people.yaml file created to add authors info

unytics · Nov 6, 2024 · c2dec44 · c2dec44
1 parent b99783c
commit c2dec44
Show file tree

Hide file tree

Showing 149 changed files with 285 additions and 587 deletions.
diff --git a/bigfun/cli.py b/bigfun/cli.py
@@ -13,6 +13,7 @@
 from . import utils
 
 TABLES_FOLDER = 'data'
+PEOPLE_FILENAME = 'people.yaml'
 THIS_FOLDER = os.path.dirname(os.path.realpath(__file__)).replace('\\', '/')
 WEBSITE_CONFIG_FOLDER = THIS_FOLDER + '/website'
 CATEGORIES_DOC_TEMPLATE_FILENAME = f'{THIS_FOLDER}/templates/categories.md'
@@ -44,6 +45,30 @@ def get_config_value(name, config_filename):
 
 def generate_doc(project, dataset):
 
+    def get_people():
+        if not os.path.isfile(PEOPLE_FILENAME):
+            return {}
+        with open(PEOPLE_FILENAME, encoding='utf-8') as f:
+            people = yaml.safe_load(f.read())
+        return {
+            person['name']: person
+            for person in people
+        }
+
+    def enrich_bigfunctions_author(bigfunctions):
+        people = get_people()
+        for bigfunction in bigfunctions:
+            if 'author' not in bigfunction.config:
+                continue
+            author = bigfunction.config['author']
+            if isinstance(author, dict):
+                # backward compatibility
+                continue
+            if author in people:
+                bigfunction._config['author'] = people[author]
+            else:
+                bigfunction._config['author'] = {'name': author}
+
     def init_docs_folder():
         os.makedirs('docs', exist_ok=True)
         shutil.rmtree('docs/bigfunctions', ignore_errors=True)
@@ -91,6 +116,7 @@ def generate_bigfunctions_list_markdown(bigfunctions):
         bf.BigFunction(bigfunction_name, project=project, dataset=dataset)
         for bigfunction_name in bf.list_bigfunctions()
     ]
+    enrich_bigfunctions_author(bigfunctions)
     init_docs_folder()
     copy_readme_and_contributing()
     copy_default_site_config()

diff --git a/bigfunctions/README.md b/bigfunctions/README.md
@@ -66,7 +66,7 @@ BigFunctions are open-source BigQuery routines that give you **SQL-superpowers**
     | `us-west2` | `bigfunctions.us_west2` |
     | `us-west3` | `bigfunctions.us_west3` |
     | `us-west4` | `bigfunctions.us_west4` |
-
+    
 
 
 
@@ -77,6 +77,7 @@ BigFunctions are open-source BigQuery routines that give you **SQL-superpowers**
 - [<code>ask_ai(prompt, model)</code>](ask_ai.md): Ask Anything!
 - [<code>ask_appstore_reviews(prompt, app_url_in_appstore)</code>](ask_appstore_reviews.md): Ask AI what your app users think.
 - [<code>ask_my_data(question, fully_qualified_table)</code>](ask_my_data.md): Ask your data any `question` in natural language.
+- [<code>categorize(items)</code>](categorize.md): Categorize `items` in categories and subcategories.
 - [<code>classify_text(text, candidate_labels)</code>](classify_text.md): Classify `text` among `candidate_labels`
 - [<code>generate_categories(items)</code>](generate_categories.md): Return `categories` of `items`.
 - [<code>generate_face_embedding(image_url)</code>](generate_face_embedding.md): Detect Face on image and Generate its Embedding
@@ -270,3 +271,5 @@ BigFunctions are open-source BigQuery routines that give you **SQL-superpowers**
 - [<code>timestamp_from_unix_date_time(unix_date_time, date_time_part)</code>](timestamp_from_unix_date_time.md): Interprets `unix_date_time` as the number of `date_time_part` since `1970-01-01 00:00:00 UTC`.
 - [<code>timestamp_to_unix_date_time(timestamp_expression, date_time_part)</code>](timestamp_to_unix_date_time.md): Returns the number of `date_time_part` since `1970-01-01 00:00:00 UTC`.
 - [<code>upsert(query_or_table_or_view, destination_table, insertion_mode, primary_keys, recency_field)</code>](upsert.md): Merges `query_or_table_or_view` into the `destination_table`.
+
+
diff --git a/bigfunctions/are_arrays_equal.yaml b/bigfunctions/are_arrays_equal.yaml
@@ -1,9 +1,6 @@
 type: function_sql
 category: transform_array
-author:
-  name: Sid Ali
-  url: https://www.linkedin.com/company/esmoz/
-  avatar_url: "https://esmoz.fr/wp-content/uploads/2022/03/logo_esmoz_40x20-1.png"
+author: Sid Ali
 description: |
   Return true if `array1` = `array2`
   and false otherwise

