skore-mlflow-project/0.0.1

What's Changed

• feat(skore-mlflow-project): Add integration with MLflow by @cakedev0 in #2527

Full Changelog: 015a001

skore/0.13.1

What's Changed

• fix(skore): Ensure figure-level legend is included when saving PredictionErrorDisplay plot by @MuditAtrey in #2530
• feat(skore): Add aggregate parameter to ImpurityDecreaseDisplay by @MuditAtrey in #2539
• refactor(skore): Calling underlying estimator method instead of factory by @glemaitre in #2516
• feat(skore/ComparisonReport): Add permutation importance by @GaetandeCast in #2511

Full Changelog: skore/0.13.0...skore/0.13.1

skore-hub-project/0.0.18

What's Changed

• fix(skore-hub-project/splitting_strategy): Use _safe_indexing with report.y by @thomass-dev in #2550

Full Changelog: skore-hub-project/0.0.17...skore-hub-project/0.0.18

skore/0.13.0

What's Changed

• fix(skore): Standardize dataframe column names to singular form by @Sharkyii in #2392
• feat(skore): Add an HTML representation for interactive environment by @glemaitre in #2316
• fix(skore): Different y axis for comparisons in CoefficientsDisplay by @GaetandeCast in #2403
• chore(skore): Suppress seaborn deprecation warnings in box/strip plots by @Sharkyii in #2405
• fix(skore): Prevent memory overflow from dangerous arange by @cakedev0 in #2404
• fix(skore/progress-bar): Disable progress-bar on demand by @thomass-dev in #2425
• chore(skore/inspection): Increase alpha in shaded background by @GaetandeCast in #2428
• fix(skore/reports): Fix auto-completion in IPython by @jeromedockes in #2427
• chore(skore/cross-validation-report): Refine progress-bar message on split predictions by @thomass-dev in #2400
• feat(skore): Allow to set pos_label after creating report by @glemaitre in #2438
• fix(skore): Don't crash when y is a list/tuple by @cakedev0 in #2433
• fix(skore): Link to right repo in source url by @GaetandeCast in #2448
• feat(skore): Enable interactive matplotlib mode by default by @thomass-dev in #2446
• docs(skore): Mention split in class docstring by @GaetandeCast in #2447
• fix(skore): Fix the link to source code in docs by @GaetandeCast in #2451
• feat(skore/Project): Clarify single ML task constraint by @auguste-probabl in #2452
• fix(skore): Don't create a tuple from a string for the cache key by @cakedev0 in #2456
• fix(skore): Robustify normalization of X and y to a frame (_retrieve_data_as_frame) by @cakedev0 in #2440
• fix(skore): Add support for multioutput regression in prediction error display by @GaetandeCast in #2434
• chore(skore): Make ipython and ipywidget optional dependencies by @glemaitre in #2482
• refactor(skore): Remove _verbose_name in favor of using registered named from accessor by @glemaitre in #2475
• fix(skore): Do not catch exception in cross-validation fitting by @glemaitre in #2462
• feat(skore/project)!: Enforce mode in a dedicated parameter by @thomass-dev in #2401
• docs(skore): Add small example to illustrate the usage of the skore.Project in local by @glemaitre in #2481
• fix(skore): Improve error message if missing skore-hub-project by @glemaitre in #2458
• refactor(skore): Introduce _report_type to avoid hard coding when needed by @glemaitre in #2476
• fix(skore): Fix wrong cache read / missing check in metrics accessor (CV report) by @cakedev0 in #2492
• feat(skore/ConfusionMatrixDislay): Introduce threshold_value="all" option by @glemaitre in #2463
• chore(skore): Disallow clustering models in reports by @GaetandeCast in #2489
• feat(skore/ComparisonReport): Add impurity_decrease method by @auguste-probabl in #2387
• refactor(skore): Uniform cache key sanitizing by @cakedev0 in #2483
• fix(skore/configuration)!: Make the configuration inheritable between threads by @thomass-dev in #2431
• fix(skore): Disable unecessary plotting made by skrub by @thomass-dev in #2494
• fix(skore/tests): Make tests pass with pandas>=3 by @auguste-probabl in #2504
• feat(skore): Add cross-validation support for permutation importance by @glemaitre in #2370
• fix(skore): Fix the index in permutation importance and docs by @glemaitre in #2506

