.coveragerc
.git-blame-ignore-revs
.gitignore
.pre-commit-config.yaml
CHANGES.rst
CODE_OF_CONDUCT.md
CONTRIBUTING.rst
LICENSE.txt
README.rst
RELEASE_PROCESS.rst
codecov.yml
pixi.lock
pyproject.toml
.binder/postBuild
.binder/requirements.txt
.binder/runtime.txt
.circleci/config.yml
.github/dependabot.yml
.github/ISSUE_TEMPLATE/bug_report.yml
.github/ISSUE_TEMPLATE/config.yml
.github/ISSUE_TEMPLATE/doc_improvement.yml
.github/ISSUE_TEMPLATE/feature_request.yml
.github/PULL_REQUEST_TEMPLATE/bug_fix.md
.github/PULL_REQUEST_TEMPLATE/documentation.md
.github/PULL_REQUEST_TEMPLATE/feature.md
.github/PULL_REQUEST_TEMPLATE/refactoring.md
.github/workflows/changelog.yml
.github/workflows/check_stub_files_diff.yaml
.github/workflows/main.yml
.github/workflows/run-code-format-checks.yaml
.github/workflows/test-javascript.yml
.github/workflows/testing.yml
.github/workflows/update_pixi_lock_files.yml
build_tools/generate_data_ops_stub.py
build_tools/circle/build_doc.sh
build_tools/circle/checkout_merge_commit.sh
build_tools/circle/push_doc.sh
doc/Makefile
doc/about.rst
doc/api_reference.py
doc/column_level_featurizing.rst
doc/conf.py
doc/configuration_and_utils.rst
doc/data_ops.rst
doc/data_ops_report.py
doc/default_wrangling.rst
doc/development.rst
doc/documentation.rst
doc/exploring_a_dataframe.rst
doc/generate_data_ops_example_for_index.py
doc/index.rst
doc/install.rst
doc/joining_dataframes.rst
doc/jupyter-lite.json
doc/learning_materials.rst
doc/multi_column_operations.rst
doc/skrub.png
doc/skrub.svg
doc/skrub_unzoomed.png
doc/table_report.py
doc/tutorial_example.rst
doc/version.json
doc/vision.rst
doc/_static/08_example_aggjoiner.png
doc/_static/08_example_data.png
doc/_static/credit_fraud_diagram.svg
doc/_static/dataops_graph.svg
doc/_static/encoding_dark.png
doc/_static/encoding_light.png
doc/_static/gap.png
doc/_static/periodic_features.png
doc/_static/sklearn_pipeline.svg
doc/_static/skrub-cover.svg
doc/_static/skrub.svg
doc/_static/skrub_3d_1.svg
doc/_static/skrub_3d_2.svg
doc/_static/skrub_3d_3.svg
doc/_static/skrub_3d_4.svg
doc/_static/skrub_data_ops.svg
doc/_static/skrub_pipeline.svg
doc/_static/css/custom.css
doc/_static/scripts/sg_plotly_resize.js
doc/_templates/base.rst
doc/_templates/data_op_class.rst
doc/_templates/demo_gap_encoder.html
doc/_templates/demo_table_report_code.html
doc/_templates/demo_tabular_pipeline.html
doc/_templates/index.html
doc/_templates/numpydoc_docstring.rst
doc/binder/requirements.txt
doc/includes/big_toc_css.rst
doc/modules/column_level_featurizing/feature_engineering_categorical.rst
doc/modules/column_level_featurizing/feature_engineering_datetimes.rst
doc/modules/column_level_featurizing/robust_scaling.rst
doc/modules/configuration_and_utils/customizing_configuration.rst
doc/modules/configuration_and_utils/deduplicate_categorical_data.rst
doc/modules/configuration_and_utils/fetching_datasets.rst
doc/modules/data_ops/basics/building_data_ops_plan.rst
doc/modules/data_ops/basics/control_flow.rst
doc/modules/data_ops/basics/data_ops_vs_alternatives.rst
doc/modules/data_ops/basics/direct_access_methods.rst
doc/modules/data_ops/basics/using_previews.rst
doc/modules/data_ops/basics/what_are_data_ops.rst
doc/modules/data_ops/ml_pipeline/applying_different_transformers.rst
doc/modules/data_ops/ml_pipeline/applying_ml_estimators.rst
doc/modules/data_ops/ml_pipeline/documenting_data_ops_plan.rst