diff --git a/bigfunctions/array_intersect.yaml b/bigfunctions/array_intersect.yaml
@@ -1,9 +1,6 @@
 type: function_sql
 category: transform_array
-author:
-  name: Axel Thevenot
-  url: https://www.linkedin.com/in/axel-thevenot/
-  avatar_url: "https://avatars.githubusercontent.com/u/39374103?v=4"
+author: Axel Thevenot
 description: |
   Returns the intersection of two arrays.
 arguments:

diff --git a/bigfunctions/array_union.yaml b/bigfunctions/array_union.yaml
@@ -1,9 +1,6 @@
 type: function_sql
 category: transform_array
-author:
-  name: Axel Thevenot
-  url: https://www.linkedin.com/in/axel-thevenot/
-  avatar_url: "https://avatars.githubusercontent.com/u/39374103?v=4"
+author: Axel Thevenot
 description: |
   Returns the union of two arrays.
 arguments:

diff --git a/bigfunctions/ask_ai.yaml b/bigfunctions/ask_ai.yaml
@@ -1,9 +1,6 @@
 type: function_py
 category: AI
-author:
-  name: Paul Marcombes
-  url: https://www.linkedin.com/in/paul-marcombes
-  avatar_url: "https://lh3.googleusercontent.com/a/ACg8ocIAw-jJTmt7AkDhU6_OvDQwsy9uyuRiWX8MxUBOdpro8lRJEgk5=s288-c-no"
+author: Paul Marcombes
 description: |
   Ask Anything!
 

diff --git a/bigfunctions/ask_appstore_reviews.yaml b/bigfunctions/ask_appstore_reviews.yaml
@@ -1,9 +1,6 @@
 type: function_sql
 category: AI
-author:
-  name: Paul Marcombes
-  url: https://www.linkedin.com/in/paul-marcombes
-  avatar_url: "https://lh3.googleusercontent.com/a/ACg8ocIAw-jJTmt7AkDhU6_OvDQwsy9uyuRiWX8MxUBOdpro8lRJEgk5=s288-c-no"
+author: Paul Marcombes
 description: |
   Ask AI what your app users think.
 

diff --git a/bigfunctions/ask_my_data.yaml b/bigfunctions/ask_my_data.yaml
@@ -1,9 +1,6 @@
 type: procedure
 category: AI
-author:
-  name: Paul Marcombes
-  url: https://www.linkedin.com/in/paul-marcombes
-  avatar_url: "https://lh3.googleusercontent.com/a/ACg8ocIAw-jJTmt7AkDhU6_OvDQwsy9uyuRiWX8MxUBOdpro8lRJEgk5=s288-c-no"
+author: Paul Marcombes
 description: |
   Ask your data any `question` in natural language.
 

diff --git a/bigfunctions/benford_distance.yaml b/bigfunctions/benford_distance.yaml
@@ -1,9 +1,6 @@
 type: function_sql
 category: transform_array
-author:
-  name: Thomas F McGeehan V
-  url: https://www.linkedin.com/in/tfmv5
-  avatar_url: "https://avatars.githubusercontent.com/u/3191913?s=60&v=4"
+author: Thomas F McGeehan V
 description: |
   Calculate the distance from Benford's Law for given `values`.
 

diff --git a/bigfunctions/camel2snake.yaml b/bigfunctions/camel2snake.yaml
@@ -1,9 +1,6 @@
 type: function_sql
 category: transform_string
-author:
-  name: Paul Marcombes
-  url: https://www.linkedin.com/in/paul-marcombes
-  avatar_url: "https://lh3.googleusercontent.com/a/ACg8ocIAw-jJTmt7AkDhU6_OvDQwsy9uyuRiWX8MxUBOdpro8lRJEgk5=s288-c-no"
+author: Paul Marcombes
 description: Convert `string` from camelCase to snake_case
 arguments:
   - name: camelCaseString

diff --git a/bigfunctions/categorize.yaml b/bigfunctions/categorize.yaml
@@ -1,9 +1,6 @@
 type: function_py
 category: AI
-author:
-  name: Paul Marcombes
-  url: https://www.linkedin.com/in/paul-marcombes
-  avatar_url: "https://lh3.googleusercontent.com/a/ACg8ocIAw-jJTmt7AkDhU6_OvDQwsy9uyuRiWX8MxUBOdpro8lRJEgk5=s288-c-no"
+author: Paul Marcombes
 description: |
   Categorize `items` in categories and subcategories.
 

