the Source form or
|
114 |
+
documentation, if provided along with the Derivative Works; or,
|
115 |
+
within a display generated by the Derivative Works, if and
|
116 |
+
wherever such third-party notices normally appear. The contents
|
117 |
+
of the NOTICE file are for informational purposes only and
|
118 |
+
do not modify the License. You may add Your own attribution
|
119 |
+
notices within Derivative Works that You distribute, alongside
|
120 |
+
or as an addendum to the NOTICE text from the Work, provided
|
121 |
+
that such additional attribution notices cannot be construed
|
122 |
+
as modifying the License.
|
123 |
+
|
124 |
+
You may add Your own copyright statement to Your modifications and
|
125 |
+
may provide additional or different license terms and conditions
|
126 |
+
for use, reproduction, or distribution of Your modifications, or
|
127 |
+
for any such Derivative Works as a whole, provided Your use,
|
128 |
+
reproduction, and distribution of the Work otherwise complies with
|
129 |
+
the conditions stated in this License.
|
130 |
+
|
131 |
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
132 |
+
any Contribution intentionally submitted for inclusion in the Work
|
133 |
+
by You to the Licensor shall be under the terms and conditions of
|
134 |
+
this License, without any additional terms or conditions.
|
135 |
+
Notwithstanding the above, nothing herein shall supersede or modify
|
136 |
+
the terms of any separate license agreement you may have executed
|
137 |
+
with Licensor regarding such Contributions.
|
138 |
+
|
139 |
+
6. Trademarks. This License does not grant permission to use the trade
|
140 |
+
names, trademarks, service marks, or product names of the Licensor,
|
141 |
+
except as required for reasonable and customary use in describing the
|
142 |
+
origin of the Work and reproducing the content of the NOTICE file.
|
143 |
+
|
144 |
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
145 |
+
agreed to in writing, Licensor provides the Work (and each
|
146 |
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
147 |
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
148 |
+
implied, including, without limitation, any warranties or conditions
|
149 |
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
150 |
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
151 |
+
appropriateness of using or redistributing the Work and assume any
|
152 |
+
risks associated with Your exercise of permissions under this License.
|
153 |
+
|
154 |
+
8. Limitation of Liability. In no event and under no legal theory,
|
155 |
+
whether in tort (including negligence), contract, or otherwise,
|
156 |
+
unless required by applicable law (such as deliberate and grossly
|
157 |
+
negligent acts) or agreed to in writing, shall any Contributor be
|
158 |
+
liable to You for damages, including any direct, indirect, special,
|
159 |
+
incidental, or consequential damages of any character arising as a
|
160 |
+
result of this License or out of the use or inability to use the
|
161 |
+
Work (including but not limited to damages for loss of goodwill,
|
162 |
+
work stoppage, computer failure or malfunction, or any and all
|
163 |
+
other commercial damages or losses), even if such Contributor
|
164 |
+
has been advised of the possibility of such damages.
|
165 |
+
|
166 |
+
9. Accepting Warranty or Additional Liability. While redistributing
|
167 |
+
the Work or Derivative Works thereof, You may choose to offer,
|
168 |
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
169 |
+
or other liability obligations and/or rights consistent with this
|
170 |
+
License. However, in accepting such obligations, You may act only
|
171 |
+
on Your own behalf and on Your sole responsibility, not on behalf
|
172 |
+
of any other Contributor, and only if You agree to indemnify,
|
173 |
+
defend, and hold each Contributor harmless for any liability
|
174 |
+
incurred by, or claims asserted against, such Contributor by reason
|
175 |
+
of your accepting any such warranty or additional liability.
|
176 |
+
|
177 |
+
END OF TERMS AND CONDITIONS
|
178 |
+
|
179 |
+
APPENDIX: How to apply the Apache License to your work.
