Files
presidio/samples/python/batch_processing/index.html

2296 lines
59 KiB
HTML

<!doctype html>
<html lang="en" class="no-js">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width,initial-scale=1">
<meta name="description" content="PII anonymization for text and images.">
<meta name="author" content="Microsoft">
<link rel="canonical" href="https://microsoft.github.io/presidio/samples/python/batch_processing/">
<link rel="icon" href="../../../assets/ms_icon.png">
<meta name="generator" content="mkdocs-1.5.3, mkdocs-material-9.5.4">
<title>Batch processing - Microsoft Presidio</title>
<link rel="stylesheet" href="../../../assets/stylesheets/main.50c56a3b.min.css">
<link rel="stylesheet" href="../../../assets/stylesheets/palette.06af60db.min.css">
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
<link rel="stylesheet" href="https://fonts.googleapis.com/css?family=Roboto:300,300i,400,400i,700,700i%7CRoboto+Mono:400,400i,700,700i&display=fallback">
<style>:root{--md-text-font:"Roboto";--md-code-font:"Roboto Mono"}</style>
<link rel="stylesheet" href="../../../assets/_mkdocstrings.css">
<link rel="stylesheet" href="../../../css/ansi-colours.css">
<link rel="stylesheet" href="../../../css/jupyter-cells.css">
<link rel="stylesheet" href="../../../css/pandas-dataframe.css">
<script>__md_scope=new URL("../../..",location),__md_hash=e=>[...e].reduce((e,_)=>(e<<5)-e+_.charCodeAt(0),0),__md_get=(e,_=localStorage,t=__md_scope)=>JSON.parse(_.getItem(t.pathname+"."+e)),__md_set=(e,_,t=localStorage,a=__md_scope)=>{try{t.setItem(a.pathname+"."+e,JSON.stringify(_))}catch(e){}}</script>
<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", "5pd40fk720");
</script>
</head>
<body dir="ltr" data-md-color-scheme="default" data-md-color-primary="blue-grey" data-md-color-accent="indigo">
<input class="md-toggle" data-md-toggle="drawer" type="checkbox" id="__drawer" autocomplete="off">
<input class="md-toggle" data-md-toggle="search" type="checkbox" id="__search" autocomplete="off">
<label class="md-overlay" for="__drawer"></label>
<div data-md-component="skip">
<a href="#run-presidio-on-structured-semi-structured-data" class="md-skip">
Skip to content
</a>
</div>
<div data-md-component="announce">
</div>
<header class="md-header md-header--shadow" data-md-component="header">
<nav class="md-header__inner md-grid" aria-label="Header">
<a href="../../.." title="Microsoft Presidio" class="md-header__button md-logo" aria-label="Microsoft Presidio" data-md-component="logo">
<img src="../../../assets/ms_icon.png" alt="logo">
</a>
<label class="md-header__button md-icon" for="__drawer">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M3 6h18v2H3V6m0 5h18v2H3v-2m0 5h18v2H3v-2Z"/></svg>
</label>
<div class="md-header__title" data-md-component="header-title">
<div class="md-header__ellipsis">
<div class="md-header__topic">
<span class="md-ellipsis">
Microsoft Presidio
</span>
</div>
<div class="md-header__topic" data-md-component="header-topic">
<span class="md-ellipsis">
Batch processing
</span>
</div>
</div>
</div>
<label class="md-header__button md-icon" for="__search">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.516 6.516 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5Z"/></svg>
</label>
<div class="md-search" data-md-component="search" role="dialog">
<label class="md-search__overlay" for="__search"></label>
<div class="md-search__inner" role="search">
<form class="md-search__form" name="search">
<input type="text" class="md-search__input" name="query" aria-label="Search" placeholder="Search" autocapitalize="off" autocorrect="off" autocomplete="off" spellcheck="false" data-md-component="search-query" required>
<label class="md-search__icon md-icon" for="__search">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.516 6.516 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5Z"/></svg>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M20 11v2H8l5.5 5.5-1.42 1.42L4.16 12l7.92-7.92L13.5 5.5 8 11h12Z"/></svg>
</label>
<nav class="md-search__options" aria-label="Search">
<button type="reset" class="md-search__icon md-icon" title="Clear" aria-label="Clear" tabindex="-1">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M19 6.41 17.59 5 12 10.59 6.41 5 5 6.41 10.59 12 5 17.59 6.41 19 12 13.41 17.59 19 19 17.59 13.41 12 19 6.41Z"/></svg>
</button>
</nav>
</form>
<div class="md-search__output">
<div class="md-search__scrollwrap" data-md-scrollfix>
<div class="md-search-result" data-md-component="search-result">
<div class="md-search-result__meta">
Initializing search
</div>
<ol class="md-search-result__list" role="presentation"></ol>
</div>
</div>
</div>
</div>
</div>
<div class="md-header__source">
<a href="https://github.com/microsoft/presidio/" title="Go to repository" class="md-source" data-md-component="source">
<div class="md-source__icon md-icon">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512"><!--! Font Awesome Free 6.5.1 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2023 Fonticons, Inc.--><path d="M439.55 236.05 244 40.45a28.87 28.87 0 0 0-40.81 0l-40.66 40.63 51.52 51.52c27.06-9.14 52.68 16.77 43.39 43.68l49.66 49.66c34.23-11.8 61.18 31 35.47 56.69-26.49 26.49-70.21-2.87-56-37.34L240.22 199v121.85c25.3 12.54 22.26 41.85 9.08 55a34.34 34.34 0 0 1-48.55 0c-17.57-17.6-11.07-46.91 11.25-56v-123c-20.8-8.51-24.6-30.74-18.64-45L142.57 101 8.45 235.14a28.86 28.86 0 0 0 0 40.81l195.61 195.6a28.86 28.86 0 0 0 40.8 0l194.69-194.69a28.86 28.86 0 0 0 0-40.81z"/></svg>
</div>
<div class="md-source__repository">
GitHub
</div>
</a>
</div>
</nav>
</header>
<div class="md-container" data-md-component="container">
<main class="md-main" data-md-component="main">
<div class="md-main__inner md-grid">
<div class="md-sidebar md-sidebar--primary" data-md-component="sidebar" data-md-type="navigation" >
<div class="md-sidebar__scrollwrap">
<div class="md-sidebar__inner">
<nav class="md-nav md-nav--primary" aria-label="Navigation" data-md-level="0">
<label class="md-nav__title" for="__drawer">
<a href="../../.." title="Microsoft Presidio" class="md-nav__button md-logo" aria-label="Microsoft Presidio" data-md-component="logo">
<img src="../../../assets/ms_icon.png" alt="logo">
</a>
Microsoft Presidio
</label>
<div class="md-nav__source">
<a href="https://github.com/microsoft/presidio/" title="Go to repository" class="md-source" data-md-component="source">