diff --git a/bigfunctions/chart.yaml b/bigfunctions/chart.yaml
@@ -1,9 +1,6 @@
 type: function_sql
 category: explore
-author:
-  name: Paul Marcombes
-  url: https://www.linkedin.com/in/paul-marcombes
-  avatar_url: "https://lh3.googleusercontent.com/a-/ACB-R5RDf2yxcw1p_IYLCKmiUIScreatDdhG8B83om6Ohw=s260"
+author: Paul Marcombes
 description: |-
   Return html with a chartjs chart
 arguments:

diff --git a/bigfunctions/classify_text.yaml b/bigfunctions/classify_text.yaml
@@ -1,9 +1,6 @@
 type: function_py
 category: AI
-author:
-  name: Paul Marcombes
-  url: https://www.linkedin.com/in/paul-marcombes
-  avatar_url: "https://lh3.googleusercontent.com/a/ACg8ocIAw-jJTmt7AkDhU6_OvDQwsy9uyuRiWX8MxUBOdpro8lRJEgk5=s288-c-no"
+author: Paul Marcombes
 description: |
   Classify `text` among `candidate_labels`
   using [zero-shot classification](https://huggingface.co/tasks/zero-shot-classification)

diff --git a/bigfunctions/connected_components.yaml b/bigfunctions/connected_components.yaml
@@ -1,9 +1,6 @@
 type: procedure
 category: graph
-author:
-  name: Furcy Pin
-  url: https://www.linkedin.com/in/furcy-pin-3790b028/
-  avatar_url: "https://media.licdn.com/dms/image/C4D03AQFK5YDJyod_3A/profile-displayphoto-shrink_200_200/0/1590431668428?e=1677110400&v=beta&t=_DHEt_NWaU5CIIC2UyYdK3gHj7KKUjzH9DTVhZcEmOY"
+author: Furcy Pin
 description: |
   Compute the connected components of a non-directed graph.
 

diff --git a/bigfunctions/convert_non_ascii_characters_to_unicode_escape_sequences.yaml b/bigfunctions/convert_non_ascii_characters_to_unicode_escape_sequences.yaml
@@ -1,9 +1,6 @@
 type: function_sql
 category: transform_string
-author:
-  name: "Benjamin Tabet"
-  url: https://www.linkedin.com/in/benjamin-tabet
-  avatar_url: "https://taskfilescsm.s3.amazonaws.com/uploads/speaker_thumb/2022-11-0912%253A07%253A34879766-BenjaminTabet.jpg"
+author: "Benjamin Tabet"
 description: "Replace all non ASCII characters with escape unicode"
 arguments:
   - name: text

diff --git a/bigfunctions/create_materialized_view_w_flattened_json_column.yaml b/bigfunctions/create_materialized_view_w_flattened_json_column.yaml
@@ -1,9 +1,6 @@
 type: procedure
 category: transform_json
-author:
-  name: Paul Marcombes
-  url: https://www.linkedin.com/in/paul-marcombes
-  avatar_url: "https://lh3.googleusercontent.com/a/ACg8ocIAw-jJTmt7AkDhU6_OvDQwsy9uyuRiWX8MxUBOdpro8lRJEgk5=s288-c-no"
+author: Paul Marcombes
 description: |
   Create a Materialized view of a table with `json_column` flattened
   .

diff --git a/bigfunctions/date_sub_isoyear.yaml b/bigfunctions/date_sub_isoyear.yaml
@@ -1,9 +1,6 @@
 type: function_sql
 category: transform_date
-author:
-  name: Stephane KNOCKAERT
-  url: "https://www.linkedin.com/in/knockaertstephane/"
-  avatar_url: "https://media.licdn.com/dms/image/C4E03AQGAa5CX20cU5g/profile-displayphoto-shrink_200_200/0/1651827360843?e=1691020800&v=beta&t=0M3BkmD7Nc6EiGv7ZHtRQb6HFn-USSvkK_WSnSIAB6k"
+author: Stephane KNOCKAERT
 description: |
   Returns same day `years` before
   (same week number and same day of week)

