diff --git a/.github/ISSUE_TEMPLATE/bug-report.yml b/.github/ISSUE_TEMPLATE/bug-report.yml
index 67e5268c3..3429f6718 100644
--- a/.github/ISSUE_TEMPLATE/bug-report.yml
+++ b/.github/ISSUE_TEMPLATE/bug-report.yml
@@ -16,7 +16,7 @@ body:
       label: What happened?
       description: |
         Describe what happened and how to reproduce the bug.
-        Include the full code and data to reproduce it. Use a simple toy data set, e.g. from `vega_datasets`.
+        Include the full code and data to reproduce it. Use a simple toy data set, e.g. from `altair.datasets`.
     validations:
       required: true
   - type: textarea
diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
index 97aba4227..078843bd2 100644
--- a/CONTRIBUTING.md
+++ b/CONTRIBUTING.md
@@ -198,7 +198,7 @@ Every example should:
 - not make any external calls to download data within the script (i.e. don't
   use urllib). You can define your data directly within the example file,
   generate your data using pandas and numpy, or you can use data
-  available in the `vega_datasets` package.
+  available in the `altair.datasets` module.
 
 The easiest way to get started would be to adapt examples from the [Vega-Lite
 example gallery](https://vega.github.io/vega-lite/examples/) which are missing
@@ -225,12 +225,9 @@ Some additional notes:
   If the example requires multiple dataframes then this does not apply. See
   other examples for guidance. 
 - Example code should not require downloading external datasets. We suggest
-  using the `vega_datasets` package if possible.
-  If you are using the `vega_datasets` package there are multiple ways to refer
-  to a data source. If the dataset you would like to use is included in local
-  installation (`vega_datasets.local_data.list_datasets()`) then the data can
-  be referenced directly, such as `source = data.iris()`. If the data is not
-  included then it should be referenced by URL, such as `source =
+  using the `altair.datasets` module if possible.
+  If you are using the `altair.datasets` module there are multiple ways to refer
+  to a data source. The data can be referenced directly, such as `source = data.penguins()`, or it can be referenced by URL, such as `source =
   data.movies.url`. This is to ensure that Altair's automated test suite does
   not depend on availability of external HTTP resources.
 - If VlConvert does not support PNG export of the chart (e.g. in the case of emoji),
diff --git a/README.md b/README.md
index 3fa703d80..1571ad016 100644
--- a/README.md
+++ b/README.md
@@ -31,7 +31,7 @@ Here is an example using Vega-Altair to quickly visualize and display a dataset
 import altair as alt
 
 # load a simple dataset as a pandas DataFrame
-from vega_datasets import data
+from altair.datasets import data
 cars = data.cars()
 
 alt.Chart(cars).mark_point().encode(
@@ -48,7 +48,7 @@ With a few modifications to the example above we can create a linked histogram t
 
 ```python 
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.cars()
 
diff --git a/altair/theme.py b/altair/theme.py
index 9c952b8c9..9c37fdd83 100644
--- a/altair/theme.py
+++ b/altair/theme.py
@@ -221,7 +221,7 @@ def custom_theme() -> theme.ThemeConfig:
 
     Until another theme has been enabled, all charts will use defaults set in ``custom_theme()``::
 
-        from vega_datasets import data
+        from altair.datasets import data
 
         source = data.stocks()
         lines = (
diff --git a/altair/vegalite/v6/api.py b/altair/vegalite/v6/api.py
index c0def05ab..b5d4d80c9 100644
--- a/altair/vegalite/v6/api.py
+++ b/altair/vegalite/v6/api.py
@@ -996,14 +996,16 @@ def then(self, statement: _StatementType, /, **kwds: Any) -> Then[Any]:
         Simple conditions may be expressed without defining a default::
 
             import altair as alt
-            from vega_datasets import data
+            from altair.datasets import data
 
             source = data.movies()
-            predicate = (alt.datum.IMDB_Rating == None) | (alt.datum.Rotten_Tomatoes_Rating == None)
+            predicate = (alt.datum["IMDB Rating"] == None) | (
+                alt.datum["Rotten Tomatoes Rating"] == None
+            )
 
             alt.Chart(source).mark_point(invalid=None).encode(
-                x="IMDB_Rating:Q",
-                y="Rotten_Tomatoes_Rating:Q",
+                x="IMDB Rating:Q",
+                y="Rotten Tomatoes Rating:Q",
                 color=alt.when(predicate).then(alt.value("grey")),
             )
         """
@@ -1072,7 +1074,7 @@ def otherwise(
         Points outside of ``brush`` will not appear highlighted::
 
             import altair as alt
-            from vega_datasets import data
+            from altair.datasets import data
 
             source = data.cars()
             brush = alt.selection_interval()
@@ -1159,7 +1161,7 @@ def when(
         Chain calls to express precise queries::
 
             import altair as alt
-            from vega_datasets import data
+            from altair.datasets import data
 
             source = data.cars()
             color = (
@@ -1264,19 +1266,21 @@ def then(self, statement: _StatementType, /, **kwds: Any) -> Then[_Conditions]:
         Multiple conditions with an implicit default::
 
             import altair as alt
-            from vega_datasets import data
+            from altair.datasets import data
 
             source = data.movies()
-            predicate = (alt.datum.IMDB_Rating == None) | (alt.datum.Rotten_Tomatoes_Rating == None)
+            predicate = (alt.datum["IMDB Rating"] == None) | (
+                alt.datum["Rotten Tomatoes Rating"] == None
+            )
             color = (
                 alt.when(predicate)
                 .then(alt.value("grey"))
-                .when(alt.datum.IMDB_Votes < 5000)
+                .when(alt.datum["IMDB Votes"] < 5000)
                 .then(alt.value("lightblue"))
             )
 
             alt.Chart(source).mark_point(invalid=None).encode(
-                x="IMDB_Rating:Q", y="Rotten_Tomatoes_Rating:Q", color=color
+                x="IMDB Rating:Q", y="Rotten Tomatoes Rating:Q", color=color
             )
         """
         condition = self._when_then(statement, kwds)
@@ -1344,7 +1348,7 @@ def when(
     Setting up a common chart::
 
         import altair as alt
-        from vega_datasets import data
+        from altair.datasets import data
 
         source = data.cars()
         brush = alt.selection_interval()
@@ -3166,7 +3170,7 @@ def transform_filter(
 
             import altair as alt
             from altair import datum
-            from vega_datasets import data
+            from altair.datasets import data
 
             source = data.population.url
             chart = (
diff --git a/doc/case_studies/exploring-weather.rst b/doc/case_studies/exploring-weather.rst
index ad2a3bc2d..2dab50bf1 100644
--- a/doc/case_studies/exploring-weather.rst
+++ b/doc/case_studies/exploring-weather.rst
@@ -23,7 +23,7 @@ dataframes, and contains a loader for this and other built-in datasets:
 .. altair-plot::
     :output: repr
 
-    from vega_datasets import data
+    from altair.datasets import data
 
     df = data.seattle_weather()
     df.head()
diff --git a/doc/conf.py b/doc/conf.py
index 7ad2674f0..7b8f92c00 100644
--- a/doc/conf.py
+++ b/doc/conf.py
@@ -158,7 +158,6 @@
         },
     ],
     "header_links_before_dropdown": 4,
-    "announcement": """This website is for version 5. You can find the documentation for version 4 <a href='https://altair-viz.github.io/altair-viz-v4/'>here</a>.""",
     "analytics": {
         "plausible_analytics_domain": "altair-viz.github.io",
         "plausible_analytics_url": ("https://views.scientific-python.org/js/script.js"),
diff --git a/doc/getting_started/installation.rst b/doc/getting_started/installation.rst
index 87bb9dd27..7852b61a3 100644
--- a/doc/getting_started/installation.rst
+++ b/doc/getting_started/installation.rst
@@ -38,6 +38,5 @@ for details on how to contribute to the Altair project.
 
 .. _conda: https://docs.conda.io/
 .. _Vega-Lite: http://vega.github.io/vega-lite
-.. _vega_datasets: https://github.com/altair-viz/vega_datasets
 .. _JupyterLab: http://jupyterlab.readthedocs.io/
 .. _Jupyter Notebook: https://jupyter-notebook.readthedocs.io/
diff --git a/doc/getting_started/overview.rst b/doc/getting_started/overview.rst
index 81b9676fd..a651a24aa 100644
--- a/doc/getting_started/overview.rst
+++ b/doc/getting_started/overview.rst
@@ -17,7 +17,7 @@ an interactive scatter plot:
     import altair as alt
 
     # load a sample dataset as a pandas DataFrame
-    from vega_datasets import data
+    from altair.datasets import data
     cars = data.cars()
 
     # make the chart 
diff --git a/doc/getting_started/resources.rst b/doc/getting_started/resources.rst
index 36d7b1b36..73bc36675 100644
--- a/doc/getting_started/resources.rst
+++ b/doc/getting_started/resources.rst
@@ -104,14 +104,6 @@ Altair backend for the pandas plotting API.
 .. List of links.
 .. _altair_pandas: https://github.com/altair-viz/altair_pandas
 
-vega_datasets_
-~~~~~~~~~~~~~~
-
-Offline access to the Vega datasets used in the Altair documentation.
-
-.. List of links.
-.. _vega_datasets: https://github.com/altair-viz/vega_datasets
-
 altair_recipes_
 ~~~~~~~~~~~~~~~
 
diff --git a/doc/user_guide/compound_charts.rst b/doc/user_guide/compound_charts.rst
index a05bc3564..214ab156b 100644
--- a/doc/user_guide/compound_charts.rst
+++ b/doc/user_guide/compound_charts.rst
@@ -34,7 +34,7 @@ same data; for example:
 .. altair-plot::
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     stocks = data.stocks.url
 
@@ -76,13 +76,13 @@ heat-map:
 .. altair-plot::
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.movies.url
 
     heatmap = alt.Chart(source).mark_rect().encode(
-        alt.X('IMDB_Rating:Q').bin(),
-        alt.Y('Rotten_Tomatoes_Rating:Q').bin(),
+        alt.X('IMDB Rating:Q').bin(),
+        alt.Y('Rotten Tomatoes Rating:Q').bin(),
         alt.Color('count()').scale(scheme='greenblue')
     )
 
@@ -90,8 +90,8 @@ heat-map:
         color='black',
         size=5,
     ).encode(
-        x='IMDB_Rating:Q',
-        y='Rotten_Tomatoes_Rating:Q',
+        x='IMDB Rating:Q',
+        y='Rotten Tomatoes Rating:Q',
     )
 
     heatmap + points
@@ -121,7 +121,7 @@ distribution of its points:
 .. altair-plot::
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     penguins = data.penguins.url
 
@@ -174,7 +174,7 @@ with a ``brush`` selection to add interaction:
 .. altair-plot::
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.sp500.url
 
@@ -219,7 +219,7 @@ showing how ``repeat`` can be used to build the chart more efficiently:
 .. altair-plot::
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     penguins = data.penguins.url
 
@@ -251,7 +251,7 @@ method, makes this type of chart a bit easier to produce:
 .. altair-plot::
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
     penguins = data.penguins.url
 
     alt.Chart(penguins).mark_point().encode(
@@ -271,21 +271,21 @@ encodings for the row and/or column which can be referred to in the chart's
 encoding specification using ``alt.repeat('row')`` or ``alt.repeat('column')``.
 
 Another option to use the ``repeat`` method is for layering. Here below the
-columns ``US_Gross`` and ``Worldwide_Gross`` are layered on the ``y``-axis
+columns ``US Gross`` and ``Worldwide Gross`` are layered on the ``y``-axis
 using ``alt.repeat('layer')``:
 
 .. altair-plot::
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.movies()
 
     alt.Chart(source).mark_line().encode(
-        x=alt.X("IMDB_Rating").bin(),
+        x=alt.X("IMDB Rating").bin(),
         y=alt.Y(alt.repeat('layer')).aggregate('mean').title("Mean of US and Worldwide Gross"),
         color=alt.ColorDatum(alt.repeat('layer'))
-    ).repeat(layer=["US_Gross", "Worldwide_Gross"])
+    ).repeat(layer=["US Gross", "Worldwide Gross"])
 
 Currently ``repeat`` can only be encodings (not, e.g., data transforms)
 but there is discussion within the Vega-Lite community about making this pattern
diff --git a/doc/user_guide/configuration.rst b/doc/user_guide/configuration.rst
index d737899c5..2751ad626 100644
--- a/doc/user_guide/configuration.rst
+++ b/doc/user_guide/configuration.rst
@@ -98,7 +98,7 @@ the :meth:`Chart.configure_header` method. Here is an example:
 .. altair-plot::
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.cars.url
 
@@ -142,7 +142,7 @@ Here is an example:
 .. altair-plot::
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.cars.url
 
@@ -270,7 +270,7 @@ Here is an example:
 .. altair-plot::
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.cars.url
 
@@ -305,7 +305,7 @@ be controlled:
 .. altair-plot::
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.cars.url
 
diff --git a/doc/user_guide/customization.rst b/doc/user_guide/customization.rst
index 8c3781865..99981e04e 100644
--- a/doc/user_guide/customization.rst
+++ b/doc/user_guide/customization.rst
@@ -20,7 +20,7 @@ For example, suppose we are creating a scatter plot of the ``cars`` dataset:
 .. altair-plot::
 
    import altair as alt
-   from vega_datasets import data
+   from altair.datasets import data
    cars = data.cars.url
 
    alt.Chart(cars).mark_point().encode( 
@@ -128,7 +128,7 @@ By default an Altair chart does not have a title, as seen in this example.
 .. altair-plot::
 
    import altair as alt
-   from vega_datasets import data
+   from altair.datasets import data
    
    iowa = data.iowa_electricity.url
    
@@ -237,7 +237,7 @@ following plot:
 .. altair-plot::
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     cars = data.cars.url
 
@@ -359,14 +359,14 @@ A legend is added to the chart automatically when the ``color``, ``shape`` or ``
 .. altair-plot::
 
   import altair as alt
-  from vega_datasets import data
+  from altair.datasets import data
 
-  iris = data.iris()
+  cars = data.cars()
 
-  alt.Chart(iris).mark_point().encode(
-      x='petalWidth',
-      y='petalLength',
-      color='species'
+  alt.Chart(cars).mark_point().encode(
+      x='Horsepower:Q',
+      y='Miles_per_Gallon:Q',
+      color='Origin:N'
   )
 
 In this case, the legend can be customized by introducing the :class:`Color` class and taking advantage of its :meth:`legend` method. The ``shape`` and ``size`` arguments have their own corresponding classes.
@@ -376,14 +376,14 @@ The legend option on all of them expects a :class:`Legend` object as its input,
 .. altair-plot::
 
   import altair as alt
-  from vega_datasets import data
+  from altair.datasets import data
 
-  iris = data.iris()
+  cars = data.cars()
 
-  alt.Chart(iris).mark_point().encode(
-      x='petalWidth',
-      y='petalLength',
-      color=alt.Color('species').legend(orient="left")
+  alt.Chart(cars).mark_point().encode(
+      x='Horsepower:Q',
+      y='Miles_per_Gallon:Q',
+      color=alt.Color('Origin:N').legend(orient="left")
   )
 
 Another thing you can do is set a ``title``; in this case we can use the :meth:`title` method directly as a shortcut or specify the ``title`` parameter inside the :meth:`legend` method:.
@@ -391,14 +391,14 @@ Another thing you can do is set a ``title``; in this case we can use the :meth:`
 .. altair-plot::
 
   import altair as alt
-  from vega_datasets import data
+  from altair.datasets import data
 
-  iris = data.iris()
+  cars = data.cars()
 
-  alt.Chart(iris).mark_point().encode(
-      x='petalWidth',
-      y='petalLength',
-      color=alt.Color('species').title("Species by color")
+  alt.Chart(cars).mark_point().encode(
+      x='Horsepower:Q',
+      y='Miles_per_Gallon:Q',
+      color=alt.Color('Origin:N').title("Origin")
   )
 
 
@@ -407,14 +407,14 @@ You can remove the legend entirely by submitting a null value.
 .. altair-plot::
 
   import altair as alt
-  from vega_datasets import data
+  from altair.datasets import data
 
-  iris = data.iris()
+  cars = data.cars()
 
-  alt.Chart(iris).mark_point().encode(
-      x='petalWidth',
-      y='petalLength',
-      color=alt.Color('species').legend(None),
+  alt.Chart(cars).mark_point().encode(
+      x='Horsepower:Q',
+      y='Miles_per_Gallon:Q',
+      color=alt.Color('Origin:N').legend(None),
   )
 
 Removing the Chart Border
@@ -427,14 +427,14 @@ As an example, let's start with a simple scatter plot.
 .. altair-plot::
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
-    iris = data.iris()
+    cars = data.cars()
 
-    alt.Chart(iris).mark_point().encode(
-        x='petalWidth',
-        y='petalLength',
-        color='species'
+    alt.Chart(cars).mark_point().encode(
+        x='Horsepower:Q',
+        y='Miles_per_Gallon:Q',
+        color='Origin:N'
     )
 
 First remove the grid using the :meth:`configure_axis` method.
@@ -442,14 +442,14 @@ First remove the grid using the :meth:`configure_axis` method.
 .. altair-plot::
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
-    iris = data.iris()
+    cars = data.cars()
 
-    alt.Chart(iris).mark_point().encode(
-        x='petalWidth',
-        y='petalLength',
-        color='species'
+    alt.Chart(cars).mark_point().encode(
+        x='Horsepower:Q',
+        y='Miles_per_Gallon:Q',
+        color='Origin:N'
     ).configure_axis(
         grid=False
     )
@@ -461,14 +461,14 @@ Hide it by setting ``stroke=None`` inside :meth:`configure_view`
 .. altair-plot::
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
-    iris = data.iris()
+    cars = data.cars()
 
-    alt.Chart(iris).mark_point().encode(
-        x='petalWidth',
-        y='petalLength',
-        color='species'
+    alt.Chart(cars).mark_point().encode(
+        x='Horsepower:Q',
+        y='Miles_per_Gallon:Q',
+        color='Origin:N'
     ).configure_axis(
         grid=False
     ).configure_view(
@@ -482,14 +482,14 @@ combining the above option with setting ``axis`` to ``None`` during encoding.
 .. altair-plot::
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
-    iris = data.iris()
+    cars = data.cars()
 
-    alt.Chart(iris).mark_point().encode(
-        alt.X('petalWidth').axis(None),
-        alt.Y('petalLength').axis(None),
-        color='species'
+    alt.Chart(cars).mark_point().encode(
+        alt.X('Horsepower:Q').axis(None),
+        alt.Y('Miles_per_Gallon:Q').axis(None),
+        color='Origin:N'
     ).configure_axis(
         grid=False
     ).configure_view(
@@ -516,7 +516,7 @@ can be passed to the `scheme` argument of the :meth:`scale` method:
 .. altair-plot::
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     cars = data.cars()
 
@@ -636,7 +636,7 @@ For example:
 .. altair-plot::
 
    import altair as alt
-   from vega_datasets import data
+   from altair.datasets import data
 
    cars = data.cars()
 
@@ -727,7 +727,7 @@ added to its specification:
     :output: repr
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     chart = alt.Chart(data.cars.url).mark_point().encode(
         x='Horsepower:Q',
@@ -815,7 +815,7 @@ fill unless otherwise specified:
 .. altair-plot::
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     # define, register and enable theme
     
@@ -868,7 +868,7 @@ Italian locale (named ``it-IT``) for both currencies and dates:
    :output: none
 
    import altair as alt
-   from vega_datasets import data
+   from altair.datasets import data
 
    alt.renderers.set_embed_options(format_locale="it-IT", time_format_locale="it-IT")
 
diff --git a/doc/user_guide/data.rst b/doc/user_guide/data.rst
index 6b5cb5447..c38a1b764 100644
--- a/doc/user_guide/data.rst
+++ b/doc/user_guide/data.rst
@@ -70,7 +70,7 @@ Similarly, we must also specify the data type when referencing data by URL:
 .. altair-plot::
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
     url = data.cars.url
 
     alt.Chart(url).mark_point().encode(
@@ -494,9 +494,9 @@ define the type of data as ``topjoson`` in the ``alt.DataFormat()`` object.
 .. altair-plot::
    :output: repr
 
-   from vega_datasets import data
+   from altair.datasets import data
 
-   url_topojson = data.londonBoroughs.url
+   url_topojson = data.london_boroughs.url
 
    data_url_topojson = alt.Data(
        url=url_topojson, format=alt.DataFormat(feature="boroughs", type="topojson")
@@ -538,9 +538,9 @@ without fill color.
 
 .. altair-plot::
 
-   from vega_datasets import data
+   from altair.datasets import data
 
-   url_topojson = data.londonBoroughs.url
+   url_topojson = data.london_boroughs.url
 
    data_url_topojson_mesh = alt.Data(
        url=url_topojson, format=alt.DataFormat(mesh="boroughs", type="topojson")
diff --git a/doc/user_guide/display_frontends.rst b/doc/user_guide/display_frontends.rst
index cc3fcffd5..48b465294 100644
--- a/doc/user_guide/display_frontends.rst
+++ b/doc/user_guide/display_frontends.rst
@@ -321,7 +321,7 @@ output displayed. This turns out to be true of Altair charts as well:
     :output: none
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
     cars = data.cars.url
 
     chart = alt.Chart(cars).mark_point().encode(
diff --git a/doc/user_guide/encodings/channels.rst b/doc/user_guide/encodings/channels.rst
index 7feb9136e..8ca3a49fe 100644
--- a/doc/user_guide/encodings/channels.rst
+++ b/doc/user_guide/encodings/channels.rst
@@ -97,7 +97,7 @@ We map the ``symbol`` variable to ``detail`` to use them to group lines.
 .. altair-plot::
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.stocks()
     alt.Chart(source).mark_line().encode(
@@ -117,7 +117,7 @@ For stacked marks, this controls the order of components of the stack. Here, the
 .. altair-plot::
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     barley = data.barley()
 
@@ -133,7 +133,7 @@ The order can be reversed by changing the sort option to `descending`.
 .. altair-plot::
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     barley = data.barley()
 
@@ -149,7 +149,7 @@ The same approach works for other mark types, like stacked areas charts.
 .. altair-plot::
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     barley = data.barley()
 
@@ -170,7 +170,7 @@ For line marks, the :class:`Order` channel encodes the order in which data point
 .. altair-plot::
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     driving = data.driving()
 
diff --git a/doc/user_guide/encodings/index.rst b/doc/user_guide/encodings/index.rst
index 19cd0117c..bf6cf4e91 100644
--- a/doc/user_guide/encodings/index.rst
+++ b/doc/user_guide/encodings/index.rst
@@ -18,7 +18,7 @@ For example, here we will visualize the cars dataset using four of the available
 .. altair-plot::
 
    import altair as alt
-   from vega_datasets import data
+   from altair.datasets import data
 
 
    cars = data.cars()
@@ -399,7 +399,7 @@ x-axis, using the barley dataset:
 .. altair-plot::
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     barley = data.barley()
 
@@ -464,7 +464,7 @@ to use when sorting:
 .. altair-plot::
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     barley = data.barley()
     base = alt.Chart(barley).mark_point().encode(
@@ -537,7 +537,7 @@ threshold value (e.g., 300 dollars stock price).
 .. altair-plot::
     
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.stocks()
     base = alt.Chart(source)
@@ -571,7 +571,7 @@ with ``alt.datum("MSFT")``.
 .. altair-plot::
     
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.stocks()
     base = alt.Chart(source)
@@ -598,7 +598,7 @@ the color scale used for the lines, you can use ``value``, e.g. ``alt.value("red
 .. altair-plot::
     
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.stocks()
     base = alt.Chart(source)
diff --git a/doc/user_guide/interactions/bindings_widgets.rst b/doc/user_guide/interactions/bindings_widgets.rst
index 9a62307dc..492345e6b 100644
--- a/doc/user_guide/interactions/bindings_widgets.rst
+++ b/doc/user_guide/interactions/bindings_widgets.rst
@@ -45,7 +45,7 @@ where a drop-down is used to highlight cars of a specific ``Origin``:
 .. altair-plot::
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     cars = data.cars.url
 
diff --git a/doc/user_guide/interactions/expressions.rst b/doc/user_guide/interactions/expressions.rst
index a4e9440ab..2b3471d3f 100644
--- a/doc/user_guide/interactions/expressions.rst
+++ b/doc/user_guide/interactions/expressions.rst
@@ -126,7 +126,7 @@ We also need to reference the field specified by the selection parameter
 
 .. altair-plot::
 
-    from vega_datasets import data
+    from altair.datasets import data
     
     cars = data.cars.url
     input_dropdown = alt.binding_select(options=['Europe', 'Japan', 'USA'], name='Region ')
diff --git a/doc/user_guide/interactions/jupyter_chart.rst b/doc/user_guide/interactions/jupyter_chart.rst
index a4ad028d1..0163cb85f 100644
--- a/doc/user_guide/interactions/jupyter_chart.rst
+++ b/doc/user_guide/interactions/jupyter_chart.rst
@@ -241,7 +241,7 @@ the legend.
 .. code-block:: python
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.cars()
     brush = alt.selection_point(name="point", encodings=["color"], bind="legend")
@@ -294,7 +294,7 @@ extract the selected rows in the input DataFrame.
 .. code-block:: python
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.cars()
     brush = alt.selection_point(name="point")
@@ -332,7 +332,7 @@ is a dictionary from column names to selection intervals
 .. code-block:: python
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.cars()
     brush = alt.selection_interval(name="interval")
@@ -387,7 +387,7 @@ is used to combine the chart and HTML table in a column layout.
     from ipywidgets import HTML, VBox
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.cars()
     brush = alt.selection_interval(name="brush")
diff --git a/doc/user_guide/interactions/parameters.rst b/doc/user_guide/interactions/parameters.rst
index 0801ab801..50858499a 100644
--- a/doc/user_guide/interactions/parameters.rst
+++ b/doc/user_guide/interactions/parameters.rst
@@ -27,7 +27,7 @@ Here is a simple scatter-plot created from the ``cars`` dataset:
 .. altair-plot::
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     cars = data.cars.url
 
@@ -111,7 +111,7 @@ Here is a simple scatter-plot created from the ``cars`` dataset:
 .. altair-plot::
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     cars = data.cars.url
 
@@ -435,7 +435,7 @@ containing the 2008 financial crisis:
 .. altair-plot::
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
     import datetime as dt
 
     source = data.sp500.url
diff --git a/doc/user_guide/internals.rst b/doc/user_guide/internals.rst
index 326bd4750..7948259f4 100644
--- a/doc/user_guide/internals.rst
+++ b/doc/user_guide/internals.rst
@@ -30,7 +30,7 @@ from which we can output the JSON representation:
     :output: stdout
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     chart = alt.Chart(data.cars.url).mark_point().encode(
         x='Horsepower:Q',
diff --git a/doc/user_guide/large_datasets.rst b/doc/user_guide/large_datasets.rst
index d8a72f63f..eaba39605 100644
--- a/doc/user_guide/large_datasets.rst
+++ b/doc/user_guide/large_datasets.rst
@@ -278,7 +278,7 @@ using the ``url`` attribute:
 
