Trigger hub build conditionally

.github/workflows/docusaurus-gh-pages.yml

@@ -4,7 +4,6 @@ name: Deploy Docusaurus with GitHub Pages dependencies preinstalled
 on:
  # Runs on pushes targeting the default branch & contrib subdirectory
  push:
- branches: ["user_contrib", "main"]
  paths:
  - 'contrib/**'
 
@@ -25,7 +24,7 @@ concurrency:
 
 jobs:
  branch-build:
- if: GITHUB_REF_NAME != 'main'
+ if: ${{ github.ref != 'refs/heads/main' }}
  environment:
  name: github-pages
  url: ${{ steps.deployment.outputs.page_url }}
@@ -64,7 +63,7 @@ jobs:
  run: yarn build
  # 👆 Build steps
  deploy:
- if: GITHUB_REF_NAME == 'main'
+ if: ${{ github.ref == 'refs/heads/main' }}
  environment:
  name: github-pages
  url: ${{ steps.deployment.outputs.page_url }}

contrib/hamilton/contrib/user/skrawcz/author.md

@@ -0,0 +1,10 @@
+# skrawcz
+
+Hi I'm Stefan Krawczyk. I am on of the co-creators of Hamilton.
+
+# Github
+https:/skrawcz
+# Linkedin
+https://www.linkedin.com/in/skrawczyk
+# X (Twitter)
+https://www.twitter.com/stefkrawczyk

contrib/hamilton/contrib/user/skrawcz/hello_world/README.md

@@ -0,0 +1,14 @@
+# Purpose of this module
+
+This module implements a hello world dataflow to show transforming columns from a dataframe.
+
+You can pass in your own values for spend & signups, or use the default.
+
+# Configuration Options
+This module can be configured with the following options:
+ - {"default": "True"} to run it without any inputs.
+ - {} to have to pass in `spend` and `signups`.
+
+# Limitations
+
+None to really note.

contrib/hamilton/contrib/user/skrawcz/hello_world/__init__.py

@@ -0,0 +1,66 @@
+import logging
+
+logger = logging.getLogger(__name__)
+
+from hamilton import contrib
+
+with contrib.catch_import_errors(__name__, __file__, logger):
+ import pandas as pd
+
+from hamilton.function_modifiers import config, extract_columns
+
+
+@extract_columns("spend", "signups")
+@config.when(default="True")
+def default_data() -> pd.DataFrame:
+ return pd.DataFrame(
+ {
+ "signups": pd.Series([1, 10, 50, 100, 200, 400]),
+ "spend": pd.Series([10, 10, 20, 40, 40, 50]),
+ }
+ )
+
+
+def avg_3wk_spend(spend: pd.Series) -> pd.Series:
+ """Rolling 3 week average spend."""
+ return spend.rolling(3).mean()
+
+
+def spend_per_signup(spend: pd.Series, signups: pd.Series) -> pd.Series:
+ """The cost per signup in relation to spend."""
+ return spend / signups
+
+
+def spend_mean(spend: pd.Series) -> float:
+ """Shows function creating a scalar. In this case it computes the mean of the entire column."""
+ return spend.mean()
+
+
+def spend_zero_mean(spend: pd.Series, spend_mean: float) -> pd.Series:
+ """Shows function that takes a scalar. In this case to zero mean spend."""
+ return spend - spend_mean
+
+
+def spend_std_dev(spend: pd.Series) -> float:
+ """Function that computes the standard deviation of the spend column."""
+ return spend.std()
+
+
+def spend_zero_mean_unit_variance(spend_zero_mean: pd.Series, spend_std_dev: float) -> pd.Series:
+ """Function showing one way to make spend have zero mean and unit variance."""
+ return spend_zero_mean / spend_std_dev
+
+
+if __name__ == "__main__":
+ # run as a script to test Hamilton's execution
+ import __init__ as hello_world
+
+ from hamilton import base, driver
+
+ dr = driver.Driver(
+ {"default": "True"},
+ hello_world,
+ adapter=base.DefaultAdapter(),
+ )
+ # create the DAG image
+ dr.display_all_functions("dag", {"format": "png", "view": False})

contrib/hamilton/contrib/user/skrawcz/hello_world/requirements.txt

@@ -0,0 +1 @@
+pandas

contrib/hamilton/contrib/user/skrawcz/hello_world/tags.json

@@ -0,0 +1,7 @@
+{
+ "schema": "1.0",
+ "use_case_tags": ["example", "transformation"],
+ "secondary_tags": {
+ "dataframe-library": "pandas"
+ }
+}

contrib/hamilton/contrib/user/skrawcz/hello_world/valid_configs.jsonl

@@ -0,0 +1,2 @@
+{"description": "Default way to run the dataflow.", "name": "default", "config": {"default": "True"}}
+{"description": "Bring your own spend & signup values.", "name": "bring-your-own", "config": {}}