Updated docs website and notebooks (#1086)

microsoft · Jun 4, 2023 · 0e5c3b7 · 0e5c3b7
1 parent dda4444
commit 0e5c3b7
Show file tree

Hide file tree

Showing 20 changed files with 2,044 additions and 1,781 deletions.
diff --git a/.gitignore b/.gitignore
@@ -134,4 +134,4 @@ vendor/
 .idea
 
 #mkdocs
-/mkdocs
+mkdocs/
diff --git a/docs/api/analyzer_python.md b/docs/api/analyzer_python.md
@@ -1,79 +1,6 @@
 # Presidio Analyzer API Reference
 
-## AnalyzerEngine
-
-::: presidio_analyzer.AnalyzerEngine
-    handler: python
-    selection:
-      docstring_style: restructured-text
-
-## RecognizerRegistry
-
-::: presidio_analyzer.RecognizerRegistry
-    handler: python
-    selection:
-      docstring_style: restructured-text
-
-## EntityRecognizer
-
-::: presidio_analyzer.EntityRecognizer
-    handler: python
-    selection:
-      docstring_style: restructured-text
-
-## RemoteRecognizer
-
-::: presidio_analyzer.RemoteRecognizer
-    handler: python
-    selection:
-      docstring_style: restructured-text
-
-## LocalRecognizer
-
-::: presidio_analyzer.LocalRecognizer
-    handler: python
-    selection:
-      docstring_style: restructured-text
-
-## PatternRecognizer
-
-::: presidio_analyzer.PatternRecognizer
-    handler: python
-    selection:
-      docstring_style: restructured-text
-
-## NlpArtifacts
-
-::: presidio_analyzer.nlp_engine.NlpArtifacts
-    handler: python
-    selection:
-      docstring_style: restructured-text
-
-::: presidio_analyzer.nlp_engine.NlpEngine
-    handler: python
-    selection:
-      docstring_style: restructured-text
-
-::: presidio_analyzer.nlp_engine.SpacyNlpEngine
-    handler: python
-    selection:
-      docstring_style: restructured-text
-
-::: presidio_analyzer.nlp_engine.NlpEngineProvider
-    handler: python
-    selection:
-      docstring_style: restructured-text
-
-## RecognizerResult
-
-::: presidio_analyzer.recognizer_result.RecognizerResult
-    handler: python
-    selection:
-      docstring_style: restructured-text
-
-## Pattern
-
-::: presidio_analyzer.Pattern
+::: presidio_analyzer
     handler: python
     selection:
-      docstring_style: restructured-text
+      docstring_style: sphinx
diff --git a/docs/api/anonymizer_python.md b/docs/api/anonymizer_python.md
@@ -3,4 +3,4 @@
 ::: presidio_anonymizer
     handler: python
     selection:
-      docstring_style: restructured-text
+      docstring_style: sphinx
diff --git a/docs/api/image_redactor_python.md b/docs/api/image_redactor_python.md
@@ -5,11 +5,11 @@
 ::: presidio_image_redactor.ImageRedactorEngine
     handler: python
     selection:
-      docstring_style: restructured-text
+      docstring_style: sphinx
 
 ## ImageAnalyzerEngine class
 
 ::: presidio_image_redactor.ImageAnalyzerEngine
     handler: python
     selection:
-      docstring_style: restructured-text
+      docstring_style: sphinx
diff --git a/docs/requirements-docs.txt b/docs/requirements-docs.txt
@@ -1,11 +1,10 @@
 mkdocs
 mkdocs-material
-mkdocs-jupyter
-pymdown-extensions<9.4
+mknotebooks
+pymdown-extensions
 markdown
-mkdocstrings[python-legacy]
+mkdocstrings-python
 presidio_analyzer
 presidio_anonymizer
 presidio_image_redactor
-jupyter_contrib_nbextensions
-pygments>=2.10,<2.12
+pygments>=2.10
diff --git a/docs/samples/index.md b/docs/samples/index.md
@@ -2,27 +2,27 @@
 