 .. code-block:: python
 
-   from vega_datasets import data
+   from altair.datasets import data
    source = data.cars.url
 
    alt.Chart(source).mark_point() # etc.
@@ -310,7 +310,7 @@ it is convenient to pass the unaggregated data to Altair:
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.barley()
 
@@ -337,7 +337,7 @@ You could also precalculate the sum in pandas which would reduce the size of the
 .. altair-plot::
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.barley()
     source_aggregated = (
@@ -357,7 +357,7 @@ in Altair.
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     df = data.cars()
 
@@ -378,7 +378,7 @@ to calculate the boundaries of the whiskers.
     
     import altair as alt
     import pandas as pd
-    from vega_datasets import data
+    from altair.datasets import data
 
     k = 1.5
     group_by_column = "Origin"
diff --git a/doc/user_guide/marks/area.rst b/doc/user_guide/marks/area.rst
index b58c66f2a..faf702beb 100644
--- a/doc/user_guide/marks/area.rst
+++ b/doc/user_guide/marks/area.rst
@@ -59,7 +59,7 @@ the following area chart shows a number of unemployment people in the US over ti
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.unemployment_across_industries.url
 
@@ -77,7 +77,7 @@ to ``true`` or an object defining a property of the overlaying point marks, we c
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.stocks.url
 
@@ -94,7 +94,7 @@ In this example, we are also customizing the overlay. For more information about
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.stocks()
 
@@ -123,7 +123,7 @@ Adding a color field to area chart creates stacked area chart by default. For ex
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.unemployment_across_industries.url
 
@@ -141,7 +141,7 @@ You can also create a normalized stacked area chart by setting ``stack`` to ``"n
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.unemployment_across_industries.url
 
@@ -160,7 +160,7 @@ Adding the ``interactive`` method allows for zooming and panning the x-scale.
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.unemployment_across_industries.url
 
@@ -177,7 +177,7 @@ Specifying ``X2`` or ``Y2`` for the quantitative axis of area marks produce rang
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.seattle_weather()
 
diff --git a/doc/user_guide/marks/bar.rst b/doc/user_guide/marks/bar.rst
index 85482f888..a2488b30e 100644
--- a/doc/user_guide/marks/bar.rst
+++ b/doc/user_guide/marks/bar.rst
@@ -49,7 +49,7 @@ Mapping a quantitative field to either ``x`` or ``y`` of the ``bar`` mark produc
 .. altair-plot::
     import altair as alt
     from altair import datum
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.population.url
 
@@ -67,7 +67,7 @@ If we map a different discrete field to the ``y`` channel, we can produce a hori
 .. altair-plot::
     import altair as alt
     from altair import datum
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.population.url
 
@@ -90,7 +90,7 @@ bars on continuous scales will be set based on the ``continuousBandSize`` config
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.seattle_weather()
 
@@ -107,12 +107,12 @@ If the data is not pre-aggregated (i.e. each record in the data field represents
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.movies.url
 
     alt.Chart(source).mark_bar().encode(
-        alt.X("IMDB_Rating:Q").bin(),
+        alt.X("IMDB Rating:Q").bin(),
         y='count()',
     )
 
@@ -122,7 +122,7 @@ Adding color to the bar chart (by using the ``color`` attribute) creates a stack
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.barley()
 
diff --git a/doc/user_guide/marks/boxplot.rst b/doc/user_guide/marks/boxplot.rst
index ed9291dbf..f8ca2161d 100644
--- a/doc/user_guide/marks/boxplot.rst
+++ b/doc/user_guide/marks/boxplot.rst
@@ -27,7 +27,7 @@ By default, the extent is ``1.5``.
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.cars()
 
@@ -40,7 +40,7 @@ By default, the extent is ``1.5``.
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.cars()
 
@@ -59,7 +59,7 @@ A box plot’s orientation is automatically determined by the continuous field a
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.cars()
 
@@ -80,7 +80,7 @@ An example of a box plot where the ``color`` encoding channel is specified.
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.cars()
 
@@ -100,7 +100,7 @@ If the field in the tooltip encoding is unaggregated, it replaces the tooltips o
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.cars()
 
diff --git a/doc/user_guide/marks/circle.rst b/doc/user_guide/marks/circle.rst
index 71d41a3bc..43516c7d7 100644
--- a/doc/user_guide/marks/circle.rst
+++ b/doc/user_guide/marks/circle.rst
@@ -22,7 +22,7 @@ Here is an example scatter plot with ``circle`` marks:
 
 .. altair-plot::
    import altair as alt
-   from vega_datasets import data
+   from altair.datasets import data
 
    source = data.cars.url
 
diff --git a/doc/user_guide/marks/errorband.rst b/doc/user_guide/marks/errorband.rst
index 9ce28107b..7740eb59e 100644
--- a/doc/user_guide/marks/errorband.rst
+++ b/doc/user_guide/marks/errorband.rst
@@ -27,7 +27,7 @@ All the properties and usage of error band are identical to error bar’s, excep
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.cars.url
 
@@ -45,7 +45,7 @@ All the properties and usage of error band are identical to error bar’s, excep
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.cars.url
 
@@ -111,7 +111,7 @@ A **1D error band** shows the error range of a continuous field; it can be used
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.cars.url
 
@@ -131,7 +131,7 @@ A **2D error** band shows the error range of a continuous field for each dimensi
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.cars()
 
@@ -156,7 +156,7 @@ Here is an example of a ``errorband`` with the ``color`` encoding channel set to
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.cars.url
 
diff --git a/doc/user_guide/marks/errorbar.rst b/doc/user_guide/marks/errorbar.rst
index 8fc4ae89b..023515e02 100644
--- a/doc/user_guide/marks/errorbar.rst
+++ b/doc/user_guide/marks/errorbar.rst
@@ -29,7 +29,7 @@ If the data is not aggregated yet, Altair will aggregate the data based on the `
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.barley()
 
@@ -52,7 +52,7 @@ If the data is not aggregated yet, Altair will aggregate the data based on the `
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.barley()
 
@@ -73,7 +73,7 @@ If the data is not aggregated yet, Altair will aggregate the data based on the `
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.barley()
 
@@ -165,7 +165,7 @@ The orientation of an error bar is automatically determined by the continuous fi
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.barley()
 
@@ -188,7 +188,7 @@ For 2D error bars with one continuous field and one discrete field, the error ba
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.barley()
 
@@ -215,7 +215,7 @@ Here is an example of a ``errorbar`` with the ``color`` encoding channel set to
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.barley()
 
@@ -241,7 +241,7 @@ You can add custom tooltips to error bars. The custom tooltip will override the
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.barley()
 
diff --git a/doc/user_guide/marks/geoshape.rst b/doc/user_guide/marks/geoshape.rst
index 824a17e68..bdf00145e 100644
--- a/doc/user_guide/marks/geoshape.rst
+++ b/doc/user_guide/marks/geoshape.rst
@@ -17,7 +17,7 @@ Altair can work with many different geographical data formats, including geojson
 .. altair-plot::
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
     import geopandas as gpd
 
     url = "https://naciscdn.org/naturalearth/110m/cultural/ne_110m_admin_0_countries.zip"
diff --git a/doc/user_guide/marks/line.rst b/doc/user_guide/marks/line.rst
index feda5bbf5..ee9d32d9b 100644
--- a/doc/user_guide/marks/line.rst
+++ b/doc/user_guide/marks/line.rst
@@ -84,7 +84,7 @@ Using line with one temporal or ordinal field (typically on ``x``) and another q
 .. altair-plot::
     import altair as alt
     from altair import datum
-    from vega_datasets import data
+    from altair.datasets import data
 
 
     source = data.stocks()
@@ -102,7 +102,7 @@ Adding a field to a mark property channel such as ``color`` groups data points i
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.stocks()
 
@@ -116,7 +116,7 @@ We can further apply selection to highlight a certain line on hover.
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.stocks()
 
@@ -150,7 +150,7 @@ Adding a field to ``strokeDash`` also produces a multi-series line chart.
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.stocks()
 
@@ -184,7 +184,7 @@ To group lines by a field without mapping the field to any visual properties, we
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.stocks()
 
@@ -198,7 +198,7 @@ The same method can be used to group lines for a ranged dot plot.
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.countries()
 
@@ -235,7 +235,7 @@ By setting the ``point`` property of the mark definition to ``True`` or an objec
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.stocks()
 
@@ -253,7 +253,7 @@ Here we create stroked points by setting ``filled`` to ``False`` and ``fill`` to
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.stocks()
 
@@ -276,7 +276,7 @@ datapoint (2010) is the other endpoint of the line.
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.driving()
 
@@ -293,7 +293,7 @@ The ``interpolate`` property of a mark definition can be used to change line int
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.stocks()
 
@@ -308,7 +308,7 @@ We can also set ``interpolate`` to ``"step-after"`` to create a step-chart.
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.stocks()
 
@@ -327,7 +327,7 @@ By mapping geographic coordinate data to ``longitude`` and ``latitude`` channels
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
     import pandas as pd
 
     airports = data.airports.url
diff --git a/doc/user_guide/marks/point.rst b/doc/user_guide/marks/point.rst
index 0f1cac33b..c572cb23b 100644
--- a/doc/user_guide/marks/point.rst
+++ b/doc/user_guide/marks/point.rst
@@ -13,7 +13,7 @@ Point Mark Properties
     :div_class: properties-example
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.cars()
 
@@ -70,11 +70,11 @@ Mapping a field to either only ``x`` or only ``y`` of point marks creates a dot
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.movies()
     alt.Chart(source).mark_point().encode(
-        x="IMDB_Rating:Q"
+        x="IMDB Rating:Q"
     )
 
 Scatter Plot
@@ -83,7 +83,7 @@ Mapping fields to both the ``x`` and ``y`` channels creates a scatter plot.
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.cars()
 
@@ -96,7 +96,7 @@ By default, ``point`` marks only have borders and are transparent inside. You ca
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.cars()
 
@@ -111,7 +111,7 @@ By mapping a third field to the ``size`` channel in the scatter plot, we can cre
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.cars()
 
@@ -128,7 +128,7 @@ Fields can also be encoded in the scatter plot using the ``color`` or ``shape``
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.cars()
 
@@ -146,7 +146,7 @@ To jitter points on a discrete scale, you can add a random offset:
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.cars()
 
@@ -167,7 +167,7 @@ We can also use point mark with ``wedge`` as ``shape`` and ``angle`` encoding to
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.windvectors()
 
@@ -185,7 +185,7 @@ By mapping geographic coordinate data to ``longitude`` and ``latitude`` channels
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     airports = data.airports()
     states = alt.topo_feature(data.us_10m.url, feature="states")
diff --git a/doc/user_guide/marks/rect.rst b/doc/user_guide/marks/rect.rst
index 3bb51f23d..a5650b980 100644
--- a/doc/user_guide/marks/rect.rst
+++ b/doc/user_guide/marks/rect.rst
@@ -53,7 +53,7 @@ Using the ``rect`` marks with discrete fields on ``x`` and ``y`` channels create
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.seattle_weather()
 
@@ -72,7 +72,7 @@ For example, we can use ``rect`` to create an annotation ``layer`` that provides
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.cars()
 
diff --git a/doc/user_guide/marks/rule.rst b/doc/user_guide/marks/rule.rst
index bd7069bb6..ebaa55696 100644
--- a/doc/user_guide/marks/rule.rst
+++ b/doc/user_guide/marks/rule.rst
@@ -71,7 +71,7 @@ We can use rules to show the average price of different stocks akin to ``tick``
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.stocks()
 
@@ -86,7 +86,7 @@ The fact that rule marks span the width or the height of a single view make them
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.stocks()
 
@@ -108,17 +108,17 @@ We can also use a rule mark to show global mean value over a histogram.
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.movies.url
 
     base = alt.Chart(source)
     bar = base.mark_bar().encode(
-        x=alt.X("IMDB_Rating:Q").bin().axis(None),
+        x=alt.X("IMDB Rating:Q").bin().axis(None),
         y="count()"
     )
     rule = base.mark_rule(color="red").encode(
-        x="mean(IMDB_Rating):Q",
+        x="mean(IMDB Rating):Q",
         size=alt.value(5),
     )
 
@@ -133,7 +133,7 @@ For example, we can use ``y`` and ``y2`` show the ``"min"`` and ``"max"`` values
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.cars()
 
diff --git a/doc/user_guide/marks/square.rst b/doc/user_guide/marks/square.rst
index 2d146c686..b7ac04ecc 100644
--- a/doc/user_guide/marks/square.rst
+++ b/doc/user_guide/marks/square.rst
@@ -18,7 +18,7 @@ Scatter Plot with Square
 ------------------------
 .. altair-plot::
    import altair as alt
-   from vega_datasets import data
+   from altair.datasets import data
 
    source = data.cars()
 
diff --git a/doc/user_guide/marks/text.rst b/doc/user_guide/marks/text.rst
index 9f5ee64cf..bccd11ee9 100644
--- a/doc/user_guide/marks/text.rst
+++ b/doc/user_guide/marks/text.rst
@@ -109,7 +109,7 @@ Text Table Heatmap
 ^^^^^^^^^^^^^^^^^^
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.cars()
 
@@ -196,7 +196,7 @@ Mapping a field to ``text`` channel of text mark sets the mark's text value. For
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
     from altair import datum
 
     source = data.cars()
@@ -214,7 +214,7 @@ By mapping geographic coordinate data to ``longitude`` and ``latitude`` channels
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     states = alt.topo_feature(data.us_10m.url, feature="states")
 
diff --git a/doc/user_guide/marks/tick.rst b/doc/user_guide/marks/tick.rst
index 07875e962..46c523ebd 100644
--- a/doc/user_guide/marks/tick.rst
+++ b/doc/user_guide/marks/tick.rst
@@ -22,7 +22,7 @@ The following dot plot uses tick marks to show the distribution of precipitation
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.seattle_weather()
 
@@ -36,7 +36,7 @@ By adding a ``y`` field, a strip plot can be created that shows the distribution
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.cars()
 
@@ -50,7 +50,7 @@ Customizing Tick’s Size and Thickness
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.seattle_weather()
 
diff --git a/doc/user_guide/marks/trail.rst b/doc/user_guide/marks/trail.rst
index 1bba127f8..a76bab327 100644
--- a/doc/user_guide/marks/trail.rst
+++ b/doc/user_guide/marks/trail.rst
@@ -21,7 +21,7 @@ Line Chart with Varying Size
 
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.stocks()
 
@@ -36,7 +36,7 @@ Comet Chart Showing Changes Between Two States
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 .. altair-plot::
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     alt.Chart(data.barley.url).transform_pivot(
         "year",
diff --git a/doc/user_guide/saving_charts.rst b/doc/user_guide/saving_charts.rst
index 652fb3173..7d871ab6c 100644
--- a/doc/user_guide/saving_charts.rst
+++ b/doc/user_guide/saving_charts.rst
@@ -22,7 +22,7 @@ For example, here we save a simple scatter-plot to JSON:
 .. code-block:: python
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     chart = alt.Chart(data.cars.url).mark_point().encode(
         x='Horsepower:Q',
@@ -239,7 +239,7 @@ specification in the online Vega editor_.
     :output: repr
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     chart = alt.Chart(data.cars.url).mark_point().encode(
         x='Horsepower:Q',
diff --git a/doc/user_guide/scale_resolve.rst b/doc/user_guide/scale_resolve.rst
index 80bc1509f..29bf1835c 100644
--- a/doc/user_guide/scale_resolve.rst
+++ b/doc/user_guide/scale_resolve.rst
@@ -16,7 +16,7 @@ a union of the two color encoding domains:
 .. altair-plot::
 
    import altair as alt
-   from vega_datasets import data
+   from altair.datasets import data
    
    source = data.cars()
    
@@ -56,7 +56,7 @@ each layer.
 .. altair-plot::
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.cars()
 
diff --git a/doc/user_guide/times_and_dates.rst b/doc/user_guide/times_and_dates.rst
index 98ad9390c..0f5a6050d 100644
--- a/doc/user_guide/times_and_dates.rst
+++ b/doc/user_guide/times_and_dates.rst
@@ -25,9 +25,9 @@ containing hourly temperatures measured in Seattle:
     :output: repr
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
-    temps = data.seattle_temps()
+    temps = data.seattle_weather_hourly_normals()
     temps.head()
 
 We can see from the ``dtypes`` attribute that the times are encoded as a standard
@@ -47,7 +47,7 @@ example, we'll limit ourselves to the first two weeks of data:
 
     alt.Chart(temps).mark_line().encode(
         x='date:T',
-        y='temp:Q'
+        y='temperature:Q'
     )
 
 Notice that for date/time values we use the ``T`` to indicate a temporal
@@ -69,7 +69,7 @@ x-axis, and day of the month on the y-axis:
     alt.Chart(temps).mark_rect().encode(
         alt.X('hoursminutes(date):O').title('hour of day'),
         alt.Y('monthdate(date):O').title('date'),
-        alt.Color('temp:Q').title('temperature (F)')
+        alt.Color('temperature:Q').title('temperature (C)')
     )
 
 Unless you are using a non-ES6 browser (See :ref:`note-browser-compliance`),
@@ -108,7 +108,7 @@ render **according to the timezone of the browser rendering it**:
     alt.Chart(temps).mark_rect().encode(
         alt.X('hoursminutes(date_pacific):O').title('hour of day'),
         alt.Y('monthdate(date_pacific):O').title('date'),
-        alt.Color('temp:Q').title('temperature (F)')
+        alt.Color('temperature:Q').title('temperature (C)')
     )
 
 If you are viewing this chart on a computer whose time is set to the west coast
@@ -136,7 +136,7 @@ regardless of the system location:
     alt.Chart(temps).mark_rect().encode(
         alt.X('utchoursminutes(date_pacific):O').title('UTC hour of day'),
         alt.Y('utcmonthdate(date_pacific):O').title('UTC date'),
-        alt.Color('temp:Q').title('temperature (F)')
+        alt.Color('temperature:Q').title('temperature (C)')
     )
 
 To make your charts as portable as possible (even in non-ES6 browsers which parse
@@ -151,7 +151,7 @@ in UTC time, both on the pandas side and on the Vega-Lite side:
    alt.Chart(temps).mark_rect().encode(
        alt.X('utchoursminutes(date_utc):O').title('hour of day'),
        alt.Y('utcmonthdate(date_utc):O').title('date'),
-       alt.Color('temp:Q').title('temperature (F)')
+       alt.Color('temperature:Q').title('temperature (C)')
    )
 
 This is somewhat less convenient than the default behavior for timezone-agnostic
diff --git a/doc/user_guide/transform/aggregate.rst b/doc/user_guide/transform/aggregate.rst
index e36c284d0..849dfd75f 100644
--- a/doc/user_guide/transform/aggregate.rst
+++ b/doc/user_guide/transform/aggregate.rst
@@ -21,7 +21,7 @@ grouped by the number of Cylinders.
 .. altair-plot::
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     cars = data.cars.url
 
diff --git a/doc/user_guide/transform/bin.rst b/doc/user_guide/transform/bin.rst
index 6129cd3ec..fd71f8719 100644
--- a/doc/user_guide/transform/bin.rst
+++ b/doc/user_guide/transform/bin.rst
@@ -13,12 +13,12 @@ An common application of a bin transform is when creating a histogram:
 .. altair-plot::
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     movies = data.movies.url
 
     alt.Chart(movies).mark_bar().encode(
-        alt.X("IMDB_Rating:Q").bin(),
+        alt.X("IMDB Rating:Q").bin(),
         y='count()',
     )
 
@@ -28,7 +28,7 @@ bin a continuous field to create a discrete color map:
 .. altair-plot::
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     cars = data.cars.url
 
@@ -52,7 +52,7 @@ Here is the above histogram created using a top-level bin transform:
 .. altair-plot::
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     movies = data.movies.url
 
@@ -60,7 +60,7 @@ Here is the above histogram created using a top-level bin transform:
         x='binned_rating:O',
         y='count()',
     ).transform_bin(
-        'binned_rating', field='IMDB_Rating'
+        'binned_rating', field='IMDB Rating'
     )
 
 And here is the transformed color scale using a top-level bin transform:
@@ -68,7 +68,7 @@ And here is the transformed color scale using a top-level bin transform:
 .. altair-plot::
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     cars = data.cars.url
 
diff --git a/doc/user_guide/transform/density.rst b/doc/user_guide/transform/density.rst
index 4e6f770c2..031007eb1 100644
--- a/doc/user_guide/transform/density.rst
+++ b/doc/user_guide/transform/density.rst
@@ -14,13 +14,13 @@ dataset:
 .. altair-plot::
 
    import altair as alt
-   from vega_datasets import data
+   from altair.datasets import data
 
    alt.Chart(data.movies.url).transform_density(
-       'IMDB_Rating',
-       as_=['IMDB_Rating', 'density'],
+       'IMDB Rating',
+       as_=['IMDB Rating', 'density'],
    ).mark_area().encode(
-       x="IMDB_Rating:Q",
+       x="IMDB Rating:Q",
        y='density:Q',
    )
 
@@ -30,7 +30,7 @@ argument. Here we split the above density computation across movie genres:
 .. altair-plot::
 
    import altair as alt
-   from vega_datasets import data
+   from altair.datasets import data
 
    alt.Chart(
        data.movies.url,
@@ -39,12 +39,12 @@ argument. Here we split the above density computation across movie genres:
    ).transform_filter(
        'isValid(datum.Major_Genre)'
    ).transform_density(
-       'IMDB_Rating',
+       'IMDB Rating',
        groupby=['Major_Genre'],
-       as_=['IMDB_Rating', 'density'],
+       as_=['IMDB Rating', 'density'],
        extent=[1, 10],
    ).mark_area().encode(
-       x="IMDB_Rating:Q",
+       x="IMDB Rating:Q",
        y='density:Q',
    ).facet(
        'Major_Genre:N',
diff --git a/doc/user_guide/transform/filter.rst b/doc/user_guide/transform/filter.rst
index 62ee6e334..df4428d3c 100644
--- a/doc/user_guide/transform/filter.rst
+++ b/doc/user_guide/transform/filter.rst
@@ -35,7 +35,7 @@ For example:
     import altair as alt
     from altair import datum
 
-    from vega_datasets import data
+    from altair.datasets import data
     pop = data.population.url
 
     alt.Chart(pop).mark_area().encode(
@@ -75,7 +75,7 @@ values from year 2000 as in the above chart:
 .. altair-plot::
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
     pop = data.population.url
 
     alt.Chart(pop).mark_line().encode(
@@ -92,7 +92,7 @@ of specific values:
 .. altair-plot::
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
     pop = data.population.url
 
     alt.Chart(pop).mark_line().encode(
@@ -109,7 +109,7 @@ particular continuous range:
 .. altair-plot::
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
     pop = data.population.url
 
     alt.Chart(pop).mark_line().encode(
@@ -132,7 +132,7 @@ to select the data to be shown in the top chart:
 .. altair-plot::
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
     pop = data.population.url
 
     selection = alt.selection_point(fields=['year'])
@@ -170,7 +170,7 @@ First, we use a :class:`~FieldRangePredicate` to select *1950-1960*:
     :output: none
     
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.population.url
     chart = alt.Chart(source).mark_line().encode(
diff --git a/doc/user_guide/transform/index.rst b/doc/user_guide/transform/index.rst
index 541922e4d..526e612e5 100644
--- a/doc/user_guide/transform/index.rst
+++ b/doc/user_guide/transform/index.rst
@@ -75,7 +75,7 @@ to extract a pandas DataFrame containing the transformed data.
     :output: repr
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     cars = data.cars.url
     chart = alt.Chart(cars).mark_bar().encode(
diff --git a/doc/user_guide/transform/joinaggregate.rst b/doc/user_guide/transform/joinaggregate.rst
index 43a4d76bc..de3fb6896 100644
--- a/doc/user_guide/transform/joinaggregate.rst
+++ b/doc/user_guide/transform/joinaggregate.rst
@@ -49,18 +49,18 @@ standard deviation, which requires calculations on the joined data:
 .. altair-plot::
 
    import altair as alt
-   from vega_datasets import data
+   from altair.datasets import data
 
    alt.Chart(data.movies.url).transform_filter(
-       'datum.IMDB_Rating != null  && datum.Rotten_Tomatoes_Rating != null'
+       'datum["IMDB Rating"] != null  && datum["Rotten Tomatoes Rating"] != null'
    ).transform_joinaggregate(
-       IMDB_mean='mean(IMDB_Rating)',
-       IMDB_std='stdev(IMDB_Rating)',
-       RT_mean='mean(Rotten_Tomatoes_Rating)',
-       RT_std='stdev(Rotten_Tomatoes_Rating)'
+       IMDB_mean='mean(IMDB Rating)',
+       IMDB_std='stdev(IMDB Rating)',
+       RT_mean='mean(Rotten Tomatoes Rating)',
+       RT_std='stdev(Rotten Tomatoes Rating)'
    ).transform_calculate(
-       IMDB_Deviation="(datum.IMDB_Rating - datum.IMDB_mean) / datum.IMDB_std",
-       Rotten_Tomatoes_Deviation="(datum.Rotten_Tomatoes_Rating - datum.RT_mean) / datum.RT_std"
+       IMDB_Deviation='(datum["IMDB Rating"] - datum.IMDB_mean) / datum.IMDB_std',
+       Rotten_Tomatoes_Deviation='(datum["Rotten Tomatoes Rating"] - datum.RT_mean) / datum.RT_std'
    ).mark_point().encode(
        x='IMDB_Deviation:Q',
        y="Rotten_Tomatoes_Deviation:Q"
diff --git a/doc/user_guide/transform/lookup.rst b/doc/user_guide/transform/lookup.rst
index ab7bb550f..63a0238ca 100644
--- a/doc/user_guide/transform/lookup.rst
+++ b/doc/user_guide/transform/lookup.rst
@@ -11,12 +11,12 @@ at the top level of a chart using the :meth:`Chart.transform_lookup` method.
 By way of example, imagine you have two sources of data that you would like
 to combine and plot: one is a list of names of people along with their height
 and weight, and the other is some information about which groups they belong
-to. This example data is available in ``vega_datasets``:
+to. This example data is available in the `altair.datasets` package:
 
 .. altair-plot::
    :output: none
 
-   from vega_datasets import data
+   from altair.datasets import data
    people = data.lookup_people()
    groups = data.lookup_groups()
 
@@ -107,7 +107,7 @@ of unemployment rates per county in the US:
 .. altair-plot::
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     counties = alt.topo_feature(data.us_10m.url, 'counties')
     unemp_data = data.unemployment.url
diff --git a/doc/user_guide/transform/pivot.rst b/doc/user_guide/transform/pivot.rst
index 80f38030f..61fb5b12b 100644
--- a/doc/user_guide/transform/pivot.rst
+++ b/doc/user_guide/transform/pivot.rst
@@ -44,7 +44,7 @@ values on multiple lines:
 .. altair-plot::
 
    import altair as alt
-   from vega_datasets import data
+   from altair.datasets import data
 
    source = data.stocks()
    base = alt.Chart(source).encode(x='date:T')
diff --git a/doc/user_guide/transform/sample.rst b/doc/user_guide/transform/sample.rst
index 7253fe99c..d8369de34 100644
--- a/doc/user_guide/transform/sample.rst
+++ b/doc/user_guide/transform/sample.rst
@@ -15,7 +15,7 @@ rows:
 .. altair-plot::
 
    import altair as alt
-   from vega_datasets import data
+   from altair.datasets import data
 
    source = data.cars.url
 
diff --git a/doc/user_guide/transform/stack.rst b/doc/user_guide/transform/stack.rst
index 088bc95e8..8a1fce2db 100644
--- a/doc/user_guide/transform/stack.rst
+++ b/doc/user_guide/transform/stack.rst
@@ -10,7 +10,7 @@ of encodings. For example, consider this stacked bar chart:
 .. altair-plot::
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.barley()
 
@@ -28,7 +28,7 @@ We can construct that same chart manually using the stack transform:
 .. altair-plot::
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = data.barley()
 
diff --git a/doc/user_guide/transform/timeunit.rst b/doc/user_guide/transform/timeunit.rst
index b36d3e3bc..850c83042 100644
--- a/doc/user_guide/transform/timeunit.rst
+++ b/doc/user_guide/transform/timeunit.rst
@@ -25,33 +25,33 @@ These are the available time units:
 
 TimeUnit Within Encoding
 ^^^^^^^^^^^^^^^^^^^^^^^^
-Any temporal field definition can include a ``timeUnit`` argument to discretize
-the temporal data.
+Any temperatureoral field definition can include a ``timeUnit`` argument to discretize
+the temperatureoral data.
 