doc/modules/data_ops/ml_pipeline/evaluating_debugging_data_ops.rst
doc/modules/data_ops/ml_pipeline/subsampling_data.rst
doc/modules/data_ops/ml_pipeline/using_part_of_data_ops_plan.rst
doc/modules/data_ops/validation/exporting_data_ops.rst
doc/modules/data_ops/validation/hyperparameter_tuning.rst
doc/modules/data_ops/validation/nested_cross_validation.rst
doc/modules/data_ops/validation/nesting_choices_choosing_pipelines.rst
doc/modules/data_ops/validation/tuning_validating_data_ops.rst
doc/modules/data_ops/validation/tuning_with_optuna.rst
doc/modules/default_wrangling/cleaning_dataframes.rst
doc/modules/default_wrangling/table_vectorizer.rst
doc/modules/default_wrangling/tabular_pipeline.rst
doc/modules/joining_tables/assembling.rst
doc/modules/multi_column_operations/advanced_selectors.rst
doc/modules/multi_column_operations/drop_uninformative.rst
doc/modules/multi_column_operations/multi_column_operations.rst
doc/modules/multi_column_operations/selectors.rst
doc/modules/multi_column_operations/type_of_selectors.rst
doc/modules/tablereport/exploring_dataframes_interactively.rst
doc/modules/tablereport/finding_correlated_columns.rst
doc/reference/index.rst.template
doc/reference/module.rst.template
doc/sphinxext/MANIFEST.in
doc/sphinxext/autoshortsummary.py
doc/sphinxext/github_link.py
doc/sphinxext/sphinx_issues.py
examples/0000_getting_started.py
examples/0010_encodings.py
examples/0020_text_with_string_encoders.py
examples/0030_datetime_encoder.py
examples/0040_fuzzy_joining.py
examples/0050_deduplication.py
examples/0060_multiple_key_join.py
examples/0070_join_aggregation.py
examples/0080_interpolation_join.py
examples/0090_apply_to_cols.py
examples/0100_squashing_scaler.py
examples/GALLERY_HEADER.rst
examples/FIXME/07_grid_searching_with_the_tablevectorizer.py
examples/FIXME/08_join_aggregation_full.py
examples/data_ops/1110_data_ops_intro.py
examples/data_ops/1120_multiple_tables.py
examples/data_ops/1130_choices.py
examples/data_ops/1131_optuna_choices.py
examples/data_ops/1140_subsampling.py
examples/data_ops/1150_use_case.py
examples/data_ops/1160_pytorch.py
examples/data_ops/GALLERY_HEADER.rst
skrub/VERSION.txt
skrub/__init__.py
skrub/_agg_joiner.py
skrub/_apply_to_cols.py
skrub/_apply_to_frame.py
skrub/_check_input.py
skrub/_clean_categories.py
skrub/_clean_null_strings.py
skrub/_column_associations.py
skrub/_config.py
skrub/_datetime_encoder.py
skrub/_deduplicate.py
skrub/_dispatch.py
skrub/_drop_uninformative.py
skrub/_fast_hash.py
skrub/_fuzzy_join.py
skrub/_gap_encoder.py
skrub/_interpolation_joiner.py
skrub/_join_utils.py
skrub/_joiner.py
skrub/_matching.py
skrub/_minhash_encoder.py
skrub/_multi_agg_joiner.py
skrub/_scaling_factor.py
skrub/_select_cols.py
skrub/_similarity_encoder.py
skrub/_single_column_transformer.py
skrub/_sklearn_compat.py
skrub/_squashing_scaler.py
skrub/_string_distances.py
skrub/_string_encoder.py
skrub/_table_vectorizer.py
skrub/_tabular_pipeline.py
skrub/_text_encoder.py
skrub/_to_categorical.py
skrub/_to_datetime.py
skrub/_to_float.py
skrub/_to_str.py
skrub/_utils.py
skrub/_wrap_transformer.py
skrub/conftest.py
skrub.egg-info/PKG-INFO
skrub.egg-info/SOURCES.txt
skrub.egg-info/dependency_links.txt
skrub.egg-info/requires.txt
skrub.egg-info/top_level.txt
skrub/_data_ops/__init__.py
skrub/_data_ops/_choosing.py
skrub/_data_ops/_data_ops.py
skrub/_data_ops/_data_ops.pyi
skrub/_data_ops/_estimator.py
skrub/_data_ops/_evaluation.py
