Validate code snippets in datasets documentation - Part 1

kedro/extras/datasets/email/message_dataset.py

@@ -46,7 +46,6 @@ class EmailMessageDataSet(
         >>> msg["From"] = '"sin studly17"'
         >>> msg["To"] = '"strong bad"'
         >>>
-        >>> # data_set = EmailMessageDataSet(filepath="gcs://bucket/test")
         >>> data_set = EmailMessageDataSet(filepath="test")
         >>> data_set.save(msg)
         >>> reloaded = data_set.load()

kedro/extras/datasets/geopandas/geojson_dataset.py

@@ -37,10 +37,7 @@ class GeoJSONDataSet(
         >>>
         >>> data = gpd.GeoDataFrame({'col1': [1, 2], 'col2': [4, 5],
         >>>                      'col3': [5, 6]}, geometry=[Point(1,1), Point(2,4)])
-        >>> # data_set = GeoJSONDataSet(filepath="gcs://bucket/test.geojson",
-        >>>                                save_args=None)
-        >>> data_set = GeoJSONDataSet(filepath="test.geojson",
-        >>>                                save_args=None)
+        >>> data_set = GeoJSONDataSet(filepath="test.geojson", save_args=None)
         >>> data_set.save(data)
         >>> reloaded = data_set.load()
         >>>

kedro/extras/datasets/json/json_dataset.py

@@ -28,17 +28,13 @@ class JSONDataSet(AbstractVersionedDataSet[Any, Any]):
         >>> json_dataset:
         >>>   type: json.JSONDataSet
         >>>   filepath: data/01_raw/location.json
-        >>>   load_args:
-        >>>     lines: True
         >>>
         >>> cars:
         >>>   type: json.JSONDataSet
         >>>   filepath: gcs://your_bucket/cars.json
         >>>   fs_args:
         >>>     project: my-project
         >>>   credentials: my_gcp_credentials
-        >>>   load_args:
-        >>>     lines: True
 
     Example using Python API:
     ::
@@ -47,7 +43,6 @@ class JSONDataSet(AbstractVersionedDataSet[Any, Any]):
         >>>
         >>> data = {'col1': [1, 2], 'col2': [4, 5], 'col3': [5, 6]}
         >>>
-        >>> # data_set = JSONDataSet(filepath="gcs://bucket/test.json")
         >>> data_set = JSONDataSet(filepath="test.json")
         >>> data_set.save(data)
         >>> reloaded = data_set.load()

kedro/extras/datasets/pandas/csv_dataset.py

@@ -60,7 +60,6 @@ class CSVDataSet(AbstractVersionedDataSet[pd.DataFrame, pd.DataFrame]):
         >>> data = pd.DataFrame({'col1': [1, 2], 'col2': [4, 5],
         >>>                      'col3': [5, 6]})
         >>>
-        >>> # data_set = CSVDataSet(filepath="gcs://bucket/test.csv")
         >>> data_set = CSVDataSet(filepath="test.csv")
         >>> data_set.save(data)
         >>> reloaded = data_set.load()

kedro/extras/datasets/pandas/excel_dataset.py

@@ -59,7 +59,6 @@ class ExcelDataSet(
         >>> data = pd.DataFrame({'col1': [1, 2], 'col2': [4, 5],
         >>>                      'col3': [5, 6]})
         >>>
-        >>> # data_set = ExcelDataSet(filepath="gcs://bucket/test.xlsx")
         >>> data_set = ExcelDataSet(filepath="test.xlsx")
         >>> data_set.save(data)
         >>> reloaded = data_set.load()

kedro/extras/datasets/pandas/feather_dataset.py

@@ -37,7 +37,6 @@ class FeatherDataSet(AbstractVersionedDataSet[pd.DataFrame, pd.DataFrame]):
         >>> data = pd.DataFrame({'col1': [1, 2], 'col2': [4, 5],
         >>>                      'col3': [5, 6]})
         >>>
-        >>> # data_set = FeatherDataSet(filepath="gcs://bucket/test.feather")
         >>> data_set = FeatherDataSet(filepath="test.feather")
         >>>
         >>> data_set.save(data)

kedro/extras/datasets/pandas/generic_dataset.py

@@ -73,7 +73,6 @@ class GenericDataSet(AbstractVersionedDataSet[pd.DataFrame, pd.DataFrame]):
         >>> data = pd.DataFrame({'col1': [1, 2], 'col2': [4, 5],
         >>>                      'col3': [5, 6]})
         >>>
-        >>> # data_set = GenericDataSet(filepath="s3://test.csv", file_format='csv')
         >>> data_set = GenericDataSet(filepath="test.csv", file_format='csv')
         >>> data_set.save(data)
         >>> reloaded = data_set.load()