 | Topic       | Type                                  | Sample                                                                                                                                          |
 | :---------- |:--------------------------------------| :---------------------------------------------------------------------------------------------------------------------------------------------- |
-| Usage       | Python Notebook                       | [Presidio Basic Usage Notebook](python/presidio_notebook.ipynb)                                                                                 |
-| Usage       | Python Notebook                       | [Customizing Presidio Analyzer](python/customizing_presidio_analyzer.ipynb)                                                                     |
-| Usage       | Python                                | [Remote Recognizer](python/example_remote_recognizer.py)                                                                                        |
-| Usage       | Python                                | [Text Analytics as a Remote Recognizer](python/text_analytics/index.md)                                                                         |
-| Usage       | Python Notebook                       | [Integrating with external services](python/integrating_with_external_services.ipynb)                                                           |
-| Usage       | Python                                | [Passing a lambda as a Presidio anonymizer using Faker](python/example_custom_lambda_anonymizer.py)                                             |
-| Usage       | Python Notebook                       | [Encrypting and Decrypting identified entities](python/encrypt_decrypt.ipynb)                                                           |
-| Usage       | Python Notebook                       | [Analyzing structured / semi-structured data in batch](python/batch_processing.ipynb)                                                           |
-| Usage       | Python                                | [Analyze and Anonymize CSV file](python/process_csv_file.py)                                                           |
-| Usage       | Python Notebook                       | [Getting the identified entity value using a custom Operator](python/getting_entity_values.ipynb)                                               |
-| Usage       | Python                                | [Using Flair as an external PII model](python/flair_recognizer.py)                                               |
-| Usage       | Python                                | [Using Transformers as an external PII model](python/transformers_recognizer/index.md)                                               |
-| Usage       | Python Notebook                       | [Anonymizing known values](python/Anonymizing%20known%20values.ipynb)
-| Usage       | Python Notebook                       | [Redacting text PII from DICOM images](python/example_dicom_image_redactor.ipynb)
-| Usage       | Python Notebook                       | [Annotating PII in a PDF](python/example_pdf_annotation.ipynb)
-| Usage       | REST API (postman)                    | [Presidio as a REST endpoint](docker/index.md)                                              |
-| Deployment  | App Service                           | [Presidio with App Service](deployments/app-service/index.md)                                                                                   |
-| Deployment  | Kubernetes                            | [Presidio with Kubernetes](deployments/k8s/index.md)                                                                                            |
-| Deployment  | Spark/Azure Databricks                | [Presidio with Spark](deployments/spark/index.md)                                                                                               |
-| Deployment  | Azure Data Factory with App Service   | [ETL for small dataset](deployments/data-factory/presidio-data-factory.md#option-1-presidio-as-an-http-rest-endpoint)           |
-| Deployment  | Azure Data Factory with Databricks    | [ETL for large datasets](deployments/data-factory/presidio-data-factory.md#option-2-presidio-on-azure-databricks)                 |
-| ADF Pipeline  | Azure Data Factory                    | [Add Presidio as an HTTP service to your Azure Data Factory](deployments/data-factory/presidio-data-factory-template-gallery-http.md)                |
-| ADF Pipeline  | Azure Data Factory                    | [Add Presidio on Databricks to your Azure Data Factory](deployments/data-factory/presidio-data-factory-template-gallery-databricks.md)               |
-| Demo | Streamlit                             | [Create a simple demo app using Streamlit](python/streamlit/index.md)
+| Usage       | Python Notebook                       | [Presidio Basic Usage Notebook](python/presidio_notebook.ipynb)  |
+| Usage       | Python Notebook                       | [Customizing Presidio Analyzer](python/customizing_presidio_analyzer.ipynb) |
+| Usage       | Python Notebook                       | [Analyzing structured / semi-structured data in batch](python/batch_processing.ipynb)|
+| Usage       | Python Notebook                       | [Encrypting and Decrypting identified entities](python/encrypt_decrypt.ipynb)|
+| Usage       | Python Notebook                       | [Getting the identified entity value using a custom Operator](python/getting_entity_values.ipynb)|
+| Usage       | Python Notebook                       | [Anonymizing known values](https://github.com/microsoft/presidio/blob/main/docs/samples/python/Anonymizing%20known%20values.ipynb)
+| Usage       | Python Notebook                       | [Redacting text PII from DICOM images](https://github.com/microsoft/presidio/blob/main/docs/samples/python/example_dicom_image_redactor.ipynb)
