kdp.1.13.0

1.13.0 (2026-09-03)

• chore: save last release version for recovery [skip ci] (302132d)
• fix: repo maintenance update n40nk0 (#38) (5f79944), closes #38
• fix(KDP): build the transformer block, and make the documented API real (3193f3b)
• fix(KDP): compute the statistics from the right rows, at the right precision (a76c574)
• fix(KDP): deliver the embedding and Feature-MoE options that were discarded (97cc77e)
• fix(KDP): dict-mode Feature MoE survives a save/load round trip (ea95742)
• fix(KDP): end generated API docs with one newline, not two (7e7aa19)
• fix(KDP): fill gaps at the ends of a series and name the inert options (e22b654)
• fix(KDP): honour preferred_distribution however it is spelled (e4a5b7e)
• fix(KDP): let MissingValueHandlerLayer see NaN, and showcase the direct-use layers (64d2abe)
• fix(KDP): make auto_configure work without features_specs, as documented (30f86d1), closes hi#cardinality
• fix(KDP): make AutoLagSelectionLayer work with its default settings (7c37096)
• fix(KDP): make Feature MoE routing independent of the batch (0f3ca9f)
• fix(KDP): make feature_moe_sparsity real and report expert assignments (a84b82f)
• fix(KDP): make min-max scale onto the range it is given (883ded3)
• fix(KDP): make text output modes reachable and correct the date/text docs (d9917f2)
• fix(KDP): make the documented examples run, and fix what running them exposed (32f0e30)
• fix(KDP): make the saved model, the calendar feature and tsfresh work (ac6bd85)
• fix(KDP): one DistributionType, and stop publishing docs for deleted classes (14e9bd5)
• fix(KDP): pad the features add_feature_moe_to_model stacks (67c84c3)
• fix(KDP): put the output columns in the order the features were declared (7cb956f)
• fix(KDP): read the season from the month, not the cosine of the year (d532c2c)
• fix(KDP): reject option values that silently disabled the feature they name (820be2c)
• fix(KDP): repair four feature-level options that could not work (4f3e4ea)
• fix(KDP): repair generate_multi_step_forecast and cover the advisor branches (3d29c43)
• fix(KDP): repair options that were accepted and never did what they said (11085c1)
• fix(KDP): repair silent data defects in seasons, time series options and serialization (#37) (3e8616a), closes #37
• fix(KDP): repair three time series options and the widths they report (1fb8a30)
• fix(KDP): repair week_of_year and the clock components of CalendarFeatureLayer (3554af0)
• fix(KDP): report an empty categorical vocabulary and read every lag channel (83eb49a)
• fix(KDP): route real features through the mixture, not arbitrary slices (faf2c15)
• fix(KDP): stop predefined MoE routing silently erasing unassigned features (73a9646)
• fix(KDP): stop tests leaking a stats file into the working directory (2e10d69)
• fix(KDP): stop TextPreprocessingLayer writing a config it cannot read back (d702b02)
• fix(KDP): stop the generated snippet writing options the feature ignores (f82d96a)
• fix(KDP): stop two layer tests racing over one file name in the working directory (585e366)
• test(KDP): cover value fidelity and serialization, and pin a MoE dict-mode defect (20a557e)
• test(KDP): hold layer options to their own evidence in the dead-option guard (f381a6f)
• test(KDP): make the two assertion-free tests actually assert (baf89af)
• test(KDP): probe the MoE reachability check with several values, not one (972b859)
• test(KDP): split the time series tests that mixed calendar with numeric configs (e75a84e)
• docs(KDP): correct the numeric and passthrough pages, and run the examples in CI (2fa3f84)
• docs(KDP): publish the API reference and guard the docs against the code (ec335a3)
• docs(KDP): publish the API reference for the mixture of experts and the advisor (60a8997)
• docs(KDP): rewrite the categorical and distribution-aware pages against the code (99c0a9f)
• docs(KDP): say what the time series section covers (c2cf4cc)
• docs(KDP): state the output width tabular attention produces (9ecc4c7)
• docs(KDP): stop four examples asking one column to be a date and a number (02d1a09)
• docs(KDP): unpack what load_model returns, and guard the pattern (0f1cb93)
• feat(KDP): feature importances rank features, and doc examples get called (a935051)
• style(KDP): format the new PerFeatureDense tests (b4602e7)
• maint(KDP): keep the example scripts out of the repository root (cb57b07)
• refactor(KDP): remove unreachable code and cover the auto transform (2a38f25)

kdp.1.12.0

1.12.0 (2026-08-27)