Full Changelog: skore/0.12.0...skore/0.13.0

skore-hub-project/0.0.17

What's Changed

• fix(skore-hub-project): Replace switch_mpl_backend by switch_mpl_ioff by @thomass-dev in #2439
• fix(skore-hub-project): Raise when project name is empty by @auguste-probabl in #2453
• fix(skore-hub-project): Raise earlier an error when pos_label not provided before serialization by @glemaitre in #2436
• fix(skore-hub-project): Limit project name length to 64 by @auguste-probabl in #2454
• fix(skore-hub-project): Serialize pandas.Timestamp by @thomass-dev in #2484
• fix(skore-hub-project): Opt into pandas 3 behaviour by @auguste-probabl in #2485
• feat(skore-hub-project/project): Refactor initialization to raise custom exceptions by @thomass-dev in #2487
• feat(skore-hub-project): Print report URL after put by @rouk1 in #2488
• fix(skore-hub-project): Do not aggregate importance when sending to hub by @glemaitre in #2445
• fix(skore-hub-project): Restore switch_mpl_backend for use in conjunction with plt.ioff() by @thomass-dev in #2498
• feat(skore-hub-project/put): Improve progress tracking by @thomass-dev in #2424
• feat(skore-hub-project): Send inspection media for cross-validation reports by @glemaitre in #2510
• feat(skore-hub-project/put): Send also performance media as dataframe by @thomass-dev in #2514
• feat(skore-hub-project/put): Send confusion matrix by @thomass-dev in #2525

Full Changelog: skore-hub-project/0.0.16...skore-hub-project/0.0.17

skore/0.12.0

What's Changed

• feat(skore): Add support for ComparisonReport in ConfusionMatrixDisplay by @GaetandeCast in #2236
• fix(skore): Use display API for coefficients display by @glemaitre in #2152
• chore(skore): Moving confusion matrix display kwargs into set_style by @glemaitre in #2293
• chore(skore): Clean up docs references to seaborn by @GaetandeCast in #2294
• fix: Add accuracy as default metric for classifiers by @auguste-probabl in #2295
• chore(skore): Moving precision recall kwargs into set_style by @glemaitre in #2298
• chore(skore): Moving coefficients kwargs into set_style by @glemaitre in #2300
• chore(skore): Moving table report kwargs into set_style by @glemaitre in #2299
• chore(skore): Improve documentation of set_style() by @GaetandeCast in #2306
• feat(skore): Refactor PredictionErrorDisplay to use seaborn and add subplot_by option by @GaetandeCast in #2292
• fix(skore): Actually suppress warning in prc display by @GaetandeCast in #2312
• feat!: Rename indicator_favorability to favorability by @auguste-probabl in #2314
• chore(skore): Add the feature importance accessor to the API reference by @GaetandeCast in #2315
• feat(skore): Refactor RocCurveDisplay to use seaborn and add subplot_by by @GaetandeCast in #2313
• feat(skore): Rename tenant to workspace by @thomass-dev in #2325
• chore(skore): Make summary and widget modules private by @ShantKhatri in #2332
• feat(skore): Create PermutationImportanceDisplay for permutation() method by @glemaitre in #2304
• feat(skore): Create an EstimatorReport from a Comparison/CrossValidationReport by @GaetandeCast in #2326
• feat(skore): Add data_source="both" to ComparisonReport metrics frames by @Adrien-1997 in #2201
• fix(skore): Cast report to EstimatorReport for mypy by @glemaitre in #2345
• feat(skore/CoefficientsDisplay): Add select_k and sorting_order parameters to frame and plot by @adwait-godbole in #2305
• chore(skore): Homogenize display factories & follow up datasource='both' by @GaetandeCast in #2343
• chore(skore)!: Rename feature_importance to inspection and the underlying functions by @GaetandeCast in #2346
• feat(skore)!: Refactor hub authentication by @thomass-dev in #2340
• fix(skore): Error with set_style in PermutationImportanceDisplay by @Premkumar-2004 in #2364
• chore(skore)!: Homogenize the attributes in Displays by @glemaitre in #2367
• feat(skore): Create ImpurityDecreaseDisplay for the impurity_decrease method by @glemaitre in #2341
• fix(skore/CoefficientsDisplay): Change default ordering to None by @Premkumar-2004 in #2375
• fix(skore): Avoid accessing frame[output] when the column does not exist by @GaetandeCast in #2382
• fix(skore): Make the progress thread-safe by @thomass-dev in #2357
• chore(skore/estimator-report): Clean some parts of the metrics accessor by @auguste-probabl in #2331
• feat(skore/CrossValidationReport): Add impurity_decrease method by @auguste-probabl in #2385