+| Usage       | Python Notebook                       | [Annotating PII in a PDF](https://github.com/microsoft/presidio/blob/main/docs/samples/python/example_pdf_annotation.ipynb)
+| Usage       | Python Notebook                       | [Integrating with external services](https://github.com/microsoft/presidio/blob/main/docs/samples/python/integrating_with_external_services.ipynb) |
+| Usage       | Python                                | [Remote Recognizer](https://github.com/microsoft/presidio/blob/main/docs/samples/python/example_remote_recognizer.py) |
+| Usage       | Python                                | [Text Analytics as a Remote Recognizer](https://github.com/microsoft/presidio/blob/main/docs/samples/python/text_analytics/index.md)  |
+| Usage       | Python                                | [Analyze and Anonymize CSV file](https://github.com/microsoft/presidio/blob/main/docs/samples/python/process_csv_file.py) |
+| Usage       | Python                                | [Using Flair as an external PII model](https://github.com/microsoft/presidio/blob/main/docs/samples/python/flair_recognizer.py)|
+| Usage       | Python                                | [Using Transformers as an external PII model](python/transformers_recognizer/index.md)|
+| Usage       | Python                                | [Passing a lambda as a Presidio anonymizer using Faker](https://github.com/microsoft/presidio/blob/main/docs/samples/python/example_custom_lambda_anonymizer.py)|
+| Usage       | REST API (postman)                    | [Presidio as a REST endpoint](docker/index.md)|
+| Deployment  | App Service                           | [Presidio with App Service](deployments/app-service/index.md)|
+| Deployment  | Kubernetes                            | [Presidio with Kubernetes](deployments/k8s/index.md)|
+| Deployment  | Spark/Azure Databricks                | [Presidio with Spark](deployments/spark/index.md)|
+| Deployment  | Azure Data Factory with App Service   | [ETL for small dataset](deployments/data-factory/presidio-data-factory.md#option-1-presidio-as-an-http-rest-endpoint) |
+| Deployment  | Azure Data Factory with Databricks    | [ETL for large datasets](deployments/data-factory/presidio-data-factory.md#option-2-presidio-on-azure-databricks) |
+| ADF Pipeline  | Azure Data Factory | [Add Presidio as an HTTP service to your Azure Data Factory](deployments/data-factory/presidio-data-factory-template-gallery-http.md) |
+| ADF Pipeline  | Azure Data Factory | [Add Presidio on Databricks to your Azure Data Factory](deployments/data-factory/presidio-data-factory-template-gallery-databricks.md) |
+| Demo | Streamlit | [Create a simple demo app using Streamlit](python/streamlit/index.md)
diff --git a/docs/samples/python/Anonymizing known values.ipynb b/docs/samples/python/Anonymizing known values.ipynb
@@ -1,5 +1,26 @@
 {
  "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "bcddce7b",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [],
+   "source": [
+    "# download presidio\n",
+    "!pip install presidio_analyzer presidio_anonymizer"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3345f1c4",
+   "metadata": {},
+   "source": [
+    "Path to notebook: [https://www.github.com/microsoft/presidio/blob/main/docs/samples/python/Anonymizing%20known%20values.ipynb](https://www.github.com/microsoft/presidio/blob/main/docs/samples/python/Anonymizing%20known%20values.ipynb)"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "a71c2409",
@@ -24,7 +45,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 2,
    "id": "3d1e9cc1",
    "metadata": {},
    "outputs": [],
@@ -35,7 +56,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 3,
    "id": "dc54fc31",
    "metadata": {},
    "outputs": [],
@@ -46,7 +67,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 4,
    "id": "b926f0a0",
    "metadata": {},
    "outputs": [],
@@ -57,7 +78,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 5,
    "id": "f5448009",
    "metadata": {},
    "outputs": [],
@@ -72,7 +93,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 6,
    "id": "ec9e24e3",
    "metadata": {},
    "outputs": [
@@ -118,7 +139,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 7,
    "id": "d57a02d6",
    "metadata": {},
    "outputs": [
@@ -136,7 +157,7 @@
        "  'free_text': \"X1T2 is R2D2's special value\"}]"
       ]
      },
-     "execution_count": 6,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -166,7 +187,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 8,
    "id": "b342fc25",
    "metadata": {},
    "outputs": [
@@ -211,7 +232,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 9,
    "id": "bd347adf",
    "metadata": {},
    "outputs": [
@@ -232,7 +253,7 @@
        "  'anonymized_free_text': \"<special_value> is <name>'s special value\"}]"
       ]
      },
-     "execution_count": 8,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -252,7 +273,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 10,
    "id": "7abaea43",
    "metadata": {},
    "outputs": [],
@@ -271,7 +292,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 11,
    "id": "5800fcc6",
    "metadata": {},
    "outputs": [
@@ -283,7 +304,7 @@
        " type: LOCATION, start: 45, end: 62, score: 0.85]"
       ]
      },
-     "execution_count": 10,
+     "execution_count": 11,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -311,6 +332,14 @@
     "- For more info on Presidio Anonymize, see [this documentation](https://microsoft.github.io/presidio/anonymizer/)\n",
     "- To further customize the anonymization type, see [this tutorial](https://microsoft.github.io/presidio/tutorial/11_custom_anonymization/)\n"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "51da9e15",
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
@@ -329,7 +358,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.12"
+   "version": "3.9.16"
   }
  },
  "nbformat": 4,