10.2.2.2

10.2.2.2 - 2024-07-19

Fixed

• (core) Documentation of the specific_pairs parameter for the train_predictor and
  train_recoder core API functions.

Deprecated

• (core) The following parameters of the train_predictor core API functions:
  • max_groups
  • max_intervals
  • min_group_frequency
  • min_interval_frequency
  • results_prefix
  • snb_predictor
  • univariate_predictor_number
  • discretization_method for supervised learning
  • grouping_method for supervised learning

10.2.2.1

Release date: 2024-07-05

Changed

• Internals:
  • The OpenMPI backend now executes with the --allow-run-as-root option.

10.2.2.0

Release date: 2024-07-03

Added

• (sklearn) Support for sparse arrays in sklearn estimators.

Changed

• Internals:
  • MPI backend from MPICH to OpenMPI for native + Pip-based Linux installations.

Fixed

• core
  • Metric name search in estimator analyis report.

10.2.2.0-rc.1

For testing purposes only

10.2.1.0

Release Date: 2024-03-26

For installation instructions see https://khiops.org

Added

• sklearn: 1:1 relations to multi-table datasets.
• sklearn: Estimators' fit methods now accept single-column pandas dataframes as y target.

Changed

• core: Improve user error and warning messaging.

Fixed

• General: Reinstate Rocky Linux 8 support.

10.2.0.0

Note: This release marks the open sourcing of Khiops:

• The khiops-python replaces the old pykhiops package. We recommend to uninstall pykhiops
  before installing khiops-python. More information at the Khiops website.
• khiops-python uses a new four digit versioning convention.
• The khiops conda package is available for many environments. See the Khiops website
  for more information.

Added

• General:
  • khiops-python is now available with conda khiops package. This package bundles
    khiops-python and the Khiops binaries so no system-wide Khiops installation is needed. More
    information at the Khiops website.
  • Support for python 3.12.
• sklearn
  • Estimator classes can now be trained from Numpy arrays in single-table mode.
• core
  • stdout_file_path and stderr_file_path parameters for khiops.core.api functions. These
    parameters allow to save the stdout/stderr output of the Khiops execution.

Changed

• sklearn
  • Estimator classes now comply with scikit-learn standards.
• core
  • The JSON initialization of AnalysisResults, CoclusteringResults and its component classes
    is coherent with the empty initialization.