Duplicate from langdonholmes/piilo

Co-authored-by: Langdon Holmes <[email protected]>

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1 @@
+__pycache__/*

LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

Pipfile

@@ -0,0 +1,22 @@
+[[source]]
+url = "https://pypi.org/simple"
+verify_ssl = true
+name = "pypi"
+
+[packages]
+pandas = "==1.4.3"
+presidio-analyzer = "==2.2.28"
+presidio-anonymizer = "==2.2.28"
+spacy = "==3.4.1"
+spacy-transformers = "==1.1.7"
+st-annotated-text = "==3.0.0"
+streamlit = "==1.17.0"
+tokenizers = "==0.12.1"
+torch = "==1.12.0"
+en-student-name-detector = {file = "https://huggingface.co/langdonholmes/en_student_name_detector/resolve/main/en_student_name_detector-any-py3-none-any.whl"}
+names-dataset = "*"
+
+[dev-packages]
+
+[requires]
+python_version = "3.10"

README.md

@@ -0,0 +1,26 @@
+---
+title: Piilo
+emoji: 🏃
+colorFrom: purple
+colorTo: purple
+sdk: streamlit
+sdk_version: 1.10.0
+app_file: app.py
+pinned: false
+license: apache-2.0
+duplicated_from: langdonholmes/piilo
+---
+
+For development, try working with pipenv:
+
+1. Clone the repository
+`git clone https://huggingface.co/spaces/langdonholmes/piilo`
+
+2. Install dependencies from Pipfile
+`pip install --user pipenv`
+
+3. Run streamlit app
+`streamlit run .\app.py`
+
+TODO:
+Create a command line version using Typer in this same repository.

analyzer.py

@@ -0,0 +1,141 @@
+import logging
+from typing import Optional, List, Tuple, Set
+
+from presidio_analyzer import (AnalysisExplanation, AnalyzerEngine,
+                               LocalRecognizer, RecognizerRegistry,
+                               RecognizerResult)
+from presidio_analyzer.nlp_engine import NlpArtifacts, NlpEngineProvider
+
+logger = logging.getLogger('presidio-analyzer')
+
+class CustomSpacyRecognizer(LocalRecognizer):
+    ENTITIES = [
+        'STUDENT',
+    ]
+
+    DEFAULT_EXPLANATION = 'Identified as {} by a Student Name Detection Model'
+
+    CHECK_LABEL_GROUPS = [
+        ({'STUDENT'}, {'STUDENT'}),
+    ]
+
+    MODEL_LANGUAGES = {
+        'en': 'langdonholmes/en_student_name_detector',
+    }
+
+    def __init__(
+        self,
+        supported_language: str = 'en',
+        supported_entities: Optional[List[str]] = None,
+        check_label_groups: Optional[Tuple[Set, Set]] = None,
+        ner_strength: float = 0.85,
+    ):
+        self.ner_strength = ner_strength
+        self.check_label_groups = (
+            check_label_groups if check_label_groups else self.CHECK_LABEL_GROUPS
+        )
+        supported_entities = supported_entities if supported_entities else self.ENTITIES
+        super().__init__(
+            supported_entities=supported_entities,
+            supported_language=supported_language,
+        )
+
+    def load(self) -> None:
+        '''Load the model, not used. Model is loaded during initialization.'''
+        pass
+
+    def get_supported_entities(self) -> List[str]:
+        '''
+        Return supported entities by this model.
+        :return: List of the supported entities.
+        '''
+        return self.supported_entities
+
+    def build_spacy_explanation(
