presidio/docs/samples/python/keep_entities.ipynb

{
    "cells": [
        {
            "cell_type": "code",
            "execution_count": null,
            "id": "bcddce7b",
            "metadata": {
                "scrolled": true
            },
            "outputs": [],
            "source": [
                "# download presidio\n",
                "!pip install presidio_analyzer presidio_anonymizer\n",
                "!python -m spacy download en_core_web_lg"
            ]
        },
        {
            "cell_type": "markdown",
            "id": "3345f1c4",
            "metadata": {},
            "source": [
                "###### Path to notebook: [https://www.github.com/data-privacy-stack/presidio/blob/main/docs/samples/python/keep_entities.ipynb](https://www.github.com/data-privacy-stack/presidio/blob/main/docs/samples/python/keep_entities.ipynb)"
            ]
        },
        {
            "cell_type": "markdown",
            "id": "gothic-trademark",
            "metadata": {},
            "source": [
                "# Keeping some PIIs from being anonymized\n",
                "\n",
                "This sample shows how to use Presidio's `keep` anonymizer to keep some of the identified PIIs in the output string"
            ]
        },
        {
            "cell_type": "markdown",
            "id": "roman-allergy",
            "metadata": {},
            "source": [
                "### Set up imports"
            ]
        },
        {
            "cell_type": "code",
            "execution_count": 1,
            "id": "extensive-greensboro",
            "metadata": {},
            "outputs": [],
            "source": [
                "from presidio_anonymizer import AnonymizerEngine\n",
                "from presidio_anonymizer.entities import RecognizerResult, OperatorConfig"
            ]
        },
        {
            "cell_type": "markdown",
            "id": "metropolitan-atlantic",
            "metadata": {},
            "source": [
                "### Presidio Anonymizer: Keep person names\n",
                "\n",
                "This example input has 2 PIIs, an person name and a location. We configure the anonymizer to replace the location name with a placeholder, but keep the person name unmodified."
            ]
        },
        {
            "cell_type": "code",
            "execution_count": 2,
            "id": "medium-ridge",
            "metadata": {},
            "outputs": [],
            "source": [
                "engine = AnonymizerEngine()\n",
                "\n",
                "# Invoke the anonymize function with the text,\n",
                "# analyzer results (potentially coming from presidio-analyzer)\n",
                "# and 'keep' operator on <PERSON> PIIs\n",
                "anonymize_result = engine.anonymize(\n",
                "    text=\"My name is James Bond, I live in London\",\n",
                "    analyzer_results=[\n",
                "        RecognizerResult(entity_type=\"PERSON\", start=11, end=21, score=0.8),\n",
                "        RecognizerResult(entity_type=\"LOCATION\", start=33, end=39, score=0.8),\n",
                "    ],\n",
                "    operators={\n",
                "        \"PERSON\": OperatorConfig(\"keep\"),\n",
                "        \"DEFAULT\": OperatorConfig(\"replace\"),\n",
                "    },\n",
                ")"
            ]
        },
        {
            "cell_type": "markdown",
            "id": "1d2cabaa-4aa6-49cf-875d-4bdf407215b4",
            "metadata": {},
            "source": [
                "### Result: Name unmodified, but tracked\n",
                "\n",
                "The person name is preserved in the result text, but remains tracked in the items list."
            ]
        },
        {
            "cell_type": "code",
            "execution_count": 3,
            "id": "421c2914-9b75-4c33-a270-e410d91d036b",
            "metadata": {
                "tags": []
            },
            "outputs": [
                {
                    "data": {
                        "text/plain": [
                            "text: My name is James Bond, I live in <LOCATION>\n",
                            "items:\n",
                            "[\n",
                            "    {'start': 33, 'end': 43, 'entity_type': 'LOCATION', 'text': '<LOCATION>', 'operator': 'replace'},\n",
                            "    {'start': 11, 'end': 21, 'entity_type': 'PERSON', 'text': 'James Bond', 'operator': 'keep'}\n",
                            "]"
                        ]
                    },
                    "execution_count": 3,
                    "metadata": {},
                    "output_type": "execute_result"
                }
            ],
            "source": [
                "anonymize_result"
            ]
        }
    ],
    "metadata": {
        "kernelspec": {
            "display_name": "Python 3 (ipykernel)",
            "language": "python",
            "name": "python3"
        },
        "language_info": {
            "codemirror_mode": {
                "name": "ipython",
                "version": 3
            },
            "file_extension": ".py",
            "mimetype": "text/x-python",
            "name": "python",
            "nbconvert_exporter": "python",
            "pygments_lexer": "ipython3",
            "version": "3.10.10"
        }
    },
    "nbformat": 4,
    "nbformat_minor": 5
}