diff --git a/bigfunctions/deduplicate_rows.yaml b/bigfunctions/deduplicate_rows.yaml
@@ -1,9 +1,6 @@
 type: procedure
 category: utils
-author:
-  name: Shivam Singh
-  url: https://www.linkedin.com/in/shivamsingh012/
-  avatar_url: "https://media.licdn.com/dms/image/D4D03AQERv0qwECH0DA/profile-displayphoto-shrink_200_200/0/1675233460732?e=1686182400&v=beta&t=HqngiSx5zd4llZStwf3L0k2T_pE8qvnEj7NguWNJTOo"
+author: Shivam Singh
 description: Returns the deduplicated rows of `query_or_table_or_view`
 arguments:
   - name: query_or_table_or_view

diff --git a/bigfunctions/deidentify.yaml b/bigfunctions/deidentify.yaml
@@ -1,9 +1,6 @@
 type: function_py
 category: transform_string
-author:
-  name: Shivam Singh
-  url: https://www.linkedin.com/in/shivamsingh012/
-  avatar_url: "https://media.licdn.com/dms/image/D4D03AQERv0qwECH0DA/profile-displayphoto-shrink_200_200/0/1675233460732?e=1686182400&v=beta&t=HqngiSx5zd4llZStwf3L0k2T_pE8qvnEj7NguWNJTOo"
+author: Shivam Singh
 description: |
   Masks sensitive information of type `info_types` in `text`
   using [Cloud Data Loss Prevention](https://cloud.google.com/dlp)

diff --git a/bigfunctions/detect_anomalies.yaml b/bigfunctions/detect_anomalies.yaml
@@ -1,8 +1,6 @@
 type: function_py
 category: detect_anomalies
-author:
-  name: Thomas F McGeehan V
-  url: https://www.linkedin.com/in/tfmv5
+author: Thomas F McGeehan V
 description: |
   Detect anomalies in time-series data to identify outliers and unusual patterns.
   This function uses Z-score to find anomalies in the specified column of a BigQuery table.

diff --git a/bigfunctions/detect_sensitive_info.yaml b/bigfunctions/detect_sensitive_info.yaml
@@ -1,9 +1,6 @@
 type: function_py
 category: transform_string
-author:
-  name: Shivam Singh
-  url: https://www.linkedin.com/in/shivamsingh012/
-  avatar_url: "https://media.licdn.com/dms/image/D4D03AQERv0qwECH0DA/profile-displayphoto-shrink_200_200/0/1675233460732?e=1686182400&v=beta&t=HqngiSx5zd4llZStwf3L0k2T_pE8qvnEj7NguWNJTOo"
+author: Shivam Singh
 description: |
   Detect sensitive information in `text`
   using [Cloud Data Loss Prevention](https://cloud.google.com/dlp)

diff --git a/bigfunctions/distinct_values.yaml b/bigfunctions/distinct_values.yaml
@@ -1,9 +1,6 @@
 type: function_sql
 category: transform_array
-author:
-  name: Paul Marcombes
-  url: https://www.linkedin.com/in/paul-marcombes
-  avatar_url: "https://lh3.googleusercontent.com/a/ACg8ocIAw-jJTmt7AkDhU6_OvDQwsy9uyuRiWX8MxUBOdpro8lRJEgk5=s288-c-no"
+author: Paul Marcombes
 description: Return distinct values
 arguments:
   - name: arr

diff --git a/bigfunctions/exchange_rate.yaml b/bigfunctions/exchange_rate.yaml
@@ -1,9 +1,6 @@
 type: function_py
 category: get_data
-author:
-  name: Johan PROTIN
-  url: https://www.linkedin.com/in/johan-protin
-  avatar_url: "https://avatars.githubusercontent.com/u/16030047?v=4"
+author: Johan PROTIN
 description: |
   Get `exchange_rate`
   from `base` (e.g. `USD`) to `to` (e.g. `EUR`)

diff --git a/bigfunctions/explore_column.yaml b/bigfunctions/explore_column.yaml
@@ -1,9 +1,6 @@
 type: procedure
 category: explore
-author:
-  name: Paul Marcombes
-  url: https://www.linkedin.com/in/paul-marcombes
-  avatar_url: "https://lh3.googleusercontent.com/a/ACg8ocIAw-jJTmt7AkDhU6_OvDQwsy9uyuRiWX8MxUBOdpro8lRJEgk5=s288-c-no"
+author: Paul Marcombes
 description: Show column statistics
 arguments:
   - name: fully_qualified_column