-For example, here we plot a dataset that consists of hourly temperature
+For example, here we plot a dataset that consists of hourly temperatureerature
 measurements in Seattle during the year 2010:
 
 .. altair-plot::
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
-    temps = data.seattle_temps.url
+    temperatures = data.seattle_weather_hourly_normals.url
 
-    alt.Chart(temps).mark_line().encode(
+    alt.Chart(temperatures).mark_line().encode(
         x='date:T',
-        y='temp:Q'
+        y='temperature:Q'
     )
 
 The plot is too busy due to the amount of data points squeezed into the short
 time; we can make it a bit cleaner by discretizing it, for example, by month
-and plotting only the mean monthly temperature:
+and plotting only the mean monthly temperatureerature:
 
 .. altair-plot::
 
-    alt.Chart(temps).mark_line().encode(
+    alt.Chart(temperatures).mark_line().encode(
         x='month(date):T',
-        y='mean(temp):Q'
+        y='mean(temperature):Q'
     )
 
 Notice that by default timeUnit output is a continuous quantity; if you would
@@ -61,23 +61,23 @@ This can be useful when plotting a bar chart or other discrete chart type:
 
 .. altair-plot::
 
-    alt.Chart(temps).mark_bar().encode(
+    alt.Chart(temperatures).mark_bar().encode(
         x='month(date):O',
-        y='mean(temp):Q'
+        y='mean(temperature):Q'
     )
 
 Multiple time units can be combined within a single plot to yield interesting
 views of your data; for example, here we extract both the month and the day
-to give a profile of Seattle temperatures through the year:
+to give a profile of Seattle temperatureeratures through the year:
 
 .. altair-plot::
 
-    alt.Chart(temps).mark_rect().encode(
+    alt.Chart(temperatures).mark_rect().encode(
         alt.X('date(date):O').title('day'),
         alt.Y('month(date):O').title('month'),
-        color='max(temp):Q'
+        color='max(temperature):Q'
     ).properties(
-        title="2010 Daily High Temperatures in Seattle (F)"
+        title="2010 Daily High Temperatures in Seattle (C)"
     )
 
 TimeUnit as a Transform
@@ -89,9 +89,9 @@ method. For example:
 
 .. altair-plot::
 
-    alt.Chart(temps).mark_line().encode(
+    alt.Chart(temperatures).mark_line().encode(
         alt.X('month:T').axis(format='%b'),
-        y='mean(temp):Q'
+        y='mean(temperature):Q'
     ).transform_timeunit(
         month='month(date)'
     )
diff --git a/doc/user_guide/transform/window.rst b/doc/user_guide/transform/window.rst
index 9f79bd970..2efcb2f43 100644
--- a/doc/user_guide/transform/window.rst
+++ b/doc/user_guide/transform/window.rst
@@ -13,23 +13,28 @@ For example, consider the following cumulative frequency distribution:
 .. altair-plot::
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
-    alt.Chart(data.movies.url).transform_window(
-        sort=[{'field': 'IMDB_Rating'}],
+    alt.Chart(data.movies.url).transform_aggregate(
+        count='count(*)',
+        groupby=['IMDB Rating']
+    ).transform_window(
+        sort=[{'field': 'IMDB Rating'}],
         frame=[None, 0],
-        cumulative_count='count(*)',
+        cumulative_count='sum(count)',
     ).mark_area().encode(
-        x='IMDB_Rating:Q',
+        x='IMDB Rating:Q',
         y='cumulative_count:Q',
     )
 
-First, we pass a sort field definition, which indicates how data objects should be sorted within the window.
+First, we aggregate the data to count movies grouped by IMDB Rating.
+This creates a dataset where each row represents a unique IMDB Rating and its count.
+Next, we apply the window transform with a sort field definition, which indicates how data objects should be sorted within the window.
 Here, movies should be sorted by their IMDB rating.
-Next, we pass the frame, which indicates how many data objects before and after the current data object should be included within the window.
+We then pass the frame, which indicates how many data objects before and after the current data object should be included within the window.
 Here, all movies up to and including the current movie should be included.
 Finally, we pass a window field definition, which indicates how data objects should be aggregated within the window.
-Here, the number of movies should be counted.
+Here, we sum the counts to create a cumulative count.
 
 There are many aggregation functions built into Altair.
 As well as those given in :ref:`agg-func-table`, we can use the following within window field definitions:
@@ -57,7 +62,7 @@ For example, consider the following time series of stock prices:
 .. altair-plot::
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     alt.Chart(data.stocks.url).mark_line().encode(
         x='date:T',
@@ -71,7 +76,7 @@ If we plot the `z-scores`_ of the stock prices, rather than the stock prices the
 .. altair-plot::
 
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     alt.Chart(data.stocks.url).transform_window(
         mean_price='mean(price)',
diff --git a/pyproject.toml b/pyproject.toml
index 2fd8d99fb..d6de92f89 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -59,7 +59,6 @@ save = [
 ]
 all = [
     "altair[save]",
-    "vega_datasets>=0.9.0",
     "pandas>=1.1.3",
     "numpy",
     "pyarrow>=11",
@@ -230,7 +229,6 @@ extra-standard-library = ["typing_extensions"]
 known-first-party = [
     "altair_tiles",
     "sphinxext_altair",
-    "vega_datasets",
     "vegafusion",
     "vl_convert",
 ]
@@ -330,7 +328,6 @@ pretty = true
 
 [[tool.mypy.overrides]]
 module = [
-    "vega_datasets.*",
     "pyarrow.*",
     "yaml.*",
     "pandas.lib.*",
diff --git a/sphinxext/altairgallery.py b/sphinxext/altairgallery.py
index ea3a17837..1a0c97437 100644
--- a/sphinxext/altairgallery.py
+++ b/sphinxext/altairgallery.py
@@ -46,13 +46,16 @@
 
 This gallery contains a selection of examples of the plots Altair can create. Some may seem fairly complicated at first glance, but they are built by combining a simple set of declarative building blocks.
 
-Many draw upon sample datasets compiled by the `Vega <https://vega.github.io/vega/>`_ project. To access them yourself, install `vega_datasets <https://github.com/altair-viz/vega_datasets>`_.
+Many draw upon sample datasets compiled by the `Vega <https://vega.github.io/vega/>`_ project.
 
-.. code-block:: none
+If you can't find the plots you are looking for here, make sure to check out the :ref:`altair-ecosystem` section, which has links to packages for making e.g. network diagrams and animations.
 
-   python -m pip install vega_datasets
+.. note::
 
-If you can't find the plots you are looking for here, make sure to check out the :ref:`altair-ecosystem` section, which has links to packages for making e.g. network diagrams and animations.
+    With the release of Altair 6, the documentation was updated to use
+    ``from altair.datasets import data`` instead of ``from vega_datasets import data``.
+    This change also introduced updated column names in some datasets (e.g., spaces
+    instead of underscores).
 
 {% for grouper, group in examples %}
 
diff --git a/sphinxext/code_ref.py b/sphinxext/code_ref.py
index 93be67916..2c4071af1 100644
--- a/sphinxext/code_ref.py
+++ b/sphinxext/code_ref.py
@@ -58,7 +58,7 @@ def validate_output(output: Any) -> _OutputLong:
 
 def validate_packages(packages: Any) -> str:
     if packages is None:
-        return '["altair"]'
+        return '["altair", "vega-datasets"]'
     else:
         split = [pkg.strip() for pkg in packages.split(",")]
         if len(split) == 1:
@@ -221,6 +221,35 @@ def run(self) -> Sequence[nodes.Node]:
             assign_to="chart",
             indent=4,
         )
+        # For PyScript/Pyodide compatibility, use vega_datasets until new Altair is published
+        py_code = py_code.replace(
+            "from altair.datasets import data", "from vega_datasets import data"
+        )
+        # vega_datasets uses underscores in column names, not spaces
+        # Order matters: do aggregation functions first (they contain field names)
+        py_code = py_code.replace("mean(IMDB Rating)", "mean(IMDB_Rating)")
+        py_code = py_code.replace(
+            "mean(Rotten Tomatoes Rating)", "mean(Rotten_Tomatoes_Rating)"
+        )
+        py_code = py_code.replace('datum["IMDB Rating"]', "datum.IMDB_Rating")
+        py_code = py_code.replace(
+            'datum["Rotten Tomatoes Rating"]', "datum.Rotten_Tomatoes_Rating"
+        )
+        py_code = py_code.replace('datum["IMDB Votes"]', "datum.IMDB_Votes")
+        # Field references in encodings (remaining ones)
+        py_code = py_code.replace('"IMDB Rating"', '"IMDB_Rating"')
+        py_code = py_code.replace(
+            '"Rotten Tomatoes Rating"', '"Rotten_Tomatoes_Rating"'
+        )
+        py_code = py_code.replace('"IMDB Votes"', '"IMDB_Votes"')
+        py_code = py_code.replace('"Release Date"', '"Release_Date"')
+        py_code = py_code.replace("'IMDB Rating'", "'IMDB_Rating'")
+        py_code = py_code.replace(
+            "'Rotten Tomatoes Rating'", "'Rotten_Tomatoes_Rating'"
+        )
+        py_code = py_code.replace("'IMDB Votes'", "'IMDB_Votes'")
+        py_code = py_code.replace("'Release Date'", "'Release_Date'")
+
         results.extend(
             pyscript(packages, TARGET_DIV_ID, loading_label, py_code=py_code)
         )
diff --git a/tests/altair_theme_test.py b/tests/altair_theme_test.py
index 2f376bfb5..4e4564fec 100644
--- a/tests/altair_theme_test.py
+++ b/tests/altair_theme_test.py
@@ -9,13 +9,13 @@
 
 def alt_theme_test() -> ChartType:
     import altair as alt
+    from altair.datasets import data
 
-    VEGA_DATASETS = "https://cdn.jsdelivr.net/npm/vega-datasets@v3.2.1/data/"
-    us_10m = f"{VEGA_DATASETS}us-10m.json"
-    unemployment = f"{VEGA_DATASETS}unemployment.tsv"
-    movies = f"{VEGA_DATASETS}movies.json"
-    barley = f"{VEGA_DATASETS}barley.json"
-    iowa_electricity = f"{VEGA_DATASETS}iowa-electricity.csv"
+    us_10m = data.us_10m.url
+    unemployment = data.unemployment.url
+    movies = data.movies.url
+    barley = data.barley.url
+    iowa_electricity = data.iowa_electricity.url
     common_data = alt.InlineData(
         [
             {"Index": 1, "Value": 28, "Position": 1, "Category": "A"},
@@ -77,16 +77,16 @@ def alt_theme_test() -> ChartType:
     point = (
         alt.Chart(movies, height=STANDARD, width=STANDARD, title="Point")
         .mark_point(tooltip=True)
-        .transform_filter(alt.datum["IMDB_Rating"] != None)
+        .transform_filter(alt.datum["IMDB Rating"] != None)
         .transform_filter(
-            alt.FieldRangePredicate("Release_Date", [None, 2019], timeUnit="year")
+            alt.FieldRangePredicate("Release Date", [None, 2019], timeUnit="year")
         )
-        .transform_joinaggregate(Average_Rating="mean(IMDB_Rating)")
+        .transform_joinaggregate(Average_Rating="mean(IMDB Rating)")
         .transform_calculate(
-            Rating_Delta=alt.datum["IMDB_Rating"] - alt.datum.Average_Rating
+            Rating_Delta=alt.datum["IMDB Rating"] - alt.datum.Average_Rating
         )
         .encode(
-            x=alt.X("Release_Date:T").title("Release Date"),
+            x=alt.X("Release Date:T").title("Release Date"),
             y=alt.Y("Rating_Delta:Q").title("Rating Delta"),
             color=alt.Color("Rating_Delta:Q").title("Rating Delta").scale(domainMid=0),
         )
diff --git a/tests/examples_arguments_syntax/airport_connections.py b/tests/examples_arguments_syntax/airport_connections.py
index 6f5f62ed3..3a80b5668 100644
--- a/tests/examples_arguments_syntax/airport_connections.py
+++ b/tests/examples_arguments_syntax/airport_connections.py
@@ -7,7 +7,7 @@
 """
 # category: case studies
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 # Since these data are each more than 5,000 rows we'll import from the URLs
 airports = data.airports.url
diff --git a/tests/examples_arguments_syntax/annual_weather_heatmap.py b/tests/examples_arguments_syntax/annual_weather_heatmap.py
index 972c42404..5e8ba60ff 100644
--- a/tests/examples_arguments_syntax/annual_weather_heatmap.py
+++ b/tests/examples_arguments_syntax/annual_weather_heatmap.py
@@ -4,7 +4,7 @@
 """
 # category: tables
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.seattle_weather()
 
diff --git a/tests/examples_arguments_syntax/anscombe_plot.py b/tests/examples_arguments_syntax/anscombe_plot.py
index 71342fd90..b84b2aa62 100644
--- a/tests/examples_arguments_syntax/anscombe_plot.py
+++ b/tests/examples_arguments_syntax/anscombe_plot.py
@@ -13,7 +13,7 @@
 """
 # category: case studies
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.anscombe()
 
diff --git a/tests/examples_arguments_syntax/area_chart_gradient.py b/tests/examples_arguments_syntax/area_chart_gradient.py
index 4e2babf3f..80000a44d 100644
--- a/tests/examples_arguments_syntax/area_chart_gradient.py
+++ b/tests/examples_arguments_syntax/area_chart_gradient.py
@@ -7,7 +7,7 @@
 # category: area charts
 
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.stocks()
 
diff --git a/tests/examples_arguments_syntax/area_faceted.py b/tests/examples_arguments_syntax/area_faceted.py
index 4869a4157..2ed996109 100644
--- a/tests/examples_arguments_syntax/area_faceted.py
+++ b/tests/examples_arguments_syntax/area_faceted.py
@@ -7,7 +7,7 @@
 """
 # category: area charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.stocks()
 
diff --git a/tests/examples_arguments_syntax/bar_and_line_with_dual_axis.py b/tests/examples_arguments_syntax/bar_and_line_with_dual_axis.py
index 78e3010ec..34b64458d 100644
--- a/tests/examples_arguments_syntax/bar_and_line_with_dual_axis.py
+++ b/tests/examples_arguments_syntax/bar_and_line_with_dual_axis.py
@@ -7,7 +7,7 @@
 """
 # category: bar charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.wheat()
 
diff --git a/tests/examples_arguments_syntax/bar_chart_horizontal.py b/tests/examples_arguments_syntax/bar_chart_horizontal.py
index 9d145f7fd..8ed8afc59 100644
--- a/tests/examples_arguments_syntax/bar_chart_horizontal.py
+++ b/tests/examples_arguments_syntax/bar_chart_horizontal.py
@@ -5,7 +5,7 @@
 """
 # category: bar charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.wheat()
 
diff --git a/tests/examples_arguments_syntax/bar_chart_sorted.py b/tests/examples_arguments_syntax/bar_chart_sorted.py
index 1a88deb85..5a1308d98 100644
--- a/tests/examples_arguments_syntax/bar_chart_sorted.py
+++ b/tests/examples_arguments_syntax/bar_chart_sorted.py
@@ -5,7 +5,7 @@
 """
 # category: bar charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.barley()
 
diff --git a/tests/examples_arguments_syntax/bar_chart_with_highlighted_bar.py b/tests/examples_arguments_syntax/bar_chart_with_highlighted_bar.py
index 1041fb99f..944a62dff 100644
--- a/tests/examples_arguments_syntax/bar_chart_with_highlighted_bar.py
+++ b/tests/examples_arguments_syntax/bar_chart_with_highlighted_bar.py
@@ -5,7 +5,7 @@
 """
 # category: bar charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.wheat()
 
diff --git a/tests/examples_arguments_syntax/bar_chart_with_highlighted_segment.py b/tests/examples_arguments_syntax/bar_chart_with_highlighted_segment.py
index 09292fe55..1b6439c08 100644
--- a/tests/examples_arguments_syntax/bar_chart_with_highlighted_segment.py
+++ b/tests/examples_arguments_syntax/bar_chart_with_highlighted_segment.py
@@ -6,7 +6,7 @@
 # category: bar charts
 import altair as alt
 import pandas as pd
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.wheat()
 threshold = pd.DataFrame([{"threshold": 90}])
diff --git a/tests/examples_arguments_syntax/bar_chart_with_labels.py b/tests/examples_arguments_syntax/bar_chart_with_labels.py
index a477bb471..39171d63d 100644
--- a/tests/examples_arguments_syntax/bar_chart_with_labels.py
+++ b/tests/examples_arguments_syntax/bar_chart_with_labels.py
@@ -5,7 +5,7 @@
 """
 # category: bar charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 
 source = data.wheat()
diff --git a/tests/examples_arguments_syntax/bar_chart_with_labels_measured_luminance.py b/tests/examples_arguments_syntax/bar_chart_with_labels_measured_luminance.py
index bd08223c0..01664a3db 100644
--- a/tests/examples_arguments_syntax/bar_chart_with_labels_measured_luminance.py
+++ b/tests/examples_arguments_syntax/bar_chart_with_labels_measured_luminance.py
@@ -5,7 +5,7 @@
 """
 # category: bar charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.barley()
 
diff --git a/tests/examples_arguments_syntax/bar_chart_with_mean_line.py b/tests/examples_arguments_syntax/bar_chart_with_mean_line.py
index 047578f98..1ab164d67 100644
--- a/tests/examples_arguments_syntax/bar_chart_with_mean_line.py
+++ b/tests/examples_arguments_syntax/bar_chart_with_mean_line.py
@@ -5,7 +5,7 @@
 """
 # category: bar charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.wheat()
 
diff --git a/tests/examples_arguments_syntax/bar_chart_with_negatives.py b/tests/examples_arguments_syntax/bar_chart_with_negatives.py
index d3ff3fbc5..71c4e44af 100644
--- a/tests/examples_arguments_syntax/bar_chart_with_negatives.py
+++ b/tests/examples_arguments_syntax/bar_chart_with_negatives.py
@@ -5,7 +5,7 @@
 """
 # category: bar charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.us_employment()
 
diff --git a/tests/examples_arguments_syntax/bar_chart_with_range.py b/tests/examples_arguments_syntax/bar_chart_with_range.py
index ef9e1dea2..820170f0a 100644
--- a/tests/examples_arguments_syntax/bar_chart_with_range.py
+++ b/tests/examples_arguments_syntax/bar_chart_with_range.py
@@ -5,7 +5,7 @@
 """
 # category: bar charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.seattle_weather()
 
diff --git a/tests/examples_arguments_syntax/bar_faceted_stacked.py b/tests/examples_arguments_syntax/bar_faceted_stacked.py
index 57f3816d7..9096738c3 100644
--- a/tests/examples_arguments_syntax/bar_faceted_stacked.py
+++ b/tests/examples_arguments_syntax/bar_faceted_stacked.py
@@ -7,7 +7,7 @@
 """
 # category: bar charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.barley()
 
diff --git a/tests/examples_arguments_syntax/bar_rounded.py b/tests/examples_arguments_syntax/bar_rounded.py
index f01ce6027..180c31928 100644
--- a/tests/examples_arguments_syntax/bar_rounded.py
+++ b/tests/examples_arguments_syntax/bar_rounded.py
@@ -5,7 +5,7 @@
 """
 # category: bar charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.seattle_weather()
 
diff --git a/tests/examples_arguments_syntax/bar_with_rolling_mean.py b/tests/examples_arguments_syntax/bar_with_rolling_mean.py
index dc1dd38a6..3d269c741 100644
--- a/tests/examples_arguments_syntax/bar_with_rolling_mean.py
+++ b/tests/examples_arguments_syntax/bar_with_rolling_mean.py
@@ -5,7 +5,7 @@
 """
 # category: bar charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.wheat()
 
diff --git a/tests/examples_arguments_syntax/beckers_barley_facet.py b/tests/examples_arguments_syntax/beckers_barley_facet.py
index 5ae4cfa39..98a7d858f 100644
--- a/tests/examples_arguments_syntax/beckers_barley_facet.py
+++ b/tests/examples_arguments_syntax/beckers_barley_facet.py
@@ -11,7 +11,7 @@
 """
 # category: case studies
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.barley()
 
diff --git a/tests/examples_arguments_syntax/beckers_barley_wrapped_facet.py b/tests/examples_arguments_syntax/beckers_barley_wrapped_facet.py
index 82d682d8f..eeada0326 100644
--- a/tests/examples_arguments_syntax/beckers_barley_wrapped_facet.py
+++ b/tests/examples_arguments_syntax/beckers_barley_wrapped_facet.py
@@ -11,7 +11,7 @@
 """
 # category: case studies
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.barley.url
 
diff --git a/tests/examples_arguments_syntax/boxplot.py b/tests/examples_arguments_syntax/boxplot.py
index a98c637b1..92964a0d3 100644
--- a/tests/examples_arguments_syntax/boxplot.py
+++ b/tests/examples_arguments_syntax/boxplot.py
@@ -8,7 +8,7 @@
 """
 # category: distributions
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.population.url
 
diff --git a/tests/examples_arguments_syntax/bubble_plot.py b/tests/examples_arguments_syntax/bubble_plot.py
index 44b74bced..f9080079b 100644
--- a/tests/examples_arguments_syntax/bubble_plot.py
+++ b/tests/examples_arguments_syntax/bubble_plot.py
@@ -5,7 +5,7 @@
 """
 # category: scatter plots
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.cars()
 
diff --git a/tests/examples_arguments_syntax/bump_chart.py b/tests/examples_arguments_syntax/bump_chart.py
index 0d1fb99b3..72a79dccb 100644
--- a/tests/examples_arguments_syntax/bump_chart.py
+++ b/tests/examples_arguments_syntax/bump_chart.py
@@ -8,7 +8,7 @@
 # category: line charts
 
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 import pandas as pd
 
 stocks = data.stocks()
diff --git a/tests/examples_arguments_syntax/calculate_residuals.py b/tests/examples_arguments_syntax/calculate_residuals.py
index b8e8fe227..7714e211f 100644
--- a/tests/examples_arguments_syntax/calculate_residuals.py
+++ b/tests/examples_arguments_syntax/calculate_residuals.py
@@ -8,11 +8,10 @@
 Adapted from `Calculate Residuals <https://vega.github.io/vega-lite/examples/joinaggregate_residual_graph.html>`_.
 """
 # category: advanced calculations
-
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
-imdb_rating = alt.datum["IMDB_Rating"]
+imdb_rating = alt.datum["IMDB Rating"]
 source = data.movies.url
 
 chart = (
@@ -20,12 +19,12 @@
     .mark_point()
     .transform_filter(imdb_rating != None)
     .transform_filter(
-        alt.FieldRangePredicate("Release_Date", [None, 2019], timeUnit="year")
+        alt.FieldRangePredicate("Release Date", [None, 2019], timeUnit="year")
     )
-    .transform_joinaggregate(Average_Rating="mean(IMDB_Rating)")
+    .transform_joinaggregate(Average_Rating="mean(IMDB Rating)")
     .transform_calculate(Rating_Delta=imdb_rating - alt.datum.Average_Rating)
     .encode(
-        x=alt.X("Release_Date:T", title="Release Date"),
+        x=alt.X("Release Date:T", title="Release Date"),
         y=alt.Y("Rating_Delta:Q", title="Rating Delta"),
         color=alt.Color(
             "Rating_Delta:Q",
diff --git a/tests/examples_arguments_syntax/candlestick_chart.py b/tests/examples_arguments_syntax/candlestick_chart.py
index 4dc524782..c8a4cc831 100644
--- a/tests/examples_arguments_syntax/candlestick_chart.py
+++ b/tests/examples_arguments_syntax/candlestick_chart.py
@@ -8,7 +8,7 @@
 """
 # category: advanced calculations
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.ohlc()
 
diff --git a/tests/examples_arguments_syntax/choropleth.py b/tests/examples_arguments_syntax/choropleth.py
index 889edb2f5..d4f2d6ae0 100644
--- a/tests/examples_arguments_syntax/choropleth.py
+++ b/tests/examples_arguments_syntax/choropleth.py
@@ -5,7 +5,7 @@
 """
 # category: maps
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 counties = alt.topo_feature(data.us_10m.url, 'counties')
 source = data.unemployment.url
diff --git a/tests/examples_arguments_syntax/choropleth_repeat.py b/tests/examples_arguments_syntax/choropleth_repeat.py
index 3cd913ec4..637a4c71d 100644
--- a/tests/examples_arguments_syntax/choropleth_repeat.py
+++ b/tests/examples_arguments_syntax/choropleth_repeat.py
@@ -5,7 +5,7 @@
 """
 # category: maps
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 states = alt.topo_feature(data.us_10m.url, 'states')
 source = data.population_engineers_hurricanes.url
diff --git a/tests/examples_arguments_syntax/co2_concentration.py b/tests/examples_arguments_syntax/co2_concentration.py
index cd53d4ed7..4ec8af311 100644
--- a/tests/examples_arguments_syntax/co2_concentration.py
+++ b/tests/examples_arguments_syntax/co2_concentration.py
@@ -7,7 +7,7 @@
 """
 # category: case studies
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.co2_concentration.url
 
diff --git a/tests/examples_arguments_syntax/comet_chart.py b/tests/examples_arguments_syntax/comet_chart.py
index 32dd9392c..481467552 100644
--- a/tests/examples_arguments_syntax/comet_chart.py
+++ b/tests/examples_arguments_syntax/comet_chart.py
@@ -9,10 +9,10 @@
 # category: advanced calculations
 
 import altair as alt
-import vega_datasets
+from altair.datasets import data
 
 (
-    alt.Chart(vega_datasets.data.barley.url)
+    alt.Chart(data.barley.url)
     .transform_pivot("year", value="yield", groupby=["variety", "site"])
     .transform_fold(["1931", "1932"], as_=["year", "yield"])
     .transform_calculate(calculate="datum['1932'] - datum['1931']", as_="delta")
diff --git a/tests/examples_arguments_syntax/cumulative_count_chart.py b/tests/examples_arguments_syntax/cumulative_count_chart.py
index 6ee7ad277..4aaaae463 100644
--- a/tests/examples_arguments_syntax/cumulative_count_chart.py
+++ b/tests/examples_arguments_syntax/cumulative_count_chart.py
@@ -8,14 +8,14 @@
 # category: distributions
 
