DataItem -> Dataset

Author: martinfleis

doc/source/api.rst

@@ -27,7 +27,7 @@ Database-level API
 
 The database of dataset metadata is handled via custom dict-based classes.
 
-.. class:: DataItem
+.. class:: Dataset
 
    A dict with attribute-access and that can be called to update keys.
 

doc/source/contributing.md

@@ -11,7 +11,7 @@ contributions to the codebase and documentation.
 If you want to add a new dataset, simply add its details to
 `geodatasets/json/database.json`.
 
-You can add a single `DataItem` or a `Bunch` of `DataItem`s. Use the following
+You can add a single `Dataset` or a `Bunch` of `Dataset`s. Use the following
 schema to add a single dataset:
 
 ```json

doc/source/index.md

@@ -7,6 +7,7 @@ maxdepth: 2
 caption: Documentation
 hidden: true
 ---
+introduction
 api
 contributing
 GitHub <https://github.com/geopandas/geodatasets>

geodatasets/__init__.py

@@ -1,6 +1,6 @@
 from .api import get_path, get_url, fetch  # noqa
 from .data import data  # noqa
-from .lib import Bunch, DataItem  # noqa
+from .lib import Bunch, Dataset  # noqa
 
 from importlib.metadata import PackageNotFoundError, version
 

geodatasets/lib.py

@@ -15,7 +15,7 @@
 class Bunch(dict):
     """A dict with attribute-access
 
-    :class:`Bunch` is used to store :class:`DataItem` objects.
+    :class:`Bunch` is used to store :class:`Dataset` objects.
     """
 
     def __getattr__(self, key):
@@ -31,8 +31,8 @@ def _repr_html_(self, inside=False):
 
         children = ""
         for key in self.keys():
-            if isinstance(self[key], DataItem):
-                obj = "geodatasets.DataItem"
+            if isinstance(self[key], Dataset):
+                obj = "geodatasets.Dataset"
             else:
                 obj = "geodatasets.Bunch"
             uid = str(uuid.uuid4())
@@ -69,19 +69,19 @@ def _repr_html_(self, inside=False):
     def flatten(self) -> dict:
         """Return the nested :class:`Bunch` collapsed into the one level dictionary.
 
-        Dictionary keys are :class:`DataItem` names (e.g. ``geoda.airbnb``)
-        and its values are :class:`DataItem` objects.
+        Dictionary keys are :class:`Dataset` names (e.g. ``geoda.airbnb``)
+        and its values are :class:`Dataset` objects.
 
         Returns
         -------
         flattened : dict
-            dictionary of :class:`DataItem` objects
+            dictionary of :class:`Dataset` objects
         """
 
         flat = {}
 
         def _get_items(item):
-            if isinstance(item, DataItem):
+            if isinstance(item, Dataset):
                 flat[item.name] = item
             else:
                 for prov in item.values():
@@ -91,10 +91,10 @@ def _get_items(item):
 
         return flat
 
-    def query_name(self, name: str) -> DataItem:
-        """Return :class:`DataItem` based on the name query
+    def query_name(self, name: str) -> Dataset:
+        """Return :class:`Dataset` based on the name query
 
-        Returns a matching :class:`DataItem` from the :class:`Bunch` if the ``name``
+        Returns a matching :class:`Dataset` from the :class:`Bunch` if the ``name``
         contains the same letters in the same order as the item's name irrespective
         of the letter case, spaces, dashes and other characters.
         See examples for details.
@@ -106,7 +106,7 @@ def query_name(self, name: str) -> DataItem:
 
         Returns
         -------
-        match: DataItem
+        match: Dataset
         """
         xyz_flat_lower = {
             k.translate(QUERY_NAME_TRANSLATION).lower(): v
@@ -119,7 +119,7 @@ def query_name(self, name: str) -> DataItem:
         raise ValueError(f"No matching item found for the query '{name}'.")
 
 
-class DataItem(Bunch):
+class Dataset(Bunch):
     """
     A dict with attribute-access and that
     can be called to update keys
@@ -136,18 +136,18 @@ def __init__(self, *args, **kwargs):
             msg = (
                 f"The attributes {required} "
                 f"are required to initialise "
-                f"a `DataItem`. Please provide values for: "
+                f"a `Dataset`. Please provide values for: "
                 f'`{"`, `".join(missing)}`'