kedro/extras/datasets/pandas/hdf_dataset.py

@@ -45,7 +45,6 @@ class HDFDataSet(AbstractVersionedDataSet[pd.DataFrame, pd.DataFrame]):
         >>> data = pd.DataFrame({'col1': [1, 2], 'col2': [4, 5],
         >>>                      'col3': [5, 6]})
         >>>
-        >>> # data_set = HDFDataSet(filepath="gcs://bucket/test.hdf", key='data')
         >>> data_set = HDFDataSet(filepath="test.h5", key='data')
         >>> data_set.save(data)
         >>> reloaded = data_set.load()

kedro/extras/datasets/pandas/json_dataset.py

@@ -52,7 +52,6 @@ class JSONDataSet(AbstractVersionedDataSet[pd.DataFrame, pd.DataFrame]):
         >>> data = pd.DataFrame({'col1': [1, 2], 'col2': [4, 5],
         >>>                      'col3': [5, 6]})
         >>>
-        >>> # data_set = JSONDataSet(filepath="gcs://bucket/test.json")
         >>> data_set = JSONDataSet(filepath="test.json")
         >>> data_set.save(data)
         >>> reloaded = data_set.load()

kedro/extras/datasets/pandas/parquet_dataset.py

@@ -64,7 +64,6 @@ class ParquetDataSet(AbstractVersionedDataSet[pd.DataFrame, pd.DataFrame]):
         >>> data = pd.DataFrame({'col1': [1, 2], 'col2': [4, 5],
         >>>                      'col3': [5, 6]})
         >>>
-        >>> # data_set = ParquetDataSet(filepath="gcs://bucket/test.parquet")
         >>> data_set = ParquetDataSet(filepath="test.parquet")
         >>> data_set.save(data)
         >>> reloaded = data_set.load()

kedro/extras/datasets/pandas/xml_dataset.py

@@ -35,7 +35,6 @@ class XMLDataSet(AbstractVersionedDataSet[pd.DataFrame, pd.DataFrame]):
         >>> data = pd.DataFrame({'col1': [1, 2], 'col2': [4, 5],
         >>>                      'col3': [5, 6]})
         >>>
-        >>> # data_set = XMLDataSet(filepath="gcs://bucket/test.xml")
         >>> data_set = XMLDataSet(filepath="test.xml")
         >>> data_set.save(data)
         >>> reloaded = data_set.load()

kedro/extras/datasets/pickle/pickle_dataset.py

@@ -55,13 +55,11 @@ class PickleDataSet(AbstractVersionedDataSet[Any, Any]):
         >>> data = pd.DataFrame({'col1': [1, 2], 'col2': [4, 5],
         >>>                      'col3': [5, 6]})
         >>>
-        >>> # data_set = PickleDataSet(filepath="gcs://bucket/test.pkl")
         >>> data_set = PickleDataSet(filepath="test.pkl", backend="pickle")
         >>> data_set.save(data)
         >>> reloaded = data_set.load()
         >>> assert data.equals(reloaded)
         >>>
-        >>> # Add "compress_pickle[lz4]" to requirements.txt
         >>> data_set = PickleDataSet(filepath="test.pickle.lz4",
         >>>                          backend="compress_pickle",
         >>>                          load_args={"compression":"lz4"},

kedro/extras/datasets/pillow/image_dataset.py

@@ -26,7 +26,6 @@ class ImageDataSet(AbstractVersionedDataSet[Image.Image, Image.Image]):
 
         >>> from kedro.extras.datasets.pillow import ImageDataSet
         >>>
-        >>> # data_set = ImageDataSet(filepath="gcs://bucket/test.png")
         >>> data_set = ImageDataSet(filepath="test.png")
         >>> image = data_set.load()
         >>> image.show()

kedro/extras/datasets/plotly/plotly_dataset.py

@@ -23,21 +23,21 @@ class PlotlyDataSet(JSONDataSet):
     the JSON file directly from a pandas DataFrame through ``plotly_args``.
 
