Release Notes

Future Release

  • Enhancements

  • Fixes
    • Update to avoid error with a categorical target with unused categories (#349)

  • Changes
    • Transition to pure pyproject.toml for project metadata (#351)

  • Documentation Changes

  • Testing Changes
    • Add create feedstock PR workflow (#346)

Thanks to the following people for contributing to this release: @gsheni, @thehomebrewnerd

v0.9.1 Nov 2, 2022

  • Changes
    • Explicitly set series dtype for LabelTimes.target_types (#337)

  • Documentation Changes
    • Fix docs build and clean up release notes (#336)

Thanks to the following people for contributing to this release: @thehomebrewnerd

v0.9.0 May 12, 2022

Warning

Compose will no longer support Python 3.7.

  • Changes
    • Update ipython to 7.31.1 (#286)

    • Transition to pyproject.toml and setup.cfg (#310, #313)

    • Add support for python 3.10 (#318)

    • Fix Makefile output filepath (#320)

  • Documentation Changes
    • Update README.md with Alteryx link (#289, #290, #314)

    • Add in-line tabs and copy-paste functionality to docs (#293)

    • Update nbconvert to version 6.4.5 to fix docs build issue (#305)

    • Update slack invite link to new (#316)

    • Update release.md with correct process (#324)

  • Testing Changes
    • Add woodwork to test-requirements.txt (#296)

    • Upgrade black version to 22.3.0 to fix linting issue (#309)

Thanks to the following people for contributing to this release: @gsheni, @mingdavidqi, @thehomebrewnerd

v0.8.0 Jan 20, 2022

  • Enhancements
    • Add issue templates for bugs, feature requests and documentation improvements (#271)

  • Changes
    • Update pip to 21.3.1 for test requirements (#265)

    • Restrict to Python 3.7 to 3.9 (#265)

    • Use black and remove autopep8 for linting (#265)

    • Update minimum dependency checker with the correct reviewers (#267)

    • Rename LabelMaker.target_entity to LabelMaker.target_dataframe_name (#276)

  • Documentation Changes
    • Update install instructions to specify correct python versions (#265)

    • Update example notebooks to use latest Featuretools and EvalML APIs (#275)

  • Testing Changes
    • Add unit test for dropping empty data slices (#280)

    • Add auto approve workflow for dependency updates (#281)

Thanks to the following people for contributing to this release: @gsheni, @jeff-hernandez, @thehomebrewnerd

Warning

Breaking Changes
  • The target_entity attribute of LabelMaker has been renamed to target_dataframe_name.

v0.7.0 Nov 2, 2021

  • Enhancements
    • Add maximum_data parameter to control when a search should stop (#216)

    • Add optional automatic update checker (#223, #229, #232)

    • Varying first cutoff time for each target group (#258)

  • Documentation Changes
    • Update doc tutorials to the latest API changes (#227)

    • Pin documentation requirements to avoid warnings and breaking changes (#244)

  • Testing Changes
    • Check if release notes were updated (#217)

    • Add minimum dependency checker to generate minimum requirement files (#218)

    • Add CI workflow for unit tests with minimum dependencies (#220)

    • Create separate worksflows for each CI job (#220)

    • Pass token to authorize uploading of codecov reports (#226)

    • Update minimum unit tests to run on all pull requests (#230)

    • Add workflow to check latest dependencies (#233)

    • Update reviewers for minimum and latest dependency checkers (#257)

Thanks to the following people for contributing to this release: @gsheni, @jeff-hernandez

v0.6.0 Feb 11, 2021

  • Enhancements
    • Added description for continuous target distributions (#187)

  • Fixes
    • Sorted label distribution in description (#188)

  • Documentation Changes
    • Made logo easier to read (#182)

    • Added Alteryx footer to docs (#185, #186)

    • Updated tutorials to the latest API changes (#190, #198, #204)

    • Updated repository links to GitHub (#191)

    • Added help page to docs (#194)

    • Improved docs based on tech writer feedback (#195)

    • Added open graph info to docs (#203)

  • Testing Changes
    • Migrated CI tests to Github Actions (#184, #189)

    • Updated tests to trigger on pull request events (#199)

Thanks to the following people for contributing to this release: @flowersw, @jeff-hernandez, @rwedge

v0.5.1 Sep 22, 2020

  • Documentation Changes
    • Update F1 Macro in Turbofan Degradation Tutorial (#180).

