Merge branch 'main' into noklam/add-ipylab-starter

astro-airflow-iris/{{ cookiecutter.repo_name }}/src/{{ cookiecutter.python_package }}/__main__.py

@@ -1,45 +1,21 @@
 """{{ cookiecutter.project_name }} file for ensuring the package is executable
 as `{{ cookiecutter.repo_name }}` and `python -m {{ cookiecutter.python_package }}`
 """
-import importlib
+import sys
 from pathlib import Path
 
-from kedro.framework.cli.utils import KedroCliError, load_entry_points
+from kedro.framework.cli.utils import find_run_command
 from kedro.framework.project import configure_project
 
 
-def _find_run_command(package_name):
-    try:
-        project_cli = importlib.import_module(f"{package_name}.cli")
-        # fail gracefully if cli.py does not exist
-    except ModuleNotFoundError as exc:
-        if f"{package_name}.cli" not in str(exc):
-            raise
-        plugins = load_entry_points("project")
-        run = _find_run_command_in_plugins(plugins) if plugins else None
-        if run:
-            # use run command from installed plugin if it exists
-            return run
-        # use run command from the framework project
-        from kedro.framework.cli.project import run
-
-        return run
-    # fail badly if cli.py exists, but has no `cli` in it
-    if not hasattr(project_cli, "cli"):
-        raise KedroCliError(f"Cannot load commands from {package_name}.cli")
-    return project_cli.run
-
-
-def _find_run_command_in_plugins(plugins):
-    for group in plugins:
-        if "run" in group.commands:
-            return group.commands["run"]
-
-
 def main(*args, **kwargs):
     package_name = Path(__file__).parent.name
     configure_project(package_name)
-    run = _find_run_command(package_name)
+
+    interactive = hasattr(sys, 'ps1')
+    kwargs["standalone_mode"] = not interactive
+
+    run = find_run_command(package_name)
     run(*args, **kwargs)
 
 

databricks-iris/README.md

@@ -21,16 +21,12 @@ kedro new --starter=databricks-iris
 This starter has a base configuration that allows it to run natively on Databricks. Directories to store data and logs still need to be manually created in the user's Databricks DBFS instance:
 
 ```bash
-/dbfs/FileStore/iris-databricks/data
-/dbfs/FileStore/iris-databricks/logs
+/dbfs/FileStore/iris_databricks/data
+/dbfs/FileStore/iris_databricks/logs
 ```
 
 See the documentation on deploying a packaged Kedro project to Databricks for more information.
 
-### Databricks entry point
-
-The starter contains a script and an entry point (`databricks_run.py`) that enables a packaged project created with this starter to run on Databricks. See the documentation on deploying a packaged Kedro project to Databricks for more information.
-
 ### Single configuration in `/conf/base/spark.yml`
 
 While Spark allows you to specify many different [configuration options](https://spark.apache.org/docs/latest/configuration.html), this starter uses `/conf/base/spark.yml` as a single configuration location.

databricks-iris/{{ cookiecutter.repo_name }}/pyproject.toml

@@ -8,7 +8,7 @@ readme = "README.md"
 dynamic = ["dependencies", "version"]
 
 [project.scripts]
-databricks_run = "{{ cookiecutter.python_package }}.databricks_run:main"
+{{ cookiecutter.repo_name }} = "{{ cookiecutter.python_package }}.__main__:main"
 
 [project.entry-points."kedro.hooks"]
 

databricks-iris/{{ cookiecutter.repo_name }}/src/{{ cookiecutter.python_package }}/__main__.py

@@ -0,0 +1,23 @@
+"""{{ cookiecutter.project_name }} file for ensuring the package is executable
+as `{{ cookiecutter.repo_name }}` and `python -m {{ cookiecutter.python_package }}`
+"""
+import sys
+from pathlib import Path
+
+from kedro.framework.cli.utils import find_run_command
+from kedro.framework.project import configure_project
+
+
+def main(*args, **kwargs):
+    package_name = Path(__file__).parent.name
+    configure_project(package_name)
+
+    interactive = hasattr(sys, 'ps1')
+    kwargs["standalone_mode"] = not interactive
+
+    run = find_run_command(package_name)
+    run(*args, **kwargs)
+
+
+if __name__ == "__main__":
+    main()

spaceflights-pandas-viz/{{ cookiecutter.repo_name }}/conf/base/catalog.yml

@@ -1,7 +1,7 @@
 # Here you can define all your data sets by using simple YAML syntax.
 #
 # Documentation for this file format can be found in "The Data Catalog"
-# Link: https://kedro.readthedocs.io/en/stable/data/data_catalog.html
+# Link: https://docs.kedro.org/en/stable/data/data_catalog.html
 #
 # We support interacting with a variety of data stores including local file systems, cloud, network and HDFS
 #
@@ -37,7 +37,7 @@
 #
 # The Data Catalog supports being able to reference the same file using two different Dataset implementations
 # (transcoding), templating and a way to reuse arguments that are frequently repeated. See more here:
-# https://kedro.readthedocs.io/en/stable/data/data_catalog.html
+# https://docs.kedro.org/en/stable/data/data_catalog.html
 