<div class="md-source__icon md-icon">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512"><!--! Font Awesome Free 6.5.1 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2023 Fonticons, Inc.--><path d="M439.55 236.05 244 40.45a28.87 28.87 0 0 0-40.81 0l-40.66 40.63 51.52 51.52c27.06-9.14 52.68 16.77 43.39 43.68l49.66 49.66c34.23-11.8 61.18 31 35.47 56.69-26.49 26.49-70.21-2.87-56-37.34L240.22 199v121.85c25.3 12.54 22.26 41.85 9.08 55a34.34 34.34 0 0 1-48.55 0c-17.57-17.6-11.07-46.91 11.25-56v-123c-20.8-8.51-24.6-30.74-18.64-45L142.57 101 8.45 235.14a28.86 28.86 0 0 0 0 40.81l195.61 195.6a28.86 28.86 0 0 0 40.8 0l194.69-194.69a28.86 28.86 0 0 0 0-40.81z"/></svg>
</div>
<div class="md-source__repository">
GitHub
</div>
</a>
</div>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../.." class="md-nav__link">
<span class="md-ellipsis">
Home
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../installation/" class="md-nav__link">
<span class="md-ellipsis">
Installation
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../getting_started/" class="md-nav__link">
<span class="md-ellipsis">
Quickstart
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_4" >
<label class="md-nav__link" for="__nav_4" id="__nav_4_label" tabindex="0">
<span class="md-ellipsis">
Handling text
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_4_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_4">
<span class="md-nav__icon md-icon"></span>
Handling text
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../../text_anonymization/" class="md-nav__link">
<span class="md-ellipsis">
Home
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_4_2" >
<label class="md-nav__link" for="__nav_4_2" id="__nav_4_2_label" tabindex="0">
<span class="md-ellipsis">
Step by step tutorial
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="2" aria-labelledby="__nav_4_2_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_4_2">
<span class="md-nav__icon md-icon"></span>
Step by step tutorial
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../../tutorial/" class="md-nav__link">
<span class="md-ellipsis">
Home
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../tutorial/00_getting_started/" class="md-nav__link">
<span class="md-ellipsis">
Getting started
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../tutorial/01_deny_list/" class="md-nav__link">
<span class="md-ellipsis">
Deny-list recognizers
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../tutorial/02_regex/" class="md-nav__link">
<span class="md-ellipsis">
Regex recognizers
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../tutorial/03_rule_based/" class="md-nav__link">
<span class="md-ellipsis">
Rule-based recognizers
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../tutorial/05_languages/" class="md-nav__link">
<span class="md-ellipsis">
Additional models/languages
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../tutorial/04_external_services/" class="md-nav__link">
<span class="md-ellipsis">
External services
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../tutorial/06_context/" class="md-nav__link">
<span class="md-ellipsis">
Context enhancement
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../tutorial/07_decision_process/" class="md-nav__link">
<span class="md-ellipsis">
Decision process
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../tutorial/08_no_code/" class="md-nav__link">
<span class="md-ellipsis">
No-code recognizers
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../tutorial/09_ad_hoc/" class="md-nav__link">
<span class="md-ellipsis">
Ad-hoc recognizers
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../tutorial/10_simple_anonymization/" class="md-nav__link">
<span class="md-ellipsis">
Simple anonymization
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../tutorial/11_custom_anonymization/" class="md-nav__link">
<span class="md-ellipsis">
Custom anonymization
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../tutorial/12_encryption/" class="md-nav__link">
<span class="md-ellipsis">
Encryption/Decryption
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../tutorial/13_allow_list/" class="md-nav__link">
<span class="md-ellipsis">
Allow-lists
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_4_3" >
<label class="md-nav__link" for="__nav_4_3" id="__nav_4_3_label" tabindex="0">
<span class="md-ellipsis">
Presidio Analyzer
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="2" aria-labelledby="__nav_4_3_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_4_3">
<span class="md-nav__icon md-icon"></span>
Presidio Analyzer
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../../analyzer/" class="md-nav__link">
<span class="md-ellipsis">
Home
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_4_3_2" >
<label class="md-nav__link" for="__nav_4_3_2" id="__nav_4_3_2_label" tabindex="0">
<span class="md-ellipsis">
Developing PII recognizers
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="3" aria-labelledby="__nav_4_3_2_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_4_3_2">
<span class="md-nav__icon md-icon"></span>
Developing PII recognizers
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../../analyzer/adding_recognizers/" class="md-nav__link">
<span class="md-ellipsis">
Tutorial
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../analyzer/developing_recognizers/" class="md-nav__link">
<span class="md-ellipsis">
Best practices in developing recognizers
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="../../../analyzer/languages/" class="md-nav__link">
<span class="md-ellipsis">
Multi-language support
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_4_3_4" >
<label class="md-nav__link" for="__nav_4_3_4" id="__nav_4_3_4_label" tabindex="0">
<span class="md-ellipsis">
Customizing the NLP model
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="3" aria-labelledby="__nav_4_3_4_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_4_3_4">
<span class="md-nav__icon md-icon"></span>
Customizing the NLP model
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../../analyzer/customizing_nlp_models/" class="md-nav__link">
<span class="md-ellipsis">
Home
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../analyzer/nlp_engines/spacy_stanza/" class="md-nav__link">
