From 1806821be48f615822ce0c52cde81577a36e4383 Mon Sep 17 00:00:00 2001
From: Guillaume Tauzin <4648633+gtauzin@users.noreply.github.com>
Date: Sat, 8 Feb 2025 11:51:24 +0100
Subject: [PATCH 01/15] Enable datasets_from_catalog to return factory-based
 datasets

Signed-off-by: Guillaume Tauzin <4648633+gtauzin@users.noreply.github.com>
---
 .../20250208_114146_4648633+gtauzin.md        | 47 +++++++++++++++++++
 vizro-core/docs/pages/explanation/authors.md  |  2 +-
 .../pages/user-guides/kedro-data-catalog.md   | 31 ++++++++++--
 .../vizro/integrations/kedro/_data_manager.py | 44 +++++++++++++----
 .../kedro/fixtures/test_catalog.yaml          | 24 +++++++---
 .../kedro/test_kedro_data_manager.py          | 26 ++++++++--
 6 files changed, 151 insertions(+), 23 deletions(-)
 create mode 100644 vizro-core/changelog.d/20250208_114146_4648633+gtauzin.md

diff --git a/vizro-core/changelog.d/20250208_114146_4648633+gtauzin.md b/vizro-core/changelog.d/20250208_114146_4648633+gtauzin.md
new file mode 100644
index 000000000..b1946eb20
--- /dev/null
+++ b/vizro-core/changelog.d/20250208_114146_4648633+gtauzin.md
@@ -0,0 +1,47 @@
+<!--
+A new scriv changelog fragment.
+
+Uncomment the section that is right (remove the HTML comment wrapper).
+-->
+
+<!--
+### Highlights ✨
+
+- A bullet item for the Highlights ✨ category with a link to the relevant PR at the end of your entry, e.g. Enable feature XXX. ([#1](https://github.com/mckinsey/vizro/pull/1))
+
+-->
+<!--
+### Removed
+
+- A bullet item for the Removed category with a link to the relevant PR at the end of your entry, e.g. Enable feature XXX. ([#1](https://github.com/mckinsey/vizro/pull/1))
+
+-->
+<!--
+### Added
+
+- A bullet item for the Added category with a link to the relevant PR at the end of your entry, e.g. Enable feature XXX. ([#1](https://github.com/mckinsey/vizro/pull/1))
+
+-->
+<!--
+### Changed
+
+- A bullet item for the Changed category with a link to the relevant PR at the end of your entry, e.g. Enable feature XXX. ([#1](https://github.com/mckinsey/vizro/pull/1))
+
+-->
+<!--
+### Deprecated
+
+- A bullet item for the Deprecated category with a link to the relevant PR at the end of your entry, e.g. Enable feature XXX. ([#1](https://github.com/mckinsey/vizro/pull/1))
+
+-->
+
+### Fixed
+
+- Fix a bug where datasets generated by dataset factories would not be returned by `kedro_integration.datasets_from_catalog`. ([#1001](https://github.com/mckinsey/vizro/pull/1001))
+
+<!--
+### Security
+
+- A bullet item for the Security category with a link to the relevant PR at the end of your entry, e.g. Enable feature XXX. ([#1](https://github.com/mckinsey/vizro/pull/1))
+
+-->
diff --git a/vizro-core/docs/pages/explanation/authors.md b/vizro-core/docs/pages/explanation/authors.md
index 7632f5c10..2f9b4cd5c 100644
--- a/vizro-core/docs/pages/explanation/authors.md
+++ b/vizro-core/docs/pages/explanation/authors.md
@@ -10,7 +10,7 @@
 
 <!-- vale off -->
 
-[Ann Marie Ward](https://github.com/AnnMarieW), [Anna Xiong](https://github.com/Anna-Xiong), [Annie Wachsmuth](https://github.com/anniecwa), [ataraexia](https://github.com/ataraexia), [axa99](https://github.com/axa99), [Bhavana Sundar](https://github.com/bhavanaeh), [Bo Xu](https://github.com/boxuboxu), [Chiara Pullem](https://github.com/chiara-sophie), [Denis Lebedev](https://github.com/DenisLebedevMcK), [Elena Fridman](https://github.com/EllenWie), [Ferida Mohammed](https://github.com/feridaaa), [Hamza Oza](https://github.com/hamzaoza), [Hansaem Park](https://github.com/sammitako), [Hilary Ivy](https://github.com/hxe00570), [Jasmine Wu](https://github.com/jazwu), [Jenelle Yonkman](https://github.com/yonkmanjl), [Jingjing Guo](https://github.com/jjguo-mck), [Juan Luis Cano Rodríguez](https://github.com/astrojuanlu), [Kee Wen Ng](https://github.com/KeeWenNgQB), [Leon Nallamuthu](https://github.com/leonnallamuthu), [Lydia Pitts](https://github.com/LydiaPitts), [Manuel Konrad](https://github.com/manuelkonrad), [Ned Letcher](https://github.com/ned2), [Nikolaos Tsaousis](https://github.com/tsanikgr), [njmcgrat](https://github.com/njmcgrat), [Oleksandr Serdiuk](https://github.com/oserdiuk-lohika), [Prateek Bajaj](https://github.com/prateekdev552), [Qiuyi Chen](https://github.com/Qiuyi-Chen), [Rashida Kanchwala](https://github.com/rashidakanchwala), [Riley Dou](https://github.com/rilieo), [Rosheen C.](https://github.com/rc678), [Sylvie Zhang](https://github.com/sylviezhang37), and [Upekesha Ngugi](https://github.com/upekesha).
+[Ann Marie Ward](https://github.com/AnnMarieW), [Anna Xiong](https://github.com/Anna-Xiong), [Annie Wachsmuth](https://github.com/anniecwa), [ataraexia](https://github.com/ataraexia), [axa99](https://github.com/axa99), [Bhavana Sundar](https://github.com/bhavanaeh), [Bo Xu](https://github.com/boxuboxu), [Chiara Pullem](https://github.com/chiara-sophie), [Denis Lebedev](https://github.com/DenisLebedevMcK), [Elena Fridman](https://github.com/EllenWie), [Ferida Mohammed](https://github.com/feridaaa), [Guillaume Tauzin](https://github.com/gtauzin), [Hamza Oza](https://github.com/hamzaoza), [Hansaem Park](https://github.com/sammitako), [Hilary Ivy](https://github.com/hxe00570), [Jasmine Wu](https://github.com/jazwu), [Jenelle Yonkman](https://github.com/yonkmanjl), [Jingjing Guo](https://github.com/jjguo-mck), [Juan Luis Cano Rodríguez](https://github.com/astrojuanlu), [Kee Wen Ng](https://github.com/KeeWenNgQB), [Leon Nallamuthu](https://github.com/leonnallamuthu), [Lydia Pitts](https://github.com/LydiaPitts), [Manuel Konrad](https://github.com/manuelkonrad), [Ned Letcher](https://github.com/ned2), [Nikolaos Tsaousis](https://github.com/tsanikgr), [njmcgrat](https://github.com/njmcgrat), [Oleksandr Serdiuk](https://github.com/oserdiuk-lohika), [Prateek Bajaj](https://github.com/prateekdev552), [Qiuyi Chen](https://github.com/Qiuyi-Chen), [Rashida Kanchwala](https://github.com/rashidakanchwala), [Riley Dou](https://github.com/rilieo), [Rosheen C.](https://github.com/rc678), [Sylvie Zhang](https://github.com/sylviezhang37), and [Upekesha Ngugi](https://github.com/upekesha).
 
 with thanks to Sam Bourton and Kevin Staight for sponsorship, inspiration and guidance,
 
diff --git a/vizro-core/docs/pages/user-guides/kedro-data-catalog.md b/vizro-core/docs/pages/user-guides/kedro-data-catalog.md
index ce4b060fa..69279d47e 100644
--- a/vizro-core/docs/pages/user-guides/kedro-data-catalog.md
+++ b/vizro-core/docs/pages/user-guides/kedro-data-catalog.md
@@ -12,7 +12,7 @@ pip install vizro[kedro]
 
 ## Use datasets from the Kedro Data Catalog
 
-`vizro.integrations.kedro` provides functions to help generate and process a [Kedro Data Catalog](https://docs.kedro.org/en/stable/data/index.html). Given a Kedro Data Catalog `catalog`, the general pattern to add datasets into the Vizro data manager is:
+`vizro.integrations.kedro` provides functions to help generate and process a [Kedro Data Catalog](https://docs.kedro.org/en/stable/data/index.html). It supports both the original [DataCatalog](https://docs.kedro.org/en/stable/data/data_catalog.html) and the more recently introduced [KedroDataCatalog](https://docs.kedro.org/en/stable/data/index.html#kedrodatacatalog-experimental-feature). Given a Kedro Data Catalog `catalog`, the general pattern to add datasets into the Vizro data manager is:
 
 ```python
 from vizro.integrations import kedro as kedro_integration
@@ -23,6 +23,19 @@ for dataset_name, dataset in kedro_integration.datasets_from_catalog(catalog).it
     data_manager[dataset_name] = dataset
 ```
 
+To add datasets that are defined using the [Kedro dataset factory](https://docs.kedro.org/en/stable/data/kedro_dataset_factories.html), `datasets_from_catalog` needs to access the pipelines that use them.
+
+```python
+from vizro.integrations import kedro as kedro_integration
+from vizro.managers import data_manager
+
+
+pipeline = pipelines.get("my_pipeline_name")
+
+for dataset_name, dataset in kedro_integration.datasets_from_catalog(catalog, pipeline=pipeline).items():
+    data_manager[dataset_name] = dataset
+```
+
 This imports all datasets of type [`kedro_datasets.pandas`](https://docs.kedro.org/en/stable/kedro_datasets.html) from the Kedro `catalog` into the Vizro `data_manager`.
 
