File size: 12,870 Bytes
384d9d6
3477655
547518c
3477655
384d9d6
3477655
384d9d6
 
d0e1245
384d9d6
3477655
384d9d6
3477655
d6241cc
 
 
 
 
 
 
384d9d6
 
3477655
 
 
 
 
 
 
 
 
 
 
 
 
 
 
af33981
384d9d6
 
 
3477655
384d9d6
 
 
 
3477655
 
 
 
 
 
384d9d6
3477655
 
 
 
 
17f243f
 
3477655
 
 
 
 
384d9d6
3477655
 
 
 
384d9d6
3477655
 
 
 
 
 
 
17f243f
3477655
 
 
 
 
17f243f
3477655
 
 
17f243f
3477655
17f243f
3477655
 
17f243f
3477655
 
 
 
 
 
 
 
 
384d9d6
 
 
547518c
384d9d6
547518c
 
 
 
 
 
 
 
 
 
384d9d6
d6241cc
 
 
3477655
 
 
 
 
17f243f
 
 
 
3477655
 
 
 
 
 
17f243f
 
3477655
 
 
 
 
 
 
17f243f
 
 
 
547518c
 
17f243f
547518c
 
 
 
 
3477655
547518c
 
17f243f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3477655
 
 
 
 
17f243f
3477655
 
 
 
384d9d6
547518c
 
 
 
3477655
384d9d6
 
 
d6241cc
 
 
3477655
384d9d6
 
3477655
 
 
 
384d9d6
 
3477655
 
 
 
 
 
 
 
 
 
 
 
 
 
384d9d6
3477655
 
 
 
 
 
 
17f243f
 
3477655
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
384d9d6
3477655
384d9d6
 
 
 
 
 
 
 
 
 
3477655
384d9d6
3477655
384d9d6
 
3477655
 
 
 
 
 
 
 
 
 
d6241cc
384d9d6
3477655
 
 
 
384d9d6
3477655
 
 
 
 
 
 
 
 
 
384d9d6
3477655
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
384d9d6
3477655
 
 
 
 
 
 
 
 
384d9d6
3477655
 
 
 
 
 
 
 
 
384d9d6
3477655
 
 
 
 
 
 
 
 
275566f
3477655
 
 
 
275566f
 
 
 
 
 
 
 
 
 
 
 
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
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
"""Streamlit app for Presidio."""
import logging
import os
import traceback

import dotenv
import pandas as pd
import streamlit as st
import streamlit.components.v1 as components
from annotated_text import annotated_text
from streamlit_tags import st_tags

from openai_fake_data_generator import OpenAIParams
from presidio_helpers import (
    get_supported_entities,
    analyze,
    anonymize,
    annotate,
    create_fake_data,
    analyzer_engine,
)

st.set_page_config(
    page_title="Presidio demo",
    layout="wide",
    initial_sidebar_state="expanded",
    menu_items={
        "About": "https://microsoft.github.io/presidio/",
    },
)

dotenv.load_dotenv()
logger = logging.getLogger("presidio-streamlit")


allow_other_models = os.getenv("ALLOW_OTHER_MODELS", False)


# Sidebar
st.sidebar.header(
    """
PII De-Identification with [Microsoft Presidio](https://microsoft.github.io/presidio/)
"""
)


model_help_text = """
    Select which Named Entity Recognition (NER) model to use for PII detection, in parallel to rule-based recognizers.
    Presidio supports multiple NER packages off-the-shelf, such as spaCy, Huggingface, Stanza and Flair,
    as well as service such as Azure Text Analytics PII.
    """
st_ta_key = st_ta_endpoint = ""

model_list = [
    "spaCy/en_core_web_lg",
    "flair/ner-english-large",
    "HuggingFace/obi/deid_roberta_i2b2",
    "HuggingFace/StanfordAIMI/stanford-deidentifier-base",
    "stanza/en",
    "Azure AI Language",
    "Other",
]
if not allow_other_models:
    model_list.pop()
# Select model
st_model = st.sidebar.selectbox(
    "NER model package",
    model_list,
    index=2,
    help=model_help_text,
)

# Extract model package.
st_model_package = st_model.split("/")[0]

# Remove package prefix (if needed)
st_model = (
    st_model
    if st_model_package.lower() not in ("spacy", "stanza", "huggingface")
    else "/".join(st_model.split("/")[1:])
)

if st_model == "Other":
    st_model_package = st.sidebar.selectbox(
        "NER model OSS package", options=["spaCy", "stanza", "Flair", "HuggingFace"]
    )
    st_model = st.sidebar.text_input(f"NER model name", value="")

if st_model == "Azure AI Language":
    st_ta_key = st.sidebar.text_input(
        f"Azure AI Language key", value=os.getenv("TA_KEY", ""), type="password"
    )
    st_ta_endpoint = st.sidebar.text_input(
        f"Azure AI Language endpoint",
        value=os.getenv("TA_ENDPOINT", default=""),
        help="For more info: https://learn.microsoft.com/en-us/azure/cognitive-services/language-service/personally-identifiable-information/overview",  # noqa: E501
    )