|
180 |
+
|
181 |
+
To apply the Apache License to your work, attach the following
|
182 |
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
183 |
+
replaced with your own identifying information. (Don't include
|
184 |
+
the brackets!) The text should be enclosed in the appropriate
|
185 |
+
comment syntax for the file format. We also recommend that a
|
186 |
+
file or class name and description of purpose be included on the
|
187 |
+
same "printed page" as the copyright notice for easier
|
188 |
+
identification within third-party archives.
|
189 |
+
|
190 |
+
Copyright [yyyy] [name of copyright owner]
|
191 |
+
|
192 |
+
Licensed under the Apache License, Version 2.0 (the "License");
|
193 |
+
you may not use this file except in compliance with the License.
|
194 |
+
You may obtain a copy of the License at
|
195 |
+
|
196 |
+
http://www.apache.org/licenses/LICENSE-2.0
|
197 |
+
|
198 |
+
Unless required by applicable law or agreed to in writing, software
|
199 |
+
distributed under the License is distributed on an "AS IS" BASIS,
|
200 |
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
201 |
+
See the License for the specific language governing permissions and
|
202 |
+
limitations under the License.
|
Pipfile
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[[source]]
|
2 |
+
url = "https://pypi.org/simple"
|
3 |
+
verify_ssl = true
|
4 |
+
name = "pypi"
|
5 |
+
|
6 |
+
[packages]
|
7 |
+
pandas = "==1.4.3"
|
8 |
+
presidio-analyzer = "==2.2.28"
|
9 |
+
presidio-anonymizer = "==2.2.28"
|
10 |
+
spacy = "==3.4.1"
|
11 |
+
spacy-transformers = "==1.1.7"
|
12 |
+
st-annotated-text = "==3.0.0"
|
13 |
+
streamlit = "==1.17.0"
|
14 |
+
tokenizers = "==0.12.1"
|
15 |
+
torch = "==1.12.0"
|
16 |
+
en-student-name-detector = {file = "https://huggingface.co/langdonholmes/en_student_name_detector/resolve/main/en_student_name_detector-any-py3-none-any.whl"}
|
17 |
+
names-dataset = "*"
|
18 |
+
|
19 |
+
[dev-packages]
|
20 |
+
|
21 |
+
[requires]
|
22 |
+
python_version = "3.10"
|
Pipfile.lock
ADDED
The diff for this file is too large to render.
See raw diff
|
|
README.md
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
title: Piilo
|
3 |
+
emoji: 🏃
|
4 |
+
colorFrom: purple
|
5 |
+
colorTo: purple
|
6 |
+
sdk: streamlit
|
7 |
+
sdk_version: 1.10.0
|
8 |
+
app_file: app.py
|
9 |
+
pinned: false
|
10 |
+
license: apache-2.0
|
11 |
+
duplicated_from: langdonholmes/piilo
|
12 |
+
---
|
13 |
+
|
14 |
+
For development, try working with pipenv:
|
15 |
+
|
16 |
+
1. Clone the repository
|
17 |
+
`git clone https://huggingface.co/spaces/langdonholmes/piilo`
|
18 |
+
|
19 |
+
2. Install dependencies from Pipfile
|
20 |
+
`pip install --user pipenv`
|
21 |
+
|
22 |
+
3. Run streamlit app
|
23 |
+
`streamlit run .\app.py`
|
24 |
+
|
25 |
+
TODO:
|
26 |
+
Create a command line version using Typer in this same repository.