Full Changelog: skore/0.11.7...skore/0.12.0

skore-hub-project/0.0.16

What's Changed

• ci(skore-hub-project): Filter deprecation warnings caused by seaborn when using skore>=0.11.6 by @thomass-dev in #2282
• fix(skore-hub-project/metrics): Raise exception from thread by @thomass-dev in #2296
• fix(skore-hub-project/tests): Ignore Precision is ill-defined warning by @thomass-dev in #2307
• chore(skore-hub-project/tests): Improve test_metrics_raises_exception by @thomass-dev in #2311
• fix(skore-hub-project/project): Slugify tenant and project name by @thomass-dev in #2321 and #2339
• feat(skore-hub-project): Rename tenant to workspace by @thomass-dev in #2324
• feat(skore-hub-project)!: Refactor authentication by @thomass-dev in #2333
• feat(skore-hub-project)!: Ensure compatibility with skore>=0.12 by @thomass-dev in #2378

Full Changelog: skore-hub-project/0.0.15...skore-hub-project/0.0.16

skore/0.11.7

What's Changed

• fix: Allow subplot_by=None for PRC in multiclass by @GaetandeCast in #2273
• docs: Rework landing page to show takeaway messages by @glemaitre in #2281

Full Changelog: skore/0.11.6...skore/0.11.7

skore/0.11.6

What's Changed

Chore

• docs: Use skrub instead of scikit-learn to fetch california housing dataset by @thomass-dev in #2244
• ci: Drop support of scikit-learn==1.4 in favor of scikit-learn==1.8 by @thomass-dev in #2209
• docs: Use reo.dev tracker on all pages by @thomass-dev in #2246
• chore: Refresh dates in LICENSE by @auguste-probabl in #2263
• docs: Specify explicitly the subplot_by available string by @glemaitre in #2272
• docs: Remove large dependencies by @auguste-probabl in #2270
• docs: Refresh "getting started" example by @auguste-probabl in #2269
• docs: Replace plausible by posthog by @thomass-dev in #2279

Improvements

• feat: Refactor PR curve display and add subplot_by option by @GaetandeCast in #2193
• feat: Add support for CrossValidationReport in ConfusionMatrixDisplay by @GaetandeCast in #2221
• fix: Add response_method argument to every metrics accessor by @auguste-probabl in #2276

Full Changelog: skore/0.11.5...skore/0.11.6

skore-hub-project/0.0.15

What's Changed

• feat: Add target range by @rouk1 in #2271
• feat: Send target distribution for regression tasks by @rouk1 in #2248
• feat: Thread the compute of report metrics by @thomass-dev in #2178
• fix(hubclient): Send X-Skore-Client with semver instead of PyPI version by @thomass-dev in #2243
• fix(client): Fix bad import of importlib.metadata in conda by @thomass-dev in #2192
• fix(login): Ignore token URI when using API key by @thomass-dev in #2191
• feat!: Improve cross-validation splits property by @thomass-dev in #2214
• feat: Add performance media to cross-validation report by @thomass-dev in #2215
• feat!: Rename splits to splitting_strategy by @rouk1 in #2234

Full Changelog: skore-hub-project/0.0.13...skore-hub-project/0.0.15