Merge branch 'main' into noklam/devops

kedro-org · Jul 22, 2024 · 80715d5 · 80715d5
2 parents bbe227b + 142342d
commit 80715d5
Show file tree

Hide file tree

Showing 23 changed files with 684 additions and 285 deletions.
diff --git a/.github/workflows/e2e-tests.yml b/.github/workflows/e2e-tests.yml
@@ -12,8 +12,6 @@ on:
 
 jobs:
   e2e-tests:
-    env:
-      UV_HTTP_TIMEOUT: 1000
     defaults:
       run:
         shell: bash
@@ -33,7 +31,7 @@ jobs:
           restore-keys: ${{inputs.plugin}}
       - name: Install uv
         run: |
-          python -m pip install "uv==0.1.13"
+          python -m pip install "uv==0.2.21"
       - name: Install dependencies
         run: |
           cd ${{ inputs.plugin }}

diff --git a/.github/workflows/kedro-datasets.yml b/.github/workflows/kedro-datasets.yml
@@ -38,8 +38,6 @@ jobs:
 
   check-docs:
     runs-on: ubuntu-latest
-    env:
-      UV_HTTP_TIMEOUT: 1000
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
@@ -55,7 +53,7 @@ jobs:
           restore-keys: kedro-datasets
       - name: Install uv
         run: |
-          python -m pip install "uv==0.1.13"
+          python -m pip install "uv==0.2.21"
       - name: Install dependencies
         run: |
           cd kedro-datasets

diff --git a/.github/workflows/lint.yml b/.github/workflows/lint.yml
@@ -12,8 +12,6 @@ on:
 
 jobs:
   lint:
-    env:
-      UV_HTTP_TIMEOUT: 1000
     defaults:
       run:
         shell: bash
@@ -33,7 +31,7 @@ jobs:
           restore-keys: ${{inputs.plugin}}
       - name: Install uv
         run: |
-          python -m pip install "uv==0.1.13"
+          python -m pip install "uv==0.2.21"
       - name: Install dependencies
         run: |
             cd ${{ inputs.plugin }}

diff --git a/.github/workflows/unit-tests.yml b/.github/workflows/unit-tests.yml
@@ -14,8 +14,6 @@ jobs:
 
   unit-tests:
     runs-on: ${{ inputs.os }}
-    env:
-      UV_HTTP_TIMEOUT: 1000
     defaults:
       run:
         shell: bash
@@ -45,7 +43,7 @@ jobs:
         uses: microsoft/setup-msbuild@v2
       - name: Install uv
         run: |
-          python -m pip install "uv==0.1.13"
+          python -m pip install "uv==0.2.21"
       - name: Install dependencies
         run: |
           cd ${{ inputs.plugin }}

diff --git a/kedro-datasets/RELEASE.md b/kedro-datasets/RELEASE.md
@@ -1,5 +1,11 @@
 # Upcoming Release
 ## Major features and improvements
+## Bug fixes and other changes
+## Breaking Changes
+## Community contributions
+
+# Release 4.0.0
+## Major features and improvements
 
 * Added the following new **experimental** datasets:
 
@@ -9,21 +15,34 @@
 | `langchain.ChatCohereDataset`       | A dataset for loading a ChatCohere langchain model.       | `kedro_datasets_experimental.langchain` |
 | `langchain.OpenAIEmbeddingsDataset` | A dataset for loading a OpenAIEmbeddings langchain model. | `kedro_datasets_experimental.langchain` |
 | `langchain.ChatOpenAIDataset`       | A dataset for loading a ChatOpenAI langchain model.       | `kedro_datasets_experimental.langchain` |
+| `rioxarray.GeoTIFFDataset`          | A dataset for loading and saving geotiff raster data      | `kedro_datasets_experimental.rioxarray` |
 | `netcdf.NetCDFDataset`              | A dataset for loading and saving "*.nc" files.            | `kedro_datasets_experimental.netcdf` |
-* `netcdf.NetCDFDataset` moved from `kedro_datasets` to `kedro_datasets_experimental`.
 