<span class="md-ellipsis">
Spacy/Stanza
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../analyzer/nlp_engines/transformers/" class="md-nav__link">
<span class="md-ellipsis">
Transformers
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="../../../analyzer/decision_process/" class="md-nav__link">
<span class="md-ellipsis">
Tracing the decision process
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_4_4" >
<label class="md-nav__link" for="__nav_4_4" id="__nav_4_4_label" tabindex="0">
<span class="md-ellipsis">
Presidio Anonymizer
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="2" aria-labelledby="__nav_4_4_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_4_4">
<span class="md-nav__icon md-icon"></span>
Presidio Anonymizer
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../../anonymizer/" class="md-nav__link">
<span class="md-ellipsis">
Home
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../anonymizer/adding_operators/" class="md-nav__link">
<span class="md-ellipsis">
Developing PII operators
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_5" >
<label class="md-nav__link" for="__nav_5" id="__nav_5_label" tabindex="0">
<span class="md-ellipsis">
Handling images
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_5_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_5">
<span class="md-nav__icon md-icon"></span>
Handling images
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../../image-redactor/" class="md-nav__link">
<span class="md-ellipsis">
Home
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../image-redactor/evaluating_dicom_redaction/" class="md-nav__link">
<span class="md-ellipsis">
Evaluating DICOM redaction
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="../../" class="md-nav__link">
<span class="md-ellipsis">
Samples
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_7" >
<label class="md-nav__link" for="__nav_7" id="__nav_7_label" tabindex="0">
<span class="md-ellipsis">
General
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_7_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_7">
<span class="md-nav__icon md-icon"></span>
General
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../../supported_entities/" class="md-nav__link">
<span class="md-ellipsis">
Supported entities
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_7_2" >
<label class="md-nav__link" for="__nav_7_2" id="__nav_7_2_label" tabindex="0">
<span class="md-ellipsis">
Development and design
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="2" aria-labelledby="__nav_7_2_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_7_2">
<span class="md-nav__icon md-icon"></span>
Development and design
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../../design/" class="md-nav__link">
<span class="md-ellipsis">
Design
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../development/" class="md-nav__link">
<span class="md-ellipsis">
Setting up a development environment
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../build_release/" class="md-nav__link">
<span class="md-ellipsis">
Build and release process
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../presidio_V2/" class="md-nav__link">
<span class="md-ellipsis">
Changes from V1 to V2
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_7_2_5" >
<label class="md-nav__link" for="__nav_7_2_5" id="__nav_7_2_5_label" tabindex="0">
<span class="md-ellipsis">
Python API reference
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="3" aria-labelledby="__nav_7_2_5_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_7_2_5">
<span class="md-nav__icon md-icon"></span>
Python API reference
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../../api/" class="md-nav__link">
<span class="md-ellipsis">
Home
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../api/analyzer_python/" class="md-nav__link">
<span class="md-ellipsis">
Presidio Analyzer Python API
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../api/anonymizer_python/" class="md-nav__link">
<span class="md-ellipsis">
Presidio Anonymizer Python API
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../api/image_redactor_python/" class="md-nav__link">
<span class="md-ellipsis">
Presidio Image Redactor Python API
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="https://microsoft.github.io/presidio/api-docs/api-docs.html" target="_blank" class="md-nav__link">
<span class="md-ellipsis">
REST API reference
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="../../../community/" class="md-nav__link">
<span class="md-ellipsis">
Community
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../faq/" class="md-nav__link">
<span class="md-ellipsis">
FAQ
</span>
</a>
</li>
<li class="md-nav__item">
<a href="https://huggingface.co/spaces/presidio/presidio_demo" target="_blank" class="md-nav__link">
<span class="md-ellipsis">
Demo
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</div>
</div>
</div>
<div class="md-sidebar md-sidebar--secondary" data-md-component="sidebar" data-md-type="toc" >
<div class="md-sidebar__scrollwrap">
<div class="md-sidebar__inner">
<nav class="md-nav md-nav--secondary" aria-label="Table of contents">
<label class="md-nav__title" for="__toc">
<span class="md-nav__icon md-icon"></span>
Table of contents
</label>
<ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
<li class="md-nav__item">
<a href="#set-up-imports" class="md-nav__link">
<span class="md-ellipsis">
Set up imports
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#example-using-sample-tabular-data" class="md-nav__link">
<span class="md-ellipsis">
Example using sample tabular data
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#example-using-json" class="md-nav__link">
<span class="md-ellipsis">
Example using JSON
</span>
</a>
<nav class="md-nav" aria-label="Example using JSON">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#ignoring-specific-keys" class="md-nav__link">
<span class="md-ellipsis">
Ignoring specific keys
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#ignoring-nested-keys" class="md-nav__link">
<span class="md-ellipsis">
Ignoring nested keys
</span>
</a>
<nav class="md-nav" aria-label="Ignoring nested keys">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#note" class="md-nav__link">
<span class="md-ellipsis">
Note!