 The `catalog` variable may have been created in a number of different ways:
@@ -31,6 +44,11 @@ The `catalog` variable may have been created in a number of different ways:
 1. [Kedro Jupyter session](https://docs.kedro.org/en/stable/notebooks_and_ipython/kedro_and_notebooks.html). This automatically exposes `catalog`.
 1. Data Catalog configuration file (`catalog.yaml`). This can create a `catalog` entirely independently of a Kedro project using [`kedro.io.DataCatalog.from_config`](https://docs.kedro.org/en/stable/kedro.io.DataCatalog.html#kedro.io.DataCatalog.from_config).
 
+Conversely, the `pipelines` variable may have been created the following ways:
+
+1. Kedro project path. Vizro exposes a helper function `vizro.integrations.kedro.pipelines_from_project` to generate a `pipelines` given the path to a Kedro project.
+1. [Kedro Jupyter session](https://docs.kedro.org/en/stable/notebooks_and_ipython/kedro_and_notebooks.html). This automatically exposes `pipelines`.
+
 The full code for these different cases is given below.
 
 !!! example "Import a Kedro Data Catalog into the Vizro data manager"
@@ -39,10 +57,13 @@ The full code for these different cases is given below.
         from vizro.integrations import kedro as kedro_integration
         from vizro.managers import data_manager
 
+        project_path = "/path/to/kedro/project"
+        catalog = kedro_integration.catalog_from_project(project_path)
+        pipelines = kedro_integration.catalog_from_project(project_path)
 
-        catalog = kedro_integration.catalog_from_project("/path/to/kedro/project")
+        pipeline = pipelines.get("my_pipeline")
 
-        for dataset_name, dataset in kedro_integration.datasets_from_catalog(catalog).items():
+        for dataset_name, dataset in kedro_integration.datasets_from_catalog(catalog, pipeline=pipeline).items():
             data_manager[dataset_name] = dataset
         ```
 
@@ -51,7 +72,9 @@ The full code for these different cases is given below.
         from vizro.managers import data_manager
 
 
-        for dataset_name, dataset in kedro_integration.datasets_from_catalog(catalog).items():
+        pipeline = pipelines.get("my_pipeline")
+
+        for dataset_name, dataset in kedro_integration.datasets_from_catalog(catalog, pipeline=pipeline).items():
             data_manager[dataset_name] = dataset
         ```
 
diff --git a/vizro-core/src/vizro/integrations/kedro/_data_manager.py b/vizro-core/src/vizro/integrations/kedro/_data_manager.py
index 28c565a6c..2397a2587 100644
--- a/vizro-core/src/vizro/integrations/kedro/_data_manager.py
+++ b/vizro-core/src/vizro/integrations/kedro/_data_manager.py
@@ -3,14 +3,15 @@
 
 from kedro.framework.session import KedroSession
 from kedro.framework.startup import bootstrap_project
-from kedro.io import DataCatalog
+from kedro.io import CatalogProtocol, KedroDataCatalog
+from kedro.pipeline import Pipeline
 
 from vizro.managers._data_manager import pd_DataFrameCallable
 
 
 def catalog_from_project(
     project_path: Union[str, Path], env: Optional[str] = None, extra_params: Optional[dict[str, Any]] = None
-) -> DataCatalog:
+) -> CatalogProtocol | KedroDataCatalog:
     bootstrap_project(project_path)
     with KedroSession.create(
         project_path=project_path, env=env, save_on_close=False, extra_params=extra_params
@@ -18,10 +19,35 @@ def catalog_from_project(
         return session.load_context().catalog
 
 
-def datasets_from_catalog(catalog: DataCatalog) -> dict[str, pd_DataFrameCallable]:
-    datasets = {}
-    for name in catalog.list():
-        dataset = catalog._get_dataset(name, suggest=False)
-        if "pandas" in dataset.__module__:
-            datasets[name] = dataset.load
-    return datasets
+def pipelines_from_project(project_path: Union[str, Path]) -> Pipeline:
+    bootstrap_project(project_path)
+    from kedro.framework.project import pipelines
+
+    return pipelines
+
+
+def datasets_from_catalog(
+    catalog: CatalogProtocol | KedroDataCatalog, *, pipeline: Pipeline = None
+) -> dict[str, pd_DataFrameCallable]:
+    # This doesn't include things added to the catalog at run time but that is ok for our purposes.
+    config_resolver = catalog.config_resolver
+    kedro_datasets = config_resolver.config.copy()
+
+    if pipeline is not None:
+        # Go through all dataset names that weren't in catalog and try to resolve them. Those that cannot be
+        # resolved give an empty dictionary and are ignored.
+        for dataset_name in set(pipeline.datasets()) - set(kedro_datasets):
+            if dataset_config := config_resolver.resolve_pattern(dataset_name):
+                kedro_datasets[dataset_name] = dataset_config
+
+    vizro_data_sources = {}
+
+    for dataset_name, dataset_config in kedro_datasets.items():
+        # "type" key always exists because we filtered out patterns that resolve to empty dictionary above.
+        if "pandas" in dataset_config["type"]:
+            # TODO: in future update to use lambda: catalog.load(dataset_name) instead of _get_dataset
+            #  but need to check if works with caching.
+            dataset = catalog._get_dataset(dataset_name, suggest=False)
+            vizro_data_sources[dataset_name] = dataset.load
+
+    return vizro_data_sources
diff --git a/vizro-core/tests/unit/vizro/integrations/kedro/fixtures/test_catalog.yaml b/vizro-core/tests/unit/vizro/integrations/kedro/fixtures/test_catalog.yaml
index 8ae6ef952..184d8625e 100644
--- a/vizro-core/tests/unit/vizro/integrations/kedro/fixtures/test_catalog.yaml
+++ b/vizro-core/tests/unit/vizro/integrations/kedro/fixtures/test_catalog.yaml
@@ -1,7 +1,19 @@
-companies:
-  type: pandas.JSONDataset
-  filepath: companies.json
+"{pandas_factory}1":
+  type: pandas.CSVDataset
+  filepath: ./{pandas_factory}.csv
 
-reviews:
-  type: pickle.PickleDataset
-  filepath: reviews.pkl
+pandas_excel:
+  type: pandas.ExcelDataset
+  filepath: pandas_excel.xlsx
+
+pandas_parquet:
+  type: pandas.ParquetDataset
+  filepath: pandas_parquet.parquet
+
+polars:
+  type: polars.CSVDataset
+  filepath: polars.csv
+
+not_dataframe:
+  type: picke.PickleDataset
+  filepath: pickle.pkl
diff --git a/vizro-core/tests/unit/vizro/integrations/kedro/test_kedro_data_manager.py b/vizro-core/tests/unit/vizro/integrations/kedro/test_kedro_data_manager.py
index cb6cb796d..fd1b63330 100644
--- a/vizro-core/tests/unit/vizro/integrations/kedro/test_kedro_data_manager.py
+++ b/vizro-core/tests/unit/vizro/integrations/kedro/test_kedro_data_manager.py
@@ -8,6 +8,7 @@
 
 kedro = pytest.importorskip("kedro")
 
+import kedro.pipeline as kp  # noqa: E402
 from kedro.io import DataCatalog  # noqa: E402
 
 from vizro.integrations.kedro import datasets_from_catalog  # noqa: E402
@@ -20,6 +21,25 @@ def catalog_path():
 
 def test_datasets_from_catalog(catalog_path):
     catalog = DataCatalog.from_config(yaml.safe_load(catalog_path.read_text(encoding="utf-8")))
-    assert "companies" in datasets_from_catalog(catalog)
-    assert isinstance(datasets_from_catalog(catalog), dict)
-    assert isinstance(datasets_from_catalog(catalog)["companies"], types.MethodType)
+
+    datasets = datasets_from_catalog(catalog)
+    assert isinstance(datasets, dict)
+    assert set(datasets) == {"pandas_excel", "pandas_parquet"}
+    for dataset in datasets.values():
+        assert isinstance(dataset, types.MethodType)
+
+
+def test_datasets_from_catalog_with_pipeline(catalog_path):
+    catalog = DataCatalog.from_config(yaml.safe_load(catalog_path.read_text(encoding="utf-8")))
+    pipeline = kp.pipeline(
+        [
+            kp.node(
+                func=lambda *args: None,
+                inputs=["pandas_excel", "C1", "polars", "Z", "parameters", "params:z"],
+                outputs=["pandas_parquet", "not_dataframe"],
+            ),
+        ]
+    )
+
+    datasets = datasets_from_catalog(catalog, pipeline=pipeline)
+    assert set(datasets) == {"pandas_excel", "pandas_parquet", "C1"}

