v2.7.0

This release improves reproducibility and correctness across AutoML and tuning, including consistent random seed handling for SGD, logistic regression, random forest, and XGBoost, per-fold resampling for class imbalance, corrected quantized float sampling, per-metric trial averages, and preservation of zero-valued anonymous tuning metrics. It strengthens data preparation and evaluation with stable categorical encoding, aligned sample weights for non-shuffled and group splits, and free-memory propagation, while adding compatibility for recent scikit-learn and statsmodels changes. It corrects Statsmodels future forecast horizons and adds a Simplified Chinese README. It also adds Windows ARM64 CI, hardens GitHub Actions permissions and action pinning, and refreshes documentation and dependencies.

Thank you to all contributors for the PRs, issues, reviewing and testing.

Welcome Imran Ahamed (@immu4989), Arpit Jain (@arpitjain099), Arushi Sagar (@arushiiii18), Dan Fiedler (@danfiedler-msft), Nefelibata (@MeiSiristhebest), Amir Fathi (@AmirF194), Jeremy Schoemaker (@shoemoney), Venish Paneliya (@VenishPaneliya), Nithin Aashik PS (@nithin-aashik-mcw), betacatsling, 玉升 (@wangyusheng1985), and YE (@JasonYeYuhe) to the community!

What's Changed

• Bump fast-uri from 3.1.0 to 3.1.2 in /website by Dependabot (@dependabot)[bot] in #1542
• Bump @babel/plugin-transform-modules-systemjs from 7.19.6 to 7.29.4 in /website by Dependabot (@dependabot)[bot] in #1543
• ci(docs): always trigger docs workflow on PRs; move filtering into workflow by Li Jiang (@thinkall) in #1544
• fix: SGD results now reproducible by Imran Ahamed (@immu4989) in #1541
• fix: LRL1 results now reproducible by Imran Ahamed (@immu4989) in #1546
• fix: RandomForestEstimator honors random_seed config by Imran Ahamed (@immu4989) in #1547
• Add explicit least-privilege permissions to CD workflow by Arpit Jain (@arpitjain099) in #1548
• Bump brace-expansion from 5.0.5 to 5.0.6 in /website by Dependabot (@dependabot)[bot] in #1550
• fix: XGBoostSklearnEstimator honors random_seed config by Imran Ahamed (@immu4989) in #1549
• fix: XGBoostEstimator honors random_seed config by Imran Ahamed (@immu4989) in #1551
• fix: LRL2Classifier honors random_seed config by Imran Ahamed (@immu4989) in #1552
• fix: prepare_data crashes with non shuffle split + sample_weight (#887, #1553) by Imran Ahamed (@immu4989) in #1554
• fix: LRL1/LRL2 — migrate off sklearn 1.10 deprecations (penalty, n_jobs) by Imran Ahamed (@immu4989) in #1556
• fix: FLOW2.reach() handles mixed-type conditional parameters (#903) by Imran Ahamed (@immu4989) in #1557
• Bump shell-quote from 1.7.4 to 1.8.4 in /website by Dependabot (@dependabot)[bot] in #1559
• docs: ensemble component predict pattern + regression test (#1136) by Imran Ahamed (@immu4989) in #1558
• Bump joi from 17.7.0 to 17.13.4 in /website by Dependabot (@dependabot)[bot] in #1560
• fix: DataTransformer pins categorical codes at fit time + warns on unseen values (#1101) by Imran Ahamed (@immu4989) in #1561
• docs: production-deployment guide for trained FLAML models by Imran Ahamed (@immu4989) in #1562
• build(deps): bump http-proxy-middleware from 2.0.9 to 2.0.10 in /website by Dependabot (@dependabot)[bot] in #1565
• Avoid pandas resample crash in Windows Python 3.12 forecast tests by Li Jiang (@thinkall) with @Copilot in #1566
• build(deps): bump websocket-driver from 0.7.4 to 0.7.5 in /website by Dependabot (@dependabot)[bot] in #1572
• docs: cross-link AutoML and zero-shot LightGBM notebooks by Arushi Sagar (@arushiiii18) in #1571
• Fix MLflow autologged model reload fitted-state detection for scikit-learn>=1.8.0 by Li Jiang (@thinkall) with @Copilot in #1573
• build(deps): bump brace-expansion from 5.0.6 to 5.0.7 in /website by Dependabot (@dependabot)[bot] in #1574
