File size: 7,484 Bytes
28a039d |
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 |
"""
Helper methods for the Presidio Streamlit app
"""
from typing import List, Optional, Tuple
import streamlit as st
from presidio_analyzer import (
AnalyzerEngine,
RecognizerResult,
RecognizerRegistry,
PatternRecognizer,
)
from presidio_analyzer.nlp_engine import NlpEngine
from presidio_anonymizer import AnonymizerEngine
from presidio_anonymizer.entities import OperatorConfig
from openai_fake_data_generator import (
set_openai_key,
call_completion_model,
create_prompt,
)
from presidio_nlp_engine_config import (
create_nlp_engine_with_spacy,
create_nlp_engine_with_flair,
create_nlp_engine_with_transformers,
create_nlp_engine_with_azure_text_analytics,
)
@st.cache_resource
def nlp_engine_and_registry(
model_family: str,
model_path: str,
ta_key: Optional[str] = None,
ta_endpoint: Optional[str] = None,
) -> Tuple[NlpEngine, RecognizerRegistry]:
"""Create the NLP Engine instance based on the requested model.
:param model_family: Which model package to use for NER.
:param model_path: Which model to use for NER. E.g.,
"StanfordAIMI/stanford-deidentifier-base",
"obi/deid_roberta_i2b2",
"en_core_web_lg"
:param ta_key: Key to the Text Analytics endpoint (only if model_path = "Azure Text Analytics")
:param ta_endpoint: Endpoint of the Text Analytics instance (only if model_path = "Azure Text Analytics")
"""
# Set up NLP Engine according to the model of choice
if "spaCy" in model_family:
return create_nlp_engine_with_spacy(model_path)
elif "flair" in model_family:
return create_nlp_engine_with_flair(model_path)
elif "HuggingFace" in model_family:
return create_nlp_engine_with_transformers(model_path)
elif "Azure Text Analytics" in model_family:
return create_nlp_engine_with_azure_text_analytics(ta_key, ta_endpoint)
else:
raise ValueError(f"Model family {model_family} not supported")
@st.cache_resource
def analyzer_engine(
model_family: str,
model_path: str,
ta_key: Optional[str] = None,
ta_endpoint: Optional[str] = None,
) -> AnalyzerEngine:
"""Create the NLP Engine instance based on the requested model.
:param model_family: Which model package to use for NER.
:param model_path: Which model to use for NER:
"StanfordAIMI/stanford-deidentifier-base",
"obi/deid_roberta_i2b2",
"en_core_web_lg"
:param ta_key: Key to the Text Analytics endpoint (only if model_path = "Azure Text Analytics")
:param ta_endpoint: Endpoint of the Text Analytics instance (only if model_path = "Azure Text Analytics")
"""
nlp_engine, registry = nlp_engine_and_registry(
model_family, model_path, ta_key, ta_endpoint
)
analyzer = AnalyzerEngine(nlp_engine=nlp_engine, registry=registry)
return analyzer
@st.cache_resource
def anonymizer_engine():
"""Return AnonymizerEngine."""
return AnonymizerEngine()
@st.cache_data
def get_supported_entities(
model_family: str, model_path: str, ta_key: str, ta_endpoint: str
):
"""Return supported entities from the Analyzer Engine."""
return analyzer_engine(
model_family, model_path, ta_key, ta_endpoint
).get_supported_entities() + ["GENERIC_PII"]
@st.cache_data
def analyze(
model_family: str, model_path: str, ta_key: str, ta_endpoint: str, **kwargs
):
"""Analyze input using Analyzer engine and input arguments (kwargs)."""
if "entities" not in kwargs or "All" in kwargs["entities"]:
kwargs["entities"] = None
if "deny_list" in kwargs and kwargs["deny_list"] is not None:
ad_hoc_recognizer = create_ad_hoc_deny_list_recognizer(kwargs["deny_list"])
kwargs["ad_hoc_recognizers"] = [ad_hoc_recognizer] if ad_hoc_recognizer else []
del kwargs["deny_list"]
return analyzer_engine(model_family, model_path, ta_key, ta_endpoint).analyze(
**kwargs
)
def anonymize(
text: str,
operator: str,
analyze_results: List[RecognizerResult],
mask_char: Optional[str] = None,
number_of_chars: Optional[str] = None,
encrypt_key: Optional[str] = None,
):
"""Anonymize identified input using Presidio Anonymizer.
:param text: Full text
:param operator: Operator name
:param mask_char: Mask char (for mask operator)
:param number_of_chars: Number of characters to mask (for mask operator)
:param encrypt_key: Encryption key (for encrypt operator)
:param analyze_results: list of results from presidio analyzer engine
"""
if operator == "mask":
operator_config = {
"type": "mask",
"masking_char": mask_char,
"chars_to_mask": number_of_chars,
"from_end": False,
}
# Define operator config
elif operator == "encrypt":
operator_config = {"key": encrypt_key}
elif operator == "highlight":
operator_config = {"lambda": lambda x: x}
else:
operator_config = None
# Change operator if needed as intermediate step
if operator == "highlight":
operator = "custom"
elif operator == "synthesize":
operator = "replace"
else:
operator = operator
res = anonymizer_engine().anonymize(
text,
analyze_results,
operators={"DEFAULT": OperatorConfig(operator, operator_config)},
)
return res
def annotate(text: str, analyze_results: List[RecognizerResult]):
"""Highlight the identified PII entities on the original text
:param text: Full text
:param analyze_results: list of results from presidio analyzer engine
"""
tokens = []
# Use the anonymizer to resolve overlaps
results = anonymize(
text=text,
operator="highlight",
analyze_results=analyze_results,
)
# sort by start index
results = sorted(results.items, key=lambda x: x.start)
for i, res in enumerate(results):
if i == 0:
tokens.append(text[: res.start])
# append entity text and entity type
tokens.append((text[res.start : res.end], res.entity_type))
# if another entity coming i.e. we're not at the last results element, add text up to next entity
if i != len(results) - 1:
tokens.append(text[res.end : results[i + 1].start])
# if no more entities coming, add all remaining text
else:
tokens.append(text[res.end :])
return tokens
def create_fake_data(
text: str,
analyze_results: List[RecognizerResult],
openai_key: str,
openai_model_name: str,
):
"""Creates a synthetic version of the text using OpenAI APIs"""
if not openai_key:
return "Please provide your OpenAI key"
results = anonymize(text=text, operator="replace", analyze_results=analyze_results)
set_openai_key(openai_key)
prompt = create_prompt(results.text)
fake = call_openai_api(prompt, openai_model_name)
return fake
@st.cache_data
def call_openai_api(prompt: str, openai_model_name: str) -> str:
fake_data = call_completion_model(prompt, model=openai_model_name)
return fake_data
def create_ad_hoc_deny_list_recognizer(
deny_list=Optional[List[str]],
) -> Optional[PatternRecognizer]:
if not deny_list:
return None
deny_list_recognizer = PatternRecognizer(supported_entity="GENERIC_PII", deny_list=deny_list)
print(deny_list_recognizer.patterns)
return deny_list_recognizer
|