st.sidebar.warning("Note: Models might take some time to download. ")

analyzer_params = (st_model_package, st_model, st_ta_key, st_ta_endpoint)
logger.debug(f"analyzer_params: {analyzer_params}")

st_operator = st.sidebar.selectbox(
    "De-identification approach",
    ["redact", "replace", "synthesize", "highlight", "mask", "hash", "encrypt"],
    index=1,
    help="""
    Select which manipulation to the text is requested after PII has been identified.\n
    - Redact: Completely remove the PII text\n
    - Replace: Replace the PII text with a constant, e.g. <PERSON>\n
    - Synthesize: Replace with fake values (requires an OpenAI key)\n
    - Highlight: Shows the original text with PII highlighted in colors\n
    - Mask: Replaces a requested number of characters with an asterisk (or other mask character)\n
    - Hash: Replaces with the hash of the PII string\n
    - Encrypt: Replaces with an AES encryption of the PII string, allowing the process to be reversed
         """,
)
st_mask_char = "*"
st_number_of_chars = 15
st_encrypt_key = "WmZq4t7w!z%C&F)J"

open_ai_params = None

logger.debug(f"st_operator: {st_operator}")


def set_up_openai_synthesis():
    """Set up the OpenAI API key and model for text synthesis."""

    if os.getenv("OPENAI_TYPE", default="openai") == "Azure":
        openai_api_type = "azure"
        st_openai_api_base = st.sidebar.text_input(
            "Azure OpenAI base URL",
            value=os.getenv("AZURE_OPENAI_ENDPOINT", default=""),
        )
        openai_key = os.getenv("AZURE_OPENAI_KEY", default="")
        st_deployment_id = st.sidebar.text_input(
            "Deployment name", value=os.getenv("AZURE_OPENAI_DEPLOYMENT", default="")
        )
        st_openai_version = st.sidebar.text_input(
            "OpenAI version",
            value=os.getenv("OPENAI_API_VERSION", default="2023-05-15"),
        )
    else:
        openai_api_type = "openai"
        st_openai_version = st_openai_api_base = None
        st_deployment_id = ""
        openai_key = os.getenv("OPENAI_KEY", default="")
    st_openai_key = st.sidebar.text_input(
        "OPENAI_KEY",
        value=openai_key,
        help="See https://help.openai.com/en/articles/4936850-where-do-i-find-my-secret-api-key for more info.",
        type="password",
    )
    st_openai_model = st.sidebar.text_input(
        "OpenAI model for text synthesis",
        value=os.getenv("OPENAI_MODEL", default="text-davinci-003"),
        help="See more here: https://platform.openai.com/docs/models/",
    )
    return (
        openai_api_type,
        st_openai_api_base,
        st_deployment_id,
        st_openai_version,
        st_openai_key,
        st_openai_model,
    )


if st_operator == "mask":
    st_number_of_chars = st.sidebar.number_input(
        "number of chars", value=st_number_of_chars, min_value=0, max_value=100
    )
    st_mask_char = st.sidebar.text_input(
        "Mask character", value=st_mask_char, max_chars=1
    )
elif st_operator == "encrypt":
    st_encrypt_key = st.sidebar.text_input("AES key", value=st_encrypt_key)
elif st_operator == "synthesize":
    (
        openai_api_type,
        st_openai_api_base,
        st_deployment_id,
        st_openai_version,
        st_openai_key,
        st_openai_model,
    ) = set_up_openai_synthesis()

    open_ai_params = OpenAIParams(
        openai_key=st_openai_key,
        model=st_openai_model,
        api_base=st_openai_api_base,
        deployment_id=st_deployment_id,
        api_version=st_openai_version,
        api_type=openai_api_type,
    )

st_threshold = st.sidebar.slider(
    label="Acceptance threshold",
    min_value=0.0,
    max_value=1.0,
    value=0.35,
    help="Define the threshold for accepting a detection as PII. See more here: ",
)

st_return_decision_process = st.sidebar.checkbox(
    "Add analysis explanations to findings",
    value=False,
    help="Add the decision process to the output table. "
    "More information can be found here: https://microsoft.github.io/presidio/analyzer/decision_process/",
)

# Allow and deny lists
st_deny_allow_expander = st.sidebar.expander(
    "Allowlists and denylists",
    expanded=False,
)

with st_deny_allow_expander:
    st_allow_list = st_tags(
        label="Add words to the allowlist", text="Enter word and press enter."
    )
    st.caption(
        "Allowlists contain words that are not considered PII, but are detected as such."
    )

    st_deny_list = st_tags(
        label="Add words to the denylist", text="Enter word and press enter."
    )
    st.caption(
        "Denylists contain words that are considered PII, but are not detected as such."
    )
# Main panel

with st.expander("About this demo", expanded=False):
    st.info(
        """Presidio is an open source customizable framework for PII detection and de-identification.
        \n\n[Code](https://aka.ms/presidio) | 
        [Tutorial](https://microsoft.github.io/presidio/tutorial/) | 
        [Installation](https://microsoft.github.io/presidio/installation/) | 
        [FAQ](https://microsoft.github.io/presidio/faq/) |
        [Feedback](https://forms.office.com/r/9ufyYjfDaY) |"""
    )

    st.info(
        """
    Use this demo to:
    - Experiment with different off-the-shelf models and NLP packages.
    - Explore the different de-identification options, including redaction, masking, encryption and more.
    - Generate synthetic text with Microsoft Presidio and OpenAI.
    - Configure allow and deny lists.
    
