Merge pull request #434 from KhiopsML/prepare-release-11-0-0-0-b-0

Prepare release 11 0 0 0 b 0

Author: popescu-v

.github/workflows/api-docs.yml

@@ -1,15 +1,19 @@
 ---
 name: API Docs
 env:
-  DEFAULT_KHIOPS_PYTHON_TUTORIAL_REVISION: main
+  DEFAULT_KHIOPS_PYTHON_TUTORIAL_REVISION: 11.0.0.0-b.0
+  DEFAULT_KHIOPS_SAMPLES_REVISION: 11.0.0
 on:
   workflow_dispatch:
     inputs:
       khiops-python-tutorial-revision:
-        default: main
+        default: 11.0.0.0-b.0
         description: khiops-python-tutorial repo revision
+      khiops-samples-revision:
+        default: 11.0.0
+        description: khiops-samples repo revision
       image-tag:
-        default: 11.0.0-a.0.0
+        default: 11.0.0-b.0.0
         description: Development Docker Image Tag
   pull_request:
     paths:
@@ -41,7 +45,7 @@ jobs:
       # because the `env` context is only accessible at the step level;
       # hence, it is hard-coded
       image: |-
-        ghcr.io/khiopsml/khiops-python/khiopspydev-ubuntu22.04:${{ inputs.image-tag || '11.0.0-a.0.0' }}
+        ghcr.io/khiopsml/khiops-python/khiopspydev-ubuntu22.04:${{ inputs.image-tag || '11.0.0-b.0.0' }}
       # Use the 'runner' user (1001) from github so checkout actions work properly
       # https://github.com/actions/runner/issues/2033#issuecomment-1598547465
       options: --user 1001
@@ -56,7 +60,7 @@ jobs:
         run: |
           # Install package itself to install the samples datasets
           pip3 install .
-          kh-download-datasets --force-overwrite
+          kh-download-datasets --force-overwrite --version ${{ inputs.khiops-samples-revision || env.DEFAULT_KHIOPS_SAMPLES_REVISION }}
           kh-status
 
           # Install the doc python requirements

.github/workflows/conda.yml

@@ -3,13 +3,13 @@ name: Conda Package
 env:
   # Note: The default Khiops version must never be an alpha release as they are
   #       ephemeral. To test alpha versions run the workflow manually.
-  DEFAULT_KHIOPS_CORE_VERSION: 11.0.0a.0
+  DEFAULT_KHIOPS_CORE_VERSION: 11.0.0b.0
   DEFAULT_SAMPLES_VERSION: 11.0.0
 on:
   workflow_dispatch:
     inputs:
       khiops-core-version:
-        default: 11.0.0a.0
+        default: 11.0.0b.0
         description: khiops-core version for testing
       khiops-samples-version:
         default: 11.0.0

.github/workflows/dev-docker.yml

@@ -1,7 +1,7 @@
 ---
 name: Dev Docker
 env:
-  DEFAULT_KHIOPS_REVISION: 11.0.0-a.0
+  DEFAULT_KHIOPS_REVISION: 11.0.0-b.0
   DEFAULT_IMAGE_INCREMENT: 0
   DEFAULT_SERVER_REVISION: main
   DEFAULT_PYTHON_VERSIONS: 3.8 3.9 3.10 3.11 3.12 3.13
@@ -14,7 +14,7 @@ on:
     inputs:
       khiops-revision:
         type: string
-        default: 11.0.0-a.0
+        default: 11.0.0-b.0
         description: Khiops Revision
       image-increment:
         type: number

.github/workflows/pip.yml

@@ -9,7 +9,7 @@ on:
         default: 11.0.0
         description: khiops-samples repo revision
       image-tag:
-        default: 11.0.0-a.0.0
+        default: 11.0.0-b.0.0
         description: Development Docker Image Tag
   pull_request:
     paths:
@@ -64,7 +64,7 @@ jobs:
       # because the `env` context is only accessible at the step level;
       # hence, it is hard-coded
       image: |-
-        ghcr.io/khiopsml/khiops-python/khiopspydev-${{ matrix.container }}:${{ inputs.image-tag || '11.0.0-a.0.0' }}
+        ghcr.io/khiopsml/khiops-python/khiopspydev-${{ matrix.container }}:${{ inputs.image-tag || '11.0.0-b.0.0' }}
     steps:
       - name: Set parameters as env
         run: |