 companies:
   type: pandas.CSVDataset

spaceflights-pandas-viz/{{ cookiecutter.repo_name }}/requirements.txt

@@ -10,5 +10,6 @@ pytest-cov~=3.0
 pytest-mock>=1.7.1, <2.0
 pytest~=7.2
 ruff~=0.1.8
-scikit-learn~=1.0
+scikit-learn~=1.5.1; python_version >= "3.9"
+scikit-learn<=1.4.0,>=1.0; python_version < "3.9"
 seaborn~=0.12.1

spaceflights-pandas-viz/{{ cookiecutter.repo_name }}/src/{{ cookiecutter.python_package }}/__main__.py

@@ -1,45 +1,21 @@
 """{{ cookiecutter.project_name }} file for ensuring the package is executable
 as `{{ cookiecutter.repo_name }}` and `python -m {{ cookiecutter.python_package }}`
 """
-import importlib
+import sys
 from pathlib import Path
 
-from kedro.framework.cli.utils import KedroCliError, load_entry_points
+from kedro.framework.cli.utils import find_run_command
 from kedro.framework.project import configure_project
 
 
-def _find_run_command(package_name):
-    try:
-        project_cli = importlib.import_module(f"{package_name}.cli")
-        # fail gracefully if cli.py does not exist
-    except ModuleNotFoundError as exc:
-        if f"{package_name}.cli" not in str(exc):
-            raise
-        plugins = load_entry_points("project")
-        run = _find_run_command_in_plugins(plugins) if plugins else None
-        if run:
-            # use run command from installed plugin if it exists
-            return run
-        # use run command from the framework project
-        from kedro.framework.cli.project import run
-
-        return run
-    # fail badly if cli.py exists, but has no `cli` in it
-    if not hasattr(project_cli, "cli"):
-        raise KedroCliError(f"Cannot load commands from {package_name}.cli")
-    return project_cli.run
-
-
-def _find_run_command_in_plugins(plugins):
-    for group in plugins:
-        if "run" in group.commands:
-            return group.commands["run"]
-
-
 def main(*args, **kwargs):
     package_name = Path(__file__).parent.name
     configure_project(package_name)
-    run = _find_run_command(package_name)
+
+    interactive = hasattr(sys, 'ps1')
+    kwargs["standalone_mode"] = not interactive
+
+    run = find_run_command(package_name)
     run(*args, **kwargs)
 
 

spaceflights-pandas-viz/{{ cookiecutter.repo_name }}/src/{{ cookiecutter.python_package }}/settings.py

@@ -12,13 +12,18 @@
 # Installed plugins for which to disable hook auto-registration.
 # DISABLE_HOOKS_FOR_PLUGINS = ("kedro-viz",)
 
-# Class that manages storing KedroSession data.
 from pathlib import Path  # noqa: E402
 
 from kedro_viz.integrations.kedro.sqlite_store import SQLiteStore  # noqa: E402
 
+# Class that manages storing KedroSession data.
 SESSION_STORE_CLASS = SQLiteStore
-# Keyword arguments to pass to the `SESSION_STORE_CLASS` constructor.
+
+# Setup for Experiment Tracking
+# The SQLite DB required for experiment tracking is stored by default
+# (supported from python >= 3.9 and Kedro-Viz 9.2.0) in the .viz folder
+# of your project. To store it in another directory, provide the keyword argument
+# `SESSION_STORE_ARGS` to pass to the `SESSION_STORE_CLASS` constructor.
 SESSION_STORE_ARGS = {"path": str(Path(__file__).parents[2])}
 
 # Directory that holds configuration.

spaceflights-pandas/{{ cookiecutter.repo_name }}/requirements.txt

@@ -10,4 +10,5 @@ pytest-cov~=3.0
 pytest-mock>=1.7.1, <2.0
 pytest~=7.2
 ruff~=0.1.8
-scikit-learn~=1.0
+scikit-learn~=1.5.1; python_version >= "3.9"
+scikit-learn<=1.4.0,>=1.0; python_version < "3.9"

spaceflights-pandas/{{ cookiecutter.repo_name }}/src/{{ cookiecutter.python_package }}/__main__.py

@@ -1,45 +1,21 @@
 """{{ cookiecutter.project_name }} file for ensuring the package is executable
 as `{{ cookiecutter.repo_name }}` and `python -m {{ cookiecutter.python_package }}`
 """
-import importlib
+import sys
 from pathlib import Path
 
-from kedro.framework.cli.utils import KedroCliError, load_entry_points
+from kedro.framework.cli.utils import find_run_command
 from kedro.framework.project import configure_project
 
