v0.1.3

• Fix new package dependencies
• Switch from Travis CI to Github Actions

https://pypi.org/project/responsibly/0.1.3

v0.1.2

• Fix Travis CI issues with pipenv
• Fix bugs with word embedding bias

https://pypi.org/project/responsibly/0.1.2

v0.1.1

• Fix a dependencies issue with smart_open
• Change URLs to https

https://pypi.org/project/responsibly/0.1.1

v0.1.0

• Rename the project to responsibly from ethically
• Word embedding bias
  • Improve functionality of BiasWordEmbedding
• Threshold fairness interventions
  • Fix bugs with ROCs handling
  • Improve API and add functionality (plot_thresholds)

https://pypi.org/project/responsibly/0.1.0

v0.0.5

• Word embedding bias
  • Fix bug in computing WEAT
  • Computing and plotting factual property
    association to projections on a bias direction,
    similar to WEFAT

https://pypi.org/project/ethically/0.0.5

v0.0.4

• Word embedding bias
  • Unrestricted most_similar
  • Unrestricted generate_analogies
  • Running specific experiments with calc_all_weat
  • Plotting clustering by classification of biased neutral words

https://pypi.org/project/ethically/0.0.4

v0.0.3

• Fairness in Classification
  • Three demographic fairness criteria
    • Independence
    • Separation
    • Sufficiency
  • Equalized odds post-processing algorithmic interventions
  • Complete two notebook demos (FICO and COMPAS)
• Words embedding bias
  • Measuring bias with WEAT method
• Documentation improvements
• Fixing security issues with dependencies

https://pypi.org/project/ethically/0.0.3/

v0.0.2

• Words embedding bias
  • Generating analogies along the bias direction
  • Standard evaluations of words embedding (word pairs and analogies)
  • Plotting indirect bias
  • Scatter plot of bias direction projections between two words embedding
  • Improved verbose mode

https://pypi.org/project/ethically/0.0.2/

v0.0.1

Gender debiasing for words embedding based on Bolukbasi et al.
https://pypi.org/project/ethically/0.0.1/