|
analyzer.py
ADDED
@@ -0,0 +1,141 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import logging
|
2 |
+
from typing import Optional, List, Tuple, Set
|
3 |
+
|
4 |
+
from presidio_analyzer import (AnalysisExplanation, AnalyzerEngine,
|
5 |
+
LocalRecognizer, RecognizerRegistry,
|
6 |
+
RecognizerResult)
|
7 |
+
from presidio_analyzer.nlp_engine import NlpArtifacts, NlpEngineProvider
|
8 |
+
|
9 |
+
logger = logging.getLogger('presidio-analyzer')
|
10 |
+
|
11 |
+
class CustomSpacyRecognizer(LocalRecognizer):
|
12 |
+
ENTITIES = [
|
13 |
+
'STUDENT',
|
14 |
+
]
|
15 |
+
|
16 |
+
DEFAULT_EXPLANATION = 'Identified as {} by a Student Name Detection Model'
|
17 |
+
|
18 |
+
CHECK_LABEL_GROUPS = [
|
19 |
+
({'STUDENT'}, {'STUDENT'}),
|
20 |
+
]
|
21 |
+
|
22 |
+
MODEL_LANGUAGES = {
|
23 |
+
'en': 'langdonholmes/en_student_name_detector',
|
24 |
+
}
|
25 |
+
|
26 |
+
def __init__(
|
27 |
+
self,
|
28 |
+
supported_language: str = 'en',
|
29 |
+
supported_entities: Optional[List[str]] = None,
|
30 |
+
check_label_groups: Optional[Tuple[Set, Set]] = None,
|
31 |
+
ner_strength: float = 0.85,
|
32 |
+
):
|
33 |
+
self.ner_strength = ner_strength
|
34 |
+
self.check_label_groups = (
|
35 |
+
check_label_groups if check_label_groups else self.CHECK_LABEL_GROUPS
|
36 |
+
)
|
37 |
+
supported_entities = supported_entities if supported_entities else self.ENTITIES
|
38 |
+
super().__init__(
|
39 |
+
supported_entities=supported_entities,
|
40 |
+
supported_language=supported_language,
|
41 |
+
)
|
42 |
+
|
43 |
+
def load(self) -> None:
|
44 |
+
'''Load the model, not used. Model is loaded during initialization.'''
|
45 |
+
pass
|
46 |
+
|
47 |
+
def get_supported_entities(self) -> List[str]:
|
48 |
+
'''
|
49 |
+
Return supported entities by this model.
|
50 |
+
:return: List of the supported entities.
|
51 |
+
'''
|
52 |
+
return self.supported_entities
|
53 |
+
|
54 |
+
def build_spacy_explanation(
|
55 |
+
self, original_score: float, explanation: str
|
56 |
+
) -> AnalysisExplanation:
|
57 |
+
'''
|
58 |
+
Create explanation for why this result was detected.
|
59 |
+
:param original_score: Score given by this recognizer
|
60 |
+
:param explanation: Explanation string
|
61 |
+
:return:
|
62 |
+
'''
|
63 |
+
explanation = AnalysisExplanation(
|
64 |
+
recognizer=self.__class__.__name__,
|
65 |
+
original_score=original_score,
|
66 |
+
textual_explanation=explanation,
|
67 |
+
)
|
68 |
+
return explanation
|
69 |
+
|
70 |
+
def analyze(self,
|
71 |
+
text: str,
|
72 |
+
entities: List[str] = None,
|
73 |
+
nlp_artifacts: NlpArtifacts = None):
|
74 |
+
'''Analyze input using Analyzer engine and input arguments (kwargs).'''
|
75 |
+
|
76 |
+
if not entities or 'All' in entities:
|
77 |
+
entities = None
|
78 |
+
|
79 |
+
results = []
|
80 |
+
|
81 |
+
if not nlp_artifacts:
|
82 |
+
logger.warning('Skipping SpaCy, nlp artifacts not provided...')