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</div>
</div>
</div>
<div class="md-content" data-md-component="content">
<article class="md-content__inner md-typeset">
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/2.0.3/jquery.min.js"></script>
<script>
(function() {
function addWidgetsRenderer() {
var requireJsScript = document.createElement('script');
requireJsScript.src = 'https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js';
var mimeElement = document.querySelector('script[type="application/vnd.jupyter.widget-view+json"]');
var jupyterWidgetsScript = document.createElement('script');
var widgetRendererSrc = 'https://unpkg.com/@jupyter-widgets/html-manager@*/dist/embed-amd.js';
var widgetState;
// Fallback for older version:
try {
widgetState = mimeElement && JSON.parse(mimeElement.innerHTML);
if (widgetState && (widgetState.version_major < 2 || !widgetState.version_major)) {
widgetRendererSrc = 'jupyter-js-widgets@*/dist/embed.js';
}
} catch(e) {}
jupyterWidgetsScript.src = widgetRendererSrc;
document.body.appendChild(requireJsScript);
document.body.appendChild(jupyterWidgetsScript);
}
document.addEventListener('DOMContentLoaded', addWidgetsRenderer);
}());
</script>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="highlight"><pre><span></span><code><span class="c1"># download presidio</span>
<span class="err">!</span><span class="n">pip</span> <span class="n">install</span> <span class="n">presidio_analyzer</span> <span class="n">presidio_anonymizer</span>
<span class="err">!</span><span class="n">python</span> <span class="o">-</span><span class="n">m</span> <span class="n">spacy</span> <span class="n">download</span> <span class="n">en_core_web_lg</span>
</code></pre></div>
</div>
</div>
<div class="cell border-box-sizing text_cell rendered">
<div class="inner_cell">
<div class="text_cell_render border-box-sizing rendered_html">
<p>Path to notebook: <a href="https://www.github.com/microsoft/presidio/blob/main/docs/samples/python/batch_processing.ipynb">https://www.github.com/microsoft/presidio/blob/main/docs/samples/python/batch_processing.ipynb</a></p>
</div>
</div>
</div>
<div class="cell border-box-sizing text_cell rendered">
<div class="inner_cell">
<div class="text_cell_render border-box-sizing rendered_html">
<h1 id="run-presidio-on-structured-semi-structured-data">Run Presidio on structured / semi-structured data</h1>
<p>This sample shows how Presidio could be potentially extended to handle the anonymization of a table or data frame.
It introduces methods for the analysis and anonymization of both lists and dicts. </p>
<p>Note: this sample input here is a Pandas DataFrame and a JSON file, but it can be used in other scenarios such as querying SQL data or using Spark DataFrames.</p>
</div>
</div>
</div>
<div class="cell border-box-sizing text_cell rendered">
<div class="inner_cell">
<div class="text_cell_render border-box-sizing rendered_html">
<h3 id="set-up-imports">Set up imports</h3>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="highlight"><pre><span></span><code><span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">List</span><span class="p">,</span> <span class="n">Optional</span><span class="p">,</span> <span class="n">Dict</span><span class="p">,</span> <span class="n">Union</span><span class="p">,</span> <span class="n">Iterator</span><span class="p">,</span> <span class="n">Iterable</span>
<span class="kn">import</span> <span class="nn">collections</span>
<span class="kn">from</span> <span class="nn">dataclasses</span> <span class="kn">import</span> <span class="n">dataclass</span>
<span class="kn">import</span> <span class="nn">pprint</span>
<span class="kn">import</span> <span class="nn">pandas</span> <span class="k">as</span> <span class="nn">pd</span>
<span class="kn">from</span> <span class="nn">presidio_analyzer</span> <span class="kn">import</span> <span class="n">AnalyzerEngine</span><span class="p">,</span> <span class="n">BatchAnalyzerEngine</span><span class="p">,</span> <span class="n">RecognizerResult</span><span class="p">,</span> <span class="n">DictAnalyzerResult</span>
<span class="kn">from</span> <span class="nn">presidio_anonymizer</span> <span class="kn">import</span> <span class="n">AnonymizerEngine</span><span class="p">,</span> <span class="n">BatchAnonymizerEngine</span>
<span class="kn">from</span> <span class="nn">presidio_anonymizer.entities</span> <span class="kn">import</span> <span class="n">EngineResult</span>
</code></pre></div>
</div>
</div>
<div class="cell border-box-sizing text_cell rendered">
<div class="inner_cell">
<div class="text_cell_render border-box-sizing rendered_html">
<h2 id="example-using-sample-tabular-data">Example using sample tabular data</h2>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="highlight"><pre><span></span><code><span class="n">columns</span> <span class="o">=</span> <span class="p">[</span><span class="s2">&quot;name phrase&quot;</span><span class="p">,</span> <span class="s2">&quot;phone number phrase&quot;</span><span class="p">,</span> <span class="s2">&quot;integer&quot;</span><span class="p">,</span> <span class="s2">&quot;boolean&quot;</span> <span class="p">]</span>