skrub/_data_ops/_inspection.py
skrub/_data_ops/_optuna.py
skrub/_data_ops/_parallel_coord.py
skrub/_data_ops/_skrub_namespace.py
skrub/_data_ops/_subsampling.py
skrub/_data_ops/_utils.py
skrub/_data_ops/tests/__init__.py
skrub/_data_ops/tests/test_choosing.py
skrub/_data_ops/tests/test_data_ops.py
skrub/_data_ops/tests/test_deferred.py
skrub/_data_ops/tests/test_errors.py
skrub/_data_ops/tests/test_estimators.py
skrub/_data_ops/tests/test_evaluation.py
skrub/_data_ops/tests/test_inspection.py
skrub/_data_ops/tests/test_interactive_features.py
skrub/_data_ops/tests/test_parallel_coord.py
skrub/_data_ops/tests/test_subsampling.py
skrub/_data_ops/tests/test_utils.py
skrub/_dataframe/__init__.py
skrub/_dataframe/_common.py
skrub/_dataframe/tests/__init__.py
skrub/_dataframe/tests/test_common.py
skrub/_reporting/README.rst
skrub/_reporting/__init__.py
skrub/_reporting/_html.py
skrub/_reporting/_patching.py
skrub/_reporting/_plotting.py
skrub/_reporting/_sample_table.py
skrub/_reporting/_serve.py
skrub/_reporting/_summarize.py
skrub/_reporting/_table_report.py
skrub/_reporting/_utils.py
skrub/_reporting/_data/templates/.gitignore
skrub/_reporting/_data/templates/_variables.css
skrub/_reporting/_data/templates/base.css
skrub/_reporting/_data/templates/buttons.html
skrub/_reporting/_data/templates/column-associations.html
skrub/_reporting/_data/templates/column-filter.css
skrub/_reporting/_data/templates/column-filter.html
skrub/_reporting/_data/templates/column-summaries.css
skrub/_reporting/_data/templates/column-summaries.html
skrub/_reporting/_data/templates/column-summary.html
skrub/_reporting/_data/templates/copybutton.css
skrub/_reporting/_data/templates/dataframe-sample.css
skrub/_reporting/_data/templates/dataframe-sample.html
skrub/_reporting/_data/templates/inline-report.html
skrub/_reporting/_data/templates/no-filter-matches.html
skrub/_reporting/_data/templates/report.css
skrub/_reporting/_data/templates/report.html
skrub/_reporting/_data/templates/report.js
skrub/_reporting/_data/templates/standalone-report.css
skrub/_reporting/_data/templates/standalone-report.html
skrub/_reporting/_data/templates/summary-statistics.css
skrub/_reporting/_data/templates/summary-statistics.html
skrub/_reporting/_data/templates/table-bar.html
skrub/_reporting/_data/templates/tables.css
skrub/_reporting/_data/templates/tabs.css
skrub/_reporting/_data/templates/tabs.html
skrub/_reporting/_data/templates/toggletip.css
skrub/_reporting/_data/templates/data_ops/data_ops-report.js
skrub/_reporting/_data/templates/data_ops/data_ops.css
skrub/_reporting/_data/templates/data_ops/graph-nav.html
skrub/_reporting/_data/templates/data_ops/graph.html
skrub/_reporting/_data/templates/data_ops/index.html
skrub/_reporting/_data/templates/data_ops/node.html
skrub/_reporting/_data/templates/data_ops/simple-repr.html
skrub/_reporting/_data/templates/data_ops/icons/list.svg
skrub/_reporting/_data/templates/icons/LICENSE
skrub/_reporting/_data/templates/icons/README.md
skrub/_reporting/_data/templates/icons/arrow-down.svg
skrub/_reporting/_data/templates/icons/arrow-left.svg
skrub/_reporting/_data/templates/icons/arrow-right.svg
skrub/_reporting/_data/templates/icons/arrow-up.svg
skrub/_reporting/_data/templates/icons/check-lg.svg
skrub/_reporting/_data/templates/icons/clipboard.svg
skrub/_reporting/_data/templates/icons/copy.svg
skrub/_reporting/_data/templates/icons/exclamation-triangle.svg