From 828735a82c4cb2bcc92a4ab82464a013b6f6431a Mon Sep 17 00:00:00 2001
From: Guillaume Tauzin <4648633+gtauzin@users.noreply.github.com>
Date: Sat, 8 Feb 2025 12:07:53 +0100
Subject: [PATCH 02/15] Use Union instead of |

Signed-off-by: Guillaume Tauzin <4648633+gtauzin@users.noreply.github.com>
---
 vizro-core/src/vizro/integrations/kedro/_data_manager.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/vizro-core/src/vizro/integrations/kedro/_data_manager.py b/vizro-core/src/vizro/integrations/kedro/_data_manager.py
index 2397a2587..d03cf7c59 100644
--- a/vizro-core/src/vizro/integrations/kedro/_data_manager.py
+++ b/vizro-core/src/vizro/integrations/kedro/_data_manager.py
@@ -11,7 +11,7 @@
 
 def catalog_from_project(
     project_path: Union[str, Path], env: Optional[str] = None, extra_params: Optional[dict[str, Any]] = None
-) -> CatalogProtocol | KedroDataCatalog:
+) -> Union[CatalogProtocol, KedroDataCatalog]:
     bootstrap_project(project_path)
     with KedroSession.create(
         project_path=project_path, env=env, save_on_close=False, extra_params=extra_params
@@ -27,7 +27,7 @@ def pipelines_from_project(project_path: Union[str, Path]) -> Pipeline:
 
 
 def datasets_from_catalog(
-    catalog: CatalogProtocol | KedroDataCatalog, *, pipeline: Pipeline = None
+    catalog: Union[CatalogProtocol, KedroDataCatalog], *, pipeline: Pipeline = None
 ) -> dict[str, pd_DataFrameCallable]:
     # This doesn't include things added to the catalog at run time but that is ok for our purposes.
     config_resolver = catalog.config_resolver

From 0d475600bbc093715e1cb41e50cdbe5597127431 Mon Sep 17 00:00:00 2001
From: Guillaume Tauzin <4648633+gtauzin@users.noreply.github.com>
Date: Mon, 10 Feb 2025 18:06:36 +0100
Subject: [PATCH 03/15] Apply suggestions from code review

---
 .../20250208_114146_4648633+gtauzin.md        |  9 +--
 .../pages/user-guides/kedro-data-catalog.md   | 70 ++++++++++++++-----
 .../src/vizro/integrations/kedro/__init__.py  |  4 +-
 .../vizro/integrations/kedro/_data_manager.py |  6 +-
 .../kedro/fixtures/test_catalog.yaml          |  8 +--
 .../kedro/test_kedro_data_manager.py          |  6 +-
 6 files changed, 64 insertions(+), 39 deletions(-)

diff --git a/vizro-core/changelog.d/20250208_114146_4648633+gtauzin.md b/vizro-core/changelog.d/20250208_114146_4648633+gtauzin.md
index b1946eb20..c358660e7 100644
--- a/vizro-core/changelog.d/20250208_114146_4648633+gtauzin.md
+++ b/vizro-core/changelog.d/20250208_114146_4648633+gtauzin.md
@@ -16,12 +16,9 @@ Uncomment the section that is right (remove the HTML comment wrapper).
 - A bullet item for the Removed category with a link to the relevant PR at the end of your entry, e.g. Enable feature XXX. ([#1](https://github.com/mckinsey/vizro/pull/1))
 
 -->
-<!--
 ### Added
 
-- A bullet item for the Added category with a link to the relevant PR at the end of your entry, e.g. Enable feature XXX. ([#1](https://github.com/mckinsey/vizro/pull/1))
-
--->
+- Kedro integration function `datasets_from_catalog` can now handle dataset factories. ([#1001](https://github.com/mckinsey/vizro/pull/1001))
 <!--
 ### Changed
 
@@ -35,10 +32,6 @@ Uncomment the section that is right (remove the HTML comment wrapper).
 
 -->
 
-### Fixed
-
-- Fix a bug where datasets generated by dataset factories would not be returned by `kedro_integration.datasets_from_catalog`. ([#1001](https://github.com/mckinsey/vizro/pull/1001))
-
 <!--
 ### Security
 
diff --git a/vizro-core/docs/pages/user-guides/kedro-data-catalog.md b/vizro-core/docs/pages/user-guides/kedro-data-catalog.md
index 69279d47e..c43a78b70 100644
--- a/vizro-core/docs/pages/user-guides/kedro-data-catalog.md
+++ b/vizro-core/docs/pages/user-guides/kedro-data-catalog.md
@@ -12,7 +12,7 @@ pip install vizro[kedro]
 
 ## Use datasets from the Kedro Data Catalog
 
-`vizro.integrations.kedro` provides functions to help generate and process a [Kedro Data Catalog](https://docs.kedro.org/en/stable/data/index.html). It supports both the original [DataCatalog](https://docs.kedro.org/en/stable/data/data_catalog.html) and the more recently introduced [KedroDataCatalog](https://docs.kedro.org/en/stable/data/index.html#kedrodatacatalog-experimental-feature). Given a Kedro Data Catalog `catalog`, the general pattern to add datasets into the Vizro data manager is:
+`vizro.integrations.kedro` provides functions to help generate and process a [Kedro Data Catalog](https://docs.kedro.org/en/stable/data/index.html). It supports both the original [`DataCatalog`](https://docs.kedro.org/en/stable/data/data_catalog.html) and the more recently introduced [`KedroDataCatalog`](https://docs.kedro.org/en/stable/data/index.html#kedrodatacatalog-experimental-feature). Given a Kedro Data Catalog `catalog`, the general pattern to add datasets into the Vizro data manager is:
 
 ```python
 from vizro.integrations import kedro as kedro_integration
@@ -32,7 +32,7 @@ from vizro.managers import data_manager
 
 pipeline = pipelines.get("my_pipeline_name")
 
-for dataset_name, dataset in kedro_integration.datasets_from_catalog(catalog, pipeline=pipeline).items():
+for dataset_name, dataset_loader in kedro_integration.datasets_from_catalog(catalog, pipeline=pipeline).items():
     data_manager[dataset_name] = dataset
 ```
 
@@ -44,11 +44,6 @@ The `catalog` variable may have been created in a number of different ways:
 1. [Kedro Jupyter session](https://docs.kedro.org/en/stable/notebooks_and_ipython/kedro_and_notebooks.html). This automatically exposes `catalog`.
 1. Data Catalog configuration file (`catalog.yaml`). This can create a `catalog` entirely independently of a Kedro project using [`kedro.io.DataCatalog.from_config`](https://docs.kedro.org/en/stable/kedro.io.DataCatalog.html#kedro.io.DataCatalog.from_config).
 
-Conversely, the `pipelines` variable may have been created the following ways:
-
-1. Kedro project path. Vizro exposes a helper function `vizro.integrations.kedro.pipelines_from_project` to generate a `pipelines` given the path to a Kedro project.
-1. [Kedro Jupyter session](https://docs.kedro.org/en/stable/notebooks_and_ipython/kedro_and_notebooks.html). This automatically exposes `pipelines`.
-
 The full code for these different cases is given below.
 