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.movies.url
 
 alt.Chart(source).transform_window(
     cumulative_count="count()",
-    sort=[{"field": "IMDB_Rating"}],
+    sort=[{"field": "IMDB Rating"}],
 ).mark_area().encode(
-    x="IMDB_Rating:Q",
+    x="IMDB Rating:Q",
     y=alt.Y("cumulative_count:Q", stack=False)
 )
diff --git a/tests/examples_arguments_syntax/density_repeat.py b/tests/examples_arguments_syntax/density_repeat.py
index 1db2b4c60..006c3de23 100644
--- a/tests/examples_arguments_syntax/density_repeat.py
+++ b/tests/examples_arguments_syntax/density_repeat.py
@@ -1,34 +1,33 @@
 """
 Repeated Density Estimates
 --------------------------
-Density estimates for each feature of iris flower.
+Density estimates for each measurement of penguins.
 This is what we call a "repeated" plot, with one subplot
-for each feature.
+for each measurement type. All measurements are in millimeters,
+making them directly comparable on a shared x-axis.
 """
 # category: distributions
 
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
-source = data.iris()
+source = data.penguins()
 
 alt.Chart(source).transform_fold(
     [
-        "petalWidth",
-        "petalLength",
-        "sepalWidth",
-        "sepalLength",
+        "Beak Length (mm)",
+        "Beak Depth (mm)",
+        "Flipper Length (mm)",
     ],
-    as_=["Measurement_type", "value"],
+    as_=["Measurement Type", "value"],
 ).transform_density(
     density="value",
-    bandwidth=0.3,
-    groupby=["Measurement_type"],
-    extent=[0, 8],
+    groupby=["Measurement Type"]
 ).mark_area().encode(
     alt.X("value:Q"),
     alt.Y("density:Q"),
-    alt.Row("Measurement_type:N"),
+    alt.Row("Measurement Type:N", header=alt.Header(labelAngle=0, labelAlign="left"))
 ).properties(
-    width=300, height=50
+    width=300,
+    height=50
 )
diff --git a/tests/examples_arguments_syntax/density_stack.py b/tests/examples_arguments_syntax/density_stack.py
index e408e308d..a8cd0c9ac 100644
--- a/tests/examples_arguments_syntax/density_stack.py
+++ b/tests/examples_arguments_syntax/density_stack.py
@@ -3,7 +3,7 @@
 -------------------------
 To plot a stacked graph of estimates, use a shared ``extent`` and a fixed
 number of subdivision ``steps`` to ensure that the points for each area align
-well.  Density estimates of measurements for each iris flower feature are plot
+well.  Density estimates of body mass for each penguin species are plotted
 in a stacked method.  In addition, setting ``counts`` to true multiplies the
 densities by the number of data points in each group, preserving proportional
 differences.
@@ -11,25 +11,22 @@
 # category: distributions
 
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
-source = data.iris()
+source = data.penguins()
 
-alt.Chart(source).transform_fold(
-    ['petalWidth', 
-     'petalLength', 
-     'sepalWidth', 
-     'sepalLength'], 
-    as_ = ['Measurement_type', 'value']
-).transform_density(
-    density='value', 
-    bandwidth=0.3, 
-    groupby=['Measurement_type'], 
-    extent= [0, 8], 
-    counts = True, 
-    steps=200
+alt.Chart(source).transform_density(
+    density='Body Mass (g)',
+    groupby=['Species'], 
+    extent= [2500, 6500],
+    counts = True,
+    steps=200    
 ).mark_area().encode(
-    alt.X('value:Q'), 
+    alt.X('value:Q').title('Body Mass (g)'), 
     alt.Y('density:Q', stack='zero'),
-    alt.Color('Measurement_type:N')
-).properties(width=400, height=100)
+    alt.Color('Species:N')
+).properties(
+    width=400,
+    height=80,
+    title='Distribution of Body Mass of Penguins'
+)
diff --git a/tests/examples_arguments_syntax/deviation_ellipses.py b/tests/examples_arguments_syntax/deviation_ellipses.py
index 0cc45d317..83d60bbff 100644
--- a/tests/examples_arguments_syntax/deviation_ellipses.py
+++ b/tests/examples_arguments_syntax/deviation_ellipses.py
@@ -1,7 +1,7 @@
 """
 Confidence Interval Ellipses
 ----------------------------
-This example shows bivariate deviation ellipses of petal length and width of three iris species.
+This example shows bivariate deviation ellipses of flipper length and body mass of three penguin species.
 
 Inspired by `ggplot2.stat_ellipse`_ and directly based on `Deviation ellipses example`_ by `@essicolo`_
 
@@ -19,7 +19,7 @@
 from scipy.stats import f as F
 
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 
 def confidence_region_2d(arr, conf_level=0.95, segments=50):
@@ -55,22 +55,22 @@ def grouped_confidence_regions(df, col_x, col_y, col_group):
     ellipses = []
     ser: pd.Series[float] = df[col_group]
     for group in ser.drop_duplicates():
-        arr = df.loc[ser == group, cols].to_numpy()
+        arr = df.loc[ser == group, cols].to_numpy(dtype=np.float64)
         ellipse = pd.DataFrame(confidence_region_2d(arr), columns=cols)
         ellipse[col_group] = group
         ellipses.append(ellipse)
     return pd.concat(ellipses).reset_index(names="order")
 
 
-col_x = "petalLength"
-col_y = "petalWidth"
-col_group = "species"
+col_x = "Flipper Length (mm)"
+col_y = "Body Mass (g)"
+col_group = "Species"
 
 x = alt.X(col_x, scale=alt.Scale(zero=False))
 y = alt.Y(col_y, scale=alt.Scale(zero=False))
 color = alt.Color(col_group)
 
-source = data.iris()
+source = data.penguins().dropna(subset=[col_x, col_y, col_group])
 ellipse = grouped_confidence_regions(source, col_x=col_x, col_y=col_y, col_group=col_group)
 points = alt.Chart(source).mark_circle(size=50, tooltip=True).encode(
     x=x,
diff --git a/tests/examples_arguments_syntax/distributions_faceted_histogram.py b/tests/examples_arguments_syntax/distributions_faceted_histogram.py
index 7aeb2f6e1..9beb7cbcf 100644
--- a/tests/examples_arguments_syntax/distributions_faceted_histogram.py
+++ b/tests/examples_arguments_syntax/distributions_faceted_histogram.py
@@ -9,7 +9,7 @@
 """
 # category: distributions
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.cars()
 
diff --git a/tests/examples_arguments_syntax/dot_dash_plot.py b/tests/examples_arguments_syntax/dot_dash_plot.py
index 64c6ef450..4e06a6e14 100644
--- a/tests/examples_arguments_syntax/dot_dash_plot.py
+++ b/tests/examples_arguments_syntax/dot_dash_plot.py
@@ -6,7 +6,7 @@
 """
 # category: distributions
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.cars()
 
diff --git a/tests/examples_arguments_syntax/empirical_cumulative_distribution_function.py b/tests/examples_arguments_syntax/empirical_cumulative_distribution_function.py
index 2563943ac..549a5933b 100644
--- a/tests/examples_arguments_syntax/empirical_cumulative_distribution_function.py
+++ b/tests/examples_arguments_syntax/empirical_cumulative_distribution_function.py
@@ -5,16 +5,16 @@
 """
 # category: distributions
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.movies.url
 
 alt.Chart(source).transform_window(
     ecdf="cume_dist()",
-    sort=[{"field": "IMDB_Rating"}],
+    sort=[{"field": "IMDB Rating"}],
 ).mark_line(
     interpolate="step-after"
 ).encode(
-    x="IMDB_Rating:Q",
+    x="IMDB Rating:Q",
     y="ecdf:Q"
 )
diff --git a/tests/examples_arguments_syntax/errorbars_with_ci.py b/tests/examples_arguments_syntax/errorbars_with_ci.py
index 55c706ecc..7f2e67aa9 100644
--- a/tests/examples_arguments_syntax/errorbars_with_ci.py
+++ b/tests/examples_arguments_syntax/errorbars_with_ci.py
@@ -7,7 +7,7 @@
 """
 # category: uncertainties and trends
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.barley()
 
diff --git a/tests/examples_arguments_syntax/errorbars_with_std.py b/tests/examples_arguments_syntax/errorbars_with_std.py
index 167bc7283..824f30606 100644
--- a/tests/examples_arguments_syntax/errorbars_with_std.py
+++ b/tests/examples_arguments_syntax/errorbars_with_std.py
@@ -6,7 +6,7 @@
 """
 # category: uncertainties and trends
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.barley()
 
diff --git a/tests/examples_arguments_syntax/filled_step_chart.py b/tests/examples_arguments_syntax/filled_step_chart.py
index dadb5770e..ed9920e38 100644
--- a/tests/examples_arguments_syntax/filled_step_chart.py
+++ b/tests/examples_arguments_syntax/filled_step_chart.py
@@ -5,7 +5,7 @@
 """
 # category: line charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.stocks()
 
diff --git a/tests/examples_arguments_syntax/gapminder_bubble_plot.py b/tests/examples_arguments_syntax/gapminder_bubble_plot.py
index 381f81017..07e9579a2 100644
--- a/tests/examples_arguments_syntax/gapminder_bubble_plot.py
+++ b/tests/examples_arguments_syntax/gapminder_bubble_plot.py
@@ -7,7 +7,7 @@
 """
 # category: case studies
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.gapminder_health_income.url
 
diff --git a/tests/examples_arguments_syntax/groupby-map.py b/tests/examples_arguments_syntax/groupby-map.py
index adb4e0256..f498df7c8 100644
--- a/tests/examples_arguments_syntax/groupby-map.py
+++ b/tests/examples_arguments_syntax/groupby-map.py
@@ -5,7 +5,7 @@
 """
 # category: maps
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 airports = data.airports.url
 states = alt.topo_feature(data.us_10m.url, feature='states')
diff --git a/tests/examples_arguments_syntax/grouped_bar_chart.py b/tests/examples_arguments_syntax/grouped_bar_chart.py
index 211167b94..5b8edb00d 100644
--- a/tests/examples_arguments_syntax/grouped_bar_chart.py
+++ b/tests/examples_arguments_syntax/grouped_bar_chart.py
@@ -5,7 +5,7 @@
 """
 # category: bar charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.barley()
 
diff --git a/tests/examples_arguments_syntax/grouped_bar_chart_horizontal.py b/tests/examples_arguments_syntax/grouped_bar_chart_horizontal.py
index b4ac2ec81..799f363ce 100644
--- a/tests/examples_arguments_syntax/grouped_bar_chart_horizontal.py
+++ b/tests/examples_arguments_syntax/grouped_bar_chart_horizontal.py
@@ -5,7 +5,7 @@
 """
 # category: bar charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.barley()
 
diff --git a/tests/examples_arguments_syntax/grouped_bar_chart_with_error_bars.py b/tests/examples_arguments_syntax/grouped_bar_chart_with_error_bars.py
index c1eab965d..3cef8ef59 100644
--- a/tests/examples_arguments_syntax/grouped_bar_chart_with_error_bars.py
+++ b/tests/examples_arguments_syntax/grouped_bar_chart_with_error_bars.py
@@ -5,7 +5,7 @@
 """
 # category: bar charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.barley()
 
diff --git a/tests/examples_arguments_syntax/heat_lane.py b/tests/examples_arguments_syntax/heat_lane.py
index 7239c1f98..f89d010fd 100644
--- a/tests/examples_arguments_syntax/heat_lane.py
+++ b/tests/examples_arguments_syntax/heat_lane.py
@@ -5,7 +5,7 @@
 """
 # category: distributions
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.cars.url
 
diff --git a/tests/examples_arguments_syntax/hexbins.py b/tests/examples_arguments_syntax/hexbins.py
index 3005fcf00..7acf6d2b8 100644
--- a/tests/examples_arguments_syntax/hexbins.py
+++ b/tests/examples_arguments_syntax/hexbins.py
@@ -5,7 +5,7 @@
 """
 # category: tables
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.seattle_weather()
 
diff --git a/tests/examples_arguments_syntax/histogram_gradient_color.py b/tests/examples_arguments_syntax/histogram_gradient_color.py
index 6bd3e7b6e..1a8a1f1e4 100644
--- a/tests/examples_arguments_syntax/histogram_gradient_color.py
+++ b/tests/examples_arguments_syntax/histogram_gradient_color.py
@@ -6,17 +6,17 @@
 """
 # category: distributions
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.movies.url
 
 alt.Chart(source).mark_bar().encode(
-    alt.X("IMDB_Rating:Q", 
+    alt.X("IMDB Rating:Q", 
         bin=alt.Bin(maxbins=20), 
         scale=alt.Scale(domain=[1, 10])
     ),
     alt.Y('count()'),
-    alt.Color("IMDB_Rating:Q", 
+    alt.Color("IMDB Rating:Q", 
         bin=alt.Bin(maxbins=20), 
         scale=alt.Scale(scheme='pinkyellowgreen')
     )
diff --git a/tests/examples_arguments_syntax/histogram_heatmap.py b/tests/examples_arguments_syntax/histogram_heatmap.py
index e284449f3..0fa1c3d5c 100644
--- a/tests/examples_arguments_syntax/histogram_heatmap.py
+++ b/tests/examples_arguments_syntax/histogram_heatmap.py
@@ -5,12 +5,12 @@
 """
 # category: distributions
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.movies.url
 
 alt.Chart(source).mark_rect().encode(
-    alt.X('IMDB_Rating:Q', bin=alt.Bin(maxbins=60)),
-    alt.Y('Rotten_Tomatoes_Rating:Q', bin=alt.Bin(maxbins=40)),
+    alt.X('IMDB Rating:Q', bin=alt.Bin(maxbins=60)),
+    alt.Y('Rotten Tomatoes Rating:Q', bin=alt.Bin(maxbins=40)),
     alt.Color('count():Q', scale=alt.Scale(scheme='greenblue'))
 )
diff --git a/tests/examples_arguments_syntax/histogram_responsive.py b/tests/examples_arguments_syntax/histogram_responsive.py
index 8e3cfdc48..e3c90c90e 100644
--- a/tests/examples_arguments_syntax/histogram_responsive.py
+++ b/tests/examples_arguments_syntax/histogram_responsive.py
@@ -7,7 +7,7 @@
 """
 # category: distributions
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.flights_5k.url
 
diff --git a/tests/examples_arguments_syntax/histogram_scatterplot.py b/tests/examples_arguments_syntax/histogram_scatterplot.py
index 482eee760..6530e4aaa 100644
--- a/tests/examples_arguments_syntax/histogram_scatterplot.py
+++ b/tests/examples_arguments_syntax/histogram_scatterplot.py
@@ -5,12 +5,12 @@
 """
 # category: distributions
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.movies.url
 
 alt.Chart(source).mark_circle().encode(
-    alt.X('IMDB_Rating:Q', bin=True),
-    alt.Y('Rotten_Tomatoes_Rating:Q', bin=True),
+    alt.X('IMDB Rating:Q', bin=True),
+    alt.Y('Rotten Tomatoes Rating:Q', bin=True),
     size='count()'
 )
diff --git a/tests/examples_arguments_syntax/histogram_with_a_global_mean_overlay.py b/tests/examples_arguments_syntax/histogram_with_a_global_mean_overlay.py
index f2cc9a390..5fcc0647b 100644
--- a/tests/examples_arguments_syntax/histogram_with_a_global_mean_overlay.py
+++ b/tests/examples_arguments_syntax/histogram_with_a_global_mean_overlay.py
@@ -5,19 +5,19 @@
 """
 # category: distributions
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.movies.url
 
 base = alt.Chart(source)
 
 bar = base.mark_bar().encode(
-    x=alt.X('IMDB_Rating:Q', bin=True, axis=None),
+    x=alt.X('IMDB Rating:Q', bin=True, axis=None),
     y='count()'
 )
 
 rule = base.mark_rule(color='red').encode(
-    x='mean(IMDB_Rating):Q',
+    x='mean(IMDB Rating):Q',
     size=alt.value(5)
 )
 
diff --git a/tests/examples_arguments_syntax/horizontal_stacked_bar_chart.py b/tests/examples_arguments_syntax/horizontal_stacked_bar_chart.py
index 89271e03e..01adc2fe3 100644
--- a/tests/examples_arguments_syntax/horizontal_stacked_bar_chart.py
+++ b/tests/examples_arguments_syntax/horizontal_stacked_bar_chart.py
@@ -5,7 +5,7 @@
 """
 # category: bar charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.barley()
 
diff --git a/tests/examples_arguments_syntax/interactive_aggregation.py b/tests/examples_arguments_syntax/interactive_aggregation.py
index 4b7aaf3de..aa024c688 100644
--- a/tests/examples_arguments_syntax/interactive_aggregation.py
+++ b/tests/examples_arguments_syntax/interactive_aggregation.py
@@ -9,7 +9,7 @@
 """
 # category: interactive charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.movies.url
 
@@ -18,18 +18,18 @@
 
 alt.layer(
     alt.Chart(source).mark_circle().encode(
-        x=alt.X("IMDB_Rating:Q", title="IMDB Rating"),
-        y=alt.Y("Rotten_Tomatoes_Rating:Q", title="Rotten Tomatoes Rating")
+        x=alt.X("IMDB Rating:Q", title="IMDB Rating"),
+        y=alt.Y("Rotten Tomatoes Rating:Q", title="Rotten Tomatoes Rating")
     ).transform_filter(
-        alt.datum["IMDB_Rating"] >= threshold
+        alt.datum["IMDB Rating"] >= threshold
     ),
 
     alt.Chart(source).mark_circle().encode(
-        x=alt.X("IMDB_Rating:Q", bin=alt.Bin(maxbins=10)),
-        y=alt.Y("Rotten_Tomatoes_Rating:Q", bin=alt.Bin(maxbins=10)),
+        x=alt.X("IMDB Rating:Q", bin=alt.Bin(maxbins=10)),
+        y=alt.Y("Rotten Tomatoes Rating:Q", bin=alt.Bin(maxbins=10)),
         size=alt.Size("count():Q", scale=alt.Scale(domain=[0,160]))
     ).transform_filter(
-        alt.datum["IMDB_Rating"] < threshold
+        alt.datum["IMDB Rating"] < threshold
     ),
 
     alt.Chart().mark_rule(color="gray").encode(
diff --git a/tests/examples_arguments_syntax/interactive_brush.py b/tests/examples_arguments_syntax/interactive_brush.py
index bee087c57..40ed35915 100644
--- a/tests/examples_arguments_syntax/interactive_brush.py
+++ b/tests/examples_arguments_syntax/interactive_brush.py
@@ -7,7 +7,7 @@
 """
 # category: interactive charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.cars()
 brush = alt.selection_interval()
diff --git a/tests/examples_arguments_syntax/interactive_cross_highlight.py b/tests/examples_arguments_syntax/interactive_cross_highlight.py
index f2b7e2d2a..5705ca3d5 100644
--- a/tests/examples_arguments_syntax/interactive_cross_highlight.py
+++ b/tests/examples_arguments_syntax/interactive_cross_highlight.py
@@ -7,15 +7,15 @@
 """
 # category: interactive charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.movies.url
 
 pts = alt.selection_point(encodings=['x'])
 
 rect = alt.Chart(data.movies.url).mark_rect().encode(
-    alt.X('IMDB_Rating:Q', bin=True),
-    alt.Y('Rotten_Tomatoes_Rating:Q', bin=True),
+    alt.X('IMDB Rating:Q', bin=True),
+    alt.Y('Rotten Tomatoes Rating:Q', bin=True),
     alt.Color('count()',
         scale=alt.Scale(scheme='greenblue'),
         legend=alt.Legend(title='Total Records')
@@ -32,7 +32,7 @@
 )
 
 bar = alt.Chart(source).mark_bar().encode(
-    x='Major_Genre:N',
+    x='Major Genre:N',
     y='count()',
     color=alt.when(pts).then(alt.ColorValue("steelblue")).otherwise(alt.ColorValue("grey"))
 ).properties(
diff --git a/tests/examples_arguments_syntax/interactive_layered_crossfilter.py b/tests/examples_arguments_syntax/interactive_layered_crossfilter.py
index 298092985..c0f11fde7 100644
--- a/tests/examples_arguments_syntax/interactive_layered_crossfilter.py
+++ b/tests/examples_arguments_syntax/interactive_layered_crossfilter.py
@@ -7,7 +7,7 @@
 """
 # category: interactive charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = alt.UrlData(
     data.flights_2k.url,
diff --git a/tests/examples_arguments_syntax/interactive_legend.py b/tests/examples_arguments_syntax/interactive_legend.py
index 61e45f44d..3b8c371ef 100644
--- a/tests/examples_arguments_syntax/interactive_legend.py
+++ b/tests/examples_arguments_syntax/interactive_legend.py
@@ -7,7 +7,7 @@
 """
 # category: interactive charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.unemployment_across_industries.url
 
diff --git a/tests/examples_arguments_syntax/interactive_reorder_stacked_bars.py b/tests/examples_arguments_syntax/interactive_reorder_stacked_bars.py
index 2fbed1dca..5e4744a2e 100644
--- a/tests/examples_arguments_syntax/interactive_reorder_stacked_bars.py
+++ b/tests/examples_arguments_syntax/interactive_reorder_stacked_bars.py
@@ -12,7 +12,7 @@
 """
 # category: interactive charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 selection = alt.selection_point(fields=['site'], bind='legend')
 
diff --git a/tests/examples_arguments_syntax/interactive_scatter_plot.py b/tests/examples_arguments_syntax/interactive_scatter_plot.py
index a6e7fc37f..145d59ffd 100644
--- a/tests/examples_arguments_syntax/interactive_scatter_plot.py
+++ b/tests/examples_arguments_syntax/interactive_scatter_plot.py
@@ -5,7 +5,7 @@
 """
 # category: interactive charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.cars()
 
diff --git a/tests/examples_arguments_syntax/interval_selection.py b/tests/examples_arguments_syntax/interval_selection.py
index 3065a8732..0eac67b92 100644
--- a/tests/examples_arguments_syntax/interval_selection.py
+++ b/tests/examples_arguments_syntax/interval_selection.py
@@ -8,7 +8,7 @@
 """
 # category: interactive charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 import datetime as dt
 
 source = data.sp500.url
diff --git a/tests/examples_arguments_syntax/iowa_electricity.py b/tests/examples_arguments_syntax/iowa_electricity.py
index 0f2081d99..c86205847 100644
--- a/tests/examples_arguments_syntax/iowa_electricity.py
+++ b/tests/examples_arguments_syntax/iowa_electricity.py
@@ -5,7 +5,7 @@
 """
 # category: case studies
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.iowa_electricity()
 
diff --git a/tests/examples_arguments_syntax/lasagna_plot.py b/tests/examples_arguments_syntax/lasagna_plot.py
index d3e60ed34..b00b29457 100644
--- a/tests/examples_arguments_syntax/lasagna_plot.py
+++ b/tests/examples_arguments_syntax/lasagna_plot.py
@@ -4,7 +4,7 @@
 """
 # category: tables
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.stocks()
 
diff --git a/tests/examples_arguments_syntax/layer_line_color_rule.py b/tests/examples_arguments_syntax/layer_line_color_rule.py
index aa948ecb7..a527346af 100644
--- a/tests/examples_arguments_syntax/layer_line_color_rule.py
+++ b/tests/examples_arguments_syntax/layer_line_color_rule.py
@@ -7,7 +7,7 @@
 """
 # category: line charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.stocks()
 
diff --git a/tests/examples_arguments_syntax/layered_area_chart.py b/tests/examples_arguments_syntax/layered_area_chart.py
index fe9e42c2c..bcf1ed601 100644
--- a/tests/examples_arguments_syntax/layered_area_chart.py
+++ b/tests/examples_arguments_syntax/layered_area_chart.py
@@ -5,7 +5,7 @@
 """
 # category: area charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.iowa_electricity()
 
diff --git a/tests/examples_arguments_syntax/layered_bar_chart.py b/tests/examples_arguments_syntax/layered_bar_chart.py
index 48d221e3b..b9cfd6b7e 100644
--- a/tests/examples_arguments_syntax/layered_bar_chart.py
+++ b/tests/examples_arguments_syntax/layered_bar_chart.py
@@ -5,7 +5,7 @@
 """
 # category: bar charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.iowa_electricity()
 
diff --git a/tests/examples_arguments_syntax/layered_chart_with_dual_axis.py b/tests/examples_arguments_syntax/layered_chart_with_dual_axis.py
index 8ef8f099b..ae535cbd6 100644
--- a/tests/examples_arguments_syntax/layered_chart_with_dual_axis.py
+++ b/tests/examples_arguments_syntax/layered_chart_with_dual_axis.py
@@ -6,7 +6,7 @@
 # category: advanced calculations
 
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.seattle_weather()
 
diff --git a/tests/examples_arguments_syntax/layered_heatmap_text.py b/tests/examples_arguments_syntax/layered_heatmap_text.py
index 7dec0fd26..6ead6b6d6 100644
--- a/tests/examples_arguments_syntax/layered_heatmap_text.py
+++ b/tests/examples_arguments_syntax/layered_heatmap_text.py
@@ -6,7 +6,7 @@
 """
 # category: tables
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.cars()
 
diff --git a/tests/examples_arguments_syntax/line_chart_with_color_datum.py b/tests/examples_arguments_syntax/line_chart_with_color_datum.py
index 17d3a1cec..f6e9e79c4 100644
--- a/tests/examples_arguments_syntax/line_chart_with_color_datum.py
+++ b/tests/examples_arguments_syntax/line_chart_with_color_datum.py
@@ -8,14 +8,14 @@
 # category: line charts
 