 * Added the following new core datasets:
+
 | Type                                | Description                                               | Location                                |
 |-------------------------------------|-----------------------------------------------------------|-----------------------------------------|
 | `dask.CSVDataset`    | A dataset for loading a CSV files using `dask`    | `kedro_datasets.dask` |
 
 * Extended preview feature to `yaml.YAMLDataset`.
 
+## Bug fixes and other changes
+* Added `metadata` parameter for a few datasets
+
+## Breaking Changes
+* `netcdf.NetCDFDataset` moved from `kedro_datasets` to `kedro_datasets_experimental`.
+
 ## Community contributions
 
 Many thanks to the following Kedroids for contributing PRs to this release:
+* [Ian Whalen](https://github.com/ianwhale)
+* [Charles Guan](https://github.com/charlesbmi)
+* [Thomas Gölles](https://github.com/tgoelles)
 * [Lukas Innig](https://github.com/derluke)
 * [Michael Sexton](https://github.com/michaelsexton)
+* [michal-mmm](https://github.com/michal-mmm)
+
+
 
 
 # Release 3.0.1

diff --git a/kedro-datasets/docs/source/api/kedro_datasets.rst b/kedro-datasets/docs/source/api/kedro_datasets.rst
@@ -11,56 +11,56 @@ kedro_datasets
    :toctree:
    :template: autosummary/class.rst
 
-   kedro_datasets.api.APIDataset
-   kedro_datasets.biosequence.BioSequenceDataset
-   kedro_datasets.dask.CSVDataset
-   kedro_datasets.dask.ParquetDataset
-   kedro_datasets.databricks.ManagedTableDataset
-   kedro_datasets.email.EmailMessageDataset
-   kedro_datasets.geopandas.GeoJSONDataset
-   kedro_datasets.holoviews.HoloviewsWriter
-   kedro_datasets.huggingface.HFDataset
-   kedro_datasets.huggingface.HFTransformerPipelineDataset
-   kedro_datasets.ibis.TableDataset
-   kedro_datasets.json.JSONDataset
-   kedro_datasets.matlab.MatlabDataset
-   kedro_datasets.matplotlib.MatplotlibWriter
-   kedro_datasets.networkx.GMLDataset
-   kedro_datasets.networkx.GraphMLDataset
-   kedro_datasets.networkx.JSONDataset
-   kedro_datasets.pandas.CSVDataset
-   kedro_datasets.pandas.DeltaTableDataset
-   kedro_datasets.pandas.ExcelDataset
-   kedro_datasets.pandas.FeatherDataset
-   kedro_datasets.pandas.GBQQueryDataset
-   kedro_datasets.pandas.GBQTableDataset
-   kedro_datasets.pandas.GenericDataset
-   kedro_datasets.pandas.HDFDataset
-   kedro_datasets.pandas.JSONDataset
-   kedro_datasets.pandas.ParquetDataset
-   kedro_datasets.pandas.SQLQueryDataset
-   kedro_datasets.pandas.SQLTableDataset
-   kedro_datasets.pandas.XMLDataset
-   kedro_datasets.partitions.IncrementalDataset
-   kedro_datasets.partitions.PartitionedDataset
-   kedro_datasets.pickle.PickleDataset
-   kedro_datasets.pillow.ImageDataset
-   kedro_datasets.plotly.JSONDataset
-   kedro_datasets.plotly.PlotlyDataset
-   kedro_datasets.polars.CSVDataset
-   kedro_datasets.polars.EagerPolarsDataset
-   kedro_datasets.polars.LazyPolarsDataset
-   kedro_datasets.redis.PickleDataset
-   kedro_datasets.snowflake.SnowparkTableDataset
-   kedro_datasets.spark.DeltaTableDataset
-   kedro_datasets.spark.SparkDataset
-   kedro_datasets.spark.SparkHiveDataset
-   kedro_datasets.spark.SparkJDBCDataset
-   kedro_datasets.spark.SparkStreamingDataset
-   kedro_datasets.svmlight.SVMLightDataset
-   kedro_datasets.tensorflow.TensorFlowModelDataset
-   kedro_datasets.text.TextDataset
-   kedro_datasets.tracking.JSONDataset
-   kedro_datasets.tracking.MetricsDataset
-   kedro_datasets.video.VideoDataset
-   kedro_datasets.yaml.YAMLDataset
+   api.APIDataset
+   biosequence.BioSequenceDataset
+   dask.CSVDataset
+   dask.ParquetDataset
+   databricks.ManagedTableDataset
+   email.EmailMessageDataset
+   geopandas.GeoJSONDataset
+   holoviews.HoloviewsWriter
+   huggingface.HFDataset
+   huggingface.HFTransformerPipelineDataset
+   ibis.TableDataset
+   json.JSONDataset
+   matlab.MatlabDataset
+   matplotlib.MatplotlibWriter
+   networkx.GMLDataset
+   networkx.GraphMLDataset
+   networkx.JSONDataset
+   pandas.CSVDataset
+   pandas.DeltaTableDataset
+   pandas.ExcelDataset
+   pandas.FeatherDataset
+   pandas.GBQQueryDataset
+   pandas.GBQTableDataset
+   pandas.GenericDataset
+   pandas.HDFDataset
+   pandas.JSONDataset
+   pandas.ParquetDataset
+   pandas.SQLQueryDataset
+   pandas.SQLTableDataset
+   pandas.XMLDataset
+   partitions.IncrementalDataset
+   partitions.PartitionedDataset
+   pickle.PickleDataset
+   pillow.ImageDataset
+   plotly.JSONDataset
+   plotly.PlotlyDataset
+   polars.CSVDataset
+   polars.EagerPolarsDataset
+   polars.LazyPolarsDataset
+   redis.PickleDataset
+   snowflake.SnowparkTableDataset
+   spark.DeltaTableDataset
+   spark.SparkDataset
+   spark.SparkHiveDataset
+   spark.SparkJDBCDataset
+   spark.SparkStreamingDataset
+   svmlight.SVMLightDataset
+   tensorflow.TensorFlowModelDataset
+   text.TextDataset
+   tracking.JSONDataset
+   tracking.MetricsDataset
+   video.VideoDataset
+   yaml.YAMLDataset
diff --git a/kedro-datasets/docs/source/api/kedro_datasets_experimental.rst b/kedro-datasets/docs/source/api/kedro_datasets_experimental.rst
@@ -11,8 +11,9 @@ kedro_datasets_experimental
    :toctree:
    :template: autosummary/class.rst
 