 !!! example "Import a Kedro Data Catalog into the Vizro data manager"
@@ -59,12 +54,10 @@ The full code for these different cases is given below.
 
         project_path = "/path/to/kedro/project"
         catalog = kedro_integration.catalog_from_project(project_path)
-        pipelines = kedro_integration.catalog_from_project(project_path)
 
-        pipeline = pipelines.get("my_pipeline")
 
-        for dataset_name, dataset in kedro_integration.datasets_from_catalog(catalog, pipeline=pipeline).items():
-            data_manager[dataset_name] = dataset
+        for dataset_name, dataset_loader in kedro_integration.datasets_from_catalog(catalog).items():
+            data_manager[dataset_name] = dataset_loader
         ```
 
     === "app.ipynb (Kedro Jupyter session)"
@@ -72,10 +65,8 @@ The full code for these different cases is given below.
         from vizro.managers import data_manager
 
 
-        pipeline = pipelines.get("my_pipeline")
-
-        for dataset_name, dataset in kedro_integration.datasets_from_catalog(catalog, pipeline=pipeline).items():
-            data_manager[dataset_name] = dataset
+        for dataset_name, dataset_loader in kedro_integration.datasets_from_catalog(catalog).items():
+            data_manager[dataset_name] = dataset_loader
         ```
 
     === "app.py (Data Catalog configuration file)"
@@ -89,6 +80,51 @@ The full code for these different cases is given below.
 
         catalog = DataCatalog.from_config(yaml.safe_load(Path("catalog.yaml").read_text(encoding="utf-8")))
 
-        for dataset_name, dataset in kedro_integration.datasets_from_catalog(catalog).items():
-            data_manager[dataset_name] = dataset
+        for dataset_name, dataset_loader in kedro_integration.datasets_from_catalog(catalog).items():
+            data_manager[dataset_name] = dataset_loader
+        ```
+
+### Use dataset factories
+
+To add datasets that are defined using a [Kedro dataset factory](https://docs.kedro.org/en/stable/data/kedro_dataset_factories.html), `datasets_from_catalog` needs to resolve dataset patterns against explicit datasets. Given a Kedro `pipelines` dictionary, you should specify a `pipeline` argument as follows:
+
+```python
+kedro_integration.datasets_from_catalog(catalog, pipeline=pipelines["__default__"])  # (1)!
+```
+
+1. You can specify the name of your pipeline, for example `pipelines["my_pipeline"]`, or even combine multiple pipelines with `pipelines["a"] + pipelines["b"]`. The Kedro `__default__` pipeline is what runs by default with the `kedro run` command.
+
+The `pipelines` variable may have been created the following ways:
+
+1. Kedro project path. Vizro exposes a helper function `vizro.integrations.kedro.pipelines_from_project` to generate a `pipelines` given the path to a Kedro project.
+1. [Kedro Jupyter session](https://docs.kedro.org/en/stable/notebooks_and_ipython/kedro_and_notebooks.html). This automatically exposes `pipelines`.
+
+The full code for these different cases is given below.
+
+!!! example "Import a Kedro Data Catalog with dataset factories into the Vizro data manager"
+    === "app.py (Kedro project path)"
+        ```python
+        from vizro.integrations import kedro as kedro_integration
+        from vizro.managers import data_manager
+
+
+        project_path = "/path/to/kedro/project"
+        catalog = kedro_integration.catalog_from_project(project_path)
+        pipelines = kedro_integration.pipelines_from_project(project_path)
+
+        for dataset_name, dataset_loader in kedro_integration.datasets_from_catalog(
+            catalog, pipeline=pipelines["__default__"]
+        ).items():
+            data_manager[dataset_name] = dataset_loader
+        ```
+
+    === "app.ipynb (Kedro Jupyter session)"
+        ```python
+        from vizro.managers import data_manager
+
+
+        for dataset_name, dataset_loader in kedro_integration.datasets_from_catalog(
+            catalog, pipeline=pipelines["__default__"]
+        ).items():
+            data_manager[dataset_name] = dataset_loader
         ```
diff --git a/vizro-core/src/vizro/integrations/kedro/__init__.py b/vizro-core/src/vizro/integrations/kedro/__init__.py
index c8ad5c1af..730002f21 100644
--- a/vizro-core/src/vizro/integrations/kedro/__init__.py
+++ b/vizro-core/src/vizro/integrations/kedro/__init__.py
@@ -1,3 +1,3 @@
-from ._data_manager import catalog_from_project, datasets_from_catalog
+from ._data_manager import catalog_from_project, datasets_from_catalog, pipelines_from_project
 
-__all__ = ["catalog_from_project", "datasets_from_catalog"]
+__all__ = ["catalog_from_project", "datasets_from_catalog", "pipelines_from_project"]
diff --git a/vizro-core/src/vizro/integrations/kedro/_data_manager.py b/vizro-core/src/vizro/integrations/kedro/_data_manager.py
index d03cf7c59..8465151de 100644
--- a/vizro-core/src/vizro/integrations/kedro/_data_manager.py
+++ b/vizro-core/src/vizro/integrations/kedro/_data_manager.py
@@ -3,7 +3,7 @@
 
 from kedro.framework.session import KedroSession
 from kedro.framework.startup import bootstrap_project
-from kedro.io import CatalogProtocol, KedroDataCatalog
+from kedro.io import CatalogProtocol
 from kedro.pipeline import Pipeline
 
 from vizro.managers._data_manager import pd_DataFrameCallable
@@ -11,7 +11,7 @@
 
 def catalog_from_project(
     project_path: Union[str, Path], env: Optional[str] = None, extra_params: Optional[dict[str, Any]] = None
-) -> Union[CatalogProtocol, KedroDataCatalog]:
+) -> CatalogProtocol:
     bootstrap_project(project_path)
     with KedroSession.create(
         project_path=project_path, env=env, save_on_close=False, extra_params=extra_params
@@ -27,7 +27,7 @@ def pipelines_from_project(project_path: Union[str, Path]) -> Pipeline:
 
 
 def datasets_from_catalog(
-    catalog: Union[CatalogProtocol, KedroDataCatalog], *, pipeline: Pipeline = None
+    catalog: CatalogProtocol, *, pipeline: Pipeline = None
 ) -> dict[str, pd_DataFrameCallable]:
     # This doesn't include things added to the catalog at run time but that is ok for our purposes.
     config_resolver = catalog.config_resolver
diff --git a/vizro-core/tests/unit/vizro/integrations/kedro/fixtures/test_catalog.yaml b/vizro-core/tests/unit/vizro/integrations/kedro/fixtures/test_catalog.yaml
index 184d8625e..708b115b3 100644
--- a/vizro-core/tests/unit/vizro/integrations/kedro/fixtures/test_catalog.yaml
+++ b/vizro-core/tests/unit/vizro/integrations/kedro/fixtures/test_catalog.yaml
@@ -1,4 +1,4 @@
-"{pandas_factory}1":
+"{pandas_factory}#csv":
   type: pandas.CSVDataset
   filepath: ./{pandas_factory}.csv
 
@@ -10,10 +10,6 @@ pandas_parquet:
   type: pandas.ParquetDataset
   filepath: pandas_parquet.parquet
 
-polars:
-  type: polars.CSVDataset
-  filepath: polars.csv
-
 not_dataframe:
-  type: picke.PickleDataset
+  type: pickle.PickleDataset
   filepath: pickle.pkl
diff --git a/vizro-core/tests/unit/vizro/integrations/kedro/test_kedro_data_manager.py b/vizro-core/tests/unit/vizro/integrations/kedro/test_kedro_data_manager.py
index fd1b63330..414224cfc 100644
--- a/vizro-core/tests/unit/vizro/integrations/kedro/test_kedro_data_manager.py
+++ b/vizro-core/tests/unit/vizro/integrations/kedro/test_kedro_data_manager.py
@@ -35,11 +35,11 @@ def test_datasets_from_catalog_with_pipeline(catalog_path):
         [
             kp.node(
                 func=lambda *args: None,
-                inputs=["pandas_excel", "C1", "polars", "Z", "parameters", "params:z"],
-                outputs=["pandas_parquet", "not_dataframe"],
+                inputs=["pandas_excel", "something#csv", "not_dataframe", "not_in_catalog", "pandas_parquet", "parameters", "params:z"],
+                outputs=None,
             ),
         ]
     )
 
     datasets = datasets_from_catalog(catalog, pipeline=pipeline)
-    assert set(datasets) == {"pandas_excel", "pandas_parquet", "C1"}
+    assert set(datasets) == {"pandas_excel", "pandas_parquet", "something#csv"}

From dbcc2f32f9b95370982d0d0acf3580cd40f293da Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Mon, 10 Feb 2025 18:40:37 +0000
Subject: [PATCH 04/15] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 .../src/vizro/integrations/kedro/_data_manager.py      |  4 +---
 .../integrations/kedro/test_kedro_data_manager.py      | 10 +++++++++-
 2 files changed, 10 insertions(+), 4 deletions(-)

diff --git a/vizro-core/src/vizro/integrations/kedro/_data_manager.py b/vizro-core/src/vizro/integrations/kedro/_data_manager.py
index 8465151de..49f848c73 100644
--- a/vizro-core/src/vizro/integrations/kedro/_data_manager.py
+++ b/vizro-core/src/vizro/integrations/kedro/_data_manager.py
@@ -26,9 +26,7 @@ def pipelines_from_project(project_path: Union[str, Path]) -> Pipeline:
     return pipelines
 