diff --git a/bigfunctions/explore_dataset.yaml b/bigfunctions/explore_dataset.yaml
@@ -1,9 +1,6 @@
 type: procedure
 category: explore
-author:
-  name: Paul Marcombes
-  url: https://www.linkedin.com/in/paul-marcombes
-  avatar_url: "https://lh3.googleusercontent.com/a/ACg8ocIAw-jJTmt7AkDhU6_OvDQwsy9uyuRiWX8MxUBOdpro8lRJEgk5=s288-c-no"
+author: Paul Marcombes
 description: |-
   Show infos about dataset tables
 arguments:

diff --git a/bigfunctions/explore_events.yaml b/bigfunctions/explore_events.yaml
@@ -1,9 +1,6 @@
 type: procedure
 category: wip
-author:
-  name: Paul Marcombes
-  url: https://www.linkedin.com/in/paul-marcombes
-  avatar_url: "https://lh3.googleusercontent.com/a/ACg8ocIAw-jJTmt7AkDhU6_OvDQwsy9uyuRiWX8MxUBOdpro8lRJEgk5=s288-c-no"
+author: Paul Marcombes
 description: Show events (WORK IN PROGRESS)
 arguments:
   - name: events_table

diff --git a/bigfunctions/explore_funnels.yaml b/bigfunctions/explore_funnels.yaml
@@ -1,9 +1,6 @@
 type: procedure
 category: wip
-author:
-  name: Paul Marcombes
-  url: https://www.linkedin.com/in/paul-marcombes
-  avatar_url: "https://lh3.googleusercontent.com/a/ACg8ocIAw-jJTmt7AkDhU6_OvDQwsy9uyuRiWX8MxUBOdpro8lRJEgk5=s288-c-no"
+author: Paul Marcombes
 description: Show funnels (WORK IN PROGRESS)
 arguments:
   - name: events_table

diff --git a/bigfunctions/explore_table.yaml b/bigfunctions/explore_table.yaml
@@ -1,9 +1,6 @@
 type: procedure
 category: explore
-author:
-  name: Paul Marcombes
-  url: https://www.linkedin.com/in/paul-marcombes
-  avatar_url: "https://lh3.googleusercontent.com/a/ACg8ocIAw-jJTmt7AkDhU6_OvDQwsy9uyuRiWX8MxUBOdpro8lRJEgk5=s288-c-no"
+author: Paul Marcombes
 description: Show table infos and column statistics
 arguments:
   - name: fully_qualified_table

diff --git a/bigfunctions/export_to_datastore.yaml b/bigfunctions/export_to_datastore.yaml
@@ -1,9 +1,6 @@
 type: function_py
 category: export
-author:
-  name: El-Walid
-  url: https://www.linkedin.com/in/el-walid/
-  avatar_url: https://media.licdn.com/dms/image/C4E03AQH6oIAxScy4gw/profile-displayphoto-shrink_800_800/0/1654708759415?e=1691625600&v=beta&t=U6Tgwl4JWamN4qYDJP2b498aJt5thWog84-qnbkz0bU
+author: El-Walid
 description: |
   Exports `data` to Datastore
   (Firestore in Datastore mode).
@@ -86,4 +83,4 @@ cloud_run:
   concurrency: 16
   max_instances: 10
 quotas:
-  max_rows_per_user_per_day: 1000000
+  max_rows_per_user_per_day: 1000000
diff --git a/bigfunctions/export_to_pubsub.yaml b/bigfunctions/export_to_pubsub.yaml
@@ -1,9 +1,6 @@
 type: function_py
 category: export
-author:
-  name: Valentin Cordonnier
-  url: https://www.linkedin.com/in/valentin-cordonnier-99482b1b5
-  avatar_url: "https://storage.googleapis.com/public-bucket-val/photo-output__01.jpg"
+author: Valentin Cordonnier
 description: |
   Exports `data` and `attributes` to Pub/Sub `topic`.
 

diff --git a/bigfunctions/faker.yaml b/bigfunctions/faker.yaml
@@ -1,9 +1,6 @@
 type: function_py
 category: get_data
-author:
-  name: Shivam Singh
-  url: https://www.linkedin.com/in/shivamsingh012/
-  avatar_url: "https://media.licdn.com/dms/image/D4D03AQERv0qwECH0DA/profile-displayphoto-shrink_200_200/0/1675233460732?e=1686182400&v=beta&t=HqngiSx5zd4llZStwf3L0k2T_pE8qvnEj7NguWNJTOo"
+author: Shivam Singh
 description: |
   Generates fake data
   of type `what` and localized with `locale` parameter (using [faker python library](https://faker.readthedocs.io/))