    This demo website shows some of Presidio's capabilities.
    [Visit our website](https://microsoft.github.io/presidio) for more info,
    samples and deployment options.    
    """
    )

    st.markdown(
        "[![Pypi Downloads](https://img.shields.io/pypi/dm/presidio-analyzer.svg)](https://img.shields.io/pypi/dm/presidio-analyzer.svg)"  # noqa
        "[![MIT license](https://img.shields.io/badge/license-MIT-brightgreen.svg)](https://opensource.org/licenses/MIT)"
        "![GitHub Repo stars](https://img.shields.io/github/stars/microsoft/presidio?style=social)"
    )

analyzer_load_state = st.info("Starting Presidio analyzer...")

analyzer_load_state.empty()

# Read default text
with open("demo_text.txt") as f:
    demo_text = f.readlines()

# Create two columns for before and after
col1, col2 = st.columns(2)

# Before:
col1.subheader("Input")
st_text = col1.text_area(
    label="Enter text", value="".join(demo_text), height=400, key="text_input"
)

try:
    # Choose entities
    st_entities_expander = st.sidebar.expander("Choose entities to look for")
    st_entities = st_entities_expander.multiselect(
        label="Which entities to look for?",
        options=get_supported_entities(*analyzer_params),
        default=list(get_supported_entities(*analyzer_params)),
        help="Limit the list of PII entities detected. "
        "This list is dynamic and based on the NER model and registered recognizers. "
        "More information can be found here: https://microsoft.github.io/presidio/analyzer/adding_recognizers/",
    )

    # Before
    analyzer_load_state = st.info("Starting Presidio analyzer...")
    analyzer = analyzer_engine(*analyzer_params)
    analyzer_load_state.empty()

    st_analyze_results = analyze(
        *analyzer_params,
        text=st_text,
        entities=st_entities,
        language="en",
        score_threshold=st_threshold,
        return_decision_process=st_return_decision_process,
        allow_list=st_allow_list,
        deny_list=st_deny_list,
    )

    # After
    if st_operator not in ("highlight", "synthesize"):
        with col2:
            st.subheader(f"Output")
            st_anonymize_results = anonymize(
                text=st_text,
                operator=st_operator,
                mask_char=st_mask_char,
                number_of_chars=st_number_of_chars,
                encrypt_key=st_encrypt_key,
                analyze_results=st_analyze_results,
            )
            st.text_area(
                label="De-identified", value=st_anonymize_results.text, height=400
            )
    elif st_operator == "synthesize":
        with col2:
            st.subheader(f"OpenAI Generated output")
            fake_data = create_fake_data(
                st_text,
                st_analyze_results,
                open_ai_params,
            )
            st.text_area(label="Synthetic data", value=fake_data, height=400)
    else:
        st.subheader("Highlighted")
        annotated_tokens = annotate(text=st_text, analyze_results=st_analyze_results)
        # annotated_tokens
        annotated_text(*annotated_tokens)

    # table result
    st.subheader(
        "Findings"
        if not st_return_decision_process
        else "Findings with decision factors"
    )
    if st_analyze_results:
        df = pd.DataFrame.from_records([r.to_dict() for r in st_analyze_results])
        df["text"] = [st_text[res.start : res.end] for res in st_analyze_results]

        df_subset = df[["entity_type", "text", "start", "end", "score"]].rename(
            {
                "entity_type": "Entity type",
                "text": "Text",
                "start": "Start",
                "end": "End",
                "score": "Confidence",
            },
            axis=1,
        )
        df_subset["Text"] = [st_text[res.start : res.end] for res in st_analyze_results]
        if st_return_decision_process:
            analysis_explanation_df = pd.DataFrame.from_records(
                [r.analysis_explanation.to_dict() for r in st_analyze_results]
            )
            df_subset = pd.concat([df_subset, analysis_explanation_df], axis=1)
        st.dataframe(df_subset.reset_index(drop=True), use_container_width=True)
    else:
        st.text("No findings")

except Exception as e:
    print(e)
    traceback.print_exc()
    st.error(e)

components.html(
    """
    <script type="text/javascript">
    (function(c,l,a,r,i,t,y){
        c[a]=c[a]||function(){(c[a].q=c[a].q||[]).push(arguments)};
        t=l.createElement(r);t.async=1;t.src="https://www.clarity.ms/tag/"+i;
        y=l.getElementsByTagName(r)[0];y.parentNode.insertBefore(t,y);
    })(window, document, "clarity", "script", "h7f8bp42n8");
    </script>
    """
)