<span class="n">sample_data</span> <span class="o">=</span> <span class="p">[</span>
<span class="p">(</span><span class="s1">&#39;Charlie likes this&#39;</span><span class="p">,</span> <span class="s1">&#39;Please call 212-555-1234 after 2pm&#39;</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="kc">True</span><span class="p">),</span>
<span class="p">(</span><span class="s1">&#39;You should talk to Mike&#39;</span><span class="p">,</span> <span class="s1">&#39;his number is 978-428-7111&#39;</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="kc">False</span><span class="p">),</span>
<span class="p">(</span><span class="s1">&#39;Mary had a little startup&#39;</span><span class="p">,</span> <span class="s1">&#39;Phone number: 202-342-1234&#39;</span><span class="p">,</span> <span class="mi">3</span><span class="p">,</span> <span class="kc">False</span><span class="p">)</span>
<span class="p">]</span>
</code></pre></div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="highlight"><pre><span></span><code><span class="c1"># Create Pandas DataFrame</span>
<span class="n">df</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">(</span><span class="n">sample_data</span><span class="p">,</span><span class="n">columns</span><span class="o">=</span><span class="n">columns</span><span class="p">)</span>
<span class="n">df</span>
</code></pre></div>
</div>
<div class="output_wrapper">
<div class="output">
<div class="output_area">
<div class="output_html rendered_html output_subarea output_execute_result">
<div>
<style scoped="">
.dataframe tbody tr th:only-of-type {
vertical-align: middle;
}
.dataframe tbody tr th {
vertical-align: top;
}
.dataframe thead th {
text-align: right;
}
</style>
<table border="1" class="dataframe">
<thead>
<tr style="text-align: right;">
<th></th>
<th>name phrase</th>
<th>phone number phrase</th>
<th>integer</th>
<th>boolean</th>
</tr>
</thead>
<tbody>
<tr>
<th>0</th>
<td>Charlie likes this</td>
<td>Please call 212-555-1234 after 2pm</td>
<td>1</td>
<td>True</td>
</tr>
<tr>
<th>1</th>
<td>You should talk to Mike</td>
<td>his number is 978-428-7111</td>
<td>2</td>
<td>False</td>
</tr>
<tr>
<th>2</th>
<td>Mary had a little startup</td>
<td>Phone number: 202-342-1234</td>
<td>3</td>
<td>False</td>
</tr>
</tbody>
</table>
</div>
</div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="highlight"><pre><span></span><code><span class="c1"># DataFrame to dict</span>
<span class="n">df_dict</span> <span class="o">=</span> <span class="n">df</span><span class="o">.</span><span class="n">to_dict</span><span class="p">(</span><span class="n">orient</span><span class="o">=</span><span class="s2">&quot;list&quot;</span><span class="p">)</span>
</code></pre></div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="highlight"><pre><span></span><code><span class="n">pprint</span><span class="o">.</span><span class="n">pprint</span><span class="p">(</span><span class="n">df_dict</span><span class="p">)</span>
</code></pre></div>
</div>
<div class="output_wrapper">
<div class="output">
<div class="output_area">
<div class="output_subarea output_stream output_stdout output_text">
<pre>
<code>{'boolean': [True, False, False],
'integer': [1, 2, 3],
'name phrase': ['Charlie likes this',
'You should talk to Mike',
'Mary had a little startup'],
'phone number phrase': ['Please call 212-555-1234 after 2pm',
'his number is 978-428-7111',
'Phone number: 202-342-1234']}
</code>
</pre>
</div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="highlight"><pre><span></span><code><span class="n">analyzer</span> <span class="o">=</span> <span class="n">AnalyzerEngine</span><span class="p">()</span>
<span class="n">batch_analyzer</span> <span class="o">=</span> <span class="n">BatchAnalyzerEngine</span><span class="p">(</span><span class="n">analyzer_engine</span><span class="o">=</span><span class="n">analyzer</span><span class="p">)</span>
<span class="n">batch_anonymizer</span> <span class="o">=</span> <span class="n">BatchAnonymizerEngine</span><span class="p">()</span>
</code></pre></div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="highlight"><pre><span></span><code><span class="n">analyzer_results</span> <span class="o">=</span> <span class="n">batch_analyzer</span><span class="o">.</span><span class="n">analyze_dict</span><span class="p">(</span><span class="n">df_dict</span><span class="p">,</span> <span class="n">language</span><span class="o">=</span><span class="s2">&quot;en&quot;</span><span class="p">)</span>
<span class="n">analyzer_results</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="n">analyzer_results</span><span class="p">)</span>
<span class="n">analyzer_results</span>
</code></pre></div>
</div>
<div class="output_wrapper">