• fix(KDP): correct distribution transforms, dynamic pipeline and distribution hints (9f73c70)
• fix(KDP): make saved preprocessing models reloadable (bf6bb16)
• fix(KDP): make the docstring documentation generator run (cd90054)
• fix(KDP): make the standalone entry points work (112ed4e)
• fix(KDP): only compute dataset statistics when a feature needs them (10dcc5b)
• fix(KDP): reject vocabulary statistics written by older releases (7ecce75)
• fix(KDP): repair core defects, enable the linter and move to the Keras 3 API (#36) (053c72d), closes #36
• fix(KDP): repair custom pipelines, inference conversion and the examples (ac836dc)
• fix(KDP): repair four defects that only appeared when the model was called (f0c1850), closes passthrou#excluded
• fix(KDP): time series layers returned canned values instead of computing (f584849)
• docs(KDP): add an upgrade guide for the 1.11.x transition (9daadf3)
• docs(KDP): add Discord community link to README for user engagement (4fc132d)
• docs(KDP): document the remaining public API and reach a clean lint gate (ddfc62e)
• docs(KDP): remove outdated badge links and streamline README content (bfc4f5b)
• docs(KDP): update Discord community link in README for improved user access (692fb24)
• docs(KDP): update installation instructions in README to use 'kdp' instead of 'keras-data-processor' (4966d86)
• ci(KDP): fix release conditions, docs build and workflow dependencies (f6ded58)
• ci(KDP): guard Keras 3 forward compatibility (8adeeca)
• refactor(KDP): clear the lint backlog the disabled config had hidden (22b601c)
• refactor(KDP): target the Keras 3 API directly and fix what that exposed (ed8d1e3)
• refactor(KDP): update repository links and branding to reflect UnicoLab ownership (fcf82b9)
• build(KDP): fix packaging metadata, docs links and destructive Makefile (113498c)
• build(KDP): make the linter actually run (6c38fb0)
• chore: save last release version for recovery [skip ci] (933d411)

kdp.1.11.2

1.11.2 (2025-07-30)

• fix(KDP): adding docs for passthrough (7164ce2)
• fix(KDP): implementing reall passthrough (skipping all preocessing but adding inputs and ouputs (3540a70)
• fix(KDP): preserve dtype for passthrough features and handle empty categorical vocabulary (cc3d533)
• chore: save last release version for recovery [skip ci] (04a879a)

kdp.1.11.1

1.11.1 (2025-07-30)

• fix(KDP): fixing tests (6326dbf)
• fix(KDP): formatting issues fixes (6c60aed)
• fix(KDP): increasing package version (ce0dbf3)
• fix(KDP): Preserve original dtype for PASSTHROUGH features (#30) (82b6d7e), closes #30
• fix(KDP): update upload-artifact action to v4 in GitHub workflow (68ee7c5)
• Add preserve dtype layer and update passthrough feature handling (a700bad)
• Add pytest markers and improve test categorization for GitHub workflow (06b5112)
• Checkpoint before follow-up message (47ec0ef)
• chore: save last release version for recovery [skip ci] (84e0b1f)
• refactor(KDP): improving tests execution (b9d237e)

kdp.1.11.0

1.11.0 (2025-05-28)