 
-def _find_run_command(package_name):
-    try:
-        project_cli = importlib.import_module(f"{package_name}.cli")
-        # fail gracefully if cli.py does not exist
-    except ModuleNotFoundError as exc:
-        if f"{package_name}.cli" not in str(exc):
-            raise
-        plugins = load_entry_points("project")
-        run = _find_run_command_in_plugins(plugins) if plugins else None
-        if run:
-            # use run command from installed plugin if it exists
-            return run
-        # use run command from the framework project
-        from kedro.framework.cli.project import run
-
-        return run
-    # fail badly if cli.py exists, but has no `cli` in it
-    if not hasattr(project_cli, "cli"):
-        raise KedroCliError(f"Cannot load commands from {package_name}.cli")
-    return project_cli.run
-
-
-def _find_run_command_in_plugins(plugins):
-    for group in plugins:
-        if "run" in group.commands:
-            return group.commands["run"]
-
-
 def main(*args, **kwargs):
     package_name = Path(__file__).parent.name
     configure_project(package_name)
-    run = _find_run_command(package_name)
+
+    interactive = hasattr(sys, 'ps1')
+    kwargs["standalone_mode"] = not interactive
+
+    run = find_run_command(package_name)
     run(*args, **kwargs)
 
 

spaceflights-pyspark-viz/{{ cookiecutter.repo_name }}/requirements.txt

@@ -10,6 +10,7 @@ pytest-cov~=3.0
 pytest-mock>=1.7.1, <2.0
 pytest~=7.2
 ruff~=0.1.8
-scikit-learn~=1.0
+scikit-learn~=1.5.1; python_version >= "3.9"
+scikit-learn<=1.4.0,>=1.0; python_version < "3.9"
 seaborn~=0.12.1
 setuptools; python_version >= "3.12"

spaceflights-pyspark-viz/{{ cookiecutter.repo_name }}/src/{{ cookiecutter.python_package }}/__main__.py

@@ -1,45 +1,21 @@
 """{{ cookiecutter.project_name }} file for ensuring the package is executable
 as `{{ cookiecutter.repo_name }}` and `python -m {{ cookiecutter.python_package }}`
 """
-import importlib
+import sys
 from pathlib import Path
 
-from kedro.framework.cli.utils import KedroCliError, load_entry_points
+from kedro.framework.cli.utils import find_run_command
 from kedro.framework.project import configure_project
 
 
-def _find_run_command(package_name):
-    try:
-        project_cli = importlib.import_module(f"{package_name}.cli")
-        # fail gracefully if cli.py does not exist
-    except ModuleNotFoundError as exc:
-        if f"{package_name}.cli" not in str(exc):
-            raise
-        plugins = load_entry_points("project")
-        run = _find_run_command_in_plugins(plugins) if plugins else None
-        if run:
-            # use run command from installed plugin if it exists
-            return run
-        # use run command from the framework project
-        from kedro.framework.cli.project import run
-
-        return run
-    # fail badly if cli.py exists, but has no `cli` in it
-    if not hasattr(project_cli, "cli"):
-        raise KedroCliError(f"Cannot load commands from {package_name}.cli")
-    return project_cli.run
-
-
-def _find_run_command_in_plugins(plugins):
-    for group in plugins:
-        if "run" in group.commands:
-            return group.commands["run"]
-
-
 def main(*args, **kwargs):
     package_name = Path(__file__).parent.name
     configure_project(package_name)
-    run = _find_run_command(package_name)
+
+    interactive = hasattr(sys, 'ps1')
+    kwargs["standalone_mode"] = not interactive
+
+    run = find_run_command(package_name)
     run(*args, **kwargs)
 
 

spaceflights-pyspark-viz/{{ cookiecutter.repo_name }}/src/{{ cookiecutter.python_package }}/settings.py

@@ -16,9 +16,13 @@
 from kedro_viz.integrations.kedro.sqlite_store import SQLiteStore  # noqa: E402
 
 # Class that manages storing KedroSession data.
-
 SESSION_STORE_CLASS = SQLiteStore
-# Keyword arguments to pass to the `SESSION_STORE_CLASS` constructor.
+
+# Setup for Experiment Tracking
+# The SQLite DB required for experiment tracking is stored by default
+# (supported from python >= 3.9 and Kedro-Viz 9.2.0) in the .viz folder
+# of your project. To store it in another directory, provide the keyword argument
+# `SESSION_STORE_ARGS` to pass to the `SESSION_STORE_CLASS` constructor.
 SESSION_STORE_ARGS = {"path": str(Path(__file__).parents[2])}
 
 # Directory that holds configuration.

spaceflights-pyspark/{{ cookiecutter.repo_name }}/requirements.txt

@@ -10,4 +10,5 @@ pytest-cov~=3.0
 pytest-mock>=1.7.1, <2.0
 pytest~=7.2
 ruff~=0.1.8
-scikit-learn~=1.0
+scikit-learn~=1.5.1; python_version >= "3.9"
+scikit-learn<=1.4.0,>=1.0; python_version < "3.9"