<div class="output">
<div class="output_area">
<div class="output_text output_subarea output_execute_result">
<pre>
<code>[DictAnalyzerResult(key='name phrase', value=['Charlie likes this', 'You should talk to Mike', 'Mary had a little startup'], recognizer_results=[[type: PERSON, start: 0, end: 7, score: 0.85], [type: PERSON, start: 19, end: 23, score: 0.85], [type: PERSON, start: 0, end: 4, score: 0.85]]),
DictAnalyzerResult(key='phone number phrase', value=['Please call 212-555-1234 after 2pm', 'his number is 978-428-7111', 'Phone number: 202-342-1234'], recognizer_results=[[type: DATE_TIME, start: 31, end: 34, score: 0.85, type: PHONE_NUMBER, start: 12, end: 24, score: 0.75], [type: PHONE_NUMBER, start: 14, end: 26, score: 0.75], [type: PHONE_NUMBER, start: 14, end: 26, score: 0.75]]),
DictAnalyzerResult(key='integer', value=[1, 2, 3], recognizer_results=[[], [], []]),
DictAnalyzerResult(key='boolean', value=[True, False, False], recognizer_results=[[], [], []])]</code>
</pre>
</div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="highlight"><pre><span></span><code><span class="n">anonymizer_results</span> <span class="o">=</span> <span class="n">batch_anonymizer</span><span class="o">.</span><span class="n">anonymize_dict</span><span class="p">(</span><span class="n">analyzer_results</span><span class="p">)</span>
</code></pre></div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="highlight"><pre><span></span><code><span class="n">scrubbed_df</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">(</span><span class="n">anonymizer_results</span><span class="p">)</span>
</code></pre></div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="highlight"><pre><span></span><code><span class="n">scrubbed_df</span>
</code></pre></div>
</div>
<div class="output_wrapper">
<div class="output">
<div class="output_area">
<div class="output_html rendered_html output_subarea output_execute_result">
<div>
<style scoped="">
.dataframe tbody tr th:only-of-type {
vertical-align: middle;
}
.dataframe tbody tr th {
vertical-align: top;
}
.dataframe thead th {
text-align: right;
}
</style>
<table border="1" class="dataframe">
<thead>
<tr style="text-align: right;">
<th></th>
<th>name phrase</th>
<th>phone number phrase</th>
<th>integer</th>
<th>boolean</th>
</tr>
</thead>
<tbody>
<tr>
<th>0</th>
<td>&lt;PERSON&gt; likes this</td>
<td>Please call &lt;PHONE_NUMBER&gt; after &lt;DATE_TIME&gt;</td>
<td>1</td>
<td>True</td>
</tr>
<tr>
<th>1</th>
<td>You should talk to &lt;PERSON&gt;</td>
<td>his number is &lt;PHONE_NUMBER&gt;</td>
<td>2</td>
<td>False</td>
</tr>
<tr>
<th>2</th>
<td>&lt;PERSON&gt; had a little startup</td>
<td>Phone number: &lt;PHONE_NUMBER&gt;</td>
<td>3</td>
<td>False</td>
</tr>
</tbody>
</table>
</div>
</div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing text_cell rendered">
<div class="inner_cell">
<div class="text_cell_render border-box-sizing rendered_html">
<h2 id="example-using-json">Example using JSON</h2>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="highlight"><pre><span></span><code><span class="n">nested_dict</span> <span class="o">=</span> <span class="p">{</span>
<span class="s2">&quot;key_a&quot;</span><span class="p">:</span> <span class="p">{</span><span class="s2">&quot;key_a1&quot;</span><span class="p">:</span> <span class="s2">&quot;My phone number is 212-121-1424&quot;</span><span class="p">},</span>
<span class="s2">&quot;key_b&quot;</span><span class="p">:</span> <span class="p">{</span><span class="s2">&quot;www.abc.com&quot;</span><span class="p">},</span>
<span class="s2">&quot;key_c&quot;</span><span class="p">:</span> <span class="mi">3</span><span class="p">,</span>
<span class="s2">&quot;names&quot;</span><span class="p">:</span> <span class="p">[</span><span class="s2">&quot;James Bond&quot;</span><span class="p">,</span> <span class="s2">&quot;Clark Kent&quot;</span><span class="p">,</span> <span class="s2">&quot;Hakeem Olajuwon&quot;</span><span class="p">,</span> <span class="s2">&quot;No name here!&quot;</span><span class="p">]</span>
<span class="p">}</span>
<span class="n">pprint</span><span class="o">.</span><span class="n">pprint</span><span class="p">(</span><span class="n">nested_dict</span><span class="p">)</span>
</code></pre></div>
</div>
<div class="output_wrapper">
<div class="output">
<div class="output_area">
<div class="output_subarea output_stream output_stdout output_text">
<pre>
<code>{'key_a': {'key_a1': 'My phone number is 212-121-1424'},
'key_b': {'www.abc.com'},
'key_c': 3,
'names': ['James Bond', 'Clark Kent', 'Hakeem Olajuwon', 'No name here!']}
</code>
</pre>
</div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="highlight"><pre><span></span><code><span class="c1"># Analyze dict</span>
<span class="n">analyzer_results</span> <span class="o">=</span> <span class="n">batch_analyzer</span><span class="o">.</span><span class="n">analyze_dict</span><span class="p">(</span><span class="n">input_dict</span> <span class="o">=</span> <span class="n">nested_dict</span><span class="p">,</span> <span class="n">language</span><span class="o">=</span><span class="s2">&quot;en&quot;</span><span class="p">)</span>
