Add two regression datasets: California Housing and Diabetes

[Shu-Wan]

Summary

This PR adds two classic regression datasets from sklearn to CausalBench for demo and testing purposes.

Datasets Added

1. California Housing Dataset

• Samples: 20,640
• Features: 9 (MedInc, HouseAge, AveRooms, AveBedrms, Population, AveOccup, Latitude, Longitude, MedHouseVal)
• Task: Regression - predict median house values in California districts
• Source: sklearn.datasets.fetch_california_housing

2. Diabetes Dataset

• Samples: 442
• Features: 11 (age, sex, bmi, bp, s1-s6, target)
• Task: Regression - predict disease progression from physiological variables
• Source: sklearn.datasets.load_diabetes

Changes

Dataset Files

Each dataset includes:

• CSV data file with all features and target
• config.yaml configuration file following CausalBench schema
• download_data.py script to regenerate data from sklearn

Deliverables

• ✅ Two regression datasets in causalbench-asu/tests/data/
• ✅ Compressed .zip files for each dataset
• ✅ Updated README.md with dataset information

Design Decisions

• No causal adjacency matrices: These are only required for causal discovery tasks, not regression tasks
• Classic sklearn datasets: Well-defined, documented, appropriate size for demos
• Standalone regression tasks: Configured explicitly as regression tasks in descriptions

Testing

All datasets successfully load through the CausalBench framework:

✅ California Housing Dataset: PASSED
✅ Diabetes Dataset: PASSED

Total: 2/2 tests passed

[kapkic]

LGTM

[Copilot]

Pull request overview

This PR adds two sklearn-sourced regression datasets (California Housing and Diabetes) to the CausalBench test data bundle for demos/testing, along with lightweight download scripts and README documentation updates.

Changes:

• Added california_housing dataset config + regeneration script (and accompanying data/zip artifacts).
• Added diabetes dataset config + CSV + regeneration script (and accompanying zip artifact).
• Updated README dataset table; minor formatting cleanup in zip_files.py.

Reviewed changes

Copilot reviewed 7 out of 10 changed files in this pull request and generated 3 comments.

Show a summary per file

File	Description
causalbench-asu/tests/zip_files.py	Minor formatting / quoting updates for zip utility.
causalbench-asu/tests/data/diabetes/download_data.py	Script to regenerate the Diabetes CSV from sklearn.
causalbench-asu/tests/data/diabetes/diabetes_data.csv	Added Diabetes dataset CSV.
causalbench-asu/tests/data/diabetes/config.yaml	Added dataset config for Diabetes.
causalbench-asu/tests/data/diabetes.zip	Added packaged dataset zip.
causalbench-asu/tests/data/california_housing/download_data.py	Script to regenerate the California Housing CSV from sklearn.
causalbench-asu/tests/data/california_housing/config.yaml	Added dataset config for California Housing.
README.md	Updated dataset list table to include the new datasets + minor whitespace cleanup.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

The column type values are set to continuous, but other dataset configs in this repo use values like ratio/nominal (e.g., tests/data/panama/config.yaml). If the dataset loader only recognizes the existing enum values, continuous will fail schema validation or parsing. Please align these column type fields with the accepted values used elsewhere (e.g., use ratio for numeric continuous variables) or update the loader/schema to explicitly support continuous.

Suggested change

	type: continuous
	data: decimal
	sex:
	header: sex
	type: continuous
	data: decimal
	bmi:
	header: bmi
	type: continuous
	data: decimal
	bp:
	header: bp
	type: continuous
	data: decimal
	s1:
	header: s1
	type: continuous
	data: decimal
	s2:
	header: s2
	type: continuous
	data: decimal
	s3:
	header: s3
	type: continuous
	data: decimal
	s4:
	header: s4
	type: continuous
	data: decimal
	s5:
	header: s5
	type: continuous
	data: decimal
	s6:
	header: s6
	type: continuous
	data: decimal
	target:
	header: target
	type: continuous
	type: ratio
	data: decimal
	sex:
	header: sex
	type: ratio
	data: decimal
	bmi:
	header: bmi
	type: ratio
	data: decimal
	bp:
	header: bp
	type: ratio
	data: decimal
	s1:
	header: s1
	type: ratio
	data: decimal
	s2:
	header: s2
	type: ratio
	data: decimal
	s3:
	header: s3
	type: ratio
	data: decimal
	s4:
	header: s4
	type: ratio
	data: decimal
	s5:
	header: s5
	type: ratio
	data: decimal
	s6:
	header: s6
	type: ratio
	data: decimal
	target:
	header: target
	type: ratio

[kapkic]

Actually, this is important. @prat-man @Shu-Wan I don't recall we do have any "type" for datasets. We may need to remove them. Please confirm.

[Copilot]

The column type fields use continuous, which is inconsistent with existing dataset configs that use values like ratio/nominal (see tests/data/panama/config.yaml, tests/data/abalone/config.yaml). If continuous isn't a recognized schema value, this dataset config may not load. Please switch these to the supported type value (likely ratio for these numeric columns) or extend the schema/loader to accept continuous.

Suggested change

	type: continuous
	data: decimal
	HouseAge:
	header: HouseAge
	type: continuous
	data: decimal
	AveRooms:
	header: AveRooms
	type: continuous
	data: decimal
	AveBedrms:
	header: AveBedrms
	type: continuous
	data: decimal
	Population:
	header: Population
	type: continuous
	data: decimal
	AveOccup:
	header: AveOccup
	type: continuous
	data: decimal
	Latitude:
	header: Latitude
	type: continuous
	data: decimal
	Longitude:
	header: Longitude
	type: continuous
	data: decimal
	MedHouseVal:
	header: MedHouseVal
	type: continuous
	type: ratio
	data: decimal
	HouseAge:
	header: HouseAge
	type: ratio
	data: decimal
	AveRooms:
	header: AveRooms
	type: ratio
	data: decimal
	AveBedrms:
	header: AveBedrms
	type: ratio
	data: decimal
	Population:
	header: Population
	type: ratio
	data: decimal
	AveOccup:
	header: AveOccup
	type: ratio
	data: decimal
	Latitude:
	header: Latitude
	type: ratio
	data: decimal
	Longitude:
	header: Longitude
	type: ratio
	data: decimal
	MedHouseVal:
	header: MedHouseVal
	type: ratio

[Copilot]

PR description mentions a new test_regression_datasets.py test script, but it doesn't appear to be included in this change set (and isn't present under causalbench-asu/tests/). If automated coverage for loading these datasets is intended, please add the test file (or update the PR description to match what’s actually being delivered).