+        self, original_score: float, explanation: str
+    ) -> AnalysisExplanation:
+        '''
+        Create explanation for why this result was detected.
+        :param original_score: Score given by this recognizer
+        :param explanation: Explanation string
+        :return:
+        '''
+        explanation = AnalysisExplanation(
+            recognizer=self.__class__.__name__,
+            original_score=original_score,
+            textual_explanation=explanation,
+        )
+        return explanation
+
+    def analyze(self,
+                text: str,
+                entities: List[str] = None,
+                nlp_artifacts: NlpArtifacts = None):
+        '''Analyze input using Analyzer engine and input arguments (kwargs).'''
+        
+        if not entities or 'All' in entities:
+            entities = None
+    
+        results = []
+        
+        if not nlp_artifacts:
+            logger.warning('Skipping SpaCy, nlp artifacts not provided...')
+            return results
+
+        ner_entities = nlp_artifacts.entities
+
+        for entity in entities:
+            if entity not in self.supported_entities:
+                continue
+            for ent in ner_entities:
+                if not self.__check_label(entity, ent.label_, self.check_label_groups):
+                    continue
+                textual_explanation = self.DEFAULT_EXPLANATION.format(
+                    ent.label_)
+                explanation = self.build_spacy_explanation(
+                    self.ner_strength, textual_explanation
+                )
+                spacy_result = RecognizerResult(
+                    entity_type=entity,
+                    start=ent.start_char,
+                    end=ent.end_char,
+                    score=self.ner_strength,
+                    analysis_explanation=explanation,
+                    recognition_metadata={
+                        RecognizerResult.RECOGNIZER_NAME_KEY: self.name
+                    },
+                )
+                results.append(spacy_result)
+
+        return results
+
+    @staticmethod
+    def __check_label(
+        entity: str, label: str, check_label_groups: Tuple[Set, Set]
+    ) -> bool:
+        return any(
+            [entity in egrp and label in lgrp for egrp, lgrp in check_label_groups]
+        )
+
+def prepare_analyzer(configuration):
+    '''Handle Preparation of Analyzer Engine for Presidio.'''
+
+    spacy_recognizer = CustomSpacyRecognizer()
+
+    # Create NLP engine based on configuration
+    provider = NlpEngineProvider(nlp_configuration=configuration)
+    nlp_engine = provider.create_engine()
+
+    # add rule-based recognizers
+    registry = RecognizerRegistry()
+    registry.load_predefined_recognizers(nlp_engine=nlp_engine)
+    registry.add_recognizer(spacy_recognizer)
+
+    # remove the nlp engine we passed, to use custom label mappings
+    registry.remove_recognizer('SpacyRecognizer')
+
+    analyzer = AnalyzerEngine(nlp_engine=nlp_engine,
+                              registry=registry,
+                              supported_languages=['en'])
+
+    return analyzer