<span class="c1"># Anonymize dict</span>
<span class="n">anonymizer_results</span> <span class="o">=</span> <span class="n">batch_anonymizer</span><span class="o">.</span><span class="n">anonymize_dict</span><span class="p">(</span><span class="n">analyzer_results</span> <span class="o">=</span> <span class="n">analyzer_results</span><span class="p">)</span>
<span class="n">pprint</span><span class="o">.</span><span class="n">pprint</span><span class="p">(</span><span class="n">anonymizer_results</span><span class="p">)</span>
</code></pre></div>
</div>
<div class="output_wrapper">
<div class="output">
<div class="output_area">
<div class="output_subarea output_stream output_stdout output_text">
<pre>
<code>{'key_a': {'key_a1': 'My phone number is &lt;PHONE_NUMBER&gt;'},
'key_b': ['&lt;URL&gt;'],
'key_c': 3,
'names': ['&lt;PERSON&gt;', '&lt;PERSON&gt;', '&lt;PERSON&gt;', 'No name here!']}
</code>
</pre>
</div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing text_cell rendered">
<div class="inner_cell">
<div class="text_cell_render border-box-sizing rendered_html">
<h3 id="ignoring-specific-keys">Ignoring specific keys</h3>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="highlight"><pre><span></span><code><span class="n">keys_to_skip</span><span class="o">=</span><span class="p">[</span><span class="s2">&quot;key_a1&quot;</span><span class="p">,</span> <span class="s2">&quot;names&quot;</span><span class="p">]</span>
<span class="n">analyzer_results</span> <span class="o">=</span> <span class="n">batch_analyzer</span><span class="o">.</span><span class="n">analyze_dict</span><span class="p">(</span><span class="n">input_dict</span> <span class="o">=</span> <span class="n">nested_dict</span><span class="p">,</span> <span class="n">language</span><span class="o">=</span><span class="s2">&quot;en&quot;</span><span class="p">,</span> <span class="n">keys_to_skip</span><span class="o">=</span><span class="n">keys_to_skip</span><span class="p">)</span>
<span class="c1"># Anonymize dict</span>
<span class="n">anonymizer_results</span> <span class="o">=</span> <span class="n">batch_anonymizer</span><span class="o">.</span><span class="n">anonymize_dict</span><span class="p">(</span><span class="n">analyzer_results</span> <span class="o">=</span> <span class="n">analyzer_results</span><span class="p">)</span>
<span class="n">pprint</span><span class="o">.</span><span class="n">pprint</span><span class="p">(</span><span class="n">anonymizer_results</span><span class="p">)</span>
</code></pre></div>
</div>
<div class="output_wrapper">
<div class="output">
<div class="output_area">
<div class="output_subarea output_stream output_stdout output_text">
<pre>
<code>{'key_a': {'key_a1': 'My phone number is 212-121-1424'},
'key_b': ['&lt;URL&gt;'],
'key_c': 3,
'names': ['James Bond', 'Clark Kent', 'Hakeem Olajuwon', 'No name here!']}
</code>
</pre>
</div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing text_cell rendered">
<div class="inner_cell">
<div class="text_cell_render border-box-sizing rendered_html">
<h3 id="ignoring-nested-keys">Ignoring nested keys</h3>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="highlight"><pre><span></span><code><span class="n">keys_to_skip</span> <span class="o">=</span> <span class="p">[</span><span class="s2">&quot;key_a.key_a1&quot;</span><span class="p">]</span>
<span class="n">analyzer_results</span> <span class="o">=</span> <span class="n">batch_analyzer</span><span class="o">.</span><span class="n">analyze_dict</span><span class="p">(</span><span class="n">input_dict</span> <span class="o">=</span> <span class="n">nested_dict</span><span class="p">,</span> <span class="n">language</span><span class="o">=</span><span class="s2">&quot;en&quot;</span><span class="p">,</span> <span class="n">keys_to_skip</span><span class="o">=</span><span class="n">keys_to_skip</span><span class="p">)</span>
<span class="c1"># Anonymize dict</span>
<span class="n">anonymizer_results</span> <span class="o">=</span> <span class="n">batch_anonymizer</span><span class="o">.</span><span class="n">anonymize_dict</span><span class="p">(</span><span class="n">analyzer_results</span> <span class="o">=</span> <span class="n">analyzer_results</span><span class="p">)</span>
<span class="n">pprint</span><span class="o">.</span><span class="n">pprint</span><span class="p">(</span><span class="n">anonymizer_results</span><span class="p">)</span>
</code></pre></div>
</div>
<div class="output_wrapper">
<div class="output">
<div class="output_area">
<div class="output_subarea output_stream output_stdout output_text">
<pre>
<code>{'key_a': {'key_a1': 'My phone number is 212-121-1424'},
'key_b': ['&lt;URL&gt;'],
'key_c': 3,
'names': ['&lt;PERSON&gt;', '&lt;PERSON&gt;', '&lt;PERSON&gt;', 'No name here!']}