             )
             raise AttributeError(msg)
 
-    def __call__(self, **kwargs) -> DataItem:
-        new = DataItem(self)  # takes a copy preserving the class
+    def __call__(self, **kwargs) -> Dataset:
+        new = Dataset(self)  # takes a copy preserving the class
         new.update(kwargs)
         return new
 
-    def copy(self, **kwargs) -> DataItem:
-        new = DataItem(self)  # takes a copy preserving the class
+    def copy(self, **kwargs) -> Dataset:
+        new = Dataset(self)  # takes a copy preserving the class
         return new
 
     def _repr_html_(self, inside=False):
@@ -162,7 +162,7 @@ def _repr_html_(self, inside=False):
         {style}
             <div class="xyz-wrap">
                 <div class="xyz-header">
-                    <div class="xyz-obj">geodatasets.DataItem</div>
+                    <div class="xyz-obj">geodatasets.Dataset</div>
                     <div class="xyz-name">{self.name}</div>
                 </div>
                 <div class="xyz-details">
@@ -187,9 +187,9 @@ def _load_json(f):
         item = data[item_name]
 
         if "url" in item.keys():
-            items[item_name] = DataItem(item)
+            items[item_name] = Dataset(item)
         else:
-            items[item_name] = Bunch({i: DataItem(item[i]) for i in item})
+            items[item_name] = Bunch({i: Dataset(item[i]) for i in item})
 
     return items
 

geodatasets/tests/test_lib.py

@@ -1,11 +1,11 @@
 import pytest
 
-from geodatasets import Bunch, DataItem, data
+from geodatasets import Bunch, Dataset, data
 
 
 @pytest.fixture
 def data1():
-    return DataItem(
+    return Dataset(
         url="https://myserver.com/data.zip",
         attribution="(C) geodatasets",
         name="my_public_data",
@@ -16,7 +16,7 @@ def data1():
 
 @pytest.fixture
 def data2():
-    return DataItem(
+    return Dataset(
         url="https://myserver.com/?dghrtnkmjnkju",
         attribution="(C) geodatasets",
         name="my_public_data2",
@@ -43,18 +43,18 @@ def test_dir(data1):
 def test_expect_name_url_attribution():
 
     with pytest.raises(AttributeError, match="`name`, `url`, `hash`, `filename`"):
-        DataItem({})
+        Dataset({})
     with pytest.raises(AttributeError, match="`url`, `hash`, `filename`"):
-        DataItem({"name": "myname"})
+        Dataset({"name": "myname"})
     with pytest.raises(AttributeError, match="`hash`, `filename`"):
-        DataItem({"url": "my_url", "name": "my_name"})
+        Dataset({"url": "my_url", "name": "my_name"})
 
 
 def test_html_repr(data1, data2):
     item_strings = [
         '<div class="xyz-wrap">',
         '<div class="xyz-header">',
-        '<div class="xyz-obj">geodatasets.DataItem</div>',
+        '<div class="xyz-obj">geodatasets.Dataset</div>',
         '<div class="xyz-name">my_public_data</div>',
         '<div class="xyz-details">',
         '<dl class="xyz-attrs">',
@@ -77,7 +77,7 @@ def test_html_repr(data1, data2):
         '<div class="xyz-name">2 items</div>',
         '<ul class="xyz-collapsible">',
         '<li class="xyz-child">',
-        "<span>geodatasets.DataItem</span>",
+        "<span>geodatasets.Dataset</span>",
         '<div class="xyz-inside">',
     ]
 
@@ -91,14 +91,14 @@ def test_html_repr(data1, data2):
 
 def test_copy(data1):
     copied = data1.copy()
-    assert isinstance(copied, DataItem)
+    assert isinstance(copied, Dataset)
 
 
 def test_callable():
     # only testing the callable functionality to override a keyword, as we
     # cannot test the actual items that need an API key
     updated_item = data.ny.bb(hash="myhash")
-    assert isinstance(updated_item, DataItem)
+    assert isinstance(updated_item, Dataset)
     assert "url" in updated_item
     assert updated_item["hash"] == "myhash"
     # check that original item dict is not modified
@@ -130,7 +130,7 @@ def test_query_name():
 
     for option in options:
         queried = data.query_name(option)
-        assert isinstance(queried, DataItem)
+        assert isinstance(queried, Dataset)
         assert queried.name == "ny.bb"
 
     with pytest.raises(ValueError, match="No matching item found"):