v0.4

This update provides several minor improvements:

• Adds support for controls to the NonparametricTwoStageLeastSquares estimator (this is a breaking change)
• Fixes a few minor problems with the Deep IV implementation
  • Added support for treatments and outcomes that are vectors rather than 2-D arrays
  • Fixes a bug in the the effect method
• Enables the BootstrapEstimator to work in non-thread-based parallel contexts
• Adds a prototype of the DMLIV estimator (this is not included in the PyPI package because it is a prototype)

v0.3

This release contains the following changes:

• Improved options for fitting models in Deep IV
• Breaking change Reordered arguments to effect method, adding default treatments for the common case of a single vector treatment.
• Added a score method to the double ML classes
• Improved notebook examples

v0.2

Welcome to our v0.2 release. This release includes the following:

• New Jupyter notebooks for classes of estimators that were previously missing them
• Performance improvements to the OrthoForest estimators
• Local linear models for OrthoForest leaves
• Refactored Double ML classes to enable future improvements to be made easily
• Enabled discrete treatments to be used with Double ML
• Enabled using controls with the Doubly-Robust Metalearner
• Many minor bugfixes, documentation improvements, and improved tests

v0.1

Initial SDK release