 
-def datasets_from_catalog(
-    catalog: CatalogProtocol, *, pipeline: Pipeline = None
-) -> dict[str, pd_DataFrameCallable]:
+def datasets_from_catalog(catalog: CatalogProtocol, *, pipeline: Pipeline = None) -> dict[str, pd_DataFrameCallable]:
     # This doesn't include things added to the catalog at run time but that is ok for our purposes.
     config_resolver = catalog.config_resolver
     kedro_datasets = config_resolver.config.copy()
diff --git a/vizro-core/tests/unit/vizro/integrations/kedro/test_kedro_data_manager.py b/vizro-core/tests/unit/vizro/integrations/kedro/test_kedro_data_manager.py
index 414224cfc..399a542a4 100644
--- a/vizro-core/tests/unit/vizro/integrations/kedro/test_kedro_data_manager.py
+++ b/vizro-core/tests/unit/vizro/integrations/kedro/test_kedro_data_manager.py
@@ -35,7 +35,15 @@ def test_datasets_from_catalog_with_pipeline(catalog_path):
         [
             kp.node(
                 func=lambda *args: None,
-                inputs=["pandas_excel", "something#csv", "not_dataframe", "not_in_catalog", "pandas_parquet", "parameters", "params:z"],
+                inputs=[
+                    "pandas_excel",
+                    "something#csv",
+                    "not_dataframe",
+                    "not_in_catalog",
+                    "pandas_parquet",
+                    "parameters",
+                    "params:z",
+                ],
                 outputs=None,
             ),
         ]

From 3f33ff3b2bd282819fe451dc21458fe7122f945a Mon Sep 17 00:00:00 2001
From: Guillaume Tauzin <4648633+gtauzin@users.noreply.github.com>
Date: Mon, 10 Feb 2025 20:15:54 +0100
Subject: [PATCH 05/15] Extend tests to both type of catalog

Signed-off-by: Guillaume Tauzin <4648633+gtauzin@users.noreply.github.com>
---
 .../kedro/test_kedro_data_manager.py            | 17 ++++++++---------
 1 file changed, 8 insertions(+), 9 deletions(-)

diff --git a/vizro-core/tests/unit/vizro/integrations/kedro/test_kedro_data_manager.py b/vizro-core/tests/unit/vizro/integrations/kedro/test_kedro_data_manager.py
index 399a542a4..8d52e2b22 100644
--- a/vizro-core/tests/unit/vizro/integrations/kedro/test_kedro_data_manager.py
+++ b/vizro-core/tests/unit/vizro/integrations/kedro/test_kedro_data_manager.py
@@ -9,19 +9,19 @@
 kedro = pytest.importorskip("kedro")
 
 import kedro.pipeline as kp  # noqa: E402
-from kedro.io import DataCatalog  # noqa: E402
+from kedro.io import DataCatalog, KedroDataCatalog  # noqa: E402
 
 from vizro.integrations.kedro import datasets_from_catalog  # noqa: E402
 
 
-@pytest.fixture
-def catalog_path():
-    return Path(__file__).parent / "fixtures/test_catalog.yaml"
+@pytest.fixture(params=[DataCatalog, KedroDataCatalog])
+def catalog(request):
+    catalog_class = request.param
+    catalog_path = Path(__file__).parent / "fixtures/test_catalog.yaml"
+    return catalog_class.from_config(yaml.safe_load(catalog_path.read_text(encoding="utf-8")))
 
 
-def test_datasets_from_catalog(catalog_path):
-    catalog = DataCatalog.from_config(yaml.safe_load(catalog_path.read_text(encoding="utf-8")))
-
+def test_datasets_from_catalog(catalog):
     datasets = datasets_from_catalog(catalog)
     assert isinstance(datasets, dict)
     assert set(datasets) == {"pandas_excel", "pandas_parquet"}
@@ -29,8 +29,7 @@ def test_datasets_from_catalog(catalog_path):
         assert isinstance(dataset, types.MethodType)
 
 
-def test_datasets_from_catalog_with_pipeline(catalog_path):
-    catalog = DataCatalog.from_config(yaml.safe_load(catalog_path.read_text(encoding="utf-8")))
+def test_datasets_from_catalog_with_pipeline(catalog):
     pipeline = kp.pipeline(
         [
             kp.node(

From 48956b214f4f5a00a8c1f3f50d9a9d252e2edd46 Mon Sep 17 00:00:00 2001
From: Antony Milne <49395058+antonymilne@users.noreply.github.com>
Date: Tue, 11 Feb 2025 11:19:55 +0000
Subject: [PATCH 06/15] Test push


From 5d332933f4a12bb876257be9387f7e07628e5b96 Mon Sep 17 00:00:00 2001
From: Antony Milne <49395058+antonymilne@users.noreply.github.com>
Date: Tue, 11 Feb 2025 11:24:19 +0000
Subject: [PATCH 07/15] Bump to kedro>=0.19.9 and enable tests for Py 3.13

---
 .../changelog.d/20250208_114146_4648633+gtauzin.md   |  5 ++---
 vizro-core/hatch.toml                                | 12 +++---------
 vizro-core/pyproject.toml                            |  2 +-
 .../integrations/kedro/test_kedro_data_manager.py    |  8 +++-----
 4 files changed, 9 insertions(+), 18 deletions(-)

diff --git a/vizro-core/changelog.d/20250208_114146_4648633+gtauzin.md b/vizro-core/changelog.d/20250208_114146_4648633+gtauzin.md
index c358660e7..f0d9ea8ef 100644
--- a/vizro-core/changelog.d/20250208_114146_4648633+gtauzin.md
+++ b/vizro-core/changelog.d/20250208_114146_4648633+gtauzin.md
@@ -19,12 +19,11 @@ Uncomment the section that is right (remove the HTML comment wrapper).
 ### Added
 
 - Kedro integration function `datasets_from_catalog` can now handle dataset factories. ([#1001](https://github.com/mckinsey/vizro/pull/1001))
-<!--
+
 ### Changed
 
-- A bullet item for the Changed category with a link to the relevant PR at the end of your entry, e.g. Enable feature XXX. ([#1](https://github.com/mckinsey/vizro/pull/1))
+- Bump optional dependency lower bound to `kedro>=0.19.9`. ([#1001](https://github.com/mckinsey/vizro/pull/1001))
 
--->
 <!--
 ### Deprecated
 
diff --git a/vizro-core/hatch.toml b/vizro-core/hatch.toml
index d7d1b8f1c..b5fc32958 100644
--- a/vizro-core/hatch.toml
+++ b/vizro-core/hatch.toml
@@ -3,13 +3,6 @@
 [[envs.all.matrix]]
 python = ["3.9", "3.10", "3.11", "3.12", "3.13"]
 
-[envs.all.overrides]
-# Kedro is currently not compatible with Python 3.13 and returns exceptions when trying to run the unit tests on
-# Python 3.13. These exceptions turned out to be difficult to ignore: https://github.com/mckinsey/vizro/pull/216
-matrix.python.features = [
-  {value = "kedro", if = ["3.9", "3.10", "3.11", "3.12"]}
-]
-
 [envs.changelog]
 dependencies = ["scriv"]
 detached = true
@@ -37,6 +30,7 @@ dependencies = [
   "pyhamcrest",
   "gunicorn"
 ]
+features = ["kedro"]
 installer = "uv"
 
 [envs.default.env-vars]
@@ -133,9 +127,9 @@ extra-dependencies = [
   "dash==2.18.0",
   "plotly==5.24.0",
   "pandas==2.0.0",
-  "numpy==1.23.0"  # Need numpy<2 to work with pandas==2.0.0. See https://stackoverflow.com/questions/78634235/.
+  "numpy==1.23.0",  # Need numpy<2 to work with pandas==2.0.0. See https://stackoverflow.com/questions/78634235/.
+  "kedro==0.19.9"
 ]
-features = ["kedro"]
 python = "3.9"
 
 [publish.index]
diff --git a/vizro-core/pyproject.toml b/vizro-core/pyproject.toml
index 2c69d6b98..3843c2dae 100644
--- a/vizro-core/pyproject.toml
+++ b/vizro-core/pyproject.toml
@@ -36,7 +36,7 @@ requires-python = ">=3.9"
 
 [project.optional-dependencies]
 kedro = [
-  "kedro>=0.17.3",
+  "kedro>=0.19.9",
   "kedro-datasets"  # no longer a dependency of kedro for kedro>=0.19.2
 ]
 
diff --git a/vizro-core/tests/unit/vizro/integrations/kedro/test_kedro_data_manager.py b/vizro-core/tests/unit/vizro/integrations/kedro/test_kedro_data_manager.py
index 8d52e2b22..473b9227a 100644
--- a/vizro-core/tests/unit/vizro/integrations/kedro/test_kedro_data_manager.py
+++ b/vizro-core/tests/unit/vizro/integrations/kedro/test_kedro_data_manager.py
@@ -6,12 +6,10 @@
 import pytest
 import yaml
 
-kedro = pytest.importorskip("kedro")
+import kedro.pipeline as kp
+from kedro.io import DataCatalog, KedroDataCatalog
 
-import kedro.pipeline as kp  # noqa: E402
-from kedro.io import DataCatalog, KedroDataCatalog  # noqa: E402
-
-from vizro.integrations.kedro import datasets_from_catalog  # noqa: E402
+from vizro.integrations.kedro import datasets_from_catalog 
 
 
 @pytest.fixture(params=[DataCatalog, KedroDataCatalog])

