Map over only data nodes, ignoring attrs (#263)

* add test from issue

* test as a property of map_over_subtree directly

* change behaviour

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* correct test

* whatsnew

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

Author: TomNicholas

datatree/mapping.py

@@ -109,8 +109,8 @@ def map_over_subtree(func: Callable) -> Callable:
 
     Applies a function to every dataset in one or more subtrees, returning new trees which store the results.
 
-    The function will be applied to any non-empty dataset stored in any of the nodes in the trees. The returned trees
-    will have the same structure as the supplied trees.
+    The function will be applied to any data-containing dataset stored in any of the nodes in the trees. The returned
+    trees will have the same structure as the supplied trees.
 
     `func` needs to return one Datasets, DataArrays, or None in order to be able to rebuild the subtrees after
     mapping, as each result will be assigned to its respective node of a new tree via `DataTree.__setitem__`. Any
@@ -206,7 +206,7 @@ def _map_over_subtree(*args, **kwargs) -> DataTree | Tuple[DataTree, ...]:
             # Now we can call func on the data in this particular set of corresponding nodes
             results = (
                 func(*node_args_as_datasets, **node_kwargs_as_datasets)
-                if not node_of_first_tree.is_empty
+                if node_of_first_tree.has_data
                 else None
             )
 

datatree/tests/test_datatree.py

@@ -603,6 +603,13 @@ def test_ipython_key_completions(self, create_test_datatree):
         var_keys = list(dt.variables.keys())
         assert all(var_key in key_completions for var_key in var_keys)
 
+    def test_operation_with_attrs_but_no_data(self):
+        # tests bug from xarray-datatree GH262
+        xs = xr.Dataset({"testvar": xr.DataArray(np.ones((2, 3)))})
+        dt = DataTree.from_dict({"node1": xs, "node2": xs})
+        dt.attrs["test_key"] = 1  # sel works fine without this line
+        dt.sel(dim_0=0)
+
 
 class TestRestructuring:
     def test_drop_nodes(self):

datatree/tests/test_mapping.py

@@ -252,6 +252,18 @@ def times_ten(ds):
         result_tree = times_ten(subtree)
         assert_equal(result_tree, expected, from_root=False)
 
+    def test_skip_empty_nodes_with_attrs(self, create_test_datatree):
+        # inspired by xarray-datatree GH262
+        dt = create_test_datatree()
+        dt["set1/set2"].attrs["foo"] = "bar"
+
+        def check_for_data(ds):
+            # fails if run on a node that has no data
+            assert len(ds.variables) != 0
+            return ds
+
+        dt.map_over_subtree(check_for_data)
+
 
 class TestMutableOperations:
     def test_construct_using_type(self):

docs/source/whats-new.rst

@@ -26,6 +26,9 @@ New Features
 Breaking changes
 ~~~~~~~~~~~~~~~~
 
+- Nodes containing only attributes but no data are now ignored by :py:func:`map_over_subtree` (:issue:`262`, :pull:`263`)
+  By `Tom Nicholas <https://github.com/TomNicholas>`_.
+
 Deprecations
 ~~~~~~~~~~~~