|
83 |
+
return results
|
84 |
+
|
85 |
+
ner_entities = nlp_artifacts.entities
|
86 |
+
|
87 |
+
for entity in entities:
|
88 |
+
if entity not in self.supported_entities:
|
89 |
+
continue
|
90 |
+
for ent in ner_entities:
|
91 |
+
if not self.__check_label(entity, ent.label_, self.check_label_groups):
|
92 |
+
continue
|
93 |
+
textual_explanation = self.DEFAULT_EXPLANATION.format(
|
94 |
+
ent.label_)
|
95 |
+
explanation = self.build_spacy_explanation(
|
96 |
+
self.ner_strength, textual_explanation
|
97 |
+
)
|
98 |
+
spacy_result = RecognizerResult(
|
99 |
+
entity_type=entity,
|
100 |
+
start=ent.start_char,
|
101 |
+
end=ent.end_char,
|
102 |
+
score=self.ner_strength,
|
103 |
+
analysis_explanation=explanation,
|
104 |
+
recognition_metadata={
|
105 |
+
RecognizerResult.RECOGNIZER_NAME_KEY: self.name
|
106 |
+
},
|
107 |
+
)
|
108 |
+
results.append(spacy_result)
|
109 |
+
|
110 |
+
return results
|
111 |
+
|
112 |
+
@staticmethod
|
113 |
+
def __check_label(
|
114 |
+
entity: str, label: str, check_label_groups: Tuple[Set, Set]
|
115 |
+
) -> bool:
|
116 |
+
return any(
|
117 |
+
[entity in egrp and label in lgrp for egrp, lgrp in check_label_groups]
|
118 |
+
)
|
119 |
+
|
120 |
+
def prepare_analyzer(configuration):
|
121 |
+
'''Handle Preparation of Analyzer Engine for Presidio.'''
|
122 |
+
|
123 |
+
spacy_recognizer = CustomSpacyRecognizer()
|
124 |
+
|
125 |
+
# Create NLP engine based on configuration
|
126 |
+
provider = NlpEngineProvider(nlp_configuration=configuration)
|
127 |
+
nlp_engine = provider.create_engine()
|
128 |
+
|
129 |
+
# add rule-based recognizers
|
130 |
+
registry = RecognizerRegistry()
|
131 |
+
registry.load_predefined_recognizers(nlp_engine=nlp_engine)
|
132 |
+
registry.add_recognizer(spacy_recognizer)
|
133 |
+
|
134 |
+
# remove the nlp engine we passed, to use custom label mappings
|
135 |
+
registry.remove_recognizer('SpacyRecognizer')
|
136 |
+
|
137 |
+
analyzer = AnalyzerEngine(nlp_engine=nlp_engine,
|
138 |
+
registry=registry,
|
139 |
+
supported_languages=['en'])
|
140 |
+
|
141 |
+
return analyzer
|
anonymizer.py
ADDED
@@ -0,0 +1,140 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import logging
|
2 |
+
from pathlib import Path
|
3 |
+
from typing import List, Optional, Tuple
|
4 |
+
|
5 |
+
import pandas as pd
|
6 |
+
from presidio_analyzer import RecognizerResult
|
7 |
+
from presidio_anonymizer import AnonymizerEngine
|
8 |
+
from presidio_anonymizer.entities import OperatorConfig
|
9 |
+
from presidio_anonymizer.operators import OperatorType
|
10 |
+
|
11 |
+
from names_database import NameDatabase
|
12 |
+
|
13 |
+
name_table = Path('data', 'ascii_names.parquet')
|
14 |
+
|
15 |
+
logger = logging.getLogger('anonymizer')
|
16 |
+
|
17 |
+
class surrogate_anonymizer(AnonymizerEngine):
|
18 |
+
def __init__(self):
|
19 |
+
super().__init__()
|
20 |
+
self.names_db = NameDatabase()
|
21 |
+
self.names_df = pd.read_parquet(name_table)
|
22 |
+
|
23 |
+
def get_random_name(
|
24 |
+
self,
|
25 |
+
country: Optional[str] = None,
|
26 |
+
gender: Optional[str] = None
|
27 |
+
) -> pd.DataFrame:
|
28 |
+
'''Returns two random names from the database as a DataFrame.
|
29 |
+
Both rows match gender and country, if provided.