anonymizer.py

@@ -0,0 +1,140 @@
+import logging
+from pathlib import Path
+from typing import List, Optional, Tuple
+
+import pandas as pd
+from presidio_analyzer import RecognizerResult
+from presidio_anonymizer import AnonymizerEngine
+from presidio_anonymizer.entities import OperatorConfig
+from presidio_anonymizer.operators import OperatorType
+
+from names_database import NameDatabase
+
+name_table = Path('data', 'ascii_names.parquet')
+
+logger = logging.getLogger('anonymizer')
+
+class surrogate_anonymizer(AnonymizerEngine):
+    def __init__(self):
+        super().__init__()
+        self.names_db = NameDatabase()
+        self.names_df = pd.read_parquet(name_table)
+        
+    def get_random_name(
+            self,
+            country: Optional[str] = None,
+            gender: Optional[str] = None
+    ) -> pd.DataFrame:
+        '''Returns two random names from the database as a DataFrame.
+        Both rows match gender and country, if provided.
+        :country: ISO country code e.g. "CO" for Columbia
+        :gender: 'M' or 'F'
+        returns two rows of the names dataframe
+        '''
+        names_view = self.names_df
+        if country:
+            names_view = names_view[names_view['country'] == country]
+        if gender:
+            names_view = names_view[names_view['gender'] == gender]
+        if names_view.size < 25:
+            return self.names_df.sample(n=2, weights=self.names_df['count'])
+        return names_view.sample(n=2, weights=names_view['count'])
+
+    def split_name(self, original_name: str) -> Tuple[str]:
+        '''Splits name into parts.
+        If one token, assume it is a first name.
+        If two tokens, first and last name.
+        If three tokens, one first name and two last names.
+        If four tokens, two first names and two last names.'''
+        names = original_name.split()
+        if len(names) == 1:
+            logger.info(f'Splitting to 1 first name: {names}')
+            return names[0], None
+        elif len(names) == 2:
+            logger.info(f'Splitting to 1 first name, 1 last name: {names}')
+            return names[0], names[1]
+        elif len(names) == 3:
+            logger.info(f'Splitting to 1 first name, 2 last names: {names}')
+            return names[0], ' '.join(names[1:])
+        elif len(names) == 4:
+            logger.info(f'Splitting to 2 first names and 2 last names: {names}')
+            return ' '.join(names[:2]), ' '.join(names[2:])
+        else:
+            logger.info(f'Splitting failed, do not match gender/country: {names}')
+            return None, None
+
+    def generate_surrogate(self, original_name: str) -> str:
+        '''Generate a surrogate name.
+        '''
+        if original_name == 'PII':
+            # Every time we call this function, Presidio will validate it
+            # by testing that the function returns a str when the input is
+            # 'PII'. Bypass this test.
+            return 'PII'
+        
+        first_names, last_names = self.split_name(original_name)
+        gender = self.names_db.get_gender(first_names) if first_names else None
+        logger.debug(f'Gender set to {gender}')
+        country = self.names_db.get_country(last_names) if last_names else None
+        logger.debug(f'Country set to {country}')
+        
+        surrogate_name = ''
+        
+        name_candidates = self.get_random_name(gender=gender, country=country)
+        
+        surrogate_name += name_candidates.iloc[0]['first']
+        logger.info(f'First name surrogate is {surrogate_name}')
+        
+        if last_names:
+            logger.info(f'Combining with {name_candidates.iloc[1]["last"]}')
+            surrogate_name += ' ' + name_candidates.iloc[1]['last']
+            
+        logger.info(f'Returning surrogate name {surrogate_name}')
+        return surrogate_name
+
+    def anonymize(
+        self,
+        text: str,
+        analyzer_results: List[RecognizerResult]
+        ):
+        '''Anonymize identified input using Presidio Anonymizer.'''
+        
+        if not text:
+            return
+
+        analyzer_results = self._remove_conflicts_and_get_text_manipulation_data(
+            analyzer_results
+        )
+                
+        operators = self._AnonymizerEngine__check_or_add_default_operator(
+            {
+            'STUDENT': OperatorConfig('custom',
+                                      {'lambda': self.generate_surrogate}),
+            'EMAIL_ADDRESS': OperatorConfig('replace',
+                                            {'new_value': '[email protected]'}),
+            'PHONE_NUMBER': OperatorConfig('replace',
+                                           {'new_value': '888-888-8888'}),
+            'URL': OperatorConfig('replace',
+                                  {'new_value': 'aol.com'}),
+            }
+        )
+        
+        res = self._operate(text,
+                            analyzer_results,
+                            operators,
+                            OperatorType.Anonymize)
+                
+        return res.text
+
+if __name__ == '__main__':
+    logging.basicConfig(level=logging.DEBUG)
+    anonymizer = surrogate_anonymizer()
+    test_names = ['Nora Wang',
+                  'MJ',
+                  '',
+                  '(',
+                  'Mario Escobar Sanchez',
+                  'Jane Fonda Michelle Rousseau',
+                  'Sir Phillipe Ricardo de la Sota Mayor']
+    for name in test_names:
+        anonymizer.generate_surrogate(name)