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.movies()
 
 alt.Chart(source).mark_line().encode(
-    x=alt.X("IMDB_Rating", bin=True),
+    x=alt.X("IMDB Rating", bin=True),
     y=alt.Y(
         alt.repeat("layer"), aggregate="mean", title="Mean of US and Worldwide Gross"
     ),
     color=alt.datum(alt.repeat("layer")),
-).repeat(layer=["US_Gross", "Worldwide_Gross"])
+).repeat(layer=["US Gross", "Worldwide Gross"])
diff --git a/tests/examples_arguments_syntax/line_chart_with_cumsum.py b/tests/examples_arguments_syntax/line_chart_with_cumsum.py
index 2b21b0845..4ec100904 100644
--- a/tests/examples_arguments_syntax/line_chart_with_cumsum.py
+++ b/tests/examples_arguments_syntax/line_chart_with_cumsum.py
@@ -5,7 +5,7 @@
 """
 # category: line charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.wheat()
 
diff --git a/tests/examples_arguments_syntax/line_chart_with_cumsum_faceted.py b/tests/examples_arguments_syntax/line_chart_with_cumsum_faceted.py
index d33df06ad..697d9b822 100644
--- a/tests/examples_arguments_syntax/line_chart_with_cumsum_faceted.py
+++ b/tests/examples_arguments_syntax/line_chart_with_cumsum_faceted.py
@@ -6,7 +6,7 @@
 """
 # category: advanced calculations
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.disasters()
 columns_sorted = ['Drought', 'Epidemic', 'Earthquake', 'Flood']
diff --git a/tests/examples_arguments_syntax/line_chart_with_custom_legend.py b/tests/examples_arguments_syntax/line_chart_with_custom_legend.py
index 992128232..685a8f3e7 100644
--- a/tests/examples_arguments_syntax/line_chart_with_custom_legend.py
+++ b/tests/examples_arguments_syntax/line_chart_with_custom_legend.py
@@ -6,7 +6,7 @@
 """
 # category: line charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 
 source = data.stocks()
diff --git a/tests/examples_arguments_syntax/line_chart_with_datum.py b/tests/examples_arguments_syntax/line_chart_with_datum.py
index 94489c089..74ef32b42 100644
--- a/tests/examples_arguments_syntax/line_chart_with_datum.py
+++ b/tests/examples_arguments_syntax/line_chart_with_datum.py
@@ -8,7 +8,7 @@
 # category: line charts
 
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.stocks()
 
diff --git a/tests/examples_arguments_syntax/line_chart_with_interpolation.py b/tests/examples_arguments_syntax/line_chart_with_interpolation.py
index 4da962337..df18c2cd8 100644
--- a/tests/examples_arguments_syntax/line_chart_with_interpolation.py
+++ b/tests/examples_arguments_syntax/line_chart_with_interpolation.py
@@ -5,7 +5,7 @@
 """
 # category: line charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.stocks()
 
diff --git a/tests/examples_arguments_syntax/line_chart_with_points.py b/tests/examples_arguments_syntax/line_chart_with_points.py
index 1cd8efa7b..ab8f07d6a 100644
--- a/tests/examples_arguments_syntax/line_chart_with_points.py
+++ b/tests/examples_arguments_syntax/line_chart_with_points.py
@@ -5,7 +5,7 @@
 """
 # category: line charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.stocks()
 
diff --git a/tests/examples_arguments_syntax/line_chart_with_points_stroked.py b/tests/examples_arguments_syntax/line_chart_with_points_stroked.py
index fd990d98b..28d57db1a 100644
--- a/tests/examples_arguments_syntax/line_chart_with_points_stroked.py
+++ b/tests/examples_arguments_syntax/line_chart_with_points_stroked.py
@@ -5,7 +5,7 @@
 """
 # category: line charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.stocks()
 
diff --git a/tests/examples_arguments_syntax/line_custom_order.py b/tests/examples_arguments_syntax/line_custom_order.py
index c564c3349..618f26469 100644
--- a/tests/examples_arguments_syntax/line_custom_order.py
+++ b/tests/examples_arguments_syntax/line_custom_order.py
@@ -16,7 +16,7 @@
 """
 # category: line charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.driving()
 
diff --git a/tests/examples_arguments_syntax/line_percent.py b/tests/examples_arguments_syntax/line_percent.py
index fd23572de..7a40f76b5 100644
--- a/tests/examples_arguments_syntax/line_percent.py
+++ b/tests/examples_arguments_syntax/line_percent.py
@@ -5,7 +5,7 @@
 """
 # category: line charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.jobs.url
 
diff --git a/tests/examples_arguments_syntax/line_with_ci.py b/tests/examples_arguments_syntax/line_with_ci.py
index 5db97915a..5885acb50 100644
--- a/tests/examples_arguments_syntax/line_with_ci.py
+++ b/tests/examples_arguments_syntax/line_with_ci.py
@@ -5,7 +5,7 @@
 """
 # category: uncertainties and trends
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.cars()
 
diff --git a/tests/examples_arguments_syntax/line_with_last_value_labeled.py b/tests/examples_arguments_syntax/line_with_last_value_labeled.py
index bc9fda7ae..e2c80764b 100644
--- a/tests/examples_arguments_syntax/line_with_last_value_labeled.py
+++ b/tests/examples_arguments_syntax/line_with_last_value_labeled.py
@@ -5,7 +5,7 @@
 """
 # category: line charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 # Import example data
 source = data.stocks()
diff --git a/tests/examples_arguments_syntax/line_with_log_scale.py b/tests/examples_arguments_syntax/line_with_log_scale.py
index b45fcd92e..6b930edd3 100644
--- a/tests/examples_arguments_syntax/line_with_log_scale.py
+++ b/tests/examples_arguments_syntax/line_with_log_scale.py
@@ -5,7 +5,7 @@
 """
 # category: line charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.population()
 
diff --git a/tests/examples_arguments_syntax/london_tube.py b/tests/examples_arguments_syntax/london_tube.py
index 3a39e6aef..31c86b0aa 100644
--- a/tests/examples_arguments_syntax/london_tube.py
+++ b/tests/examples_arguments_syntax/london_tube.py
@@ -7,11 +7,11 @@
 """
 # category: case studies
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
-boroughs = alt.topo_feature(data.londonBoroughs.url, 'boroughs')
-tubelines = alt.topo_feature(data.londonTubeLines.url, 'line')
-centroids = data.londonCentroids.url
+boroughs = alt.topo_feature(data.london_boroughs.url, 'boroughs')
+tubelines = alt.topo_feature(data.london_tube_lines.url, 'line')
+centroids = data.london_centroids.url
 
 background = alt.Chart(boroughs).mark_geoshape(
     stroke='white',
diff --git a/tests/examples_arguments_syntax/mosaic_with_labels.py b/tests/examples_arguments_syntax/mosaic_with_labels.py
index 2db0baff2..11a2dc871 100644
--- a/tests/examples_arguments_syntax/mosaic_with_labels.py
+++ b/tests/examples_arguments_syntax/mosaic_with_labels.py
@@ -5,7 +5,7 @@
 # category: tables
 
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.cars()
 
diff --git a/tests/examples_arguments_syntax/multi_series_line.py b/tests/examples_arguments_syntax/multi_series_line.py
index 024ffb636..93dacd160 100644
--- a/tests/examples_arguments_syntax/multi_series_line.py
+++ b/tests/examples_arguments_syntax/multi_series_line.py
@@ -6,7 +6,7 @@
 """
 # category: line charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.stocks()
 
diff --git a/tests/examples_arguments_syntax/multifeature_scatter_plot.py b/tests/examples_arguments_syntax/multifeature_scatter_plot.py
index 40e189bbf..7b92ff14d 100644
--- a/tests/examples_arguments_syntax/multifeature_scatter_plot.py
+++ b/tests/examples_arguments_syntax/multifeature_scatter_plot.py
@@ -5,13 +5,13 @@
 """
 # category: scatter plots
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
-source = data.iris()
+source = data.penguins()
 
 alt.Chart(source).mark_circle().encode(
-    alt.X('sepalLength', scale=alt.Scale(zero=False)),
-    alt.Y('sepalWidth', scale=alt.Scale(zero=False, padding=1)),
-    color='species',
-    size='petalWidth'
+    alt.X('Flipper Length (mm)', scale=alt.Scale(zero=False)),
+    alt.Y('Body Mass (g)', scale=alt.Scale(zero=False, padding=1)),
+    alt.Size('Beak Depth (mm)', scale=alt.Scale(zero=False)),
+    color='Species'
 )
diff --git a/tests/examples_arguments_syntax/multiline_highlight.py b/tests/examples_arguments_syntax/multiline_highlight.py
index 575c88081..a3b346ab1 100644
--- a/tests/examples_arguments_syntax/multiline_highlight.py
+++ b/tests/examples_arguments_syntax/multiline_highlight.py
@@ -8,7 +8,7 @@
 """
 # category: interactive charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.stocks()
 
diff --git a/tests/examples_arguments_syntax/multiple_interactions.py b/tests/examples_arguments_syntax/multiple_interactions.py
index 96bfb8fed..e89cc08bc 100644
--- a/tests/examples_arguments_syntax/multiple_interactions.py
+++ b/tests/examples_arguments_syntax/multiple_interactions.py
@@ -12,11 +12,11 @@
 """
 # category: interactive charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 movies = alt.UrlData(
     data.movies.url,
-    format=alt.DataFormat(parse={"Release_Date":"date"})
+    format=alt.DataFormat(parse={'Release Date':'date'})
 )
 ratings = ['G', 'NC-17', 'PG', 'PG-13', 'R']
 genres = ['Action', 'Adventure', 'Black Comedy', 'Comedy',
@@ -24,62 +24,61 @@
        'Romantic Comedy', 'Thriller/Suspense', 'Western']
 
 base = alt.Chart(movies, width=200, height=200).mark_point(filled=True).transform_calculate(
-    Rounded_IMDB_Rating = "floor(datum.IMDB_Rating)",
-    Hundred_Million_Production =  "datum.Production_Budget > 100000000.0 ? 100 : 10",
-    Release_Year = "year(datum.Release_Date)"
+    Hundred_Million_Production = "datum['Production Budget'] > 100000000.0 ? 100 : 10",
+    Release_Year = "year(datum['Release Date'])"
 ).transform_filter(
-    alt.datum.IMDB_Rating > 0
+    alt.datum['IMDB Rating'] > 0
 ).transform_filter(
-    alt.FieldOneOfPredicate(field='MPAA_Rating', oneOf=ratings)
+    alt.FieldOneOfPredicate(field='MPAA Rating', oneOf=ratings)
 ).encode(
-    x=alt.X('Worldwide_Gross:Q', scale=alt.Scale(domain=(100000,10**9), clamp=True)),
-    y='IMDB_Rating:Q',
-    tooltip="Title:N"
+    x=alt.X('Worldwide Gross:Q', scale=alt.Scale(domain=(100000,10**9), clamp=True)),
+    y='IMDB Rating:Q',
+    tooltip='Title:N'
 )
 
 # A slider filter
-year_slider = alt.binding_range(min=1969, max=2018, step=1, name="Release Year")
+year_slider = alt.binding_range(min=1969, max=2018, step=1, name='Release Year')
 slider_selection = alt.selection_point(bind=year_slider, fields=['Release_Year'])
 
 filter_year = base.add_params(
     slider_selection
 ).transform_filter(
     slider_selection
-).properties(title="Slider Filtering")
+).properties(title='Slider Filtering')
 
 # A dropdown filter
-genre_dropdown = alt.binding_select(options=genres, name="Genre")
-genre_select = alt.selection_point(fields=['Major_Genre'], bind=genre_dropdown)
+genre_dropdown = alt.binding_select(options=genres, name='Genre')
+genre_select = alt.selection_point(fields=['Major Genre'], bind=genre_dropdown)
 
 filter_genres = base.add_params(
     genre_select
 ).transform_filter(
     genre_select
-).properties(title="Dropdown Filtering")
+).properties(title='Dropdown Filtering')
 
 #color changing marks
-rating_radio = alt.binding_radio(options=ratings, name="Rating")
-rating_select = alt.selection_point(fields=['MPAA_Rating'], bind=rating_radio)
+rating_radio = alt.binding_radio(options=ratings, name='Rating')
+rating_select = alt.selection_point(fields=['MPAA Rating'], bind=rating_radio)
 
 rating_color = (
     alt.when(rating_select)
-    .then(alt.Color('MPAA_Rating:N', legend=None))
-    .otherwise(alt.value("lightgray"))
+    .then(alt.Color('MPAA Rating:N', legend=None))
+    .otherwise(alt.value('lightgray'))
 )
 
 highlight_ratings = base.add_params(
     rating_select
 ).encode(
     color=rating_color
-).properties(title="Radio Button Highlighting")
+).properties(title='Radio Button Highlighting')
 
 # Boolean selection for format changes
-input_checkbox = alt.binding_checkbox(name="Big Budget Films ")
+input_checkbox = alt.binding_checkbox(name='Big Budget Films ')
 checkbox_selection = alt.param(bind=input_checkbox)
 
 size_checkbox = (
     alt.when(checkbox_selection)
-    .then(alt.Size('Big_Budget_Film:N', scale=alt.Scale(range=[25, 150])))
+    .then(alt.Size('Big Budget Film:N', scale=alt.Scale(range=[25, 150])))
     .otherwise(alt.value(25))
 )
 
@@ -87,6 +86,6 @@
     checkbox_selection
 ).encode(
     size=size_checkbox
-).properties(title="Checkbox Formatting")
+).properties(title='Checkbox Formatting')
 
 (filter_year | budget_sizing) & (highlight_ratings | filter_genres)
diff --git a/tests/examples_arguments_syntax/natural_disasters.py b/tests/examples_arguments_syntax/natural_disasters.py
index 890580a6a..52d2c05ed 100644
--- a/tests/examples_arguments_syntax/natural_disasters.py
+++ b/tests/examples_arguments_syntax/natural_disasters.py
@@ -5,7 +5,7 @@
 """
 # category: case studies
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.disasters.url
 
diff --git a/tests/examples_arguments_syntax/normalized_stacked_area_chart.py b/tests/examples_arguments_syntax/normalized_stacked_area_chart.py
index a6bfec365..0f8a72739 100644
--- a/tests/examples_arguments_syntax/normalized_stacked_area_chart.py
+++ b/tests/examples_arguments_syntax/normalized_stacked_area_chart.py
@@ -5,7 +5,7 @@
 """
 # category: area charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.iowa_electricity()
 
diff --git a/tests/examples_arguments_syntax/normalized_stacked_bar_chart.py b/tests/examples_arguments_syntax/normalized_stacked_bar_chart.py
index 307a452d2..c5401ea5e 100644
--- a/tests/examples_arguments_syntax/normalized_stacked_bar_chart.py
+++ b/tests/examples_arguments_syntax/normalized_stacked_bar_chart.py
@@ -5,7 +5,7 @@
 """
 # category: bar charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.barley()
 
diff --git a/tests/examples_arguments_syntax/normed_parallel_coordinates.py b/tests/examples_arguments_syntax/normed_parallel_coordinates.py
index 594aac7af..f2f2c6afc 100644
--- a/tests/examples_arguments_syntax/normed_parallel_coordinates.py
+++ b/tests/examples_arguments_syntax/normed_parallel_coordinates.py
@@ -8,21 +8,21 @@
 Such a chart can be created in Altair by first transforming the data into a
 suitable representation.
 
-This example shows a modified parallel coordinates chart with the Iris dataset,
+This example shows a modified parallel coordinates chart with the Penguins dataset,
 where the y-axis shows the value after min-max rather than the raw value. It's a
 simplified Altair version of `the VegaLite version <https://vega.github.io/vega-lite/examples/parallel_coordinate.html>`_
 """
 # category: advanced calculations
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 from altair import datum
 
-source = data.iris()
+source = data.penguins()
 
 alt.Chart(source).transform_window(
     index='count()'
 ).transform_fold(
-    ['petalLength', 'petalWidth', 'sepalLength', 'sepalWidth']
+    ['Beak Length (mm)', 'Beak Depth (mm)', 'Flipper Length (mm)']
 ).transform_joinaggregate(
      min='min(value)', 
      max='max(value)',
@@ -33,7 +33,7 @@
 ).mark_line().encode(
     x='key:N',
     y='minmax_value:Q',
-    color='species:N',
+    color='Species:N',
     detail='index:N',
     opacity=alt.value(0.5)
 ).properties(width=500)
diff --git a/tests/examples_arguments_syntax/one_dot_per_zipcode.py b/tests/examples_arguments_syntax/one_dot_per_zipcode.py
index c08ff3932..4116218cb 100644
--- a/tests/examples_arguments_syntax/one_dot_per_zipcode.py
+++ b/tests/examples_arguments_syntax/one_dot_per_zipcode.py
@@ -5,7 +5,7 @@
 """
 # category: case studies
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 # Since the data is more than 5,000 rows we'll import it from a URL
 source = data.zipcodes.url
diff --git a/tests/examples_arguments_syntax/parallel_coordinates.py b/tests/examples_arguments_syntax/parallel_coordinates.py
index c46bc0129..ffe08b96c 100644
--- a/tests/examples_arguments_syntax/parallel_coordinates.py
+++ b/tests/examples_arguments_syntax/parallel_coordinates.py
@@ -6,23 +6,23 @@
 a single line for each of them.
 Such a chart can be created in Altair by first transforming the data into a
 suitable representation.
-This example shows a parallel coordinates chart with the Iris dataset.
+This example shows a parallel coordinates chart with the Penguins dataset.
 """
 # category: advanced calculations
 
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
-source = data.iris()
+source = data.penguins()
 
 alt.Chart(source).transform_window(
     index='count()'  
 ).transform_fold(
-    ['petalLength', 'petalWidth', 'sepalLength', 'sepalWidth']
+    ['Beak Length (mm)', 'Beak Depth (mm)', 'Flipper Length (mm)']
 ).mark_line().encode(
     x='key:N',
     y='value:Q',
-    color='species:N',
+    color='Species:N',
     detail='index:N',
     opacity=alt.value(0.5)
 ).properties(width=500)
diff --git a/tests/examples_arguments_syntax/point_map.py b/tests/examples_arguments_syntax/point_map.py
index d468cb434..2f2e370bb 100644
--- a/tests/examples_arguments_syntax/point_map.py
+++ b/tests/examples_arguments_syntax/point_map.py
@@ -5,7 +5,7 @@
 """
 # category: maps
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 # Read in points
 airports = data.airports()
diff --git a/tests/examples_arguments_syntax/ranged_dot_plot.py b/tests/examples_arguments_syntax/ranged_dot_plot.py
index 2ca244eb4..d529b04a7 100644
--- a/tests/examples_arguments_syntax/ranged_dot_plot.py
+++ b/tests/examples_arguments_syntax/ranged_dot_plot.py
@@ -5,7 +5,7 @@
 """
 # category: advanced calculations
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.countries.url
 
diff --git a/tests/examples_arguments_syntax/ridgeline_plot.py b/tests/examples_arguments_syntax/ridgeline_plot.py
index 7c9625cf9..9062cc097 100644
--- a/tests/examples_arguments_syntax/ridgeline_plot.py
+++ b/tests/examples_arguments_syntax/ridgeline_plot.py
@@ -10,7 +10,7 @@
 """
 # category: distributions
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.seattle_weather.url
 
diff --git a/tests/examples_arguments_syntax/scatter_faceted.py b/tests/examples_arguments_syntax/scatter_faceted.py
index 65968f932..375209afa 100644
--- a/tests/examples_arguments_syntax/scatter_faceted.py
+++ b/tests/examples_arguments_syntax/scatter_faceted.py
@@ -5,7 +5,7 @@
 """
 # category: scatter plots
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.cars()
 
diff --git a/tests/examples_arguments_syntax/scatter_href.py b/tests/examples_arguments_syntax/scatter_href.py
index d9f072521..b4ec7c07a 100644
--- a/tests/examples_arguments_syntax/scatter_href.py
+++ b/tests/examples_arguments_syntax/scatter_href.py
@@ -8,7 +8,7 @@
 # category: scatter plots
 
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.cars()
 
diff --git a/tests/examples_arguments_syntax/scatter_linked_brush.py b/tests/examples_arguments_syntax/scatter_linked_brush.py
index b8548fd02..7f2de6dda 100644
--- a/tests/examples_arguments_syntax/scatter_linked_brush.py
+++ b/tests/examples_arguments_syntax/scatter_linked_brush.py
@@ -6,7 +6,7 @@
 """
 # category: interactive charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.cars()
 
diff --git a/tests/examples_arguments_syntax/scatter_linked_table.py b/tests/examples_arguments_syntax/scatter_linked_table.py
index e17c4dbb0..9df9d85e7 100644
--- a/tests/examples_arguments_syntax/scatter_linked_table.py
+++ b/tests/examples_arguments_syntax/scatter_linked_table.py
@@ -7,7 +7,7 @@
 # category: scatter plots
 
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.cars()
 
diff --git a/tests/examples_arguments_syntax/scatter_marginal_hist.py b/tests/examples_arguments_syntax/scatter_marginal_hist.py
index 72638bcfd..916a57d18 100644
--- a/tests/examples_arguments_syntax/scatter_marginal_hist.py
+++ b/tests/examples_arguments_syntax/scatter_marginal_hist.py
@@ -6,27 +6,27 @@
 """
 # category: distributions
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
-source = data.iris()
+source = data.penguins()
 
 base = alt.Chart(source)
 base_bar = base.mark_bar(opacity=0.3, binSpacing=0)
 
-xscale = alt.Scale(domain=(4.0, 8.0))
-yscale = alt.Scale(domain=(1.9, 4.55))
+xscale = alt.Scale(domain=(170, 235))
+yscale = alt.Scale(domain=(2500, 6500))
 
 points = base.mark_circle().encode(
-    alt.X("sepalLength", scale=xscale),
-    alt.Y("sepalWidth", scale=yscale),
-    color="species",
+    alt.X("Flipper Length (mm)", scale=xscale),
+    alt.Y("Body Mass (g)", scale=yscale),
+    color="Species",
 )
 
 top_hist = (
     base_bar
     .encode(
         alt.X(
-            "sepalLength:Q",
+            "Flipper Length (mm):Q",
             # when using bins, the axis scale is set through
             # the bin extent, so we do not specify the scale here
             # (which would be ignored anyway)
@@ -35,7 +35,7 @@
             title="",
         ),
         alt.Y("count()", stack=None, title=""),
-        alt.Color("species:N"),
+        alt.Color("Species:N"),
     )
     .properties(height=60)
 )
@@ -44,13 +44,13 @@
     base_bar
     .encode(
         alt.Y(
-            "sepalWidth:Q",
+            "Body Mass (g):Q",
             bin=alt.Bin(maxbins=20, extent=yscale.domain),
             stack=None,
             title="",
         ),
         alt.X("count()", stack=None, title=""),
-        alt.Color("species:N"),
+        alt.Color("Species:N"),
     )
     .properties(width=60)
 )
diff --git a/tests/examples_arguments_syntax/scatter_matrix.py b/tests/examples_arguments_syntax/scatter_matrix.py
index 7202818fd..985ca8e58 100644
--- a/tests/examples_arguments_syntax/scatter_matrix.py
+++ b/tests/examples_arguments_syntax/scatter_matrix.py
@@ -6,7 +6,7 @@
 """
 # category: scatter plots
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.cars()
 
diff --git a/tests/examples_arguments_syntax/scatter_point_paths_hover.py b/tests/examples_arguments_syntax/scatter_point_paths_hover.py
index aea0960f6..98a72e919 100644
--- a/tests/examples_arguments_syntax/scatter_point_paths_hover.py
+++ b/tests/examples_arguments_syntax/scatter_point_paths_hover.py
@@ -13,7 +13,7 @@
 """
 # category: interactive charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 # Data source
 source = data.gapminder.url
diff --git a/tests/examples_arguments_syntax/scatter_qq.py b/tests/examples_arguments_syntax/scatter_qq.py
index 09f25acbb..a6a2b6ccc 100644
--- a/tests/examples_arguments_syntax/scatter_qq.py
+++ b/tests/examples_arguments_syntax/scatter_qq.py
@@ -6,7 +6,7 @@
 # category: distributions
 
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.normal_2d.url
 
diff --git a/tests/examples_arguments_syntax/scatter_tooltips.py b/tests/examples_arguments_syntax/scatter_tooltips.py
index 0a6c996fa..69d3ad679 100644
--- a/tests/examples_arguments_syntax/scatter_tooltips.py
+++ b/tests/examples_arguments_syntax/scatter_tooltips.py
@@ -8,7 +8,7 @@
 # category: simple charts
 
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.cars()
 
diff --git a/tests/examples_arguments_syntax/scatter_with_minimap.py b/tests/examples_arguments_syntax/scatter_with_minimap.py
index df8a9fd44..e4d9087d9 100644
--- a/tests/examples_arguments_syntax/scatter_with_minimap.py
+++ b/tests/examples_arguments_syntax/scatter_with_minimap.py
@@ -8,7 +8,7 @@
 # category: scatter plots
 
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.seattle_weather()
 
diff --git a/tests/examples_arguments_syntax/scatter_with_rolling_mean.py b/tests/examples_arguments_syntax/scatter_with_rolling_mean.py
index cf0b36cc1..a7d29dc9e 100644
--- a/tests/examples_arguments_syntax/scatter_with_rolling_mean.py
+++ b/tests/examples_arguments_syntax/scatter_with_rolling_mean.py
@@ -7,7 +7,7 @@
 # category: scatter plots
 
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.seattle_weather()
 
diff --git a/tests/examples_arguments_syntax/seattle_weather_interactive.py b/tests/examples_arguments_syntax/seattle_weather_interactive.py
index 63e93d011..9f119ae83 100644
--- a/tests/examples_arguments_syntax/seattle_weather_interactive.py
+++ b/tests/examples_arguments_syntax/seattle_weather_interactive.py
@@ -7,7 +7,7 @@
 """
 # category: case studies
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.seattle_weather()
 
diff --git a/tests/examples_arguments_syntax/select_mark_area.py b/tests/examples_arguments_syntax/select_mark_area.py
index 4cd88398d..2909042fb 100644
--- a/tests/examples_arguments_syntax/select_mark_area.py
+++ b/tests/examples_arguments_syntax/select_mark_area.py
@@ -11,7 +11,7 @@
 """
 # category: interactive charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.unemployment_across_industries.url
 
diff --git a/tests/examples_arguments_syntax/selection_histogram.py b/tests/examples_arguments_syntax/selection_histogram.py
index 155b9fc68..04c7cee6b 100644
--- a/tests/examples_arguments_syntax/selection_histogram.py
+++ b/tests/examples_arguments_syntax/selection_histogram.py
@@ -7,7 +7,7 @@
 """
 # category: interactive charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.cars()
 
diff --git a/tests/examples_arguments_syntax/selection_layer_bar_month.py b/tests/examples_arguments_syntax/selection_layer_bar_month.py
index e97914765..1878fbe76 100644
--- a/tests/examples_arguments_syntax/selection_layer_bar_month.py
+++ b/tests/examples_arguments_syntax/selection_layer_bar_month.py
@@ -7,7 +7,7 @@
 """
 # category: interactive charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.seattle_weather()
 brush = alt.selection_interval(encodings=['x'])
diff --git a/tests/examples_arguments_syntax/selection_zorder.py b/tests/examples_arguments_syntax/selection_zorder.py
index 6f6d7c93d..7d2769327 100644
--- a/tests/examples_arguments_syntax/selection_zorder.py
+++ b/tests/examples_arguments_syntax/selection_zorder.py
@@ -10,7 +10,7 @@
 # category: interactive charts
 