• build(deps): bump postcss from 8.5.10 to 8.5.25 in /website by Dependabot (@dependabot)[bot] in #1579
• build(deps): bump fast-uri from 3.1.2 to 3.1.5 in /website by Dependabot (@dependabot)[bot] in #1575
• build(deps): bump shell-quote from 1.8.4 to 1.10.0 in /website by Dependabot (@dependabot)[bot] in #1577
• build(deps): bump brace-expansion from 5.0.7 to 5.0.9 in /website by Dependabot (@dependabot)[bot] in #1578
• Pin GitHub Actions to full-length commit SHAs by Dan Fiedler (@danfiedler-msft) in #1582
• build(deps): bump nanoid from 3.3.16 to 3.3.18 in /website by Dependabot (@dependabot)[bot] in #1581
• build(deps): bump the github-actions group with 8 updates by Dependabot (@dependabot)[bot] in #1583
• docs: fix undefined variable and comment mismatch in time series forecast example by Nefelibata (@MeiSiristhebest) in #1580
• build(deps): bump hydra-core from 1.1.1 to 1.3.4 in /test/pipeline_tuning_example by Dependabot (@dependabot)[bot] in #1585
• build(deps): bump browserslist from 4.21.4 to 4.28.8 in /website by Dependabot (@dependabot)[bot] in #1590
• build(deps): bump fast-uri from 3.1.5 to 3.1.7 in /website by Dependabot (@dependabot)[bot] in #1588
• fix: support statsmodels 0.15 in naive forecasters by Li Jiang (@thinkall) in #1587
• fix(examples): compute the discrete-label threshold from the training split only by Amir Fathi (@AmirF194) in #1584
• Fix misaligned sample_weight in group holdout split by Jeremy Schoemaker (@shoemoney) in #1586
• Forward free_mem_ratio from compute_estimator to the evaluation by Venish Paneliya (@VenishPaneliya) in #1591
• Add Windows ARM64 CI support by Nithin Aashik PS (@nithin-aashik-mcw) in #1589
• docs: rerun time series forecasting notebook with saved results by Li Jiang (@thinkall) in #1592
• build(deps-dev): bump cryptography from 46.0.3 to 50.0.0 by Dependabot (@dependabot)[bot] in #1593
• Remove unsupported cryptography pin from Windows ARM CI by Li Jiang (@thinkall) with @Copilot in #1594
• Compute trial averages from per-metric report counts by betacatsling in #1601
• build(deps): bump joi from 17.13.4 to 17.13.7 in /website by Dependabot (@dependabot)[bot] in #1597
• Honor unit quantization for float sampling by betacatsling in #1599
• build(deps): bump colord from 2.9.3 to 2.10.0 in /website by Dependabot (@dependabot)[bot] in #1595
• Docs: use consistent four-space indentation in Task-Oriented AutoML by 玉升 (@wangyusheng1985) in #1596
• feat: add optional resampler= kwarg to AutoML.fit for per-fold class-imbalance handling (#1200) by Imran Ahamed (@immu4989) in #1568
• Bump version from 2.6.0 to 2.7.0 by Li Jiang (@thinkall) in #1607
• Fix Statsmodels future forecast horizon by Li Jiang (@thinkall) in #1608
• Preserve zero-valued anonymous tuning metrics by betacatsling in #1603
• docs: add Simplified Chinese translation (README.zh.md) by YE (@JasonYeYuhe) in #1604

New Contributors

• Imran Ahamed (@immu4989) made their first contribution in #1541
• Arpit Jain (@arpitjain099) made their first contribution in #1548
• Arushi Sagar (@arushiiii18) made their first contribution in #1571
• Dan Fiedler (@danfiedler-msft) made their first contribution in #1582
• Nefelibata (@MeiSiristhebest) made their first contribution in #1580
• Amir Fathi (@AmirF194) made their first contribution in #1584
• Jeremy Schoemaker (@shoemoney) made their first contribution in #1586
• Venish Paneliya (@VenishPaneliya) made their first contribution in #1591
• Nithin Aashik PS (@nithin-aashik-mcw) made their first contribution in #1589
• betacatsling made their first contribution in #1601
• 玉升 (@wangyusheng1985) made their first contribution in #1596
• YE (@JasonYeYuhe) made their first contribution in #1604

Full Changelog: v2.6.0...v2.7.0