From 5b5d14889023bd05b0d1f2d7cabec88d85993c0c Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Tue, 11 Feb 2025 11:24:43 +0000
Subject: [PATCH 08/15] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 .../unit/vizro/integrations/kedro/test_kedro_data_manager.py | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/vizro-core/tests/unit/vizro/integrations/kedro/test_kedro_data_manager.py b/vizro-core/tests/unit/vizro/integrations/kedro/test_kedro_data_manager.py
index 473b9227a..55a6a4682 100644
--- a/vizro-core/tests/unit/vizro/integrations/kedro/test_kedro_data_manager.py
+++ b/vizro-core/tests/unit/vizro/integrations/kedro/test_kedro_data_manager.py
@@ -3,13 +3,12 @@
 import types
 from pathlib import Path
 
+import kedro.pipeline as kp
 import pytest
 import yaml
-
-import kedro.pipeline as kp
 from kedro.io import DataCatalog, KedroDataCatalog
 
-from vizro.integrations.kedro import datasets_from_catalog 
+from vizro.integrations.kedro import datasets_from_catalog
 
 
 @pytest.fixture(params=[DataCatalog, KedroDataCatalog])

From e96b96b0a50f841be6ec071d012d1a08904a5172 Mon Sep 17 00:00:00 2001
From: Antony Milne <49395058+antonymilne@users.noreply.github.com>
Date: Tue, 11 Feb 2025 11:29:02 +0000
Subject: [PATCH 09/15] Small docs update

---
 .../docs/pages/user-guides/kedro-data-catalog.md    | 13 -------------
 1 file changed, 13 deletions(-)