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 
 cars = data.cars.url
diff --git a/tests/examples_arguments_syntax/simple_histogram.py b/tests/examples_arguments_syntax/simple_histogram.py
index c58f1330f..cdb9d31ea 100644
--- a/tests/examples_arguments_syntax/simple_histogram.py
+++ b/tests/examples_arguments_syntax/simple_histogram.py
@@ -6,11 +6,11 @@
 """
 # category: simple charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.movies.url
 
 alt.Chart(source).mark_bar().encode(
-    alt.X("IMDB_Rating:Q", bin=True),
+    alt.X("IMDB Rating:Q", bin=True),
     y='count()',
 )
diff --git a/tests/examples_arguments_syntax/simple_stacked_area_chart.py b/tests/examples_arguments_syntax/simple_stacked_area_chart.py
index ba640986b..529a0c6c5 100644
--- a/tests/examples_arguments_syntax/simple_stacked_area_chart.py
+++ b/tests/examples_arguments_syntax/simple_stacked_area_chart.py
@@ -5,7 +5,7 @@
 """
 # category: simple charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.iowa_electricity()
 
diff --git a/tests/examples_arguments_syntax/slope_graph.py b/tests/examples_arguments_syntax/slope_graph.py
index 422cf64b4..e9ae31ce8 100644
--- a/tests/examples_arguments_syntax/slope_graph.py
+++ b/tests/examples_arguments_syntax/slope_graph.py
@@ -5,7 +5,7 @@
 """
 # category: line charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.barley()
 
diff --git a/tests/examples_arguments_syntax/sorted_error_bars_with_ci.py b/tests/examples_arguments_syntax/sorted_error_bars_with_ci.py
index 2baac1e1d..7c0eae173 100644
--- a/tests/examples_arguments_syntax/sorted_error_bars_with_ci.py
+++ b/tests/examples_arguments_syntax/sorted_error_bars_with_ci.py
@@ -6,7 +6,7 @@
 # category: advanced calculations
 
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.barley()
 
diff --git a/tests/examples_arguments_syntax/stacked_bar_chart.py b/tests/examples_arguments_syntax/stacked_bar_chart.py
index 3cfc3870c..1a8bb13df 100644
--- a/tests/examples_arguments_syntax/stacked_bar_chart.py
+++ b/tests/examples_arguments_syntax/stacked_bar_chart.py
@@ -6,7 +6,7 @@
 """
 # category: bar charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.barley()
 
diff --git a/tests/examples_arguments_syntax/stacked_bar_chart_sorted_segments.py b/tests/examples_arguments_syntax/stacked_bar_chart_sorted_segments.py
index 2a189fedd..387eff70b 100644
--- a/tests/examples_arguments_syntax/stacked_bar_chart_sorted_segments.py
+++ b/tests/examples_arguments_syntax/stacked_bar_chart_sorted_segments.py
@@ -5,7 +5,7 @@
 """
 # category: bar charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.barley()
 
diff --git a/tests/examples_arguments_syntax/stacked_bar_chart_with_text.py b/tests/examples_arguments_syntax/stacked_bar_chart_with_text.py
index 180d20871..b5670bd64 100644
--- a/tests/examples_arguments_syntax/stacked_bar_chart_with_text.py
+++ b/tests/examples_arguments_syntax/stacked_bar_chart_with_text.py
@@ -7,7 +7,7 @@
 """
 # category: bar charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source=data.barley()
 
diff --git a/tests/examples_arguments_syntax/step_chart.py b/tests/examples_arguments_syntax/step_chart.py
index 75cc4e8cb..03f76b4fe 100644
--- a/tests/examples_arguments_syntax/step_chart.py
+++ b/tests/examples_arguments_syntax/step_chart.py
@@ -10,7 +10,7 @@
 """
 # category: line charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.stocks()
 
diff --git a/tests/examples_arguments_syntax/streamgraph.py b/tests/examples_arguments_syntax/streamgraph.py
index 64b8e4176..cfa96211d 100644
--- a/tests/examples_arguments_syntax/streamgraph.py
+++ b/tests/examples_arguments_syntax/streamgraph.py
@@ -5,7 +5,7 @@
 """
 # category: area charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.unemployment_across_industries.url
 
diff --git a/tests/examples_arguments_syntax/strip_plot.py b/tests/examples_arguments_syntax/strip_plot.py
index cc346aaa3..8568dab7d 100644
--- a/tests/examples_arguments_syntax/strip_plot.py
+++ b/tests/examples_arguments_syntax/strip_plot.py
@@ -5,7 +5,7 @@
 """
 # category: simple charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.cars()
 
diff --git a/tests/examples_arguments_syntax/strip_plot_jitter.py b/tests/examples_arguments_syntax/strip_plot_jitter.py
index e0b7d1645..842d73a2c 100644
--- a/tests/examples_arguments_syntax/strip_plot_jitter.py
+++ b/tests/examples_arguments_syntax/strip_plot_jitter.py
@@ -11,15 +11,15 @@
 """
 # category: distributions
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.movies.url
 
 gaussian_jitter = alt.Chart(source, title='Normally distributed jitter').mark_circle(size=8).encode(
-    y="Major_Genre:N",
-    x="IMDB_Rating:Q",
+    y="Major Genre:N",
+    x="IMDB Rating:Q",
     yOffset="jitter:Q",
-    color=alt.Color('Major_Genre:N', legend=None)
+    color=alt.Color('Major Genre:N', legend=None)
 ).transform_calculate(
     # Generate Gaussian jitter with a Box-Muller transform
     jitter="sqrt(-2*log(random()))*cos(2*PI*random())"
@@ -29,7 +29,7 @@
     # Generate uniform jitter
     jitter='random()'
 ).encode(
-    y=alt.Y('Major_Genre:N', axis=None)
+    y=alt.Y('Major Genre:N', axis=None)
 ).properties(
     title='Uniformly distributed jitter'
 )
diff --git a/tests/examples_arguments_syntax/table_bubble_plot_github.py b/tests/examples_arguments_syntax/table_bubble_plot_github.py
index 2720596d3..c973a9ecc 100644
--- a/tests/examples_arguments_syntax/table_bubble_plot_github.py
+++ b/tests/examples_arguments_syntax/table_bubble_plot_github.py
@@ -5,7 +5,7 @@
 """
 # category: distributions
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.github.url
 
diff --git a/tests/examples_arguments_syntax/top_k_items.py b/tests/examples_arguments_syntax/top_k_items.py
index 0c8ade36c..889b0705c 100644
--- a/tests/examples_arguments_syntax/top_k_items.py
+++ b/tests/examples_arguments_syntax/top_k_items.py
@@ -7,7 +7,7 @@
 """
 # category: advanced calculations
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.movies.url
 
@@ -16,12 +16,12 @@
     source,
 ).mark_bar().encode(
     x=alt.X('Title:N', sort='-y'),
-    y=alt.Y('IMDB_Rating:Q'),
-    color=alt.Color('IMDB_Rating:Q')
+    y=alt.Y('IMDB Rating:Q'),
+color=alt.Color('IMDB Rating:Q')
     
 ).transform_window(
-    rank='rank(IMDB_Rating)',
-    sort=[alt.SortField('IMDB_Rating', order='descending')]
+    rank='rank(IMDB Rating)',
+sort=[alt.SortField('IMDB Rating', order='descending')]
 ).transform_filter(
     (alt.datum.rank < 10)
 )
diff --git a/tests/examples_arguments_syntax/top_k_with_others.py b/tests/examples_arguments_syntax/top_k_with_others.py
index dd8fb9d4f..d4cfb3896 100644
--- a/tests/examples_arguments_syntax/top_k_with_others.py
+++ b/tests/examples_arguments_syntax/top_k_with_others.py
@@ -7,7 +7,7 @@
 """
 # category: advanced calculations
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.movies.url
 
@@ -19,7 +19,7 @@
         title=None,
     ),
 ).transform_aggregate(
-    aggregate_gross='mean(Worldwide_Gross)',
+    aggregate_gross='mean(Worldwide Gross)',
     groupby=["Director"],
 ).transform_window(
     rank='row_number()',
diff --git a/tests/examples_arguments_syntax/trail_marker.py b/tests/examples_arguments_syntax/trail_marker.py
index 8136cd37f..2d1723eeb 100644
--- a/tests/examples_arguments_syntax/trail_marker.py
+++ b/tests/examples_arguments_syntax/trail_marker.py
@@ -5,7 +5,7 @@
 """
 # category: line charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.wheat()
 
diff --git a/tests/examples_arguments_syntax/us_employment.py b/tests/examples_arguments_syntax/us_employment.py
index 2b084290e..44e34bdb5 100644
--- a/tests/examples_arguments_syntax/us_employment.py
+++ b/tests/examples_arguments_syntax/us_employment.py
@@ -6,7 +6,7 @@
 # category: case studies
 import altair as alt
 import pandas as pd
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.us_employment()
 presidents = pd.DataFrame([
diff --git a/tests/examples_arguments_syntax/us_incomebrackets_by_state_facet.py b/tests/examples_arguments_syntax/us_incomebrackets_by_state_facet.py
index 70f330481..770d51196 100644
--- a/tests/examples_arguments_syntax/us_incomebrackets_by_state_facet.py
+++ b/tests/examples_arguments_syntax/us_incomebrackets_by_state_facet.py
@@ -7,7 +7,7 @@
 # category: maps
 
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 states = alt.topo_feature(data.us_10m.url, 'states')
 source = data.income.url
diff --git a/tests/examples_arguments_syntax/us_population_over_time.py b/tests/examples_arguments_syntax/us_population_over_time.py
index 193012584..f276825c1 100644
--- a/tests/examples_arguments_syntax/us_population_over_time.py
+++ b/tests/examples_arguments_syntax/us_population_over_time.py
@@ -7,7 +7,7 @@
 """
 # category: case studies
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.population.url
 
diff --git a/tests/examples_arguments_syntax/us_population_over_time_facet.py b/tests/examples_arguments_syntax/us_population_over_time_facet.py
index fc8001981..52cf8587c 100644
--- a/tests/examples_arguments_syntax/us_population_over_time_facet.py
+++ b/tests/examples_arguments_syntax/us_population_over_time_facet.py
@@ -6,7 +6,7 @@
 """
 # category: case studies
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.population.url
 
diff --git a/tests/examples_arguments_syntax/us_population_pyramid_over_time.py b/tests/examples_arguments_syntax/us_population_pyramid_over_time.py
index 00f62f73f..e4809d1a9 100644
--- a/tests/examples_arguments_syntax/us_population_pyramid_over_time.py
+++ b/tests/examples_arguments_syntax/us_population_pyramid_over_time.py
@@ -7,7 +7,7 @@
 '''
 # category: case studies
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.population.url
 
diff --git a/tests/examples_arguments_syntax/us_state_capitals.py b/tests/examples_arguments_syntax/us_state_capitals.py
index e538dd49b..842cb493d 100644
--- a/tests/examples_arguments_syntax/us_state_capitals.py
+++ b/tests/examples_arguments_syntax/us_state_capitals.py
@@ -6,7 +6,7 @@
 """
 # category: case studies
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 states = alt.topo_feature(data.us_10m.url, 'states')
 capitals = data.us_state_capitals.url
diff --git a/tests/examples_arguments_syntax/violin_plot.py b/tests/examples_arguments_syntax/violin_plot.py
index 09977b86e..be46b7f6d 100644
--- a/tests/examples_arguments_syntax/violin_plot.py
+++ b/tests/examples_arguments_syntax/violin_plot.py
@@ -5,7 +5,7 @@
 """
 # category: distributions
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 alt.Chart(data.cars()).transform_density(
     'Miles_per_Gallon',
diff --git a/tests/examples_arguments_syntax/wheat_wages.py b/tests/examples_arguments_syntax/wheat_wages.py
index ccccbe6a4..bfb086515 100644
--- a/tests/examples_arguments_syntax/wheat_wages.py
+++ b/tests/examples_arguments_syntax/wheat_wages.py
@@ -9,7 +9,7 @@
 # category: case studies
 import altair as alt
 import pandas as pd
-from vega_datasets import data
+from altair.datasets import data
 
 
 base_wheat = alt.Chart(data.wheat.url).transform_calculate(year_end="+datum.year + 5")
diff --git a/tests/examples_arguments_syntax/wind_vector_map.py b/tests/examples_arguments_syntax/wind_vector_map.py
index 225f7b469..81f7536f0 100644
--- a/tests/examples_arguments_syntax/wind_vector_map.py
+++ b/tests/examples_arguments_syntax/wind_vector_map.py
@@ -9,7 +9,7 @@
 """
 # category: maps
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 df_wind = data.windvectors()
 data_world = alt.topo_feature(data.world_110m.url, "countries")
diff --git a/tests/examples_arguments_syntax/world_map.py b/tests/examples_arguments_syntax/world_map.py
index 34263937b..88504d3fd 100644
--- a/tests/examples_arguments_syntax/world_map.py
+++ b/tests/examples_arguments_syntax/world_map.py
@@ -8,7 +8,7 @@
 # category: maps
 
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 # Data generators for the background
 sphere = alt.sphere()
diff --git a/tests/examples_arguments_syntax/world_projections.py b/tests/examples_arguments_syntax/world_projections.py
index ffdbcd0dc..87402fc2c 100644
--- a/tests/examples_arguments_syntax/world_projections.py
+++ b/tests/examples_arguments_syntax/world_projections.py
@@ -6,7 +6,7 @@
 """
 # category: maps
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = alt.topo_feature(data.world_110m.url, 'countries')
 
diff --git a/tests/examples_methods_syntax/airport_connections.py b/tests/examples_methods_syntax/airport_connections.py
index 1d915eca4..c81d6717f 100644
--- a/tests/examples_methods_syntax/airport_connections.py
+++ b/tests/examples_methods_syntax/airport_connections.py
@@ -7,7 +7,7 @@
 """
 # category: case studies
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 # Since these data are each more than 5,000 rows we'll import from the URLs
 airports = data.airports.url
diff --git a/tests/examples_methods_syntax/annual_weather_heatmap.py b/tests/examples_methods_syntax/annual_weather_heatmap.py
index d96b1e06c..baa0857c9 100644
--- a/tests/examples_methods_syntax/annual_weather_heatmap.py
+++ b/tests/examples_methods_syntax/annual_weather_heatmap.py
@@ -4,7 +4,7 @@
 """
 # category: tables
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.seattle_weather()
 
diff --git a/tests/examples_methods_syntax/anscombe_plot.py b/tests/examples_methods_syntax/anscombe_plot.py
index 2b369f19a..183fc9c36 100644
--- a/tests/examples_methods_syntax/anscombe_plot.py
+++ b/tests/examples_methods_syntax/anscombe_plot.py
@@ -13,7 +13,7 @@
 """
 # category: case studies
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.anscombe()
 
diff --git a/tests/examples_methods_syntax/area_faceted.py b/tests/examples_methods_syntax/area_faceted.py
index b729e8c43..e806c8776 100644
--- a/tests/examples_methods_syntax/area_faceted.py
+++ b/tests/examples_methods_syntax/area_faceted.py
@@ -7,7 +7,7 @@
 """
 # category: area charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.stocks()
 
diff --git a/tests/examples_methods_syntax/bar_chart_sorted.py b/tests/examples_methods_syntax/bar_chart_sorted.py
index ab61f8cf3..ab8a2bf8e 100644
--- a/tests/examples_methods_syntax/bar_chart_sorted.py
+++ b/tests/examples_methods_syntax/bar_chart_sorted.py
@@ -5,7 +5,7 @@
 """
 # category: bar charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.barley()
 
diff --git a/tests/examples_methods_syntax/bar_chart_with_labels_measured_luminance.py b/tests/examples_methods_syntax/bar_chart_with_labels_measured_luminance.py
index 3517986ca..057824cd1 100644
--- a/tests/examples_methods_syntax/bar_chart_with_labels_measured_luminance.py
+++ b/tests/examples_methods_syntax/bar_chart_with_labels_measured_luminance.py
@@ -5,7 +5,7 @@
 """
 # category: bar charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.barley()
 
diff --git a/tests/examples_methods_syntax/bar_chart_with_range.py b/tests/examples_methods_syntax/bar_chart_with_range.py
index 5f5ce2e94..932c52667 100644
--- a/tests/examples_methods_syntax/bar_chart_with_range.py
+++ b/tests/examples_methods_syntax/bar_chart_with_range.py
@@ -5,7 +5,7 @@
 """
 # category: bar charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.seattle_weather()
 
diff --git a/tests/examples_methods_syntax/beckers_barley_facet.py b/tests/examples_methods_syntax/beckers_barley_facet.py
index 598183a01..af872d765 100644
--- a/tests/examples_methods_syntax/beckers_barley_facet.py
+++ b/tests/examples_methods_syntax/beckers_barley_facet.py
@@ -11,7 +11,7 @@
 """
 # category: case studies
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.barley()
 
diff --git a/tests/examples_methods_syntax/beckers_barley_wrapped_facet.py b/tests/examples_methods_syntax/beckers_barley_wrapped_facet.py
index a540d00dd..7e6409299 100644
--- a/tests/examples_methods_syntax/beckers_barley_wrapped_facet.py
+++ b/tests/examples_methods_syntax/beckers_barley_wrapped_facet.py
@@ -11,7 +11,7 @@
 """
 # category: case studies
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.barley.url
 
diff --git a/tests/examples_methods_syntax/bump_chart.py b/tests/examples_methods_syntax/bump_chart.py
index 8178668d8..d75cce39e 100644
--- a/tests/examples_methods_syntax/bump_chart.py
+++ b/tests/examples_methods_syntax/bump_chart.py
@@ -8,7 +8,7 @@
 # category: line charts
 
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 import pandas as pd
 
 stocks = data.stocks()
diff --git a/tests/examples_methods_syntax/calculate_residuals.py b/tests/examples_methods_syntax/calculate_residuals.py
index bb53fb788..814da7f74 100644
--- a/tests/examples_methods_syntax/calculate_residuals.py
+++ b/tests/examples_methods_syntax/calculate_residuals.py
@@ -8,11 +8,10 @@
 Adapted from `Calculate Residuals <https://vega.github.io/vega-lite/examples/joinaggregate_residual_graph.html>`_.
 """
 # category: advanced calculations
-
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
-imdb_rating = alt.datum["IMDB_Rating"]
+imdb_rating = alt.datum["IMDB Rating"]
 source = data.movies.url
 
 chart = (
@@ -20,12 +19,12 @@
     .mark_point()
     .transform_filter(imdb_rating != None)
     .transform_filter(
-        alt.FieldRangePredicate("Release_Date", [None, 2019], timeUnit="year")
+        alt.FieldRangePredicate("Release Date", [None, 2019], timeUnit="year")
     )
-    .transform_joinaggregate(Average_Rating="mean(IMDB_Rating)")
+    .transform_joinaggregate(Average_Rating="mean(IMDB Rating)")
     .transform_calculate(Rating_Delta=imdb_rating - alt.datum.Average_Rating)
     .encode(
-        x=alt.X("Release_Date:T").title("Release Date"),
+        x=alt.X("Release Date:T").title("Release Date"),
         y=alt.Y("Rating_Delta:Q").title("Rating Delta"),
         color=alt.Color("Rating_Delta:Q").title("Rating Delta").scale(domainMid=0),
     )
diff --git a/tests/examples_methods_syntax/candlestick_chart.py b/tests/examples_methods_syntax/candlestick_chart.py
index c001f7ddf..f49059b01 100644
--- a/tests/examples_methods_syntax/candlestick_chart.py
+++ b/tests/examples_methods_syntax/candlestick_chart.py
@@ -8,7 +8,7 @@
 """
 # category: advanced calculations
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.ohlc()
 
diff --git a/tests/examples_methods_syntax/co2_concentration.py b/tests/examples_methods_syntax/co2_concentration.py
index e82f830d6..74bec53b3 100644
--- a/tests/examples_methods_syntax/co2_concentration.py
+++ b/tests/examples_methods_syntax/co2_concentration.py
@@ -7,7 +7,7 @@
 """
 # category: case studies
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.co2_concentration.url
 
diff --git a/tests/examples_methods_syntax/comet_chart.py b/tests/examples_methods_syntax/comet_chart.py
index b8edff751..9c8a6cf54 100644
--- a/tests/examples_methods_syntax/comet_chart.py
+++ b/tests/examples_methods_syntax/comet_chart.py
@@ -9,10 +9,10 @@
 # category: advanced calculations
 
 import altair as alt
-import vega_datasets
+from altair.datasets import data
 
 alt.Chart(
-    vega_datasets.data.barley.url,
+    data.barley.url,
     title='Barley Yield comparison between 1932 and 1931'
 ).mark_trail().encode(
     alt.X('year:O').title(None),
diff --git a/tests/examples_methods_syntax/cumulative_count_chart.py b/tests/examples_methods_syntax/cumulative_count_chart.py
index a9b08361c..9e0f0c814 100644
--- a/tests/examples_methods_syntax/cumulative_count_chart.py
+++ b/tests/examples_methods_syntax/cumulative_count_chart.py
@@ -8,14 +8,14 @@
 # category: distributions
 
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.movies.url
 
 alt.Chart(source).transform_window(
     cumulative_count="count()",
-    sort=[{"field": "IMDB_Rating"}],
+    sort=[{"field": "IMDB Rating"}],
 ).mark_area().encode(
-    x="IMDB_Rating:Q",
+    x="IMDB Rating:Q",
     y=alt.Y("cumulative_count:Q").stack(False)
 )
diff --git a/tests/examples_methods_syntax/density_repeat.py b/tests/examples_methods_syntax/density_repeat.py
new file mode 100644
index 000000000..53a58c986
--- /dev/null
+++ b/tests/examples_methods_syntax/density_repeat.py
@@ -0,0 +1,33 @@
+"""
+Repeated Density Estimates
+--------------------------
+Density estimates for each measurement of penguins.
+This is what we call a "repeated" plot, with one subplot
+for each measurement type. All measurements are in millimeters,
+making them directly comparable on a shared x-axis.
+"""
+# category: distributions
+
+import altair as alt
+from altair.datasets import data
+
+source = data.penguins()
+
+alt.Chart(source).transform_fold(
+    [
+        "Beak Length (mm)",
+        "Beak Depth (mm)",
+        "Flipper Length (mm)",
+    ],
+    as_=["Measurement Type", "value"],
+).transform_density(
+    density="value",
+    groupby=["Measurement Type"]
+).mark_area().encode(
+    alt.X("value:Q"),
+    alt.Y("density:Q"),
+    alt.Row("Measurement Type:N").header(labelAngle=0, labelAlign="left")
+).properties(
+    width=300,
+    height=50
+)
diff --git a/tests/examples_methods_syntax/density_stack.py b/tests/examples_methods_syntax/density_stack.py
index 56b0161f1..f921f6a4c 100644
--- a/tests/examples_methods_syntax/density_stack.py
+++ b/tests/examples_methods_syntax/density_stack.py
@@ -3,7 +3,7 @@
 -------------------------
 To plot a stacked graph of estimates, use a shared ``extent`` and a fixed
 number of subdivision ``steps`` to ensure that the points for each area align
-well.  Density estimates of measurements for each iris flower feature are plot
+well.  Density estimates of body mass for each penguin species are plotted
 in a stacked method.  In addition, setting ``counts`` to true multiplies the
 densities by the number of data points in each group, preserving proportional
 differences.
@@ -11,25 +11,22 @@
 # category: distributions
 
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
-source = data.iris()
+source = data.penguins()
 
-alt.Chart(source).transform_fold(
-    ['petalWidth', 
-     'petalLength', 
-     'sepalWidth', 
-     'sepalLength'], 
-    as_ = ['Measurement_type', 'value']
-).transform_density(
-    density='value', 
-    bandwidth=0.3, 
-    groupby=['Measurement_type'], 
-    extent= [0, 8], 
-    counts = True, 
+alt.Chart(source).transform_density(
+    density='Body Mass (g)',
+    groupby=['Species'], 
+    extent= [2500, 6500],
+    counts = True,
     steps=200
 ).mark_area().encode(
-    alt.X('value:Q'), 
-    alt.Y('density:Q').stack('zero'),
-    alt.Color('Measurement_type:N')
-).properties(width=400, height=100)
+    alt.X('value:Q').title('Body Mass (g)'), 
+    alt.Y('density:Q', stack='zero'),
+    alt.Color('Species:N')
+).properties(
+    width=400,
+    height=80,
+    title='Distribution of Body Mass of Penguins'
+)
diff --git a/tests/examples_methods_syntax/deviation_ellipses.py b/tests/examples_methods_syntax/deviation_ellipses.py
index e33af7203..226482e41 100644
--- a/tests/examples_methods_syntax/deviation_ellipses.py
+++ b/tests/examples_methods_syntax/deviation_ellipses.py
@@ -1,7 +1,7 @@
 """
 Confidence Interval Ellipses
 ----------------------------
-This example shows bivariate deviation ellipses of petal length and width of three iris species.
+This example shows bivariate deviation ellipses of flipper length and body mass of three penguin species.
 