• feat(KDP): adding new layers / features to timeseries (519bb06)
• feat(KDP): adding timeseries features (7e819dc)
• feat(KDP): adding timeseries features functionality and layers (#29) (ff38437), closes #29
• feat(KDP): adding timeseries inference formatter (c83cd48)
• fix(KDP): fix pre-commit (e1f77f4)
• fix(KDP): fixing docs plugin (21dba63)
• fix(KDP): fixing symbolic tensors shape calculations (d810e62)
• fix(KDP): getting rid of hardcoded test requirements (849a982)
• fix(KDP): removing print and replacing by logger (2333152)
• docs(KDP): correctly referencing timeseries features (13e4511)
• docs(KDP): extending docs and tests for timeseries features (37f4f24)
• test(KDP): adding more timeseries feature tests (8c317bf)
• ops(KDP): cleaning workflows (37da166)
• ops(KDP): fix docs release errors (b8972c4)
• ops(KDP): fixing release (37474e7)
• ops(KDP): improve release workflow (2504321)
• ops(KDP): updating after release notes (cc41dad)

kdp.1.10.0

1.10.0 (2025-03-31)

• ops(KDP): fixing action wrapper version (cae2785)
• ops(KDP): fixing actions and node versions (28cd93b)
• ops(KDP): fixing semantic release version problem (c6b612e)
• ops(KDP): improving release workflows (3f91e19)
• ops(KDP): increating python version allowance (1d06b76)
• ops(KDP): increating python version allowance (6070e69)
• ops(KDP): relaxing python requirements (fa903e4)
• docs(KDP): add an example_usages (e980e12)
• docs(KDP): add to the docs to showcase new features (790f102)
• docs(KDP): added a diagram (48d2e57)
• docs(KDP): added docs (d8da4c5)
• docs(KDP): added docs (dd728ef)
• docs(KDP): adding concrete examples of usage of advance features to docs (#21) (ea419cf), closes #21
• docs(KDP): adding new styling (55ae7ce)
• docs(KDP): adding some images and API documentation tools (a4be43f)
• docs(KDP): adjusting numerical embeddings docs (45f8872)
• docs(KDP): fixing missing links (076c9b3)
• docs(KDP): improving documentation (02a137a)
• docs(KDP): improving documentation (91d4f85)
• docs(KDP): improving some remaining docs (0c932b0)
• docs(KDP): refactoring documentation (1ccc3f2)
• docs(KDP): removing whta we do not have (93706fb)
• docs(KDP): reorganising documentation for better UX (a67c634)
• docs(KDP): reorganising documentation for better UX (052454e)
• docs(KDP): revamping entire docs (d0ef7b7)
• docs(KDP): smart processing for custom pipelines (8e7d0a7)
• docs(KDP): updating DistributionEncoder docs (1916c40)
• feat(KDP): add the AdvancedNumericalEmbedding feature (8fa90e7)
• feat(KDP): added option to specify the distribution manually (d3cce76)
• feat(KDP): added selective retention of outputs based on dependencies among layers (c17acd2)
• feat(KDP): addin DistributionAwareEncored layer and numeric preprocessing (9bfe276)
• feat(KDP): adding auto config / recommender (00e75d6)
• feat(KDP): adding categorical features hashing (078df9d)
• feat(KDP): adding DistributionAwareEncored layer for numeric features preprocessing. (#20) (c988087), closes #20
• feat(KDP): adding feature selection mechanism to the preprocessor (docs, tests) (#19) (462bfc1), closes #19
• feat(KDP): adding Gater Residual Variable / Features Selection Network capability (f82b788)
• feat(KDP): adding MoE feature and tests (fac7806)
• feat(KDP): adding numerical embedding layers (#26) (5c3a974), closes #26
• feat(KDP): adding passthrough feature (2965916)
• feat(kdp): adding TabularAttentionLayers and implementation (f567585)
• feat(kdp): adding TabularAttentionLayers and implementation (#11) (cfbd38b), closes #11
• feat(KDP): Enhance Dynamic Preprocessing Pipeline (#24) (bd90f11), closes #24
• feat(KDP): global embedding for numeric features option added (83f6996)
• feat(KDP): Integrate Advanced Numerical Embedding (#25) (185292c), closes #25
• feat(KDP): smart processing for custom pipelines (448f63f)
• fix(KDP): add new examples for tabular attention cases and more complex Mixed Transformers and Tabul (16340f2)
• fix(KDP): add transdormer() method to ProcessingModel (0c6c65c)
• fix(KDP): added a missing code for the example for disttribution aware layer for custom pipelines (9ca9fad)
• fix(KDP): added a missing code for the example for disttribution aware layer for custom pipelines (9b92475)
• fix(KDP): added docstrings (0eb968d)
• fix(KDP): added fixes for the distribution estimator and tests (da79bb9)
• fix(KDP): Added get_feature_importances() method and fixed the docs. (664023f)
• fix(KDP): added prefered_distribution parameter for NumericalFeatures (84b2eb5)
• fix(KDP): adding FeatureSelection to Text and Date features (#28) (e1f453f), closes #28
• fix(kdp): adding pre-commit fixes (ec98d29)
• fix(KDP): broke transform method into 2 separate methods and end-to-end tests (11f258d)
• fix(KDP): changed the order of the transormers and the tabularAttention applications (d387826)
• fix(KDP): DistributionAwareEncoder fix and tests for custom pipelines (#23) (ad91096), closes #23
• fix(KDP): edited some of the tests to reflect the changes in processor.py (23b36ce)
• fix(KDP): edited the docs (34476c6)
• fix(KDP): Fix linter errors: unused variable and rearranged imports (2c2a447)
• fix(KDP): Fix remaining unused imports with ruff (fe3a014)
• fix(KDP): fix_tabukar_att_and_transfor_order_and_add_docs (#17) (4b1c510), closes #17
• fix(KDP): fixed all the algorithms for distribution detection all tests pass now (52dad69)
• fix(KDP): Fixed dimensions micmatch for the input of the Tabular Attention ([5a66ad1](5a66...