|
30 |
+
:country: ISO country code e.g. "CO" for Columbia
|
31 |
+
:gender: 'M' or 'F'
|
32 |
+
returns two rows of the names dataframe
|
33 |
+
'''
|
34 |
+
names_view = self.names_df
|
35 |
+
if country:
|
36 |
+
names_view = names_view[names_view['country'] == country]
|
37 |
+
if gender:
|
38 |
+
names_view = names_view[names_view['gender'] == gender]
|
39 |
+
if names_view.size < 25:
|
40 |
+
return self.names_df.sample(n=2, weights=self.names_df['count'])
|
41 |
+
return names_view.sample(n=2, weights=names_view['count'])
|
42 |
+
|
43 |
+
def split_name(self, original_name: str) -> Tuple[str]:
|
44 |
+
'''Splits name into parts.
|
45 |
+
If one token, assume it is a first name.
|
46 |
+
If two tokens, first and last name.
|
47 |
+
If three tokens, one first name and two last names.
|
48 |
+
If four tokens, two first names and two last names.'''
|
49 |
+
names = original_name.split()
|
50 |
+
if len(names) == 1:
|
51 |
+
logger.info(f'Splitting to 1 first name: {names}')
|
52 |
+
return names[0], None
|
53 |
+
elif len(names) == 2:
|
54 |
+
logger.info(f'Splitting to 1 first name, 1 last name: {names}')
|
55 |
+
return names[0], names[1]
|
56 |
+
elif len(names) == 3:
|
57 |
+
logger.info(f'Splitting to 1 first name, 2 last names: {names}')
|
58 |
+
return names[0], ' '.join(names[1:])
|
59 |
+
elif len(names) == 4:
|
60 |
+
logger.info(f'Splitting to 2 first names and 2 last names: {names}')
|
61 |
+
return ' '.join(names[:2]), ' '.join(names[2:])
|
62 |
+
else:
|
63 |
+
logger.info(f'Splitting failed, do not match gender/country: {names}')
|
64 |
+
return None, None
|
65 |
+
|
66 |
+
def generate_surrogate(self, original_name: str) -> str:
|
67 |
+
'''Generate a surrogate name.
|
68 |
+
'''
|
69 |
+
if original_name == 'PII':
|
70 |
+
# Every time we call this function, Presidio will validate it
|
71 |
+
# by testing that the function returns a str when the input is
|
72 |
+
# 'PII'. Bypass this test.
|
73 |
+
return 'PII'
|
74 |
+
|
75 |
+
first_names, last_names = self.split_name(original_name)
|
76 |
+
gender = self.names_db.get_gender(first_names) if first_names else None
|
77 |
+
logger.debug(f'Gender set to {gender}')
|
78 |
+
country = self.names_db.get_country(last_names) if last_names else None
|
79 |
+
logger.debug(f'Country set to {country}')
|
80 |
+
|
81 |
+
surrogate_name = ''
|
82 |
+
|
83 |
+
name_candidates = self.get_random_name(gender=gender, country=country)
|
84 |
+
|
85 |
+
surrogate_name += name_candidates.iloc[0]['first']
|
86 |
+
logger.info(f'First name surrogate is {surrogate_name}')
|
87 |
+
|
88 |
+
if last_names:
|
89 |
+
logger.info(f'Combining with {name_candidates.iloc[1]["last"]}')
|
90 |
+
surrogate_name += ' ' + name_candidates.iloc[1]['last']
|
91 |
+
|
92 |
+
logger.info(f'Returning surrogate name {surrogate_name}')
|
93 |
+
return surrogate_name
|
94 |
+
|
95 |
+
def anonymize(
|
96 |
+
self,
|
97 |
+
text: str,
|
98 |
+
analyzer_results: List[RecognizerResult]
|
99 |
+
):
|
100 |
+
'''Anonymize identified input using Presidio Anonymizer.'''