-    kedro_datasets_experimental.langchain.ChatAnthropicDataset
-    kedro_datasets_experimental.langchain.ChatCohereDataset
-    kedro_datasets_experimental.langchain.ChatOpenAIDataset
-    kedro_datasets_experimental.langchain.OpenAIEmbeddingsDataset
-    kedro_datasets_experimental.netcdf.NetCDFDataset
+   langchain.ChatAnthropicDataset
+   langchain.ChatCohereDataset
+   langchain.ChatOpenAIDataset
+   langchain.OpenAIEmbeddingsDataset
+   netcdf.NetCDFDataset
+   rioxarray.GeoTIFFDataset
diff --git a/kedro-datasets/kedro_datasets/__init__.py b/kedro-datasets/kedro_datasets/__init__.py
@@ -1,7 +1,7 @@
 """``kedro_datasets`` is where you can find all of Kedro's data connectors."""
 
 __all__ = ["KedroDeprecationWarning"]
-__version__ = "3.0.1"
+__version__ = "4.0.0"
 
 import sys
 import warnings

diff --git a/kedro-datasets/kedro_datasets_experimental/rioxarray/__init__.py b/kedro-datasets/kedro_datasets_experimental/rioxarray/__init__.py
@@ -0,0 +1,13 @@
+"""``AbstractDataset`` implementation to load/save data from/to a geospatial raster files."""
+from __future__ import annotations
+
+from typing import Any
+
+import lazy_loader as lazy
+
+# https://github.com/pylint-dev/pylint/issues/4300#issuecomment-1043601901
+GeoTIFFDataset: Any
+
+__getattr__, __dir__, __all__ = lazy.attach(
+    __name__, submod_attrs={"geotiff_dataset": ["GeoTIFFDataset"]}
+)