171 implement multi table helper functions

.pre-commit-config.yaml

@@ -33,13 +33,16 @@ repos:
     rev: 0.29.0
     hooks:
       - id: check-github-workflows
+        name: gh-workflows
         args: [--verbose]
       - id: check-github-actions
+        name: gh-actions
         args: [--verbose]
   - repo: https://github.com/jumanjihouse/pre-commit-hooks
     rev: 3.0.0
     hooks:
       - id: shellcheck
+        name: shellcheck
   - repo: local
     hooks:
       - id: samples-generation

CHANGELOG.md

@@ -6,9 +6,17 @@
   - Example: 10.2.1.4 is the 5th version that supports khiops 10.2.1.
 - Internals: Changes in *Internals* sections are unlikely to be of interest for data scientists.
 
+## 10.2.2.5 - Unreleased
+
+### Added
+
+- (General) `train_test_split_dataset` helper function to ease the splitting in train/test for
+  multi-table datasets.
+- (General) `sort_dataset` helper function to ease the sorting by key of multi-table datasets.
+
 ## 10.2.2.4 - 2024-08-05
 
-## Added
+### Added
 - (`sklearn`) Sklearn's attributes for supervised estimators.
 
 ## 10.2.2.3 - 2024-08-02

doc/convert_samples.py

@@ -67,7 +67,7 @@ def create_rest_page_header(script_name):
         subtitle += ":py:mod:`khiops.core` module."
     else:
         title = "Samples sklearn"
-        subtitle += ":py:mod:`khiops.sklearn` module."
+        subtitle += ":py:mod:`khiops.sklearn <khiops.sklearn.estimators>` module."
     return (
         ":orphan:\n"
         "\n"

doc/core/index.rst

@@ -20,9 +20,9 @@ Main Modules
   :recursive:
   :nosignatures:
 
-  khiops.core.api
-  khiops.core.dictionary
-  khiops.core.analysis_results
-  khiops.core.coclustering_results
-  khiops.core.exceptions
-  khiops.core.helpers
+  api
+  dictionary
+  analysis_results
+  coclustering_results
+  exceptions
+  helpers

doc/create-doc

@@ -90,21 +90,18 @@ fi
 
 # Create the coursework materials
 echo "Creating ZIP files"
-(cd "$KHIOPS_TUTORIAL_REPO_DIR" && cp -r data helper_functions.py "../$tutorials_dir")
 cd "$tutorials_dir"
 mkdir -p exercises
 touch exercises/.dummy # Create a dummy so the "exercises" directory is created on unzip
-zip "core_tutorials_solutions.zip" Core*.ipynb helper_functions.py data/*/* exercises/.dummy
-zip "sklearn_tutorials_solutions.zip" Sklearn*.ipynb helper_functions.py data/*/* exercises/.dummy
+zip "core_tutorials_solutions.zip" Core*.ipynb data/*/* exercises/.dummy
+zip "sklearn_tutorials_solutions.zip" Sklearn*.ipynb data/*/* exercises/.dummy
 cd "$KHIOPS_TUTORIAL_REPO_DIR"
 python create-coursework.py
 cd coursework
 mkdir -p exercises
 touch exercises/.dummy # Create a dummy so the "exercises" directory is created on unzip
-zip "../../$tutorials_dir/core_tutorials.zip" \
-  Core*.ipynb helper_functions.py data/*/* exercises/.dummy
-zip "../../$tutorials_dir/sklearn_tutorials.zip" \
-  Sklearn*.ipynb helper_functions.py data/*/* exercises/.dummy
+zip "../../$tutorials_dir/core_tutorials.zip" Core*.ipynb data/*/* exercises/.dummy
+zip "../../$tutorials_dir/sklearn_tutorials.zip" Sklearn*.ipynb data/*/* exercises/.dummy
 cd "../.."
 
 # Create the documentation with Sphinx

doc/internal/index.rst

@@ -3,17 +3,23 @@ Internals
 These are internal modules with no "data science" functionality. Their documentation is available
 for completeness.
 
+.. currentmodule:: khiops.utils
 .. autosummary::
   :nosignatures:
   :toctree: generated
 
-  khiops.sklearn.tables
-  khiops.core.internals.common
-  khiops.core.internals.filesystems
-  khiops.core.internals.io
-  khiops.core.internals.runner
-  khiops.core.internals.scenario
-  khiops.core.internals.task
-  khiops.core.internals.types
-  khiops.core.internals.version
+  dataset
 
+.. currentmodule:: khiops.core.internals
+.. autosummary::
+  :nosignatures:
+  :toctree: generated
+
+  common
+  filesystems
+  io
+  runner
+  scenario
+  task
+  types
+  version

doc/samples/samples.rst

@@ -1185,6 +1185,34 @@ Samples
         output_data_table_path,
         sort_variables=["AccidentId", "VehicleId"],
     )
+.. autofunction:: sort_data_tables_mt
+.. code-block:: python
+
+    # Imports
+    import os
+    from khiops.utils.helpers import sort_dataset
+
+    # Set the file paths
+    accidents_dir = os.path.join(kh.get_samples_dir(), "Accidents")
+    accidents_table_path = os.path.join(accidents_dir, "Accidents.txt")
+    vehicles_table_path = os.path.join(accidents_dir, "Vehicles.txt")
+    users_table_path = os.path.join(accidents_dir, "Users.txt")
+    places_table_path = os.path.join(accidents_dir, "Places.txt")
+    results_dir = os.path.join("kh_samples", "sort_data_tables_mt")
+
+    # Build the dataset spec
+    ds_spec = {
+        "main_table": "Accidents",
+        "tables": {
+            "Accidents": (accidents_table_path, "AccidentId"),
+            "Vehicles": (vehicles_table_path, ["AccidentId", "VehicleId"]),
+            "Users": (users_table_path, ["AccidentId", "VehicleId"]),
+            "Places": (places_table_path, "AccidentId"),
+        },
+    }
+
+    # Sort the dataset
+    sort_dataset(ds_spec, output_dir=results_dir)
 .. autofunction:: extract_keys_from_data_table
 .. code-block:: python