|
101 |
+
|
102 |
+
if not text:
|
103 |
+
return
|
104 |
+
|
105 |
+
analyzer_results = self._remove_conflicts_and_get_text_manipulation_data(
|
106 |
+
analyzer_results
|
107 |
+
)
|
108 |
+
|
109 |
+
operators = self._AnonymizerEngine__check_or_add_default_operator(
|
110 |
+
{
|
111 |
+
'STUDENT': OperatorConfig('custom',
|
112 |
+
{'lambda': self.generate_surrogate}),
|
113 |
+
'EMAIL_ADDRESS': OperatorConfig('replace',
|
114 |
+
{'new_value': '[email protected]'}),
|
115 |
+
'PHONE_NUMBER': OperatorConfig('replace',
|
116 |
+
{'new_value': '888-888-8888'}),
|
117 |
+
'URL': OperatorConfig('replace',
|
118 |
+
{'new_value': 'aol.com'}),
|
119 |
+
}
|
120 |
+
)
|
121 |
+
|
122 |
+
res = self._operate(text,
|
123 |
+
analyzer_results,
|
124 |
+
operators,
|
125 |
+
OperatorType.Anonymize)
|
126 |
+
|
127 |
+
return res.text
|
128 |
+
|
129 |
+
if __name__ == '__main__':
|
130 |
+
logging.basicConfig(level=logging.DEBUG)
|
131 |
+
anonymizer = surrogate_anonymizer()
|
132 |
+
test_names = ['Nora Wang',
|
133 |
+
'MJ',
|
134 |
+
'',
|
135 |
+
'(',
|
136 |
+
'Mario Escobar Sanchez',
|
137 |
+
'Jane Fonda Michelle Rousseau',
|
138 |
+
'Sir Phillipe Ricardo de la Sota Mayor']
|
139 |
+
for name in test_names:
|
140 |
+
anonymizer.generate_surrogate(name)
|
app.py
ADDED
@@ -0,0 +1,160 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
'''Streamlit app for Student Name Detection models.'''
|
3 |
+
|
4 |
+
from analyzer import prepare_analyzer
|
5 |
+
from anonymizer import surrogate_anonymizer
|
6 |
+
from presidio_anonymizer import AnonymizerEngine
|
7 |
+
import pandas as pd
|
8 |
+
from annotated_text import annotated_text
|
9 |
+
from json import JSONEncoder
|
10 |
+
import json
|
11 |
+
import warnings
|
12 |
+
import streamlit as st
|
13 |
+
import os
|
14 |
+
os.environ['TOKENIZERS_PARALLELISM'] = 'false'
|
15 |
+
warnings.filterwarnings('ignore')
|
16 |
+
|
17 |
+
# Helper methods
|
18 |
+
@st.cache(allow_output_mutation=True)
|
19 |
+
def analyzer_engine():
|
20 |
+
'''Return AnalyzerEngine and cache with Streamlit.'''
|
21 |
+
|
22 |
+
configuration = {
|
23 |
+
'nlp_engine_name': 'spacy',
|
24 |
+
'models': [
|
25 |
+
{'lang_code': 'en', 'model_name': 'en_student_name_detector'}],
|
26 |
+
}
|
27 |
+
|
28 |
+
analyzer = prepare_analyzer(configuration)
|
29 |
+
|
30 |
+
return analyzer
|
31 |
+
|
32 |
+
@st.cache(allow_output_mutation=True)
|
33 |
+
def anonymizer_engine():
|
34 |
+
'''Return generate surrogate anonymizer.'''