.github/workflows/tests.yml

@@ -2,18 +2,18 @@
 name: Tests
 env:
   DEFAULT_SAMPLES_REVISION: 11.0.0
-  DEFAULT_KHIOPS_DESKTOP_REVISION: 11.0.0-a.0
+  DEFAULT_KHIOPS_DESKTOP_REVISION: 11.0.0-b.0
 on:
   workflow_dispatch:
     inputs:
       samples-revision:
         default: 11.0.0
         description: Git Tag/Branch/Commit for the khiops-samples Repo
       image-tag:
-        default: 11.0.0-a.0.0
+        default: 11.0.0-b.0.0
         description: Development Docker Image Tag
       khiops-desktop-revision:
-        default: 11.0.0-a.0
+        default: 11.0.0-b.0
         description: Khiops Windows Desktop Application Version
       run-expensive-tests:
         type: boolean
@@ -43,7 +43,7 @@ jobs:
       # because the `env` context is only accessible at the step level;
       # hence, it is hard-coded
       image: |-
-        ghcr.io/khiopsml/khiops-python/khiopspydev-ubuntu22.04:${{ inputs.image-tag || '11.0.0-a.0.0' }}
+        ghcr.io/khiopsml/khiops-python/khiopspydev-ubuntu22.04:${{ inputs.image-tag || '11.0.0-b.0.0' }}
       credentials:
         username: ${{ github.actor }}
         password: ${{ secrets.GITHUB_TOKEN }}
@@ -315,7 +315,7 @@ jobs:
       # because the `env` context is only accessible at the step level;
       # hence, it is hard-coded
       image: |-
-        ghcr.io/khiopsml/khiops-python/khiopspydev-${{ matrix.container }}:${{ inputs.image-tag || '11.0.0-a.0.0' }}
+        ghcr.io/khiopsml/khiops-python/khiopspydev-${{ matrix.container }}:${{ inputs.image-tag || '11.0.0-b.0.0' }}
       credentials:
         username: ${{ github.actor }}
         password: ${{ secrets.GITHUB_TOKEN }}

CHANGELOG.md

@@ -6,11 +6,73 @@
   - 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.
 
-## Unreleased
+## 11.0.0.0-b.0 - 2025-07-10
+
+### Added
+- (`core`) API support for predictor interpretation and reinforcement.
+- (`core`) API support for instance-variable coclustering model training.
+- (`core`) Support for text types in prediction and coclustering models.
+- (`core`) Analysis and coclustering report JSON serialization support.
+- (`sklearn`) Automatic removal of newline characters in strings on Pandas
+  dataframe columns. This is to ensure the proper working of the Khiops engine.
+
+### Changed
+- (`core`) Syntax for additional data tables specification, which uses the data
+  paths.
+- (`core`) API specification of the results path: full paths to report files are
+  now used instead of result directories.
+- (`sklearn`) Specification of the hierarchical multi-table schemata, which now
+  uses data paths as in the Core API.
+- (`general`) Various other changes and updates for Khiops 11.0.0-b.0
+  compatibility.
+
+### Deprecated
+- (`core`) The results directory parameter of the Core API functions. The full
+  path to the reports must now be specified instead.
+- (`core`) The "``"-based secondary table path specification. The "/"-based data
+  paths must now be used instead.
+- (`sklearn`) The specification syntax for hierarchical multi-table datasets.
+  The "/"-based data paths must now be used instead, as in the Core API.
+
+### Removed
+- (`general`) All functions, attributes and features that had been deprecated in
+  the 10.3.2.0 version.
+
+## 10.3.2.0 - 2025-07-03
+
+### Fixed
+- (`sklearn`) Documentation display for the `train_test_split_dataset` sklearn
+helper function.
+
+## 10.3.1.0 - 2025-04-16
 
 ### Added
 - (`sklearn`) Support for boolean and float targets in `KhiopsClassifier`.
 
+### Fixed
+- (`sklearn`) Crash when there were no informative trees in predictors.
+
+### Deprecated
+- (`core`) The `build_multi_table_dictionary_domain` helper function.
+
+## 10.3.0.0 - 2025-02-10
+
+### Fixed
+- (`core`) Dictionary file `.json` extension check in the `khiops.dictionary.read_dictionary_file`
+function.
+
+### Changed
+- (`sklearn`) The `train_test_split_dataset` helper has been moved from `khiops.utils` to
+`khiops.sklearn`.
+- (`sklearn`) The `transform_pairs` parameter of the `KhiopsEncoder` sklearn estimator has been
+renamed to `transform_type_pairs`.
+
+### Removed
+- (`sklearn`) The `is_fitted_` estimator attribute. The Scikit-learn `check_is_fitted` function
+can be used to test the fitted state of the estimators.
+- (`sklearn`) The `n_pairs` parameter of the `KhiopsRegressor` sklearn estimator. It was never
+supported.
+
 ## 10.2.4.0 - 2024-12-19
 
 ### Added

doc/multi_table_primer.rst

@@ -76,40 +76,31 @@ feature object ``X``. Specifically, instead of a `pandas.DataFrame`, ``X`` must
 specifies the dataset schema in the following way::
 