 Inspired by `ggplot2.stat_ellipse`_ and directly based on `Deviation ellipses example`_ by `@essicolo`_
 
@@ -19,7 +19,7 @@
 from scipy.stats import f as F
 
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 
 def confidence_region_2d(arr, conf_level=0.95, segments=50):
@@ -55,22 +55,22 @@ def grouped_confidence_regions(df, col_x, col_y, col_group):
     ellipses = []
     ser: pd.Series[float] = df[col_group]
     for group in ser.drop_duplicates():
-        arr = df.loc[ser == group, cols].to_numpy()
+        arr = df.loc[ser == group, cols].to_numpy(dtype=np.float64)
         ellipse = pd.DataFrame(confidence_region_2d(arr), columns=cols)
         ellipse[col_group] = group
         ellipses.append(ellipse)
     return pd.concat(ellipses).reset_index(names="order")
 
 
-col_x = "petalLength"
-col_y = "petalWidth"
-col_group = "species"
+col_x = "Flipper Length (mm)"
+col_y = "Body Mass (g)"
+col_group = "Species"
 
 x = alt.X(col_x).scale(zero=False)
 y = alt.Y(col_y).scale(zero=False)
 color = alt.Color(col_group)
 
-source = data.iris()
+source = data.penguins().dropna(subset=[col_x, col_y, col_group])
 ellipse = grouped_confidence_regions(source, col_x=col_x, col_y=col_y, col_group=col_group)
 points = alt.Chart(source).mark_circle(size=50, tooltip=True).encode(
     x=x,
diff --git a/tests/examples_methods_syntax/distributions_faceted_histogram.py b/tests/examples_methods_syntax/distributions_faceted_histogram.py
index 23506d60e..a00f80f0e 100644
--- a/tests/examples_methods_syntax/distributions_faceted_histogram.py
+++ b/tests/examples_methods_syntax/distributions_faceted_histogram.py
@@ -9,7 +9,7 @@
 """
 # category: distributions
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.cars()
 
diff --git a/tests/examples_methods_syntax/errorbars_with_ci.py b/tests/examples_methods_syntax/errorbars_with_ci.py
index af950a45e..417820082 100644
--- a/tests/examples_methods_syntax/errorbars_with_ci.py
+++ b/tests/examples_methods_syntax/errorbars_with_ci.py
@@ -7,7 +7,7 @@
 """
 # category: uncertainties and trends
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.barley()
 
diff --git a/tests/examples_methods_syntax/errorbars_with_std.py b/tests/examples_methods_syntax/errorbars_with_std.py
index d20c154b9..bd9a31b76 100644
--- a/tests/examples_methods_syntax/errorbars_with_std.py
+++ b/tests/examples_methods_syntax/errorbars_with_std.py
@@ -6,7 +6,7 @@
 """
 # category: uncertainties and trends
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.barley()
 
diff --git a/tests/examples_methods_syntax/gapminder_bubble_plot.py b/tests/examples_methods_syntax/gapminder_bubble_plot.py
index 839212885..5ed78dd49 100644
--- a/tests/examples_methods_syntax/gapminder_bubble_plot.py
+++ b/tests/examples_methods_syntax/gapminder_bubble_plot.py
@@ -7,7 +7,7 @@
 """
 # category: case studies
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.gapminder_health_income.url
 
diff --git a/tests/examples_methods_syntax/groupby-map.py b/tests/examples_methods_syntax/groupby-map.py
index 20f0817e6..511d28932 100644
--- a/tests/examples_methods_syntax/groupby-map.py
+++ b/tests/examples_methods_syntax/groupby-map.py
@@ -5,7 +5,7 @@
 """
 # category: maps
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 airports = data.airports.url
 states = alt.topo_feature(data.us_10m.url, feature='states')
diff --git a/tests/examples_methods_syntax/grouped_bar_chart_with_error_bars.py b/tests/examples_methods_syntax/grouped_bar_chart_with_error_bars.py
index 4ef796f12..77a533f0c 100644
--- a/tests/examples_methods_syntax/grouped_bar_chart_with_error_bars.py
+++ b/tests/examples_methods_syntax/grouped_bar_chart_with_error_bars.py
@@ -5,7 +5,7 @@
 """
 # category: bar charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.barley()
 
diff --git a/tests/examples_methods_syntax/heat_lane.py b/tests/examples_methods_syntax/heat_lane.py
index 63d8dd96c..0401710e5 100644
--- a/tests/examples_methods_syntax/heat_lane.py
+++ b/tests/examples_methods_syntax/heat_lane.py
@@ -5,7 +5,7 @@
 """
 # category: distributions
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.cars.url
 
diff --git a/tests/examples_methods_syntax/hexbins.py b/tests/examples_methods_syntax/hexbins.py
index 4e23e7bb0..f4e33d36b 100644
--- a/tests/examples_methods_syntax/hexbins.py
+++ b/tests/examples_methods_syntax/hexbins.py
@@ -5,7 +5,7 @@
 """
 # category: tables
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.seattle_weather()
 
diff --git a/tests/examples_methods_syntax/histogram_gradient_color.py b/tests/examples_methods_syntax/histogram_gradient_color.py
index 645453475..ccb6e700a 100644
--- a/tests/examples_methods_syntax/histogram_gradient_color.py
+++ b/tests/examples_methods_syntax/histogram_gradient_color.py
@@ -6,12 +6,12 @@
 """
 # category: distributions
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.movies.url
 
 alt.Chart(source).mark_bar().encode(
-    alt.X("IMDB_Rating:Q").bin(maxbins=20).scale(domain=[1, 10]),
+    alt.X("IMDB Rating:Q").bin(maxbins=20).scale(domain=[1, 10]),
     alt.Y('count()'),
-    alt.Color("IMDB_Rating:Q").bin(maxbins=20).scale(scheme='pinkyellowgreen')
+    alt.Color("IMDB Rating:Q").bin(maxbins=20).scale(scheme='pinkyellowgreen')
 )
\ No newline at end of file
diff --git a/tests/examples_methods_syntax/histogram_heatmap.py b/tests/examples_methods_syntax/histogram_heatmap.py
index c697d1dd7..f3f8fb7ee 100644
--- a/tests/examples_methods_syntax/histogram_heatmap.py
+++ b/tests/examples_methods_syntax/histogram_heatmap.py
@@ -5,12 +5,12 @@
 """
 # category: distributions
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.movies.url
 
 alt.Chart(source).mark_rect().encode(
-    alt.X('IMDB_Rating:Q').bin(maxbins=60),
-    alt.Y('Rotten_Tomatoes_Rating:Q').bin(maxbins=40),
+    alt.X('IMDB Rating:Q').bin(maxbins=60),
+    alt.Y('Rotten Tomatoes Rating:Q').bin(maxbins=40),
     alt.Color('count():Q').scale(scheme='greenblue')
 )
diff --git a/tests/examples_methods_syntax/histogram_responsive.py b/tests/examples_methods_syntax/histogram_responsive.py
index e8ce16cb6..d6da0b1c4 100644
--- a/tests/examples_methods_syntax/histogram_responsive.py
+++ b/tests/examples_methods_syntax/histogram_responsive.py
@@ -7,7 +7,7 @@
 """
 # category: distributions
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.flights_5k.url
 
diff --git a/tests/examples_methods_syntax/histogram_scatterplot.py b/tests/examples_methods_syntax/histogram_scatterplot.py
index 6286b615e..7d5ac3a90 100644
--- a/tests/examples_methods_syntax/histogram_scatterplot.py
+++ b/tests/examples_methods_syntax/histogram_scatterplot.py
@@ -5,12 +5,12 @@
 """
 # category: distributions
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.movies.url
 
 alt.Chart(source).mark_circle().encode(
-    alt.X('IMDB_Rating:Q').bin(),
-    alt.Y('Rotten_Tomatoes_Rating:Q').bin(),
+    alt.X('IMDB Rating:Q').bin(),
+    alt.Y('Rotten Tomatoes Rating:Q').bin(),
     size='count()'
 )
diff --git a/tests/examples_methods_syntax/histogram_with_a_global_mean_overlay.py b/tests/examples_methods_syntax/histogram_with_a_global_mean_overlay.py
index bcb91a216..11d98e7c0 100644
--- a/tests/examples_methods_syntax/histogram_with_a_global_mean_overlay.py
+++ b/tests/examples_methods_syntax/histogram_with_a_global_mean_overlay.py
@@ -5,19 +5,19 @@
 """
 # category: distributions
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.movies.url
 
 base = alt.Chart(source)
 
 bar = base.mark_bar().encode(
-    alt.X('IMDB_Rating:Q').bin().axis(None),
+    alt.X('IMDB Rating:Q').bin().axis(None),
     y='count()'
 )
 
 rule = base.mark_rule(color='red').encode(
-    x='mean(IMDB_Rating):Q',
+    x='mean(IMDB Rating):Q',
     size=alt.value(5)
 )
 
diff --git a/tests/examples_methods_syntax/interactive_aggregation.py b/tests/examples_methods_syntax/interactive_aggregation.py
index e02de5c8b..78b0fdcf2 100644
--- a/tests/examples_methods_syntax/interactive_aggregation.py
+++ b/tests/examples_methods_syntax/interactive_aggregation.py
@@ -9,7 +9,7 @@
 """
 # category: interactive charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.movies.url
 
@@ -18,18 +18,18 @@
 
 alt.layer(
     alt.Chart(source).mark_circle().encode(
-        x=alt.X("IMDB_Rating:Q").title("IMDB Rating"),
-        y=alt.Y("Rotten_Tomatoes_Rating:Q").title("Rotten Tomatoes Rating")
+        x=alt.X("IMDB Rating:Q").title("IMDB Rating"),
+        y=alt.Y("Rotten Tomatoes Rating:Q").title("Rotten Tomatoes Rating")
     ).transform_filter(
-        alt.datum["IMDB_Rating"] >= threshold
+        alt.datum["IMDB Rating"] >= threshold
     ),
 
     alt.Chart(source).mark_circle().encode(
-        x=alt.X("IMDB_Rating:Q").bin(maxbins=10),
-        y=alt.Y("Rotten_Tomatoes_Rating:Q").bin(maxbins=10),
+        x=alt.X("IMDB Rating:Q").bin(maxbins=10),
+        y=alt.Y("Rotten Tomatoes Rating:Q").bin(maxbins=10),
         size=alt.Size("count():Q").scale(domain=[0,160])
     ).transform_filter(
-        alt.datum["IMDB_Rating"] < threshold
+        alt.datum["IMDB Rating"] < threshold
     ),
 
     alt.Chart().mark_rule(color="gray").encode(
diff --git a/tests/examples_methods_syntax/interactive_cross_highlight.py b/tests/examples_methods_syntax/interactive_cross_highlight.py
index 97dccb314..141dccbd2 100644
--- a/tests/examples_methods_syntax/interactive_cross_highlight.py
+++ b/tests/examples_methods_syntax/interactive_cross_highlight.py
@@ -7,15 +7,15 @@
 """
 # category: interactive charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.movies.url
 
 pts = alt.selection_point(encodings=['x'])
 
 rect = alt.Chart(data.movies.url).mark_rect().encode(
-    alt.X('IMDB_Rating:Q').bin(),
-    alt.Y('Rotten_Tomatoes_Rating:Q').bin(),
+    alt.X('IMDB Rating:Q').bin(),
+    alt.Y('Rotten Tomatoes Rating:Q').bin(),
     alt.Color('count()').scale(scheme='greenblue').title('Total Records')
 )
 
@@ -27,7 +27,7 @@
 )
 
 bar = alt.Chart(source, width=550, height=200).mark_bar().encode(
-    x='Major_Genre:N',
+    x='Major Genre:N',
     y='count()',
     color=alt.when(pts).then(alt.ColorValue("steelblue")).otherwise(alt.ColorValue("grey"))
 ).add_params(pts)
diff --git a/tests/examples_methods_syntax/interactive_layered_crossfilter.py b/tests/examples_methods_syntax/interactive_layered_crossfilter.py
index bc0003c0c..a51df257f 100644
--- a/tests/examples_methods_syntax/interactive_layered_crossfilter.py
+++ b/tests/examples_methods_syntax/interactive_layered_crossfilter.py
@@ -7,7 +7,7 @@
 """
 # category: interactive charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = alt.UrlData(
     data.flights_2k.url,
diff --git a/tests/examples_methods_syntax/interactive_legend.py b/tests/examples_methods_syntax/interactive_legend.py
index e6a6e36f7..9ff8365d6 100644
--- a/tests/examples_methods_syntax/interactive_legend.py
+++ b/tests/examples_methods_syntax/interactive_legend.py
@@ -7,7 +7,7 @@
 """
 # category: interactive charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.unemployment_across_industries.url
 
diff --git a/tests/examples_methods_syntax/interval_selection.py b/tests/examples_methods_syntax/interval_selection.py
index 811384717..aad560f68 100644
--- a/tests/examples_methods_syntax/interval_selection.py
+++ b/tests/examples_methods_syntax/interval_selection.py
@@ -8,7 +8,7 @@
 """
 # category: interactive charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 import datetime as dt
 
 source = data.sp500.url
diff --git a/tests/examples_methods_syntax/iowa_electricity.py b/tests/examples_methods_syntax/iowa_electricity.py
index 7f277df23..fa8440352 100644
--- a/tests/examples_methods_syntax/iowa_electricity.py
+++ b/tests/examples_methods_syntax/iowa_electricity.py
@@ -5,7 +5,7 @@
 """
 # category: case studies
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.iowa_electricity()
 
diff --git a/tests/examples_methods_syntax/lasagna_plot.py b/tests/examples_methods_syntax/lasagna_plot.py
index 31ab3ee40..be3a53b36 100644
--- a/tests/examples_methods_syntax/lasagna_plot.py
+++ b/tests/examples_methods_syntax/lasagna_plot.py
@@ -4,7 +4,7 @@
 """
 # category: tables
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.stocks()
 
diff --git a/tests/examples_methods_syntax/layered_area_chart.py b/tests/examples_methods_syntax/layered_area_chart.py
index 83eb51b75..8f8661a95 100644
--- a/tests/examples_methods_syntax/layered_area_chart.py
+++ b/tests/examples_methods_syntax/layered_area_chart.py
@@ -5,7 +5,7 @@
 """
 # category: area charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.iowa_electricity()
 
diff --git a/tests/examples_methods_syntax/layered_bar_chart.py b/tests/examples_methods_syntax/layered_bar_chart.py
index ba485fea7..8afc014f2 100644
--- a/tests/examples_methods_syntax/layered_bar_chart.py
+++ b/tests/examples_methods_syntax/layered_bar_chart.py
@@ -5,7 +5,7 @@
 """
 # category: bar charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.iowa_electricity()
 
diff --git a/tests/examples_methods_syntax/layered_chart_with_dual_axis.py b/tests/examples_methods_syntax/layered_chart_with_dual_axis.py
index 3947380a2..bef1033e4 100644
--- a/tests/examples_methods_syntax/layered_chart_with_dual_axis.py
+++ b/tests/examples_methods_syntax/layered_chart_with_dual_axis.py
@@ -6,7 +6,7 @@
 # category: advanced calculations
 
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.seattle_weather()
 
diff --git a/tests/examples_methods_syntax/layered_heatmap_text.py b/tests/examples_methods_syntax/layered_heatmap_text.py
index ba56f8539..fb013d980 100644
--- a/tests/examples_methods_syntax/layered_heatmap_text.py
+++ b/tests/examples_methods_syntax/layered_heatmap_text.py
@@ -6,7 +6,7 @@
 """
 # category: tables
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.cars()
 
diff --git a/tests/examples_methods_syntax/line_chart_with_color_datum.py b/tests/examples_methods_syntax/line_chart_with_color_datum.py
index 77cad9574..637bfce5c 100644
--- a/tests/examples_methods_syntax/line_chart_with_color_datum.py
+++ b/tests/examples_methods_syntax/line_chart_with_color_datum.py
@@ -8,16 +8,16 @@
 # category: line charts
 
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.movies()
 
 alt.Chart(source).mark_line().encode(
-    alt.X("IMDB_Rating").bin(True),
+    alt.X("IMDB Rating").bin(True),
     alt.Y(alt.repeat("layer"))
         .aggregate("mean")
         .title("Mean of US and Worldwide Gross"),
     color=alt.datum(alt.repeat("layer")),
 ).repeat(
-    layer=["US_Gross", "Worldwide_Gross"]
+    layer=["US Gross", "Worldwide Gross"]
 )
diff --git a/tests/examples_methods_syntax/line_chart_with_cumsum.py b/tests/examples_methods_syntax/line_chart_with_cumsum.py
index ef3144fe1..8d31dffda 100644
--- a/tests/examples_methods_syntax/line_chart_with_cumsum.py
+++ b/tests/examples_methods_syntax/line_chart_with_cumsum.py
@@ -5,7 +5,7 @@
 """
 # category: line charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.wheat()
 
diff --git a/tests/examples_methods_syntax/line_chart_with_cumsum_faceted.py b/tests/examples_methods_syntax/line_chart_with_cumsum_faceted.py
index 48ebc27ca..6bee0664e 100644
--- a/tests/examples_methods_syntax/line_chart_with_cumsum_faceted.py
+++ b/tests/examples_methods_syntax/line_chart_with_cumsum_faceted.py
@@ -6,7 +6,7 @@
 """
 # category: advanced calculations
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.disasters()
 columns_sorted = ['Drought', 'Epidemic', 'Earthquake', 'Flood']
diff --git a/tests/examples_methods_syntax/line_chart_with_custom_legend.py b/tests/examples_methods_syntax/line_chart_with_custom_legend.py
index 2ee60088e..dfdf9ca1e 100644
--- a/tests/examples_methods_syntax/line_chart_with_custom_legend.py
+++ b/tests/examples_methods_syntax/line_chart_with_custom_legend.py
@@ -6,7 +6,7 @@
 """
 # category: line charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 
 source = data.stocks()
diff --git a/tests/examples_methods_syntax/line_custom_order.py b/tests/examples_methods_syntax/line_custom_order.py
index 4681c2aee..33a713af3 100644
--- a/tests/examples_methods_syntax/line_custom_order.py
+++ b/tests/examples_methods_syntax/line_custom_order.py
@@ -16,7 +16,7 @@
 """
 # category: line charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.driving()
 
diff --git a/tests/examples_methods_syntax/line_percent.py b/tests/examples_methods_syntax/line_percent.py
index 52e047034..319dacff7 100644
--- a/tests/examples_methods_syntax/line_percent.py
+++ b/tests/examples_methods_syntax/line_percent.py
@@ -5,7 +5,7 @@
 """
 # category: line charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.jobs.url
 
diff --git a/tests/examples_methods_syntax/line_with_ci.py b/tests/examples_methods_syntax/line_with_ci.py
index 744f453d0..0243b0ed2 100644
--- a/tests/examples_methods_syntax/line_with_ci.py
+++ b/tests/examples_methods_syntax/line_with_ci.py
@@ -5,7 +5,7 @@
 """
 # category: uncertainties and trends
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.cars()
 
diff --git a/tests/examples_methods_syntax/line_with_last_value_labeled.py b/tests/examples_methods_syntax/line_with_last_value_labeled.py
index 1bc108a08..256f8671f 100644
--- a/tests/examples_methods_syntax/line_with_last_value_labeled.py
+++ b/tests/examples_methods_syntax/line_with_last_value_labeled.py
@@ -5,7 +5,7 @@
 """
 # category: line charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 # Import example data
 source = data.stocks()
diff --git a/tests/examples_methods_syntax/line_with_log_scale.py b/tests/examples_methods_syntax/line_with_log_scale.py
index 740a670cb..021114a75 100644
--- a/tests/examples_methods_syntax/line_with_log_scale.py
+++ b/tests/examples_methods_syntax/line_with_log_scale.py
@@ -5,7 +5,7 @@
 """
 # category: line charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.population()
 
diff --git a/tests/examples_methods_syntax/london_tube.py b/tests/examples_methods_syntax/london_tube.py
index b19ef9acc..671efaa54 100644
--- a/tests/examples_methods_syntax/london_tube.py
+++ b/tests/examples_methods_syntax/london_tube.py
@@ -7,11 +7,11 @@
 """
 # category: case studies
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
-boroughs = alt.topo_feature(data.londonBoroughs.url, 'boroughs')
-tubelines = alt.topo_feature(data.londonTubeLines.url, 'line')
-centroids = data.londonCentroids.url
+boroughs = alt.topo_feature(data.london_boroughs.url, 'boroughs')
+tubelines = alt.topo_feature(data.london_tube_lines.url, 'line')
+centroids = data.london_centroids.url
 
 background = alt.Chart(boroughs, width=700, height=500).mark_geoshape(
     stroke='white',
diff --git a/tests/examples_methods_syntax/mosaic_with_labels.py b/tests/examples_methods_syntax/mosaic_with_labels.py
index d77ed05ab..0b52bcf16 100644
--- a/tests/examples_methods_syntax/mosaic_with_labels.py
+++ b/tests/examples_methods_syntax/mosaic_with_labels.py
@@ -5,7 +5,7 @@
 # category: tables
 
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.cars()
 
diff --git a/tests/examples_methods_syntax/multifeature_scatter_plot.py b/tests/examples_methods_syntax/multifeature_scatter_plot.py
index 164b647bd..ce474bc27 100644
--- a/tests/examples_methods_syntax/multifeature_scatter_plot.py
+++ b/tests/examples_methods_syntax/multifeature_scatter_plot.py
@@ -5,13 +5,13 @@
 """
 # category: scatter plots
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
-source = data.iris()
+source = data.penguins()
 
 alt.Chart(source).mark_circle().encode(
-    alt.X('sepalLength').scale(zero=False),
-    alt.Y('sepalWidth').scale(zero=False, padding=1),
-    color='species',
-    size='petalWidth'
+    alt.X('Flipper Length (mm)').scale(zero=False),
+    alt.Y('Body Mass (g)').scale(zero=False, padding=1),
+    alt.Size('Beak Depth (mm)').scale(zero=False),
+    color='Species'
 )
diff --git a/tests/examples_methods_syntax/multiline_highlight.py b/tests/examples_methods_syntax/multiline_highlight.py
index bbc7634e8..ac8c61292 100644
--- a/tests/examples_methods_syntax/multiline_highlight.py
+++ b/tests/examples_methods_syntax/multiline_highlight.py
@@ -8,7 +8,7 @@
 """
 # category: interactive charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.stocks()
 
diff --git a/tests/examples_methods_syntax/multiple_interactions.py b/tests/examples_methods_syntax/multiple_interactions.py
index cab614148..084290afa 100644
--- a/tests/examples_methods_syntax/multiple_interactions.py
+++ b/tests/examples_methods_syntax/multiple_interactions.py
@@ -11,11 +11,11 @@
 """
 # category: interactive charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 movies = alt.UrlData(
     data.movies.url,
-    format=alt.DataFormat(parse={"Release_Date":"date"})
+    format=alt.DataFormat(parse={'Release Date':'date'})
 )
 ratings = ['G', 'NC-17', 'PG', 'PG-13', 'R']
 genres = [
@@ -25,62 +25,61 @@
 ]
 
 base = alt.Chart(movies, width=200, height=200).mark_point(filled=True).transform_calculate(
-    Rounded_IMDB_Rating = "floor(datum.IMDB_Rating)",
-    Big_Budget_Film =  "datum.Production_Budget > 100000000 ? 'Yes' : 'No'", 
-    Release_Year = "year(datum.Release_Date)",
+    Big_Budget_Film = "datum['Production Budget'] > 100000000 ? 'Yes' : 'No'", 
+    Release_Year = "year(datum['Release Date'])",
 ).transform_filter(
-    alt.datum.IMDB_Rating > 0
+    alt.datum['IMDB Rating'] > 0
 ).transform_filter(
-    alt.FieldOneOfPredicate(field='MPAA_Rating', oneOf=ratings)
+    alt.FieldOneOfPredicate(field='MPAA Rating', oneOf=ratings)
 ).encode(
-    x=alt.X('Worldwide_Gross:Q').scale(domain=(100000,10**9), clamp=True),
-    y='IMDB_Rating:Q',
-    tooltip="Title:N"
+    x=alt.X('Worldwide Gross:Q').scale(domain=(100000,10**9), clamp=True),
+    y='IMDB Rating:Q',
+    tooltip='Title:N'
 )
 
 # A slider filter
-year_slider = alt.binding_range(min=1969, max=2018, step=1, name="Release Year")
+year_slider = alt.binding_range(min=1969, max=2018, step=1, name='Release Year')
 slider_selection = alt.selection_point(bind=year_slider, fields=['Release_Year'])
 
 filter_year = base.add_params(
     slider_selection
 ).transform_filter(
     slider_selection
-).properties(title="Slider Filtering")
+).properties(title='Slider Filtering')
 
 # A dropdown filter
-genre_dropdown = alt.binding_select(options=genres, name="Genre")
-genre_select = alt.selection_point(fields=['Major_Genre'], bind=genre_dropdown)
+genre_dropdown = alt.binding_select(options=genres, name='Genre')
+genre_select = alt.selection_point(fields=['Major Genre'], bind=genre_dropdown)
 
 filter_genres = base.add_params(
     genre_select
 ).transform_filter(
     genre_select
-).properties(title="Dropdown Filtering")
+).properties(title='Dropdown Filtering')
 
 # Color changing marks
-rating_radio = alt.binding_radio(options=ratings, name="Rating")
-rating_select = alt.selection_point(fields=['MPAA_Rating'], bind=rating_radio)
+rating_radio = alt.binding_radio(options=ratings, name='Rating')
+rating_select = alt.selection_point(fields=['MPAA Rating'], bind=rating_radio)
 
 rating_color = (
     alt.when(rating_select)
-    .then(alt.Color("MPAA_Rating:N").legend(None))
-    .otherwise(alt.value("lightgray"))
+    .then(alt.Color('MPAA Rating:N').legend(None))
+    .otherwise(alt.value('lightgray'))
 )
 
 highlight_ratings = base.add_params(
     rating_select
 ).encode(
     color=rating_color
-).properties(title="Radio Button Highlighting")
+).properties(title='Radio Button Highlighting')
 
 # Boolean selection for format changes
-input_checkbox = alt.binding_checkbox(name="Big Budget Films ")
+input_checkbox = alt.binding_checkbox(name='Big Budget Films ')
 checkbox_selection = alt.param(bind=input_checkbox)
 
 size_checkbox = (
     alt.when(checkbox_selection)
-    .then(alt.Size('Big_Budget_Film:N').scale(range=[25, 150]))
+    .then(alt.Size('Big Budget Film:N').scale(range=[25, 150]))
     .otherwise(alt.value(25))
 )
 
@@ -88,6 +87,6 @@
     checkbox_selection
 ).encode(
     size=size_checkbox
-).properties(title="Checkbox Formatting")
+).properties(title='Checkbox Formatting')
 
 (filter_year | budget_sizing) & (highlight_ratings | filter_genres)
diff --git a/tests/examples_methods_syntax/natural_disasters.py b/tests/examples_methods_syntax/natural_disasters.py
index cbc5a0d68..0b16b67c9 100644
--- a/tests/examples_methods_syntax/natural_disasters.py
+++ b/tests/examples_methods_syntax/natural_disasters.py
@@ -5,7 +5,7 @@
 """
 # category: case studies
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.disasters.url
 
diff --git a/tests/examples_methods_syntax/normalized_stacked_area_chart.py b/tests/examples_methods_syntax/normalized_stacked_area_chart.py
index 5973d7174..9a5b2b8c5 100644
--- a/tests/examples_methods_syntax/normalized_stacked_area_chart.py
+++ b/tests/examples_methods_syntax/normalized_stacked_area_chart.py
@@ -5,7 +5,7 @@
 """
 # category: area charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.iowa_electricity()
 
diff --git a/tests/examples_methods_syntax/normalized_stacked_bar_chart.py b/tests/examples_methods_syntax/normalized_stacked_bar_chart.py
index 71e48b9a1..9bb6db093 100644
--- a/tests/examples_methods_syntax/normalized_stacked_bar_chart.py
+++ b/tests/examples_methods_syntax/normalized_stacked_bar_chart.py
@@ -5,7 +5,7 @@
 """
 # category: bar charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.barley()
 
diff --git a/tests/examples_methods_syntax/parallel_coordinates.py b/tests/examples_methods_syntax/parallel_coordinates.py
index f5d7cbd6e..8258a45d3 100644
--- a/tests/examples_methods_syntax/parallel_coordinates.py
+++ b/tests/examples_methods_syntax/parallel_coordinates.py
@@ -6,23 +6,23 @@
 a single line for each of them.
 Such a chart can be created in Altair by first transforming the data into a
 suitable representation.
-This example shows a parallel coordinates chart with the Iris dataset.
+This example shows a parallel coordinates chart with the Penguins dataset.
 """
 # category: advanced calculations
 