diff --git a/vizro-core/docs/pages/user-guides/kedro-data-catalog.md b/vizro-core/docs/pages/user-guides/kedro-data-catalog.md
index c43a78b70..580e34213 100644
--- a/vizro-core/docs/pages/user-guides/kedro-data-catalog.md
+++ b/vizro-core/docs/pages/user-guides/kedro-data-catalog.md
@@ -23,19 +23,6 @@ for dataset_name, dataset in kedro_integration.datasets_from_catalog(catalog).it
     data_manager[dataset_name] = dataset
 ```
 
-To add datasets that are defined using the [Kedro dataset factory](https://docs.kedro.org/en/stable/data/kedro_dataset_factories.html), `datasets_from_catalog` needs to access the pipelines that use them.
-
-```python
-from vizro.integrations import kedro as kedro_integration
-from vizro.managers import data_manager
-
-
-pipeline = pipelines.get("my_pipeline_name")
-
-for dataset_name, dataset_loader in kedro_integration.datasets_from_catalog(catalog, pipeline=pipeline).items():
-    data_manager[dataset_name] = dataset
-```
-
 This imports all datasets of type [`kedro_datasets.pandas`](https://docs.kedro.org/en/stable/kedro_datasets.html) from the Kedro `catalog` into the Vizro `data_manager`.
 
 The `catalog` variable may have been created in a number of different ways:

From 4399eb732470cb18116830f7883cdff08521f462 Mon Sep 17 00:00:00 2001
From: Antony Milne <49395058+antonymilne@users.noreply.github.com>
Date: Tue, 11 Feb 2025 11:49:34 +0000
Subject: [PATCH 10/15] Fix link

---
 vizro-core/docs/pages/explanation/faq.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/vizro-core/docs/pages/explanation/faq.md b/vizro-core/docs/pages/explanation/faq.md
index 95bed0a02..18a6dfa32 100644
--- a/vizro-core/docs/pages/explanation/faq.md
+++ b/vizro-core/docs/pages/explanation/faq.md
@@ -95,7 +95,7 @@ Any attempt at a high-level explanation must rely on an oversimplification that
 
 All are great entry points to the world of data apps. If you prefer a top-down scripting style, then Streamlit is a powerful approach. If you prefer full control and customization over callbacks and layouts, then Dash is a powerful approach. If you prefer a configuration approach with in-built best practices, and the potential for customization and scalability through Dash, then Vizro is a powerful approach.
 
-For a more detailed comparison, it may help to visit the introductory articles of [Dash](https://medium.com/plotly/introducing-dash-5ecf7191b503), [Streamlit](https://towardsdatascience.com/coding-ml-tools-like-you-code-ml-models-ddba3357eace) and [Vizro](https://quantumblack.medium.com/introducing-vizro-a-toolkit-for-creating-modular-data-visualization-applications-3a42f2bec4db), to see how each tool serves a distinct purpose, and could be the best tool of choice.
+For a more detailed comparison, it may help to read introductory articles about [Dash](https://medium.com/plotly/introducing-dash-5ecf7191b503), [Streamlit](https://blog.streamlit.io/streamlit-101-python-data-app/) and [Vizro](https://quantumblack.medium.com/introducing-vizro-a-toolkit-for-creating-modular-data-visualization-applications-3a42f2bec4db), to see how each tool serves a distinct purpose.
 
 ## How does Vizro compare with Python packages and business intelligence (BI) tools?
 

From 297f8da90b2b9b9a6d8157be8c34184a2058aca7 Mon Sep 17 00:00:00 2001
From: Guillaume Tauzin <4648633+gtauzin@users.noreply.github.com>
Date: Tue, 11 Feb 2025 17:34:04 +0100
Subject: [PATCH 11/15] Apply suggestions from code review

Co-authored-by: Petar Pejovic <108530920+petar-qb@users.noreply.github.com>
---
 vizro-core/src/vizro/integrations/kedro/_data_manager.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/vizro-core/src/vizro/integrations/kedro/_data_manager.py b/vizro-core/src/vizro/integrations/kedro/_data_manager.py
index 49f848c73..ab5773f2a 100644
--- a/vizro-core/src/vizro/integrations/kedro/_data_manager.py
+++ b/vizro-core/src/vizro/integrations/kedro/_data_manager.py
@@ -31,7 +31,7 @@ def datasets_from_catalog(catalog: CatalogProtocol, *, pipeline: Pipeline = None
     config_resolver = catalog.config_resolver
     kedro_datasets = config_resolver.config.copy()
 
-    if pipeline is not None:
+    if pipeline:
         # Go through all dataset names that weren't in catalog and try to resolve them. Those that cannot be
         # resolved give an empty dictionary and are ignored.
         for dataset_name in set(pipeline.datasets()) - set(kedro_datasets):

From b7597e43e1e927130a520925ba5c9f121f1fd82e Mon Sep 17 00:00:00 2001
From: Antony Milne <antony.milne@quantumblack.com>
Date: Tue, 11 Feb 2025 16:26:35 +0000
Subject: [PATCH 12/15] Unrelated: use packaging for vizro version check

---
 vizro-core/pyproject.toml           | 3 ++-
 vizro-core/src/vizro/__init__.py    | 5 ++++-
 vizro-core/src/vizro/_vizro.py      | 4 +++-
 vizro-core/tests/unit/test_vizro.py | 3 ++-
 4 files changed, 11 insertions(+), 4 deletions(-)

diff --git a/vizro-core/pyproject.toml b/vizro-core/pyproject.toml
index 3843c2dae..a58dad1fb 100644
--- a/vizro-core/pyproject.toml
+++ b/vizro-core/pyproject.toml
@@ -25,7 +25,8 @@ dependencies = [
   "flask_caching>=2",
   "wrapt>=1",
   "black",
-  "autoflake"
+  "autoflake",
+  "packaging"
 ]
 description = "Vizro is a package to facilitate visual analytics."
 dynamic = ["version"]
diff --git a/vizro-core/src/vizro/__init__.py b/vizro-core/src/vizro/__init__.py
index 0e7291a86..598e75420 100644
--- a/vizro-core/src/vizro/__init__.py
+++ b/vizro-core/src/vizro/__init__.py
@@ -5,6 +5,7 @@
 
 import plotly.io as pio
 from dash.development.base_component import ComponentRegistry
+from packaging.version import parse
 
 from ._constants import VIZRO_ASSETS_PATH
 from ._vizro import Vizro, _make_resource_spec
@@ -23,7 +24,9 @@
 # This would only be the case where you need to test something with serve_locally=False and have changed
 # assets compared to main. In this case you need to push your assets changes to remote for the CDN to update,
 # and it might also be necessary to clear the CDN cache: https://www.jsdelivr.com/tools/purge.
-_git_branch = __version__ if "dev" not in __version__ else "main"
+
+
+_git_branch = __version__ if not parse(__version__).is_devrelease else "main"
 BASE_EXTERNAL_URL = f"https://cdn.jsdelivr.net/gh/mckinsey/vizro@{_git_branch}/vizro-core/src/vizro/"
 # Enables the use of our own Bootstrap theme in a pure Dash app with `external_stylesheets=vizro.bootstrap`.
 bootstrap = f"{BASE_EXTERNAL_URL}static/css/vizro-bootstrap.min.css"
diff --git a/vizro-core/src/vizro/_vizro.py b/vizro-core/src/vizro/_vizro.py
index 69192056f..5c0a7e40b 100644
--- a/vizro-core/src/vizro/_vizro.py
+++ b/vizro-core/src/vizro/_vizro.py
@@ -11,6 +11,7 @@
 import plotly.io as pio
 from dash.development.base_component import ComponentRegistry
 from flask_caching import SimpleCache
+from packaging.version import parse
 
 import vizro
 from vizro._constants import VIZRO_ASSETS_PATH
@@ -209,7 +210,8 @@ def _make_resource_spec(path: Path) -> _ResourceSpec:
     # This would only be the case where you need to test something with serve_locally=False and have changed
     # assets compared to main. In this case you need to push your assets changes to remote for the CDN to update,
     # and it might also be necessary to clear the CDN cache: https://www.jsdelivr.com/tools/purge.
-    _git_branch = vizro.__version__ if "dev" not in vizro.__version__ else "main"
+
+    _git_branch = vizro.__version__ if not parse(vizro.__version__).is_devrelease else "main"
     BASE_EXTERNAL_URL = f"https://cdn.jsdelivr.net/gh/mckinsey/vizro@{_git_branch}/vizro-core/src/vizro/"
 
     # Get path relative to the vizro package root, where this file resides.
diff --git a/vizro-core/tests/unit/test_vizro.py b/vizro-core/tests/unit/test_vizro.py
index 7b94b2050..edebe0c81 100644
--- a/vizro-core/tests/unit/test_vizro.py
+++ b/vizro-core/tests/unit/test_vizro.py
@@ -2,11 +2,12 @@
 
 import dash
 import pytest
+from packaging.version import parse
 
 import vizro
 from vizro._constants import VIZRO_ASSETS_PATH
 
-_git_branch = vizro.__version__ if "dev" not in vizro.__version__ else "main"
+_git_branch = vizro.__version__ if not parse(vizro.__version__).is_devrelease else "main"
 
 
 def test_vizro_bootstrap():

From 0514fe3cc6f97d8a3f585a1fdd7fb485c6c3af91 Mon Sep 17 00:00:00 2001
From: Antony Milne <antony.milne@quantumblack.com>
Date: Tue, 11 Feb 2025 17:00:49 +0000
Subject: [PATCH 13/15] Ensure compatibility with kedro>=0.19.0

---
 .../20250208_114146_4648633+gtauzin.md        |  4 +--
 vizro-core/hatch.toml                         |  2 +-
 vizro-core/pyproject.toml                     |  2 +-
 .../vizro/integrations/kedro/_data_manager.py | 28 +++++++++++++++++--
 .../kedro/test_kedro_data_manager.py          | 25 +++++++++++++++--
 5 files changed, 52 insertions(+), 9 deletions(-)

diff --git a/vizro-core/changelog.d/20250208_114146_4648633+gtauzin.md b/vizro-core/changelog.d/20250208_114146_4648633+gtauzin.md
index f0d9ea8ef..dcf3384ca 100644
--- a/vizro-core/changelog.d/20250208_114146_4648633+gtauzin.md
+++ b/vizro-core/changelog.d/20250208_114146_4648633+gtauzin.md
@@ -18,11 +18,11 @@ Uncomment the section that is right (remove the HTML comment wrapper).
 -->
 ### Added
 
-- Kedro integration function `datasets_from_catalog` can now handle dataset factories. ([#1001](https://github.com/mckinsey/vizro/pull/1001))
+- Kedro integration function `datasets_from_catalog` can now handle dataset factories for `kedro>=0.19.9`. ([#1001](https://github.com/mckinsey/vizro/pull/1001))
 
 ### Changed
 
-- Bump optional dependency lower bound to `kedro>=0.19.9`. ([#1001](https://github.com/mckinsey/vizro/pull/1001))
+- Bump optional dependency lower bound to `kedro>=0.19.0`. ([#1001](https://github.com/mckinsey/vizro/pull/1001))
 
 <!--
 ### Deprecated
diff --git a/vizro-core/hatch.toml b/vizro-core/hatch.toml
index b5fc32958..d07f5fd16 100644
--- a/vizro-core/hatch.toml
+++ b/vizro-core/hatch.toml
@@ -128,7 +128,7 @@ extra-dependencies = [
   "plotly==5.24.0",
   "pandas==2.0.0",
   "numpy==1.23.0",  # Need numpy<2 to work with pandas==2.0.0. See https://stackoverflow.com/questions/78634235/.
-  "kedro==0.19.9"
+  "kedro==0.19.0",  # Includes kedro-datasets as a dependency.
 ]
 python = "3.9"
 
diff --git a/vizro-core/pyproject.toml b/vizro-core/pyproject.toml
index a58dad1fb..a04cba8b3 100644
--- a/vizro-core/pyproject.toml
+++ b/vizro-core/pyproject.toml
@@ -37,7 +37,7 @@ requires-python = ">=3.9"
 
 [project.optional-dependencies]
 kedro = [
-  "kedro>=0.19.9",
+  "kedro>=0.19.0",
   "kedro-datasets"  # no longer a dependency of kedro for kedro>=0.19.2
 ]
 
diff --git a/vizro-core/src/vizro/integrations/kedro/_data_manager.py b/vizro-core/src/vizro/integrations/kedro/_data_manager.py
index ab5773f2a..7e6a40b30 100644
--- a/vizro-core/src/vizro/integrations/kedro/_data_manager.py
+++ b/vizro-core/src/vizro/integrations/kedro/_data_manager.py
@@ -1,13 +1,21 @@
+from __future__ import annotations
+
+from importlib.metadata import version