skrub/_reporting/_data/templates/icons/sort-alpha-down-alt.svg
skrub/_reporting/_data/templates/icons/sort-alpha-down.svg
skrub/_reporting/_data/templates/icons/sort-numeric-down-alt.svg
skrub/_reporting/_data/templates/icons/sort-numeric-down.svg
skrub/_reporting/_data/templates/icons/three-dots-vertical.svg
skrub/_reporting/_data/templates/icons/x-lg.svg
skrub/_reporting/_data/templates/pure-3.0.0/LICENSE
skrub/_reporting/_data/templates/pure-3.0.0/base-min.css
skrub/_reporting/js_tests/.gitignore
skrub/_reporting/js_tests/cypress.config.js
skrub/_reporting/js_tests/make-reports
skrub/_reporting/js_tests/package-lock.json
skrub/_reporting/js_tests/package.json
skrub/_reporting/js_tests/cypress/e2e/column-filter.cy.js
skrub/_reporting/js_tests/cypress/e2e/column-summaries.cy.js
skrub/_reporting/js_tests/cypress/e2e/copybutton.cy.js
skrub/_reporting/js_tests/cypress/e2e/dataframe-sample.cy.js
skrub/_reporting/js_tests/cypress/e2e/open-tab.cy.js
skrub/_reporting/js_tests/cypress/e2e/summary-statistics.cy.js
skrub/_reporting/js_tests/cypress/e2e/tabs.cy.js
skrub/_reporting/js_tests/cypress/fixtures/example.json
skrub/_reporting/js_tests/cypress/support/commands.js
skrub/_reporting/js_tests/cypress/support/e2e.js
skrub/_reporting/tests/conftest.py
skrub/_reporting/tests/test_patch_display.py
skrub/_reporting/tests/test_plotting.py
skrub/_reporting/tests/test_serve.py
skrub/_reporting/tests/test_summarize.py
skrub/_reporting/tests/test_table_report.py
skrub/_reporting/tests/test_utils.py
skrub/_reporting/tests/data/air_quality_tiny.csv
skrub/_reporting/tests/data/air_quality_tiny.parquet
skrub/datasets/__init__.py
skrub/datasets/_fetching.py
skrub/datasets/_generating.py
skrub/datasets/_utils.py
skrub/datasets/tests/__init__.py
skrub/datasets/tests/test_fetching.py
skrub/datasets/tests/test_generating.py
skrub/datasets/tests/test_utils.py
skrub/selectors/__init__.py
skrub/selectors/_base.py
skrub/selectors/_selectors.py
skrub/selectors/tests/test_base.py
skrub/selectors/tests/test_selectors.py
skrub/tests/__init__.py
skrub/tests/test_agg_joiner.py
skrub/tests/test_apply_to_cols.py
skrub/tests/test_check_input.py
skrub/tests/test_clean_categories.py
skrub/tests/test_clean_null_strings.py
skrub/tests/test_column_associations.py
skrub/tests/test_config.py
skrub/tests/test_data_ops_stack_description.py
skrub/tests/test_datetime_encoder.py
skrub/tests/test_deduplicate.py
skrub/tests/test_dispatch.py
skrub/tests/test_docstrings.py
skrub/tests/test_drop_uninformative.py
skrub/tests/test_fast_hash.py
skrub/tests/test_fuzzy_join.py
skrub/tests/test_gap_encoder.py
skrub/tests/test_interpolation_joiner.py
skrub/tests/test_join_utils.py
skrub/tests/test_joiner.py
skrub/tests/test_matching.py
skrub/tests/test_minhash_encoder.py
skrub/tests/test_multi_agg_joiner.py
skrub/tests/test_on_subframe.py
skrub/tests/test_scaling_factor.py
skrub/tests/test_select_cols.py
skrub/tests/test_similarity_encoder.py
skrub/tests/test_sklearn.py
skrub/tests/test_squashing_scaler.py
skrub/tests/test_string_distances.py
skrub/tests/test_string_encoder.py
skrub/tests/test_table_vectorizer.py
skrub/tests/test_tabular_pipeline.py
skrub/tests/test_text_encoder.py
skrub/tests/test_to_categorical.py
skrub/tests/test_to_datetime.py
skrub/tests/test_to_float.py
skrub/tests/test_to_str.py
skrub/tests/test_utils.py
skrub/tests/test_wrap_transformer.py
skrub/tests/utils.py