Skip to main content

Tabular synthetic data generator based on Structural Causal Models

Project description

Tabular Data Generator with Structural Causal Models

License Python Version

Description

This framework provides a tool for generating synthetic tabular data based on Structural Causal Models (SCMs). By utilizing SCMs, the framework allows for the explicit definition of causal relationships between variables, ensuring that the generated data reflects these underlying dependencies. This approach is particularly useful for:

  • Realistic data generation: Creating datasets that preserve the complex causal interactions present in real-world data.
  • Data augmentation: Increasing the size and diversity of existing datasets while maintaining causal consistency.
  • Model testing and validation: Generating controlled data to evaluate the behavior of machine learning algorithms in different scenarios.
  • Simulations: Conducting "what-if" experiments and analyzing the consequences of interventions on variables.
  • Privacy-preserving data sharing: Sharing synthetic data that retains important statistical characteristics without revealing sensitive information.

The framework offers a flexible interface for defining causal graphs, specifying the functions that describe the relationships between variables, and generating datasets of arbitrary sizes.

Occupation shared among the datasets Top-5 skills
0 Sales workers ['customer service', 'organising, planning and scheduling work and activities', 'quality assurance procedures', 'wholesale and retail sales', 'provide high quality customer service']
1 Teaching professionals ['computer programming', 'computer graphics', 'project management', 'teach teaching principles', 'web programming']
2 Legal, social and cultural professionals ['office software', 'project management', 'business ICT systems', 'computer programming', 'conduct scholarly research']
3 Personal care workers ['work under supervision in care', 'geriatrics', 'nursing and midwifery', 'computer programming', 'project management']
4 Handicraft and printing workers ['use IT tools', 'electronics', 'Adobe Illustrator', 'computer graphics', 'use technical documentation']
5 Food processing, wood working, garment and other craft and related trades workers ['customer service', 'provide high quality customer service', 'project management', 'office software', 'web programming']
6 Numerical and material recording clerks ['office software', 'customer service', 'business ICT systems', 'manage administrative systems', 'project management']
7 Hospitality, retail and other services managers ['wholesale and retail sales', 'customer service', 'project management', 'management skills', 'sales strategies']
8 Science and engineering professionals ['computer programming', 'computer graphics', 'project management', 'office software', 'electronics and automation']
9 Food preparation assistants ['use cooking techniques', 'adapt props', 'secretarial and office work', 'pallets loading', 'planning and organising']
10 Building and related trades workers, excluding electricians ['repair plumbing systems', 'use genre painting techniques', 'construction methods', 'carpentry', 'authenticate documents']
11 Business and administration professionals ['office software', 'business ICT systems', 'wholesale and retail sales', 'project management', 'accounting']
12 Production and specialised services managers ['project management', 'business ICT systems', 'office software', 'management skills', 'logistics']
13 Labourers in mining, construction, manufacturing and transport ['prepare orders', 'operate forklift', 'pick orders for dispatching', 'logistics', 'computer programming']
14 Information and communications technology professionals ['computer programming', 'web programming', 'business ICT systems', 'operating systems', 'Java (computer programming)']
15 Agricultural, forestry and fishery labourers ['office software', 'joining parts using soldering, welding or brazing techniques', 'hotel, restaurants and catering', 'turf management', 'perform tungsten inert gas welding']
16 Commissioned armed forces officers ['search engines', 'driving light vehicles', 'supervision of persons', 'management skills', 'project management']
17 Other clerical support workers ['office software', 'business ICT systems', 'human resource management', 'business and administration', 'project management']
18 Personal service workers ['office software', 'project management', 'hair removal techniques', 'hotel operations', 'customer service']
19 Science and engineering associate professionals ['computer programming', 'computer graphics', 'electricity', 'project management', 'office software']
20 Cleaners and helpers ['clean equipment', 'office software', 'provide domestic care', 'operate recycling processing equipment', 'sales strategies']
21 Chief executives, senior officials and legislators ['business and administration', 'computer programming', 'project management', 'office software', 'data mining']

Installation

    conda env create --file reqs.yml
    conda activate CausalSDG

Authors

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

causalsdg_scm-0.1.0.tar.gz (28.0 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

causalsdg_scm-0.1.0-py3-none-any.whl (26.7 kB view details)

Uploaded Python 3

File details

Details for the file causalsdg_scm-0.1.0.tar.gz.

File metadata

  • Download URL: causalsdg_scm-0.1.0.tar.gz
  • Upload date:
  • Size: 28.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for causalsdg_scm-0.1.0.tar.gz
Algorithm Hash digest
SHA256 15687c56fcba58e448dd426d47641d28af6ed354d9ac3ca19ad9487e4aa90a1d
MD5 72ed75e86df4d3c4fc50da1322bdff2c
BLAKE2b-256 b7915c8f22cd4c94f0146af34748dc94eeb1e9aa0b6027f6e80be0bcf5567e4b

See more details on using hashes here.

Provenance

The following attestation bundles were made for causalsdg_scm-0.1.0.tar.gz:

Publisher: publish.yml on jacons/causal-sdg

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file causalsdg_scm-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: causalsdg_scm-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 26.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for causalsdg_scm-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 3f0fee181cb6ced06a2b3e470626aa6c8d75ca123ce87ee124e1ad30c7475ace
MD5 4bbb3a7e0a4fac16c0b452f3768f8efe
BLAKE2b-256 fd7640ca644c27d5b448ccc19ebd4a8dfa166bb8b53c2d1871d10092f1a0641d

See more details on using hashes here.

Provenance

The following attestation bundles were made for causalsdg_scm-0.1.0-py3-none-any.whl:

Publisher: publish.yml on jacons/causal-sdg

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page