</code>
</pre>
</div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing text_cell rendered">
<div class="inner_cell">
<div class="text_cell_render border-box-sizing rendered_html">
<h4 id="note"><strong>Note!</strong></h4>
<p>JSON files with objects within lists, e.g.:
<div class="highlight"><pre><span></span><code>{
&quot;key&quot;: [
{
&quot;key2&quot;: &quot;Peter Parker&quot;
},
{
&quot;key3&quot;: &quot;555-1234&quot;
}
]
}
</code></pre></div></p>
<p>Are not yet supported. Consider breaking the JSON to parts if needed.</p>
</div>
</div>
</div>
</article>
</div>
<script>var tabs=__md_get("__tabs");if(Array.isArray(tabs))e:for(var set of document.querySelectorAll(".tabbed-set")){var tab,labels=set.querySelector(".tabbed-labels");for(tab of tabs)for(var label of labels.getElementsByTagName("label"))if(label.innerText.trim()===tab){var input=document.getElementById(label.htmlFor);input.checked=!0;continue e}}</script>
<script>var target=document.getElementById(location.hash.slice(1));target&&target.name&&(target.checked=target.name.startsWith("__tabbed_"))</script>
</div>
</main>
<footer class="md-footer">
<div class="md-footer-meta md-typeset">
<div class="md-footer-meta__inner md-grid">
<div class="md-copyright">
Made with
<a href="https://squidfunk.github.io/mkdocs-material/" target="_blank" rel="noopener">
Material for MkDocs
</a>
</div>
<div class="md-social">
<a href="https://github.com/microsoft/presidio" target="_blank" rel="noopener" title="github.com" class="md-social__link">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 496 512"><!--! Font Awesome Free 6.5.1 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2023 Fonticons, Inc.--><path d="M165.9 397.4c0 2-2.3 3.6-5.2 3.6-3.3.3-5.6-1.3-5.6-3.6 0-2 2.3-3.6 5.2-3.6 3-.3 5.6 1.3 5.6 3.6zm-31.1-4.5c-.7 2 1.3 4.3 4.3 4.9 2.6 1 5.6 0 6.2-2s-1.3-4.3-4.3-5.2c-2.6-.7-5.5.3-6.2 2.3zm44.2-1.7c-2.9.7-4.9 2.6-4.6 4.9.3 2 2.9 3.3 5.9 2.6 2.9-.7 4.9-2.6 4.6-4.6-.3-1.9-3-3.2-5.9-2.9zM244.8 8C106.1 8 0 113.3 0 252c0 110.9 69.8 205.8 169.5 239.2 12.8 2.3 17.3-5.6 17.3-12.1 0-6.2-.3-40.4-.3-61.4 0 0-70 15-84.7-29.8 0 0-11.4-29.1-27.8-36.6 0 0-22.9-15.7 1.6-15.4 0 0 24.9 2 38.6 25.8 21.9 38.6 58.6 27.5 72.9 20.9 2.3-16 8.8-27.1 16-33.7-55.9-6.2-112.3-14.3-112.3-110.5 0-27.5 7.6-41.3 23.6-58.9-2.6-6.5-11.1-33.3 2.6-67.9 20.9-6.5 69 27 69 27 20-5.6 41.5-8.5 62.8-8.5s42.8 2.9 62.8 8.5c0 0 48.1-33.6 69-27 13.7 34.7 5.2 61.4 2.6 67.9 16 17.7 25.8 31.5 25.8 58.9 0 96.5-58.9 104.2-114.8 110.5 9.2 7.9 17 22.9 17 46.4 0 33.7-.3 75.4-.3 83.6 0 6.5 4.6 14.4 17.3 12.1C428.2 457.8 496 362.9 496 252 496 113.3 383.5 8 244.8 8zM97.2 352.9c-1.3 1-1 3.3.7 5.2 1.6 1.6 3.9 2.3 5.2 1 1.3-1 1-3.3-.7-5.2-1.6-1.6-3.9-2.3-5.2-1zm-10.8-8.1c-.7 1.3.3 2.9 2.3 3.9 1.6 1 3.6.7 4.3-.7.7-1.3-.3-2.9-2.3-3.9-2-.6-3.6-.3-4.3.7zm32.4 35.6c-1.6 1.3-1 4.3 1.3 6.2 2.3 2.3 5.2 2.6 6.5 1 1.3-1.3.7-4.3-1.3-6.2-2.2-2.3-5.2-2.6-6.5-1zm-11.4-14.7c-1.6 1-1.6 3.6 0 5.9 1.6 2.3 4.3 3.3 5.6 2.3 1.6-1.3 1.6-3.9 0-6.2-1.4-2.3-4-3.3-5.6-2z"/></svg>
</a>
<a href="https://hub.docker.com/_/microsoft-presidio" target="_blank" rel="noopener" title="hub.docker.com" class="md-social__link">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 640 512"><!--! Font Awesome Free 6.5.1 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2023 Fonticons, Inc.--><path d="M349.9 236.3h-66.1v-59.4h66.1v59.4zm0-204.3h-66.1v60.7h66.1V32zm78.2 144.8H362v59.4h66.1v-59.4zm-156.3-72.1h-66.1v60.1h66.1v-60.1zm78.1 0h-66.1v60.1h66.1v-60.1zm276.8 100c-14.4-9.7-47.6-13.2-73.1-8.4-3.3-24-16.7-44.9-41.1-63.7l-14-9.3-9.3 14c-18.4 27.8-23.4 73.6-3.7 103.8-8.7 4.7-25.8 11.1-48.4 10.7H2.4c-8.7 50.8 5.8 116.8 44 162.1 37.1 43.9 92.7 66.2 165.4 66.2 157.4 0 273.9-72.5 328.4-204.2 21.4.4 67.6.1 91.3-45.2 1.5-2.5 6.6-13.2 8.5-17.1l-13.3-8.9zm-511.1-27.9h-66v59.4h66.1v-59.4zm78.1 0h-66.1v59.4h66.1v-59.4zm78.1 0h-66.1v59.4h66.1v-59.4zm-78.1-72.1h-66.1v60.1h66.1v-60.1z"/></svg>
</a>
<a href="mailto:presidio@microsoft.com" target="_blank" rel="noopener" title="" class="md-social__link">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512"><!--! Font Awesome Free 6.5.1 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2023 Fonticons, Inc.--><path d="M48 64C21.5 64 0 85.5 0 112c0 15.1 7.1 29.3 19.2 38.4l217.6 163.2c11.4 8.5 27 8.5 38.4 0l217.6-163.2c12.1-9.1 19.2-23.3 19.2-38.4 0-26.5-21.5-48-48-48H48zM0 176v208c0 35.3 28.7 64 64 64h384c35.3 0 64-28.7 64-64V176L294.4 339.2a63.9 63.9 0 0 1-76.8 0L0 176z"/></svg>
</a>
</div>
</div>
</div>
</footer>
</div>
<div class="md-dialog" data-md-component="dialog">
<div class="md-dialog__inner md-typeset"></div>
</div>
<script id="__config" type="application/json">{"base": "../../..", "features": ["navigation.instant", "content.tabs.link"], "search": "../../../assets/javascripts/workers/search.c011b7c0.min.js", "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}}</script>
<script src="../../../assets/javascripts/bundle.7389ff0e.min.js"></script>
</body>
</html>