File size: 7,147 Bytes
7172378
41e004f
 
28a039d
 
41e004f
 
 
 
28a039d
7172378
 
28a039d
 
 
 
 
 
41e004f
28a039d
41e004f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
28a039d
41e004f
28a039d
41e004f
28a039d
41e004f
 
 
 
 
 
 
 
28a039d
41e004f
28a039d
41e004f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
28a039d
 
 
 
41e004f
 
 
28a039d
 
 
 
 
 
 
 
 
 
 
 
41e004f
28a039d
 
41e004f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
28a039d
 
 
 
41e004f
 
 
28a039d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
41e004f
 
28a039d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
41e004f
28a039d
 
 
 
 
 
 
41e004f
28a039d
 
 
 
 
 
 
41e004f
 
 
28a039d
 
 
 
 
 
 
41e004f
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
import logging
from typing import Tuple

import spacy
from presidio_analyzer import RecognizerRegistry
from presidio_analyzer.nlp_engine import (
    NlpEngine,
    NlpEngineProvider,
)

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


def create_nlp_engine_with_spacy(
    model_path: str,
) -> Tuple[NlpEngine, RecognizerRegistry]:
    """
    Instantiate an NlpEngine with a spaCy model
    :param model_path: path to model / model name.
    """
    nlp_configuration = {
        "nlp_engine_name": "spacy",
        "models": [{"lang_code": "en", "model_name": model_path}],
        "ner_model_configuration": {
            "model_to_presidio_entity_mapping": {
                "PER": "PERSON",
                "PERSON": "PERSON",
                "NORP": "NRP",
                "FAC": "FACILITY",
                "LOC": "LOCATION",
                "GPE": "LOCATION",
                "LOCATION": "LOCATION",
                "ORG": "ORGANIZATION",
                "ORGANIZATION": "ORGANIZATION",
                "DATE": "DATE_TIME",
                "TIME": "DATE_TIME",
            },
            "low_confidence_score_multiplier": 0.4,
            "low_score_entity_names": ["ORG", "ORGANIZATION"],
        },
    }

    nlp_engine = NlpEngineProvider(nlp_configuration=nlp_configuration).create_engine()

    registry = RecognizerRegistry()
    registry.load_predefined_recognizers(nlp_engine=nlp_engine)

    return nlp_engine, registry


def create_nlp_engine_with_stanza(
    model_path: str,
) -> Tuple[NlpEngine, RecognizerRegistry]:
    """
    Instantiate an NlpEngine with a stanza model
    :param model_path: path to model / model name.
    """
    nlp_configuration = {
        "nlp_engine_name": "stanza",
        "models": [{"lang_code": "en", "model_name": model_path}],
        "ner_model_configuration": {
            "model_to_presidio_entity_mapping": {
                "PER": "PERSON",
                "PERSON": "PERSON",
                "NORP": "NRP",
                "FAC": "FACILITY",
                "LOC": "LOCATION",
                "GPE": "LOCATION",
                "LOCATION": "LOCATION",
                "ORG": "ORGANIZATION",
                "ORGANIZATION": "ORGANIZATION",
                "DATE": "DATE_TIME",
                "TIME": "DATE_TIME",
            }
        },
    }

    nlp_engine = NlpEngineProvider(nlp_configuration=nlp_configuration).create_engine()

    registry = RecognizerRegistry()
    registry.load_predefined_recognizers(nlp_engine=nlp_engine)

    return nlp_engine, registry


def create_nlp_engine_with_transformers(
    model_path: str,
) -> Tuple[NlpEngine, RecognizerRegistry]:
    """
    Instantiate an NlpEngine with a TransformersRecognizer and a small spaCy model.
    The TransformersRecognizer would return results from Transformers models, the spaCy model
    would return NlpArtifacts such as POS and lemmas.
    :param model_path: HuggingFace model path.
    """
    print(f"Loading Transformers model: {model_path} of type {type(model_path)}")