|
35 |
+
return surrogate_anonymizer()
|
36 |
+
|
37 |
+
def annotate(text, st_analyze_results, st_entities):
|
38 |
+
tokens = []
|
39 |
+
# sort by start index
|
40 |
+
results = sorted(st_analyze_results, key=lambda x: x.start)
|
41 |
+
for i, res in enumerate(results):
|
42 |
+
if i == 0:
|
43 |
+
tokens.append(text[:res.start])
|
44 |
+
|
45 |
+
# append entity text and entity type
|
46 |
+
tokens.append((text[res.start: res.end], res.entity_type))
|
47 |
+
|
48 |
+
# if another entity coming i.e. we're not at the last results element, add text up to next entity
|
49 |
+
if i != len(results) - 1:
|
50 |
+
tokens.append(text[res.end:results[i+1].start])
|
51 |
+
# if no more entities coming, add all remaining text
|
52 |
+
else:
|
53 |
+
tokens.append(text[res.end:])
|
54 |
+
return tokens
|
55 |
+
|
56 |
+
|
57 |
+
st.set_page_config(page_title='Student Name Detector (English)', layout='wide')
|
58 |
+
|
59 |
+
# Side bar
|
60 |
+
st.sidebar.markdown(
|
61 |
+
'''Detect and anonymize PII in text using an [NLP model](https://huggingface.co/langdonholmes/en_student_name_detector) [trained](https://github.com/aialoe/deidentification-pipeline) on student-generated text collected by Coursera.
|
62 |
+
'''
|
63 |
+
)
|
64 |
+
|
65 |
+
st_entities = st.sidebar.multiselect(
|
66 |
+
label='Which entities to look for?',
|
67 |
+
options=analyzer_engine().get_supported_entities(),
|
68 |
+
default=list(analyzer_engine().get_supported_entities()),
|
69 |
+
)
|
70 |
+
|
71 |
+
st_threshold = st.sidebar.slider(
|
72 |
+
label='Acceptance threshold', min_value=0.0, max_value=1.0, value=0.35
|
73 |
+
)
|
74 |
+
|
75 |
+
st_return_decision_process = st.sidebar.checkbox(
|
76 |
+
'Add analysis explanations in json')
|
77 |
+
|
78 |
+
st.sidebar.info(
|
79 |
+
'This is part of a deidentification project for student-generated text.'
|
80 |
+
)
|
81 |
+
|
82 |
+
# Main panel
|
83 |
+
analyzer_load_state = st.info(
|
84 |
+
'Starting Presidio analyzer and loading Longformer-based model...')
|
85 |
+
engine = analyzer_engine()
|
86 |
+
analyzer_load_state.empty()
|
87 |
+
|
88 |
+
|
89 |
+
st_text = st.text_area(
|
90 |
+
label='Type in some text',
|
91 |
+
value='Learning Reflection\n\nWritten by John Williams and Samantha Morales\n\nIn this course I learned many things. As Liedtke (2004) said, \"Students grow when they learn\" (Erickson et al. 1998).\n\nBy John H. Williams -- (714) 328-9989 -- [email protected]',
|
92 |
+
height=200,
|
93 |
+
)
|
94 |
+
|
95 |
+
button = st.button('Detect PII')
|
96 |
+
|
97 |
+
if 'first_load' not in st.session_state:
|
98 |
+
st.session_state['first_load'] = True
|
99 |
+
|
100 |
+
# After
|
101 |
+
st.subheader('Analyzed')
|
102 |
+
with st.spinner('Analyzing...'):
|
103 |
+
if button or st.session_state.first_load:
|
104 |
+
st_analyze_results = analyzer_engine().analyze(
|
105 |
+
text=st_text,
|
106 |
+
entities=st_entities,
|
107 |
+
language='en',
|
108 |
+
score_threshold=st_threshold,
|
109 |
+
return_decision_process=st_return_decision_process,
|
110 |
+
)
|
111 |
+
annotated_tokens = annotate(st_text, st_analyze_results, st_entities)
|
112 |
+
# annotated_tokens
|
113 |
+
