Presidio example

untitled8.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "authorship_tag": "ABX9TyNcUZJO94FrY1ndKHIXI2R1",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/gist/sahuguet/9d98c0287eb6641b1a87822509633d46/untitled8.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "QWgSB3ca4n0P"
      },
      "outputs": [],
      "source": [
        "# download presidio\n",
        "!pip install presidio_analyzer presidio_anonymizer > /dev/null\n",
        "!python -m spacy download en_core_web_lg"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from presidio_analyzer import AnalyzerEngine, PatternRecognizer\n",
        "from presidio_anonymizer import AnonymizerEngine\n",
        "from presidio_anonymizer.entities import OperatorConfig\n",
        "import json\n",
        "from pprint import pprint"
      ],
      "metadata": {
        "id": "Zi2xQ1vg47zL"
      },
      "execution_count": 2,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "text_to_anonymize = \"\"\"His name is Mr. Jones.\n",
        "He has both French and US passports.\n",
        "His phone number is tel:212-555-5555.\n",
        "He worked for Nokia and NYU between 2001 and 2006.\n",
        "He is making $100,000 a year.\n",
        "He got is PhD in 2001 from BYU.\n",
        "\"\"\""
      ],
      "metadata": {
        "id": "QJAKCueP4_zU"
      },
      "execution_count": 15,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "analyzer = AnalyzerEngine()\n",
        "analyzer_results = analyzer.analyze(text=text_to_anonymize, language='en')\n",
        "\n",
        "print(analyzer_results)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "6VYEXUd45A9w",
        "outputId": "2c3b5b6c-76b0-47d4-cff3-de8df80f357b"
      },
      "execution_count": 16,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "WARNING:presidio-analyzer:Recognizer not added to registry because language is not supported by registry - CreditCardRecognizer supported languages: es, registry supported languages: en\n",
            "WARNING:presidio-analyzer:Recognizer not added to registry because language is not supported by registry - CreditCardRecognizer supported languages: it, registry supported languages: en\n",
            "WARNING:presidio-analyzer:Recognizer not added to registry because language is not supported by registry - CreditCardRecognizer supported languages: pl, registry supported languages: en\n",
            "WARNING:presidio-analyzer:Recognizer not added to registry because language is not supported by registry - EsNifRecognizer supported languages: es, registry supported languages: en\n",
            "WARNING:presidio-analyzer:Recognizer not added to registry because language is not supported by registry - EsNieRecognizer supported languages: es, registry supported languages: en\n",
            "WARNING:presidio-analyzer:Recognizer not added to registry because language is not supported by registry - ItDriverLicenseRecognizer supported languages: it, registry supported languages: en\n",
            "WARNING:presidio-analyzer:Recognizer not added to registry because language is not supported by registry - ItFiscalCodeRecognizer supported languages: it, registry supported languages: en\n",
            "WARNING:presidio-analyzer:Recognizer not added to registry because language is not supported by registry - ItVatCodeRecognizer supported languages: it, registry supported languages: en\n",
            "WARNING:presidio-analyzer:Recognizer not added to registry because language is not supported by registry - ItIdentityCardRecognizer supported languages: it, registry supported languages: en\n",
            "WARNING:presidio-analyzer:Recognizer not added to registry because language is not supported by registry - ItPassportRecognizer supported languages: it, registry supported languages: en\n",
            "WARNING:presidio-analyzer:Recognizer not added to registry because language is not supported by registry - PlPeselRecognizer supported languages: pl, registry supported languages: en\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "[type: PERSON, start: 16, end: 21, score: 0.85, type: NRP, start: 35, end: 41, score: 0.85, type: LOCATION, start: 46, end: 48, score: 0.85, type: DATE_TIME, start: 126, end: 147, score: 0.85, type: DATE_TIME, start: 196, end: 200, score: 0.85, type: PHONE_NUMBER, start: 84, end: 96, score: 0.75]\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "anonymizer = AnonymizerEngine()\n",
        "\n",
        "anonymized_results = anonymizer.anonymize(\n",
        "    text=text_to_anonymize,\n",
        "    analyzer_results=analyzer_results,\n",
        "    operators={\"DEFAULT\": OperatorConfig(\"replace\", {\"new_value\": \"<REDACTED>\"})})\n",
        "\n",
        "print(f\"text: {anonymized_results.text}\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "RZWobKFW5yLs",
        "outputId": "c79b8e76-071c-4e4c-ff4a-e7da8f241b50"
      },
      "execution_count": 17,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "text: His name is Mr. <REDACTED>.\n",
            "He has both <REDACTED> and <REDACTED> passports.\n",
            "His phone number is tel:<REDACTED>.\n",
            "He worked for Nokia and NYU <REDACTED>.\n",
            "He is making $100,000 a year.\n",
            "He got is PhD in <REDACTED> from BYU.\n",
            "\n"
          ]
        }
      ]
    }
  ]
}