    X = {
-      "main_table": <name of the main table>,
-      "tables" : {
-          <name of the main table>: (<dataframe of the main table>, <key of the main table>),
-          <name of table 1>: (<dataframe of table 1>, <key of table 1>),
-          <name of table 2>: (<dataframe of table 2>, <key of table 2>),
+      "main_table": (<dataframe of the main table>, <key of the main table>),
+      "additional_data_tables" : {
+          <data path to table 1>: (
+              <dataframe of table 1>, [<key of table 1>], <optional entity flag>
+          ),
+          <data path to table 2>: (
+              <dataframe of table 2>, [<key of table 2>], <optional entity flag>
+          ),
           ...
        }
-       "relations" : [
-            (<name of the main table>, <name of a different table>, <entity flag>),
-            (<name of another table>, <name of yet another table>, <entity flag>),
-            ...
-       ],
    }
 
 The three fields of this dictionary are:
 
-- ``main_table``: The name of the main table.
-- ``tables``: A dictionary indexed by the tables' names. Each table is associated to a 2-tuple
-  containing the following fields:
+- ``main_table``: a 2-tuple containing the following fields:
+  - The `pandas.DataFrame` object of the main table.
+  - The key columns' names: A list of strings.
+  .
+- ``additional_data_tables``: A dictionary indexed by the data paths to the secondary
+  tables. Each data path is associated to a 2-tuple containing the following fields:
 
-  - The `pandas.DataFrame` object of the table.
-  - The key columns' names : Either a list of strings or a single string.
-
-- ``relations``: An optional field containing a list of tuples describing the relations between
-  tables. The first two values (Strings) of each tuple correspond to names of both the parent and the child table
-  involved in the relation. A third value (Boolean) can be optionally added to the tuple to indicate if the relation is
-  either ``1:n`` or ``1:1`` (entity). For example, If the tuple ``(table1, table2, True)`` is contained in this
-  field, it means that:
-
-  - ``table1`` and ``table2`` are in a ``1:1`` relationship
-  - The key of ``table1`` is contained in that of ``table2`` (ie. keys are hierarchical)
-
-  If the ``relations`` field is not present then Khiops Python assumes that the tables are in a *star*
-  schema.
+  - The `pandas.DataFrame` object of the secondary table.
+  - The key columns' names : A list of strings.
+  - optionally, a flag which indicates if the secondary table is in
+    a ``1:1`` relationship to its parent table.
 
 .. note::
 
@@ -138,9 +129,8 @@ We build the input ``X`` as follows::
    accidents_df = pd.read_csv(f"{kh.get_samples_dir()}/AccidentsSummary/Accidents.txt", sep="\t")
    vehicles_df = pd.read_csv(f"{kh.get_samples_dir()}/AccidentsSummary/Vehicles.txt", sep="\t")
    X = {
-      "main_table" : "Accident",
-      "tables": {
-          "Accident": (accidents_df.drop("Gravity", axis=1), "AccidentId"),
+      "main_table" : (accidents_df.drop("Gravity", axis=1), ["AccidentId"]),
+      "additional_data_tables": {
           "Vehicle": (vehicles_df, ["AccidentId", "VehicleId"])
       }
     }
@@ -170,19 +160,12 @@ We build the input ``X`` as follows::
     places_df = pd.read_csv(f"{kh.get_samples_dir()}/Accidents/Places.txt", sep="\t")
 
     X = {
-        "main_table": "Accidents",
-        "tables": {
-            "Accidents": (accidents_df.drop("Gravity", axis=1), "AccidentId"),
+        "main_table": (accidents_df.drop("Gravity", axis=1), ["AccidentId"]),
+        "additional_data_tables": {
             "Vehicles": (vehicles_df, ["AccidentId", "VehicleId"]),
-            "Users": (users_df, ["AccidentId", "VehicleId"]),
-            "Places": (places_df, "AccidentId"),
-
+            "Vehicles/Users": (users_df, ["AccidentId", "VehicleId"]),
+            "Places": (places_df, ["AccidentId"], True),
         },
-        "relations": [
-            ("Accidents", "Vehicles"),
-            ("Vehicles", "Users"),
-            ("Accidents", "Places", True),
-        ],
     }
 
 Both datasets can be found in the Khiops samples directory.

khiops/sklearn/dataset.py

@@ -177,6 +177,18 @@ def _check_multitable_spec(ds_spec):
 
 
 def table_name_of_path(table_path):
+    """Returns the table name as the last fragment of the table data path
+
+    Parameters
+    ----------
+    table_path: str
+        Data path of the table, in the format "path/to/table".
+
+    Returns
+    -------
+    str
+        The name of the table.
+    """
     return table_path.split("/")[-1]
 
 

packaging/conda/meta.yaml

@@ -26,7 +26,7 @@ requirements:
     - python
   run:
     - python
-    - conda-forge/label/rc::khiops-core =11.0.0a.0
+    - khiops-core =11.0.0b.0
     - pandas >=0.25.3
     - scikit-learn >=0.22.2
   run_constrained: