add presidio

book/cooltools/Chapter.ipynb

@@ -2207,6 +2207,67 @@
     "def transform(prompt: str, history: list[mel.ChatMessage]) -> str:\n",
     "  return \"Hello \" + prompt"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Anonymize PII Data with `presidio`"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Working with PII data can be a neckbreaker in some cases.\n",
+    "\n",
+    "Luckily, for fast anonymization, you can use presidio.\n",
+    "\n",
+    "presidio handles anonymization of popular entities like names, phone numbers, credit card numbers or Bitcoin wallets.\n",
+    "\n",
+    "It can even handle text in images!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install presidio_analyzer presidio_anonymizer"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!python -m spacy download en_core_web_lg"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from presidio_analyzer import AnalyzerEngine\n",
+    "from presidio_anonymizer import AnonymizerEngine\n",
+    "\n",
+    "text_to_anonymize = \"His name is Mr. Jones. His phone number is 212-555-5555.\"\n",
+    "\n",
+    "analyzer = AnalyzerEngine()\n",
+    "results = analyzer.analyze(text=text_to_anonymize, entities=[\"PHONE_NUMBER\", \"PERSON\"], language='en')\n",
+    "\n",
+    "anonymizer = AnonymizerEngine()\n",
+    "\n",
+    "anonymized_text = anonymizer.anonymize(text=text_to_anonymize, analyzer_results=results)\n",
+    "\n",
+    "print(anonymized_text)\n",
+    "\n",
+    "# Output: His name is Mr. <PERSON>. His phone number is <PHONE_NUMBER>."
+   ]
   }
  ],
  "metadata": {