Avoid loading entire dataset by getting the nbytes in an array

doc/whats-new.rst

@@ -35,6 +35,9 @@ Deprecations
 Bug fixes
 ~~~~~~~~~
 
+- Accessing the property ``.nbytes`` of a DataArray, or Variable no longer
+  accidentally triggers loading the variable into memory.
+
 
 Documentation
 ~~~~~~~~~~~~~

xarray/core/variable.py

@@ -403,8 +403,8 @@ def nbytes(self) -> int:
         If the underlying data array does not include ``nbytes``, estimates
         the bytes consumed based on the ``size`` and ``dtype``.
         """
-        if hasattr(self.data, "nbytes"):
-            return self.data.nbytes
+        if hasattr(self._data, "nbytes"):
+            return self._data.nbytes
         else:
             return self.size * self.dtype.itemsize
 

xarray/tests/test_dataarray.py

@@ -3259,6 +3259,21 @@ def test_from_series_sparse(self) -> None:
         actual_sparse.data = actual_sparse.data.todense()
         assert_identical(actual_sparse, actual_dense)
 
+    @requires_sparse
+    def test_sparse_nbytes(self) -> None:
+        # https://github.com/pydata/xarray/issues/4842#issue-793245791
+        df = pd.DataFrame()
+        df["x"] = np.repeat(np.arange(10), 10)
+        df["y"] = np.repeat(np.arange(10), 10)
+        df["time"] = np.tile(pd.date_range("2000-01-01", "2000-03-10", freq="W"), 10)
+        df["rate"] = 10.0
+        df = df.set_index(["time", "y", "x"])
+
+        sparse_ds = xr.Dataset.from_dataframe(df, sparse=True)
+        rate = sparse_ds["rate"]
+        assert rate.nbytes < 8000
+        assert rate.size * rate.dtype.itemsize == 8000
+
     @requires_sparse
     def test_from_multiindex_series_sparse(self) -> None:
         # regression test for GH4019