    • Apply Pandas Docs Theme (#172).

    • Add Chicago Bike Tutorial (#157).

  • Testing Changes
    • Test Doc Builds (#165)

v0.5.0 Aug 28, 2020

  • Enhancements
    • Added Column-Based Windows (#151).

  • Changes
    • Refactored Data Slice Generator (#150).

  • Documentation Changes
    • Updated README (#164).

    • Updated Predict Next Purchase Demo (#154).

    • Updated Predict Turbofan Degradation Demo (#154).

Warning

Breaking Changes
  • Attributes of the data slice context have changed. Inside a labeling function, the timestamps of a data slice can be referenced by ds.context.slice_start and ds.context.slice_stop. For more details, see Data Slice Context.

v0.4.0 Jul 2, 2020

  • Enhancements
    • Target values can be sampled from each group (#138).

    • One of multiple targets can be selected (#147).

    • Labels can be binned using infinite edges represented as string (#133).

  • Changes
    • The label times object was refactored to improve design and structure (#135).

Warning

Breaking Changes
  • Loading label times from previous versions will result in an error.

v0.3.0 Jun 1, 2020

  • Enhancements
    • Label Search for Multiple Targets (#130)

  • Changes
    • Column renamed from cutoff_time to time (#139)

v0.2.0 Apr 23, 2020

  • Changes
    • Dropped Support for Python 3.5 (#128)

    • Rename LabelTimes.name to LabelTimes.label_name (#126)

    • Support keyword arguments in Pandas methods. (#121)

  • Documentation Changes
    • Improved data download in Predict Next Purchase (#76)

  • Testing Changes
    • Added tests that use Python 3.8 in CirlceCI (#128)

Warning

Breaking Changes
  • LabelTimes.name has been renamed to LabelTimes.label_name

v0.1.8 Mar 11, 2020

  • Fixes
    • Support for Pandas 1.0

v0.1.7 Jan 31, 2020

  • Enhancements
    • Added higher-level mappings to offsets.

    • Track settings for sample transforms.

  • Fixes
    • Pinned Pandas version.

  • Testing Changes
    • Moved Featuretools to test requirements.

v0.1.6 Oct 22, 2019

  • Enhancements
    • Serialization for Label Times

  • Fixes
    • Matplotlib Backend Fix

    • Sampling Label Times

  • Documentation Changes
    • Added Data Slice Generator Guide

  • Testing Changes
    • Integration Tests for Python Versions 3.6 and 3.7

v0.1.5 Sep 16, 2019

  • Enhancements
    • Added Slice Generator

    • Added Seaborn Plots

    • Added Data Slice Context

    • Added Count per Group

  • Documentation Changes
    • Updated README

    • Added Example: Predict Next Purchase

    • Added Example: Predict RUL

v0.1.4 Aug 7, 2019

  • Enhancements
    • Added Sample Transform

    • Improved Progress Bar

    • Improved Label Times description

v0.1.3 Jul 9, 2019

  • Enhancements
    • Improved documentation

    • Added testing for Featuretools compatibility

    • Improved description of Label Times

    • Refactored search in Label Maker

    • Improved testing for Label Transforms

v0.1.2 Jun 19, 2019

  • Enhancements
    • Add dynamic progress bar

    • Add label transform for binning labels

    • Improve code coverage

    • Update documentation

v0.1.1 May 31, 2019

  • Initial Release