annotated_text(*annotated_tokens)
|
114 |
+
|
115 |
+
# vertical space
|
116 |
+
st.text('')
|
117 |
+
|
118 |
+
st.subheader('Anonymized')
|
119 |
+
with st.spinner('Anonymizing...'):
|
120 |
+
if button or st.session_state.first_load:
|
121 |
+
st_anonymize_results = anonymizer_engine().anonymize(
|
122 |
+
st_text,
|
123 |
+
st_analyze_results)
|
124 |
+
st_anonymize_results
|
125 |
+
|
126 |
+
# table result
|
127 |
+
st.subheader('Detailed Findings')
|
128 |
+
if st_analyze_results:
|
129 |
+
res_dicts = [r.to_dict() for r in st_analyze_results]
|
130 |
+
for d in res_dicts:
|
131 |
+
d['Value'] = st_text[d['start']:d['end']]
|
132 |
+
df = pd.DataFrame.from_records(res_dicts)
|
133 |
+
df = df[['entity_type', 'Value', 'score', 'start', 'end']].rename(
|
134 |
+
{
|
135 |
+
'entity_type': 'Entity type',
|
136 |
+
'start': 'Start',
|
137 |
+
'end': 'End',
|
138 |
+
'score': 'Confidence',
|
139 |
+
},
|
140 |
+
axis=1,
|
141 |
+
)
|
142 |
+
|
143 |
+
st.dataframe(df, width=1000)
|
144 |
+
else:
|
145 |
+
st.text('No findings')
|
146 |
+
|
147 |
+
st.session_state['first_load'] = True
|
148 |
+
|
149 |
+
# json result
|
150 |
+
class ToDictListEncoder(JSONEncoder):
|
151 |
+
'''Encode dict to json.'''
|
152 |
+
|
153 |
+
def default(self, o):
|
154 |
+
'''Encode to JSON using to_dict.'''
|
155 |
+
if o:
|
156 |
+
return o.to_dict()
|
157 |
+
return []
|
158 |
+
|
159 |
+
if st_return_decision_process:
|
160 |
+
st.json(json.dumps(st_analyze_results, cls=ToDictListEncoder))
|
data/ascii_names.parquet
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:baf5cf2fa43dc172c613f72793641f668e33c30b4e23932616de36cc0ce3447d
|
3 |
+
size 33601747
|
names_database.py
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import logging
|
2 |
+
|
3 |
+
|
4 |
+
from names_dataset import NameDataset, NameWrapper
|
5 |
+
|
6 |
+
|
7 |
+
class NameDatabase(NameDataset):
|
8 |
+
def __init__(self) -> None:
|
9 |
+
super().__init__()
|
10 |
+
|
11 |
+
self.logger = logging.getLogger('anonymizer')
|
12 |
+
|
13 |
+
def search(self, name: str) -> dict:
|
14 |
+
'''Returns all entries associated with a name string.
|
15 |
+
The name string can be multiple tokens.
|
16 |
+
Both first and last names will be matched.
|
17 |
+
'''
|
18 |
+
key = name.strip().title()
|
19 |
+
fn = self.first_names.get(key) if self.first_names is not None else None
|
20 |
+
ln = self.last_names.get(key) if self.last_names is not None else None
|
21 |
+
return {'first_name': fn, 'last_name': ln}
|
22 |
+
|
23 |
+
def get_gender(self, first_names: str) -> str:
|
24 |
+
'''Return the most frequent gender code for a specific last name,
|
25 |
+
or None if a match cannot be found.
|
26 |
+
'''
|
27 |
+
gender = NameWrapper(self.search(first_names)).gender
|
28 |
+
return gender if gender else None
|
29 |
+
|
30 |
+
def get_country(self, last_names: str) -> str:
|
31 |
+
'''Return the most frequent country code for a specific last name,
|
32 |
+
or None if a match cannot be found.
|
33 |
+
'''
|
34 |
+
country = NameWrapper(self.search(last_names)).country
|
35 |
+
return country if country else None
|
requirements.txt
ADDED
Binary file (8.63 kB). View file
|
|