app.py

@@ -0,0 +1,160 @@
+
+'''Streamlit app for Student Name Detection models.'''
+
+from analyzer import prepare_analyzer
+from anonymizer import surrogate_anonymizer
+from presidio_anonymizer import AnonymizerEngine
+import pandas as pd
+from annotated_text import annotated_text
+from json import JSONEncoder
+import json
+import warnings
+import streamlit as st
+import os
+os.environ['TOKENIZERS_PARALLELISM'] = 'false'
+warnings.filterwarnings('ignore')
+
+# Helper methods
+@st.cache(allow_output_mutation=True)
+def analyzer_engine():
+    '''Return AnalyzerEngine and cache with Streamlit.'''
+
+    configuration = {
+        'nlp_engine_name': 'spacy',
+        'models': [
+            {'lang_code': 'en', 'model_name': 'en_student_name_detector'}],
+    }
+
+    analyzer = prepare_analyzer(configuration)
+
+    return analyzer
+
+@st.cache(allow_output_mutation=True)
+def anonymizer_engine():
+    '''Return generate surrogate anonymizer.'''
+    return surrogate_anonymizer()
+
+def annotate(text, st_analyze_results, st_entities):
+    tokens = []
+    # sort by start index
+    results = sorted(st_analyze_results, 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
+
+
+st.set_page_config(page_title='Student Name Detector (English)', layout='wide')
+
+# Side bar
+st.sidebar.markdown(
+    '''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.
+'''
+)
+
+st_entities = st.sidebar.multiselect(
+    label='Which entities to look for?',
+    options=analyzer_engine().get_supported_entities(),
+    default=list(analyzer_engine().get_supported_entities()),
+)
+
+st_threshold = st.sidebar.slider(
+    label='Acceptance threshold', min_value=0.0, max_value=1.0, value=0.35
+)
+
+st_return_decision_process = st.sidebar.checkbox(
+    'Add analysis explanations in json')
+
+st.sidebar.info(
+    'This is part of a deidentification project for student-generated text.'
+)
+
+# Main panel
+analyzer_load_state = st.info(
+    'Starting Presidio analyzer and loading Longformer-based model...')
+engine = analyzer_engine()
+analyzer_load_state.empty()
+
+
+st_text = st.text_area(
+    label='Type in some text',
+    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]',
+    height=200,
+)
+
+button = st.button('Detect PII')
+
+if 'first_load' not in st.session_state:
+    st.session_state['first_load'] = True
+
+# After
+st.subheader('Analyzed')
+with st.spinner('Analyzing...'):
+    if button or st.session_state.first_load:
+        st_analyze_results = analyzer_engine().analyze(
+            text=st_text,
+            entities=st_entities,
+            language='en',
+            score_threshold=st_threshold,
+            return_decision_process=st_return_decision_process,
+        )
+        annotated_tokens = annotate(st_text, st_analyze_results, st_entities)
+        # annotated_tokens
+        annotated_text(*annotated_tokens)
+
+# vertical space
+st.text('')
+
+st.subheader('Anonymized')
+with st.spinner('Anonymizing...'):
+    if button or st.session_state.first_load:
+        st_anonymize_results = anonymizer_engine().anonymize(
+                                         st_text,
+                                         st_analyze_results)
+        st_anonymize_results
+        
+# table result
+st.subheader('Detailed Findings')
+if st_analyze_results:
+    res_dicts = [r.to_dict() for r in st_analyze_results]
+    for d in res_dicts:
+        d['Value'] = st_text[d['start']:d['end']]
+    df = pd.DataFrame.from_records(res_dicts)
+    df = df[['entity_type', 'Value', 'score', 'start', 'end']].rename(
+        {
+            'entity_type': 'Entity type',
+            'start': 'Start',
+            'end': 'End',
+            'score': 'Confidence',
+        },
+        axis=1,
+    )
+
+    st.dataframe(df, width=1000)
+else:
+    st.text('No findings')
+
+st.session_state['first_load'] = True
+
+# json result
+class ToDictListEncoder(JSONEncoder):
+    '''Encode dict to json.'''
+
+    def default(self, o):
+        '''Encode to JSON using to_dict.'''
+        if o:
+            return o.to_dict()
+        return []
+
+if st_return_decision_process:
+    st.json(json.dumps(st_analyze_results, cls=ToDictListEncoder))

data/ascii_names.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baf5cf2fa43dc172c613f72793641f668e33c30b4e23932616de36cc0ce3447d
+size 33601747

names_database.py

@@ -0,0 +1,35 @@
+import logging
+
+
+from names_dataset import NameDataset, NameWrapper
+
+
+class NameDatabase(NameDataset):
+    def __init__(self) -> None:
+        super().__init__()
+        
+        self.logger = logging.getLogger('anonymizer')
+    
+    def search(self, name: str) -> dict:
+        '''Returns all entries associated with a name string.
+        The name string can be multiple tokens. 
+        Both first and last names will be matched.
+        '''
+        key = name.strip().title()
+        fn = self.first_names.get(key) if self.first_names is not None else None
+        ln = self.last_names.get(key) if self.last_names is not None else None
+        return {'first_name': fn, 'last_name': ln}
+       
+    def get_gender(self, first_names: str) -> str:
+        '''Return the most frequent gender code for a specific last name,
+        or None if a match cannot be found.
+        '''
+        gender = NameWrapper(self.search(first_names)).gender
+        return gender if gender else None
+
+    def get_country(self, last_names: str) -> str:
+        '''Return the most frequent country code for a specific last name,
+        or None if a match cannot be found.
+        '''
+        country = NameWrapper(self.search(last_names)).country
+        return country if country else None