    nlp_configuration = {
        "nlp_engine_name": "transformers",
        "models": [
            {
                "lang_code": "en",
                "model_name": {"spacy": "en_core_web_sm", "transformers": model_path},
            }
        ],
        "ner_model_configuration": {
            "model_to_presidio_entity_mapping": {
                "PER": "PERSON",
                "PERSON": "PERSON",
                "LOC": "LOCATION",
                "LOCATION": "LOCATION",
                "GPE": "LOCATION",
                "ORG": "ORGANIZATION",
                "ORGANIZATION": "ORGANIZATION",
                "NORP": "NRP",
                "AGE": "AGE",
                "ID": "ID",
                "EMAIL": "EMAIL",
                "PATIENT": "PERSON",
                "STAFF": "PERSON",
                "HOSP": "ORGANIZATION",
                "PATORG": "ORGANIZATION",
                "DATE": "DATE_TIME",
                "TIME": "DATE_TIME",
                "PHONE": "PHONE_NUMBER",
                "HCW": "PERSON",
                "HOSPITAL": "ORGANIZATION",
                "FACILITY": "LOCATION",
            },
            "low_confidence_score_multiplier": 0.4,
            "low_score_entity_names": ["ID"],
            "labels_to_ignore": [
                "CARDINAL",
                "EVENT",
                "LANGUAGE",
                "LAW",
                "MONEY",
                "ORDINAL",
                "PERCENT",
                "PRODUCT",
                "QUANTITY",
                "WORK_OF_ART",
            ],
        },
    }

    nlp_engine = NlpEngineProvider(nlp_configuration=nlp_configuration).create_engine()

    registry = RecognizerRegistry()
    registry.load_predefined_recognizers(nlp_engine=nlp_engine)

    return nlp_engine, registry


def create_nlp_engine_with_flair(
    model_path: str,
) -> Tuple[NlpEngine, RecognizerRegistry]:
    """
    Instantiate an NlpEngine with a FlairRecognizer and a small spaCy model.
    The FlairRecognizer would return results from Flair models, the spaCy model
    would return NlpArtifacts such as POS and lemmas.
    :param model_path: Flair model path.
    """
    from flair_recognizer import FlairRecognizer

    registry = RecognizerRegistry()
    registry.load_predefined_recognizers()

    # there is no official Flair NlpEngine, hence we load it as an additional recognizer

    if not spacy.util.is_package("en_core_web_sm"):
        spacy.cli.download("en_core_web_sm")
    # Using a small spaCy model + a Flair NER model
    flair_recognizer = FlairRecognizer(model_path=model_path)
    nlp_configuration = {
        "nlp_engine_name": "spacy",
        "models": [{"lang_code": "en", "model_name": "en_core_web_sm"}],
    }
    registry.add_recognizer(flair_recognizer)
    registry.remove_recognizer("SpacyRecognizer")

    nlp_engine = NlpEngineProvider(nlp_configuration=nlp_configuration).create_engine()

    return nlp_engine, registry


def create_nlp_engine_with_azure_ai_language(ta_key: str, ta_endpoint: str):
    """
    Instantiate an NlpEngine with a TextAnalyticsWrapper and a small spaCy model.
    The TextAnalyticsWrapper would return results from calling Azure Text Analytics PII, the spaCy model
    would return NlpArtifacts such as POS and lemmas.
    :param ta_key: Azure Text Analytics key.
    :param ta_endpoint: Azure Text Analytics endpoint.
    """
    from azure_ai_language_wrapper import AzureAIServiceWrapper

    if not ta_key or not ta_endpoint:
        raise RuntimeError("Please fill in the Text Analytics endpoint details")

    registry = RecognizerRegistry()
    registry.load_predefined_recognizers()

    azure_ai_language_recognizer = AzureAIServiceWrapper(
        ta_endpoint=ta_endpoint, ta_key=ta_key
    )
    nlp_configuration = {
        "nlp_engine_name": "spacy",
        "models": [{"lang_code": "en", "model_name": "en_core_web_sm"}],
    }

    nlp_engine = NlpEngineProvider(nlp_configuration=nlp_configuration).create_engine()

    registry.add_recognizer(azure_ai_language_recognizer)
    registry.remove_recognizer("SpacyRecognizer")

    return nlp_engine, registry