     Example configuration for a PlotlyDataSet in the catalog:
-    ::
+    .. code-block:: yaml
 
         >>> bar_plot:
-        >>>     type: plotly.PlotlyDataSet
-        >>>     filepath: data/08_reporting/bar_plot.json
-        >>>     plotly_args:
-        >>>         type: bar
-        >>>         fig:
-        >>>             x: features
-        >>>             y: importance
-        >>>             orientation: h
-        >>>         layout:
-        >>>             xaxis_title: x
-        >>>             yaxis_title: y
-        >>>             title: Test
+        >>>   type: plotly.PlotlyDataSet
+        >>>   filepath: data/08_reporting/bar_plot.json
+        >>>   plotly_args:
+        >>>     type: bar
+        >>>     fig:
+        >>>         x: features
+        >>>         y: importance
+        >>>         orientation: h
+        >>>     layout:
+        >>>         xaxis_title: x
+        >>>         yaxis_title: y
+        >>>         title: Title
     """
 
     # pylint: disable=too-many-arguments

kedro/extras/datasets/redis/redis_dataset.py

@@ -43,6 +43,7 @@ class PickleDataSet(AbstractDataSet[Any, Any]):
     ::
 
         >>> from kedro.extras.datasets.redis import PickleDataSet
+        >>> import pandas as pd
         >>>
         >>> data = pd.DataFrame({'col1': [1, 2], 'col2': [4, 5],
         >>>                       'col3': [5, 6]})

kedro/extras/datasets/text/text_dataset.py

@@ -27,7 +27,6 @@ class TextDataSet(AbstractVersionedDataSet[str, str]):
         >>>
         >>> string_to_write = "This will go in a file."
         >>>
-        >>> # data_set = TextDataSet(filepath="gcs://bucket/test.md")
         >>> data_set = TextDataSet(filepath="test.md")
         >>> data_set.save(string_to_write)
         >>> reloaded = data_set.load()

kedro/extras/datasets/tracking/json_dataset.py

@@ -21,7 +21,6 @@ class JSONDataSet(JDS):
         >>>
         >>> data = {'col1': 1, 'col2': 0.23, 'col3': 0.002}
         >>>
-        >>> # data_set = JSONDataSet(filepath="gcs://bucket/test.json")
         >>> data_set = JSONDataSet(filepath="test.json")
         >>> data_set.save(data)
 

kedro/extras/datasets/tracking/metrics_dataset.py

@@ -23,7 +23,6 @@ class MetricsDataSet(JSONDataSet):
         >>>
         >>> data = {'col1': 1, 'col2': 0.23, 'col3': 0.002}
         >>>
-        >>> # data_set = MetricsDataSet(filepath="gcs://bucket/test.json")
         >>> data_set = MetricsDataSet(filepath="test.json")
         >>> data_set.save(data)
 

kedro/extras/datasets/yaml/yaml_dataset.py

@@ -28,7 +28,6 @@ class YAMLDataSet(AbstractVersionedDataSet[Dict, Dict]):
         >>>
         >>> data = {'col1': [1, 2], 'col2': [4, 5], 'col3': [5, 6]}
         >>>
-        >>> # data_set = YAMLDataSet(filepath="gcs://bucket/test.yaml")
         >>> data_set = YAMLDataSet(filepath="test.yaml")
         >>> data_set.save(data)
         >>> reloaded = data_set.load()

setup.py

@@ -78,6 +78,7 @@ def _collect_requirements(requires):
     "pandas.XMLDataSet": [PANDAS, "lxml~=4.6"],
     "pandas.GenericDataSet": [PANDAS],
 }
+pickle_require = {"pickle.PickleDataSet": ["compress-pickle~=2.1.0"]}
 pillow_require = {"pillow.ImageDataSet": ["Pillow~=9.0"]}
 plotly_require = {
     "plotly.PlotlyDataSet": [PANDAS, "plotly>=4.8.0, <6.0"],
@@ -121,6 +122,7 @@ def _collect_requirements(requires):
     "holoviews": _collect_requirements(holoviews_require),
     "networkx": _collect_requirements(networkx_require),
     "pandas": _collect_requirements(pandas_require),
+    "pickle": _collect_requirements(pickle_require),
     "pillow": _collect_requirements(pillow_require),
     "plotly": _collect_requirements(plotly_require),
     "redis": _collect_requirements(redis_require),
@@ -135,6 +137,7 @@ def _collect_requirements(requires):
     **holoviews_require,
     **networkx_require,
     **pandas_require,
+    **pickle_require,
     **pillow_require,
     **plotly_require,
     **spark_require,