+
+from packaging.version import parse
 from pathlib import Path
-from typing import Any, Optional, Union
+from typing import Any, Optional, Union, TYPE_CHECKING
 
 from kedro.framework.session import KedroSession
 from kedro.framework.startup import bootstrap_project
-from kedro.io import CatalogProtocol
+
 from kedro.pipeline import Pipeline
 
 from vizro.managers._data_manager import pd_DataFrameCallable
 
+if TYPE_CHECKING:
+    from kedro.io import CatalogProtocol
+
 
 def catalog_from_project(
     project_path: Union[str, Path], env: Optional[str] = None, extra_params: Optional[dict[str, Any]] = None
@@ -26,7 +34,23 @@ def pipelines_from_project(project_path: Union[str, Path]) -> Pipeline:
     return pipelines
 
 
+def _legacy_datasets_from_catalog(catalog: CatalogProtocol) -> dict[str, pd_DataFrameCallable]:
+    # The old version of datasets_from_catalog from before https://github.com/mckinsey/vizro/pull/1001.
+    # This does not support dataset factories.
+    # We keep this version to maintain backwards compatibility with 0.19.0 <= kedro < 0.19.9.
+    # Note the pipeline argument does not exist.
+    datasets = {}
+    for name in catalog.list():
+        dataset = catalog._get_dataset(name, suggest=False)
+        if "pandas" in dataset.__module__:
+            datasets[name] = dataset.load
+    return datasets
+
+
 def datasets_from_catalog(catalog: CatalogProtocol, *, pipeline: Pipeline = None) -> dict[str, pd_DataFrameCallable]:
+    if parse(version("kedro")) < parse("0.19.9"):
+        return _legacy_datasets_from_catalog(catalog)
+
     # This doesn't include things added to the catalog at run time but that is ok for our purposes.
     config_resolver = catalog.config_resolver
     kedro_datasets = config_resolver.config.copy()
diff --git a/vizro-core/tests/unit/vizro/integrations/kedro/test_kedro_data_manager.py b/vizro-core/tests/unit/vizro/integrations/kedro/test_kedro_data_manager.py
index 55a6a4682..8891358e6 100644
--- a/vizro-core/tests/unit/vizro/integrations/kedro/test_kedro_data_manager.py
+++ b/vizro-core/tests/unit/vizro/integrations/kedro/test_kedro_data_manager.py
@@ -1,17 +1,29 @@
 """Unit tests for vizro.integrations.kedro."""
 
 import types
+from packaging.version import parse
 from pathlib import Path
 
 import kedro.pipeline as kp
 import pytest
 import yaml
-from kedro.io import DataCatalog, KedroDataCatalog
+import kedro
+from kedro.io import DataCatalog
+
+from importlib.metadata import version
 
 from vizro.integrations.kedro import datasets_from_catalog
 
+if parse(version("kedro")) >= parse("0.19.9"):
+    # KedroDataCatalog only exists and hence can only be tested against in kedro>=0.19.9.
+    from kedro.io import KedroDataCatalog
+
+    data_catalog_classes = [DataCatalog, KedroDataCatalog]
+else:
+    data_catalog_classes = [DataCatalog]
+
 
-@pytest.fixture(params=[DataCatalog, KedroDataCatalog])
+@pytest.fixture(params=data_catalog_classes)
 def catalog(request):
     catalog_class = request.param
     catalog_path = Path(__file__).parent / "fixtures/test_catalog.yaml"
@@ -46,4 +58,11 @@ def test_datasets_from_catalog_with_pipeline(catalog):
     )
 
     datasets = datasets_from_catalog(catalog, pipeline=pipeline)
-    assert set(datasets) == {"pandas_excel", "pandas_parquet", "something#csv"}
+    # Dataset factories only work for kedro>=0.19.9.
+    expected_datasets = (
+        {"pandas_excel", "pandas_parquet", "something#csv"}
+        if parse(version("kedro")) >= parse("0.19.9")
+        else {"pandas_excel", "pandas_parquet"}
+    )
+
+    assert set(datasets) == expected_datasets

From 05c3a32575c9ee878cec8623f4bb53c68cfdf656 Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Tue, 11 Feb 2025 17:16:12 +0000
Subject: [PATCH 14/15] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 vizro-core/hatch.toml                                       | 2 +-
 vizro-core/src/vizro/integrations/kedro/_data_manager.py    | 6 ++----
 .../vizro/integrations/kedro/test_kedro_data_manager.py     | 6 ++----
 3 files changed, 5 insertions(+), 9 deletions(-)

diff --git a/vizro-core/hatch.toml b/vizro-core/hatch.toml
index d07f5fd16..c3085ab89 100644
--- a/vizro-core/hatch.toml
+++ b/vizro-core/hatch.toml
@@ -128,7 +128,7 @@ extra-dependencies = [
   "plotly==5.24.0",
   "pandas==2.0.0",
   "numpy==1.23.0",  # Need numpy<2 to work with pandas==2.0.0. See https://stackoverflow.com/questions/78634235/.
-  "kedro==0.19.0",  # Includes kedro-datasets as a dependency.
+  "kedro==0.19.0"  # Includes kedro-datasets as a dependency.
 ]
 python = "3.9"
 
diff --git a/vizro-core/src/vizro/integrations/kedro/_data_manager.py b/vizro-core/src/vizro/integrations/kedro/_data_manager.py
index 7e6a40b30..cc7c1d0dc 100644
--- a/vizro-core/src/vizro/integrations/kedro/_data_manager.py
+++ b/vizro-core/src/vizro/integrations/kedro/_data_manager.py
@@ -1,15 +1,13 @@
 from __future__ import annotations
 
 from importlib.metadata import version
-
-from packaging.version import parse
 from pathlib import Path
-from typing import Any, Optional, Union, TYPE_CHECKING
+from typing import TYPE_CHECKING, Any, Optional, Union
 
 from kedro.framework.session import KedroSession
 from kedro.framework.startup import bootstrap_project
-
 from kedro.pipeline import Pipeline
+from packaging.version import parse
 
 from vizro.managers._data_manager import pd_DataFrameCallable
 
diff --git a/vizro-core/tests/unit/vizro/integrations/kedro/test_kedro_data_manager.py b/vizro-core/tests/unit/vizro/integrations/kedro/test_kedro_data_manager.py
index 8891358e6..8600b46b6 100644
--- a/vizro-core/tests/unit/vizro/integrations/kedro/test_kedro_data_manager.py
+++ b/vizro-core/tests/unit/vizro/integrations/kedro/test_kedro_data_manager.py
@@ -1,16 +1,14 @@
 """Unit tests for vizro.integrations.kedro."""
 
 import types
-from packaging.version import parse
+from importlib.metadata import version
 from pathlib import Path
 
 import kedro.pipeline as kp
 import pytest
 import yaml
-import kedro
 from kedro.io import DataCatalog
-
-from importlib.metadata import version
+from packaging.version import parse
 
 from vizro.integrations.kedro import datasets_from_catalog
 

From 177e3196f0af388fb52e37dbd4835d764048e7fd Mon Sep 17 00:00:00 2001
From: Antony Milne <49395058+antonymilne@users.noreply.github.com>
Date: Wed, 12 Feb 2025 10:10:22 +0000
Subject: [PATCH 15/15] Apply suggestions from code review

---
 vizro-core/changelog.d/20250208_114146_4648633+gtauzin.md     | 2 +-
 vizro-core/src/vizro/__init__.py                              | 2 --
 vizro-core/src/vizro/_vizro.py                                | 1 -
 .../unit/vizro/integrations/kedro/fixtures/test_catalog.yaml  | 2 +-
 .../unit/vizro/integrations/kedro/test_kedro_data_manager.py  | 4 ++--
 5 files changed, 4 insertions(+), 7 deletions(-)

diff --git a/vizro-core/changelog.d/20250208_114146_4648633+gtauzin.md b/vizro-core/changelog.d/20250208_114146_4648633+gtauzin.md
index dcf3384ca..ef5651e55 100644
--- a/vizro-core/changelog.d/20250208_114146_4648633+gtauzin.md
+++ b/vizro-core/changelog.d/20250208_114146_4648633+gtauzin.md
@@ -18,7 +18,7 @@ Uncomment the section that is right (remove the HTML comment wrapper).
 -->
 ### Added
 
-- Kedro integration function `datasets_from_catalog` can now handle dataset factories for `kedro>=0.19.9`. ([#1001](https://github.com/mckinsey/vizro/pull/1001))
+- Kedro integration function `datasets_from_catalog` can handle dataset factories for `kedro>=0.19.9`. ([#1001](https://github.com/mckinsey/vizro/pull/1001))
 
 ### Changed
 
diff --git a/vizro-core/src/vizro/__init__.py b/vizro-core/src/vizro/__init__.py
index 598e75420..0cd833bb7 100644
--- a/vizro-core/src/vizro/__init__.py
+++ b/vizro-core/src/vizro/__init__.py
@@ -24,8 +24,6 @@
 # This would only be the case where you need to test something with serve_locally=False and have changed
 # assets compared to main. In this case you need to push your assets changes to remote for the CDN to update,
 # and it might also be necessary to clear the CDN cache: https://www.jsdelivr.com/tools/purge.
-
-
 _git_branch = __version__ if not parse(__version__).is_devrelease else "main"
 BASE_EXTERNAL_URL = f"https://cdn.jsdelivr.net/gh/mckinsey/vizro@{_git_branch}/vizro-core/src/vizro/"
 # Enables the use of our own Bootstrap theme in a pure Dash app with `external_stylesheets=vizro.bootstrap`.
diff --git a/vizro-core/src/vizro/_vizro.py b/vizro-core/src/vizro/_vizro.py
index 5c0a7e40b..fc69ef479 100644
--- a/vizro-core/src/vizro/_vizro.py
+++ b/vizro-core/src/vizro/_vizro.py
@@ -210,7 +210,6 @@ def _make_resource_spec(path: Path) -> _ResourceSpec:
     # This would only be the case where you need to test something with serve_locally=False and have changed
     # assets compared to main. In this case you need to push your assets changes to remote for the CDN to update,
     # and it might also be necessary to clear the CDN cache: https://www.jsdelivr.com/tools/purge.
-
     _git_branch = vizro.__version__ if not parse(vizro.__version__).is_devrelease else "main"
     BASE_EXTERNAL_URL = f"https://cdn.jsdelivr.net/gh/mckinsey/vizro@{_git_branch}/vizro-core/src/vizro/"
 
diff --git a/vizro-core/tests/unit/vizro/integrations/kedro/fixtures/test_catalog.yaml b/vizro-core/tests/unit/vizro/integrations/kedro/fixtures/test_catalog.yaml
index 708b115b3..2e0049ef2 100644
--- a/vizro-core/tests/unit/vizro/integrations/kedro/fixtures/test_catalog.yaml
+++ b/vizro-core/tests/unit/vizro/integrations/kedro/fixtures/test_catalog.yaml
@@ -1,6 +1,6 @@
 "{pandas_factory}#csv":
   type: pandas.CSVDataset
-  filepath: ./{pandas_factory}.csv
+  filepath: "{pandas_factory}.csv"
 
 pandas_excel:
   type: pandas.ExcelDataset
diff --git a/vizro-core/tests/unit/vizro/integrations/kedro/test_kedro_data_manager.py b/vizro-core/tests/unit/vizro/integrations/kedro/test_kedro_data_manager.py
index 8600b46b6..791f6f22a 100644
--- a/vizro-core/tests/unit/vizro/integrations/kedro/test_kedro_data_manager.py
+++ b/vizro-core/tests/unit/vizro/integrations/kedro/test_kedro_data_manager.py
@@ -44,9 +44,9 @@ def test_datasets_from_catalog_with_pipeline(catalog):
                 inputs=[
                     "pandas_excel",
                     "something#csv",
+                    "something_else#csv",
                     "not_dataframe",
                     "not_in_catalog",
-                    "pandas_parquet",
                     "parameters",
                     "params:z",
                 ],
@@ -58,7 +58,7 @@ def test_datasets_from_catalog_with_pipeline(catalog):
     datasets = datasets_from_catalog(catalog, pipeline=pipeline)
     # Dataset factories only work for kedro>=0.19.9.
     expected_datasets = (
-        {"pandas_excel", "pandas_parquet", "something#csv"}
+        {"pandas_excel", "pandas_parquet", "something#csv", "something_else#csv"}
         if parse(version("kedro")) >= parse("0.19.9")
         else {"pandas_excel", "pandas_parquet"}
     )