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
-source = data.iris()
+source = data.penguins()
 
 alt.Chart(source, width=500).transform_window(
     index='count()'
 ).transform_fold(
-    ['petalLength', 'petalWidth', 'sepalLength', 'sepalWidth']
+    ['Beak Length (mm)', 'Beak Depth (mm)', 'Flipper Length (mm)']
 ).mark_line().encode(
     x='key:N',
     y='value:Q',
-    color='species:N',
+    color='Species:N',
     detail='index:N',
     opacity=alt.value(0.5)
 )
diff --git a/tests/examples_methods_syntax/ranged_dot_plot.py b/tests/examples_methods_syntax/ranged_dot_plot.py
index d2649c7ec..1741e6f54 100644
--- a/tests/examples_methods_syntax/ranged_dot_plot.py
+++ b/tests/examples_methods_syntax/ranged_dot_plot.py
@@ -5,7 +5,7 @@
 """
 # category: advanced calculations
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.countries.url
 
diff --git a/tests/examples_methods_syntax/ridgeline_plot.py b/tests/examples_methods_syntax/ridgeline_plot.py
index 8ac691d64..b41c96f53 100644
--- a/tests/examples_methods_syntax/ridgeline_plot.py
+++ b/tests/examples_methods_syntax/ridgeline_plot.py
@@ -10,7 +10,7 @@
 """
 # category: distributions
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.seattle_weather.url
 
diff --git a/tests/examples_methods_syntax/scatter_linked_table.py b/tests/examples_methods_syntax/scatter_linked_table.py
index d2fd3f317..43b7aded2 100644
--- a/tests/examples_methods_syntax/scatter_linked_table.py
+++ b/tests/examples_methods_syntax/scatter_linked_table.py
@@ -7,7 +7,7 @@
 # category: scatter plots
 
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.cars()
 
diff --git a/tests/examples_methods_syntax/scatter_marginal_hist.py b/tests/examples_methods_syntax/scatter_marginal_hist.py
index 9669b70ab..5e585b59e 100644
--- a/tests/examples_methods_syntax/scatter_marginal_hist.py
+++ b/tests/examples_methods_syntax/scatter_marginal_hist.py
@@ -6,32 +6,32 @@
 """
 # category: distributions
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
-source = data.iris()
+source = data.penguins()
 
 base = alt.Chart(source)
 base_bar = base.mark_bar(opacity=0.3, binSpacing=0)
 
-xscale = alt.Scale(domain=(4.0, 8.0))
-yscale = alt.Scale(domain=(1.9, 4.55))
+xscale = alt.Scale(domain=(170, 235))
+yscale = alt.Scale(domain=(2500, 6500))
 
 points = base.mark_circle().encode(
-    alt.X("sepalLength").scale(xscale),
-    alt.Y("sepalWidth").scale(yscale),
-    color="species",
+    alt.X("Flipper Length (mm)").scale(xscale),
+    alt.Y("Body Mass (g)").scale(yscale),
+    color="Species",
 )
 
 top_hist = (
     base_bar
     .encode(
-        alt.X("sepalLength:Q")
+        alt.X("Flipper Length (mm):Q")
             # when using bins, the axis scale is set through
             # the bin extent, so we do not specify the scale here
             # (which would be ignored anyway)
             .bin(maxbins=20, extent=xscale.domain).stack(None).title(""),
         alt.Y("count()").stack(None).title(""),
-        alt.Color("species:N"),
+        alt.Color("Species:N"),
     )
     .properties(height=60)
 )
@@ -39,12 +39,12 @@
 right_hist = (
     base_bar
     .encode(
-        alt.Y("sepalWidth:Q")
+        alt.Y("Body Mass (g):Q")
             .bin(maxbins=20, extent=yscale.domain)
             .stack(None)
             .title(""),
         alt.X("count()").stack(None).title(""),
-        alt.Color("species:N"),
+        alt.Color("Species:N"),
     )
     .properties(width=60)
 )
diff --git a/tests/examples_methods_syntax/scatter_point_paths_hover.py b/tests/examples_methods_syntax/scatter_point_paths_hover.py
index c6a9c5f19..a1829afdd 100644
--- a/tests/examples_methods_syntax/scatter_point_paths_hover.py
+++ b/tests/examples_methods_syntax/scatter_point_paths_hover.py
@@ -13,7 +13,7 @@
 """
 # category: interactive charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 # Data source
 source = data.gapminder.url
diff --git a/tests/examples_methods_syntax/scatter_with_minimap.py b/tests/examples_methods_syntax/scatter_with_minimap.py
index 9faafa720..e89e15aae 100644
--- a/tests/examples_methods_syntax/scatter_with_minimap.py
+++ b/tests/examples_methods_syntax/scatter_with_minimap.py
@@ -8,7 +8,7 @@
 # category: scatter plots
 
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.seattle_weather()
 
diff --git a/tests/examples_methods_syntax/scatter_with_rolling_mean.py b/tests/examples_methods_syntax/scatter_with_rolling_mean.py
index 914e32e4e..035e4cda8 100644
--- a/tests/examples_methods_syntax/scatter_with_rolling_mean.py
+++ b/tests/examples_methods_syntax/scatter_with_rolling_mean.py
@@ -7,7 +7,7 @@
 # category: scatter plots
 
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.seattle_weather()
 
diff --git a/tests/examples_methods_syntax/seattle_weather_interactive.py b/tests/examples_methods_syntax/seattle_weather_interactive.py
index 83c7f3e6b..d2bc754c6 100644
--- a/tests/examples_methods_syntax/seattle_weather_interactive.py
+++ b/tests/examples_methods_syntax/seattle_weather_interactive.py
@@ -7,7 +7,7 @@
 """
 # category: case studies
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.seattle_weather()
 
diff --git a/tests/examples_methods_syntax/sorted_error_bars_with_ci.py b/tests/examples_methods_syntax/sorted_error_bars_with_ci.py
index ebda26a99..1cbfcdb48 100644
--- a/tests/examples_methods_syntax/sorted_error_bars_with_ci.py
+++ b/tests/examples_methods_syntax/sorted_error_bars_with_ci.py
@@ -6,7 +6,7 @@
 # category: advanced calculations
 
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.barley()
 
diff --git a/tests/examples_methods_syntax/stacked_bar_chart_sorted_segments.py b/tests/examples_methods_syntax/stacked_bar_chart_sorted_segments.py
index 2a189fedd..387eff70b 100644
--- a/tests/examples_methods_syntax/stacked_bar_chart_sorted_segments.py
+++ b/tests/examples_methods_syntax/stacked_bar_chart_sorted_segments.py
@@ -5,7 +5,7 @@
 """
 # category: bar charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.barley()
 
diff --git a/tests/examples_methods_syntax/stacked_bar_chart_with_text.py b/tests/examples_methods_syntax/stacked_bar_chart_with_text.py
index f2641e4e2..879cda173 100644
--- a/tests/examples_methods_syntax/stacked_bar_chart_with_text.py
+++ b/tests/examples_methods_syntax/stacked_bar_chart_with_text.py
@@ -7,7 +7,7 @@
 """
 # category: bar charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source=data.barley()
 
diff --git a/tests/examples_methods_syntax/streamgraph.py b/tests/examples_methods_syntax/streamgraph.py
index b9bdcb512..70efe307f 100644
--- a/tests/examples_methods_syntax/streamgraph.py
+++ b/tests/examples_methods_syntax/streamgraph.py
@@ -5,7 +5,7 @@
 """
 # category: area charts
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.unemployment_across_industries.url
 
diff --git a/tests/examples_methods_syntax/strip_plot_jitter.py b/tests/examples_methods_syntax/strip_plot_jitter.py
index edf572b02..1df416c4c 100644
--- a/tests/examples_methods_syntax/strip_plot_jitter.py
+++ b/tests/examples_methods_syntax/strip_plot_jitter.py
@@ -11,15 +11,15 @@
 """
 # category: distributions
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.movies.url
 
 gaussian_jitter = alt.Chart(source, title='Normally distributed jitter').mark_circle(size=8).encode(
-    y="Major_Genre:N",
-    x="IMDB_Rating:Q",
+    y="Major Genre:N",
+    x="IMDB Rating:Q",
     yOffset="jitter:Q",
-    color=alt.Color('Major_Genre:N').legend(None)
+    color=alt.Color('Major Genre:N').legend(None)
 ).transform_calculate(
     # Generate Gaussian jitter with a Box-Muller transform
     jitter="sqrt(-2*log(random()))*cos(2*PI*random())"
@@ -29,7 +29,7 @@
     # Generate uniform jitter
     jitter='random()'
 ).encode(
-    alt.Y('Major_Genre:N').axis(None)
+    alt.Y('Major Genre:N').axis(None)
 ).properties(
     title='Uniformly distributed jitter'
 )
diff --git a/tests/examples_methods_syntax/top_k_items.py b/tests/examples_methods_syntax/top_k_items.py
index 49285670e..0f573997e 100644
--- a/tests/examples_methods_syntax/top_k_items.py
+++ b/tests/examples_methods_syntax/top_k_items.py
@@ -7,7 +7,7 @@
 """
 # category: advanced calculations
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.movies.url
 
@@ -16,12 +16,12 @@
     source,
 ).mark_bar().encode(
     alt.X('Title:N').sort('-y'),
-    alt.Y('IMDB_Rating:Q'),
-    alt.Color('IMDB_Rating:Q')
+    alt.Y('IMDB Rating:Q'),
+alt.Color('IMDB Rating:Q')
     
 ).transform_window(
-    rank='rank(IMDB_Rating)',
-    sort=[alt.SortField('IMDB_Rating', order='descending')]
+    rank='rank(IMDB Rating)',
+sort=[alt.SortField('IMDB Rating', order='descending')]
 ).transform_filter(
     (alt.datum.rank < 10)
 )
diff --git a/tests/examples_methods_syntax/top_k_with_others.py b/tests/examples_methods_syntax/top_k_with_others.py
index 8c2dd99aa..56afda0bc 100644
--- a/tests/examples_methods_syntax/top_k_with_others.py
+++ b/tests/examples_methods_syntax/top_k_with_others.py
@@ -7,7 +7,7 @@
 """
 # category: advanced calculations
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.movies.url
 
@@ -17,7 +17,7 @@
         .sort(op="mean", field="aggregate_gross", order="descending")
         .title(None)
 ).transform_aggregate(
-    aggregate_gross='mean(Worldwide_Gross)',
+    aggregate_gross='mean(Worldwide Gross)',
     groupby=["Director"],
 ).transform_window(
     rank='row_number()',
diff --git a/tests/examples_methods_syntax/us_employment.py b/tests/examples_methods_syntax/us_employment.py
index 24272d44d..54c0a70c4 100644
--- a/tests/examples_methods_syntax/us_employment.py
+++ b/tests/examples_methods_syntax/us_employment.py
@@ -6,7 +6,7 @@
 # category: case studies
 import altair as alt
 import pandas as pd
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.us_employment()
 presidents = pd.DataFrame([
diff --git a/tests/examples_methods_syntax/us_population_over_time.py b/tests/examples_methods_syntax/us_population_over_time.py
index 28d743e61..5b33157d7 100644
--- a/tests/examples_methods_syntax/us_population_over_time.py
+++ b/tests/examples_methods_syntax/us_population_over_time.py
@@ -7,7 +7,7 @@
 """
 # category: case studies
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.population.url
 
diff --git a/tests/examples_methods_syntax/us_population_over_time_facet.py b/tests/examples_methods_syntax/us_population_over_time_facet.py
index 6444e0d80..2ce3b9de0 100644
--- a/tests/examples_methods_syntax/us_population_over_time_facet.py
+++ b/tests/examples_methods_syntax/us_population_over_time_facet.py
@@ -6,7 +6,7 @@
 """
 # category: case studies
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.population.url
 
diff --git a/tests/examples_methods_syntax/us_population_pyramid_over_time.py b/tests/examples_methods_syntax/us_population_pyramid_over_time.py
index 334a77c6e..56da4691c 100644
--- a/tests/examples_methods_syntax/us_population_pyramid_over_time.py
+++ b/tests/examples_methods_syntax/us_population_pyramid_over_time.py
@@ -7,7 +7,7 @@
 '''
 # category: case studies
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 source = data.population.url
 
diff --git a/tests/examples_methods_syntax/us_state_capitals.py b/tests/examples_methods_syntax/us_state_capitals.py
index 76c6bdfb3..ad7520b18 100644
--- a/tests/examples_methods_syntax/us_state_capitals.py
+++ b/tests/examples_methods_syntax/us_state_capitals.py
@@ -6,7 +6,7 @@
 """
 # category: case studies
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 states = alt.topo_feature(data.us_10m.url, 'states')
 capitals = data.us_state_capitals.url
diff --git a/tests/examples_methods_syntax/violin_plot.py b/tests/examples_methods_syntax/violin_plot.py
index d09274d1e..c72cf1e59 100644
--- a/tests/examples_methods_syntax/violin_plot.py
+++ b/tests/examples_methods_syntax/violin_plot.py
@@ -5,7 +5,7 @@
 """
 # category: distributions
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 alt.Chart(data.cars(), width=100).transform_density(
     'Miles_per_Gallon',
diff --git a/tests/examples_methods_syntax/wheat_wages.py b/tests/examples_methods_syntax/wheat_wages.py
index aaa987eb5..526891ea1 100644
--- a/tests/examples_methods_syntax/wheat_wages.py
+++ b/tests/examples_methods_syntax/wheat_wages.py
@@ -9,7 +9,7 @@
 # category: case studies
 import altair as alt
 import pandas as pd
-from vega_datasets import data
+from altair.datasets import data
 
 
 base_wheat = alt.Chart(data.wheat.url).transform_calculate(year_end="+datum.year + 5")
diff --git a/tests/examples_methods_syntax/wind_vector_map.py b/tests/examples_methods_syntax/wind_vector_map.py
index 89244fc2c..039fcf7cd 100644
--- a/tests/examples_methods_syntax/wind_vector_map.py
+++ b/tests/examples_methods_syntax/wind_vector_map.py
@@ -9,7 +9,7 @@
 """
 # category: maps
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 df_wind = data.windvectors()
 data_world = alt.topo_feature(data.world_110m.url, "countries")
diff --git a/tests/test_datasets.py b/tests/test_datasets.py
index 1eef30884..e2a21991e 100644
--- a/tests/test_datasets.py
+++ b/tests/test_datasets.py
@@ -755,7 +755,7 @@ def test_list_datasets(self) -> None:
         assert isinstance(datasets, list)
         assert len(datasets) > 0
         # Check that common datasets are present
-        common_datasets = ["cars", "movies", "stocks", "iris"]
+        common_datasets = ["cars", "movies", "stocks", "penguins"]
         for dataset in common_datasets:
             if dataset in datasets:
                 break
diff --git a/tests/test_jupyter_chart.py b/tests/test_jupyter_chart.py
index be26386bb..7ce7b60f8 100644
--- a/tests/test_jupyter_chart.py
+++ b/tests/test_jupyter_chart.py
@@ -5,7 +5,7 @@
 from packaging.version import Version
 
 import altair as alt
-from vega_datasets import data
+from altair.datasets import data
 
 # If anywidget is not installed, we will skip the tests in this file.
 try:
diff --git a/tests/test_transformed_data.py b/tests/test_transformed_data.py
index 70ed6655e..fe41d79a4 100644
--- a/tests/test_transformed_data.py
+++ b/tests/test_transformed_data.py
@@ -8,6 +8,7 @@
 from packaging.version import Version
 
 import altair as alt
+from altair.datasets import data
 from altair.utils.execeval import eval_block
 from tests import (
     examples_methods_syntax,
@@ -15,7 +16,6 @@
     skip_requires_vegafusion,
     slow,
 )
-from vega_datasets import data
 
 XDIST_ENABLED: bool = "xdist" in sys.modules
 """Use as an `xfail` condition, if running in parallel may cause the test to fail."""
@@ -45,8 +45,8 @@
     ("gapminder_bubble_plot.py", 187, ["income", "population"]),
     ("grouped_bar_chart2.py", 9, ["Group", "Value_start"]),
     ("hexbins.py", 84, ["xFeaturePos", "mean_temp_max"]),
-    pytest.param("histogram_heatmap.py", 378, ["bin_maxbins_40_Rotten_Tomatoes_Rating", "__count"], marks=slow),
-    ("histogram_scatterplot.py", 64, ["bin_maxbins_10_Rotten_Tomatoes_Rating", "__count"]),
+    pytest.param("histogram_heatmap.py", 378, ["bin_maxbins_40_Rotten Tomatoes Rating", "__count"], marks=slow),
+    ("histogram_scatterplot.py", 64, ["bin_maxbins_10_Rotten Tomatoes Rating", "__count"]),
     pytest.param("interactive_legend.py", 1708, ["sum_count_start", "series"], marks=slow),
     ("iowa_electricity.py", 51, ["net_generation_start", "year"]),
     ("isotype.py", 37, ["animal", "x"]),
@@ -59,18 +59,18 @@
     ("line_custom_order.py", 55, ["miles", "gas"]),
     pytest.param("line_percent.py", 30, ["sex", "perc"], marks=slow),
     ("line_with_log_scale.py", 15, ["year", "sum_people"]),
-    ("multifeature_scatter_plot.py", 150, ["petalWidth", "species"]),
+    ("multifeature_scatter_plot.py", 342, ["Beak Depth (mm)", "Species"]),
     pytest.param("natural_disasters.py", 686, ["Deaths", "Year"], marks=xfail_vegafusion_2),
     ("normalized_stacked_area_chart.py", 51, ["source", "net_generation_start"]),
     ("normalized_stacked_bar_chart.py", 60, ["site", "sum_yield_start"]),
-    ("parallel_coordinates.py", 600, ["key", "value"]),
+    ("parallel_coordinates.py", 1032, ["key", "value"]),
     ("percentage_of_total.py", 5, ["PercentOfTotal", "TotalTime"]),
     ("pie_chart.py", 6, ["category", "value_start"]),
     ("pyramid.py", 3, ["category", "value_start"]),
     ("stacked_bar_chart_sorted_segments.py", 60, ["variety", "site"]),
     ("stem_and_leaf.py", 100, ["stem", "leaf"]),
     pytest.param("streamgraph.py", 1708, ["series", "sum_count"], marks=slow),
-    ("top_k_items.py", 10, ["rank", "IMDB_Rating_start"]),
+    ("top_k_items.py", 10, ["rank", "IMDB Rating_start"]),
     ("top_k_letters.py", 9, ["rank", "letters"]),
     pytest.param("top_k_with_others.py", 10, ["ranked_director", "mean_aggregate_gross"], marks=slow),
     ("area_faceted.py", 492, ["date", "price"]),
@@ -103,13 +103,13 @@ def test_primitive_chart_examples(filename, rows, cols, to_reconstruct):
 @pytest.mark.parametrize(("filename", "all_rows", "all_cols"), [
     ("errorbars_with_std.py", [10, 10], [["upper_yield"], ["extent_yield"]]),
     ("candlestick_chart.py", [44, 44], [["low"], ["close"]]),
-    ("co2_concentration.py", [713, 7, 7], [["first_date"], ["scaled_date"], ["end"]]),
+    ("co2_concentration.py", [741, 8, 8], [["first_date"], ["scaled_date"], ["end"]]),
     pytest.param("falkensee.py", [2, 38, 38], [["event"], ["population"], ["population"]], marks=xfail_vegafusion_2),
     ("heat_lane.py", [10, 10], [["bin_count_start"], ["y2"]]),
-    ("histogram_responsive.py", [20, 20], [["__count"], ["__count"]]),
-    ("histogram_with_a_global_mean_overlay.py", [9, 1], [["__count"], ["mean_IMDB_Rating"]]),
+    ("histogram_responsive.py", [23, 23], [["__count"], ["__count"]]),
+    ("histogram_with_a_global_mean_overlay.py", [9, 1], [["__count"], ["mean_IMDB Rating"]]),
     ("horizon_graph.py", [20, 20], [["x"], ["ny"]]),
-    pytest.param("interactive_cross_highlight.py", [64, 64, 13], [["__count"], ["__count"], ["Major_Genre"]], marks=slow),
+    pytest.param("interactive_cross_highlight.py", [64, 64, 13], [["__count"], ["__count"], ["Major Genre"]], marks=slow),
     ("interval_selection.py", [123, 123], [["price_start"], ["date"]]),
     ("layered_chart_with_dual_axis.py", [12, 12], [["month_date"], ["average_precipitation"]]),
     ("layered_heatmap_text.py", [9, 9], [["Cylinders"], ["mean_horsepower"]]),
@@ -118,7 +118,7 @@ def test_primitive_chart_examples(filename, rows, cols, to_reconstruct):
     ("pie_chart_with_labels.py", [6, 6], [["category"], ["value"]]),
     ("radial_chart.py", [6, 6], [["values"], ["values_start"]]),
     ("scatter_linked_table.py", [392, 14, 14, 14], [["Year"], ["Year"], ["Year"], ["Year"]]),
-    ("scatter_marginal_hist.py", [34, 150, 27], [["__count"], ["species"], ["__count"]]),
+    ("scatter_marginal_hist.py", [24, 342, 33], [["__count"], ["Species"], ["__count"]]),
     pytest.param(
         "scatter_with_layered_histogram.py",
         [2, 19],
diff --git a/tests/utils/test_schemapi.py b/tests/utils/test_schemapi.py
index d9e3f3b21..a634fd8d2 100644
--- a/tests/utils/test_schemapi.py
+++ b/tests/utils/test_schemapi.py
@@ -23,6 +23,7 @@
 
 import altair as alt
 from altair import load_schema
+from altair.datasets import data
 from altair.utils.schemapi import (
     _DEFAULT_JSON_SCHEMA_DRAFT_URL,
     SchemaBase,
@@ -33,7 +34,6 @@
 )
 from altair.vegalite.v6.schema.channels import X
 from altair.vegalite.v6.schema.core import FieldOneOfPredicate, Legend
-from vega_datasets import data
 
 if TYPE_CHECKING:
     from collections.abc import Callable, Iterable, Sequence
diff --git a/tests/vegalite/v6/test_api.py b/tests/vegalite/v6/test_api.py
index bf7997afd..3a7ab24bb 100644
--- a/tests/vegalite/v6/test_api.py
+++ b/tests/vegalite/v6/test_api.py
@@ -763,16 +763,16 @@ def test_when_condition_parity(
 def test_when_then_interactive() -> None:
     """Copy-related regression found in https://github.com/vega/altair/pull/3394#issuecomment-2302995453."""
     source = "https://cdn.jsdelivr.net/npm/vega-datasets@v3.2.1/data/movies.json"
-    predicate = (alt.datum.IMDB_Rating == None) | (  # noqa: E711
-        alt.datum.Rotten_Tomatoes_Rating == None  # noqa: E711
+    predicate = (alt.datum["IMDB Rating"] == None) | (  # noqa: E711
+        alt.datum["Rotten Tomatoes Rating"] == None  # noqa: E711
     )
 
     chart = (
         alt.Chart(source)
         .mark_point(invalid=None)
         .encode(
-            x="IMDB_Rating:Q",
-            y="Rotten_Tomatoes_Rating:Q",
+            x="IMDB Rating:Q",
+            y="Rotten Tomatoes Rating:Q",
             color=alt.when(predicate).then(alt.value("grey")),
         )
     )
diff --git a/tests/vegalite/v6/test_params.py b/tests/vegalite/v6/test_params.py
index fa5320ad3..0d234aa54 100644
--- a/tests/vegalite/v6/test_params.py
+++ b/tests/vegalite/v6/test_params.py
@@ -204,7 +204,7 @@ def test_selection_interval_value_typing() -> None:
 
 def test_creation_views_params_layered_repeat_chart():
     import altair as alt
-    from vega_datasets import data
+    from altair.datasets import data
 
     source = alt.UrlData(data.flights_2k.url, format={"parse": {"date": "date"}})
 
diff --git a/tools/codemod.py b/tools/codemod.py
index 0754a64c8..b278dda66 100644
--- a/tools/codemod.py
+++ b/tools/codemod.py
@@ -433,5 +433,7 @@ def __call__(self, *code: _Code) -> str:
         return self.format(self.check(code, decode=False))
 
 
-ruff_inline_docs = Ruff(ignore="E711", skip_magic_trailing_comma=True)
+ruff_inline_docs = Ruff(
+    ignore=("E711", "F821", "E402", "B018"), skip_magic_trailing_comma=True
+)
 ruff = Ruff()
diff --git a/uv.lock b/uv.lock
index 605c830a6..6e3f21450 100644
--- a/uv.lock
+++ b/uv.lock
@@ -65,7 +65,6 @@ all = [
     { name = "numpy", version = "2.3.1", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.11'" },
     { name = "pandas" },
     { name = "pyarrow" },
-    { name = "vega-datasets" },
     { name = "vegafusion" },
     { name = "vl-convert-python" },
 ]
@@ -168,7 +167,6 @@ requires-dist = [
     { name = "types-jsonschema", marker = "extra == 'dev'" },
     { name = "types-setuptools", marker = "extra == 'dev'" },
     { name = "typing-extensions", marker = "python_full_version < '3.15'", specifier = ">=4.10.0" },
-    { name = "vega-datasets", marker = "extra == 'all'", specifier = ">=0.9.0" },
     { name = "vegafusion", marker = "extra == 'all'", specifier = ">=2.0.3" },
     { name = "vl-convert-python", marker = "extra == 'all'", specifier = ">=1.8.0" },
     { name = "vl-convert-python", marker = "extra == 'save'", specifier = ">=1.8.0" },
@@ -3612,18 +3610,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/df/fb/e23895a4d5980450d26602b1f4887ce67ccc07f21e943f348bd519c6596f/uv-0.7.20-py3-none-win_arm64.whl", hash = "sha256:693ad1f9ecb87f1ddc735682d6d96fcff41a4aa90ae663c57252c7a8e57d4459", size = 17976062 },
 ]
 
-[[package]]
-name = "vega-datasets"
-version = "0.9.0"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "pandas" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/8f/a0/ce608d9a5b82fce2ebaa2311136b1e1d1dc2807f501bbdfa56bd174fff76/vega_datasets-0.9.0.tar.gz", hash = "sha256:9dbe9834208e8ec32ab44970df315de9102861e4cda13d8e143aab7a80d93fc0", size = 215013 }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/e6/9f/ca52771fe972e0dcc5167fedb609940e01516066938ff2ee28b273ae4f29/vega_datasets-0.9.0-py3-none-any.whl", hash = "sha256:3d7c63917be6ca9b154b565f4779a31fedce57b01b5b9d99d8a34a7608062a1d", size = 210822 },
-]
-
 [[package]]
 name = "vegafusion"
 version = "2.0.3"