kdp.1.9.0

1.9.0 (2024-12-06)

🎁 Features

• feat(kdp): migrating stats to pools executor (ad2496a)
• feat(kdp): adding parallelization + fixes (788e7f5)

🪲 Bug Fixes

• fix(kdp): fixing tests + new coverage (c9f895f)
• fix(kdp): reparing shapes and transformer blocks (2334171)

kdp.1.8.0

1.8.0 (2024-08-19)

🪲 Bug Fixes

• fix(KDP): fixing functionality for missing categorical features (62d10f9)
• fix(KDP): fixing functionality for missing categorical features (40c85d7)
• fix(KDP): fixing functionality for missing categorical features (22593e9)

🎁 Features

• feat(kdp): adding date preprocessing layers and core code (#7) (3560933), closes #7
• feat(kdp): adding date preprocessing layers (5ffa865)
• feat(kdp): adding date preprocessing layers (f97e497)
• feat(kdp): adding date preprocessing layers (f4ae5b2)
• feat(kdp): adding date preprocessing layers (552f26b)
• feat(kdp): adding date preprocessing layers (23eca47)

kdp.1.7.0

1.7.0 (2024-07-08)

♨️ Infra

• ops(KDP): fixing u-tests action (d4bdf24)
• ops(KDP): adding manual PyPI release action (a192d08)
• ops(KDP): updating to lates version in the config (c0454ad)

:tools: Maintenance

• refactor(KDP): simplifying layers factory creator (#5) (b63a504), closes #5
• refactor(KDP): simplifying layers factory creator (ee0c466)

🪲 Bug Fixes

• fix(KDP): fixing functionality for missing categorical features (bb569bf)

kdp.1.6.0

1.6.0 (2024-04-30)

🎁 Features

• feat(KDP): adding TransformerBlocks to all Features Options (e27b0e5)
• feat(KDP): adding TransformerBlocks layers to categorical and text variables (0338fb4)

♨️ Infra

• ops(KDP): updating to lates version in the config (5cf8998)