Add a data method to validate data frame variables

tests/core/test_data.py

@@ -1107,3 +1107,54 @@ def test_merge_continuous_file_already_exists(
             ),
         ),
     )
+
+
+@pytest.mark.parametrize(
+    argnames="vars, var_names, exp_result, exp_msg",
+    argvalues=[
+        pytest.param(
+            {"a": DataArray(np.ones(12)), "b": DataArray(np.ones(12))},
+            ["a", "b"],
+            True,
+            "Variables form a data frame",
+            id="correct",
+        ),
+        pytest.param(
+            {"a": DataArray(np.ones(12)), "b": DataArray(np.ones(12))},
+            ["a", "c"],
+            False,
+            "Missing variables: c",
+            id="missing variable",
+        ),
+        pytest.param(
+            {"a": DataArray(np.ones((12, 2))), "b": DataArray(np.ones(12))},
+            ["a", "b"],
+            False,
+            "Variables not one dimensional: a",
+            id="not all one dimensional",
+        ),
+        pytest.param(
+            {
+                "a": DataArray(np.ones(14), dims="dim_1"),
+                "b": DataArray(np.ones(12), dims="dim_2"),
+            },
+            ["a", "b"],
+            False,
+            "Variables of unequal length: 12,14",
+            id="not equal length",
+        ),
+    ],
+)
+def test_Data_confirm_variables_form_data_frame(vars, var_names, exp_result, exp_msg):
+    """Test the data frame validation mechanism."""
+
+    from virtual_ecosystem.core.data import Data
+    from virtual_ecosystem.core.grid import Grid
+
+    data = Data(grid=Grid())
+    data.add_from_dict(vars)
+
+    result, msg = data.confirm_variables_form_data_frame(var_names)
+
+    assert result == exp_result
+    assert msg == exp_msg

virtual_ecosystem/core/data.py

@@ -479,6 +479,37 @@ def output_current_state(
 
         return out_path
 
+    def confirm_variables_form_data_frame(
+        self, var_names: list[str]
+    ) -> tuple[bool, str]:
+        """Check a list of named variables form a data frame.
+
+        This is a utility method to check if a set of named variables are present in the
+        Data object and that together they form a data frame: a set of equal length, one
+        dimensional arrays, providing consistent tuples of values across the variables.
+
+        Args:
+            var_names: A list of the variable names that form a data frame.
+        """
+
+        # All vars present
+        missing_var = [v for v in var_names if v not in self]
+
+        if missing_var:
+            return False, f"Missing variables: {', '.join(missing_var)}"
+
+        # All vars one dimensional
+        data_not_one_d = [var for var in var_names if self[var].ndim > 1]
+        if data_not_one_d:
+            return False, f"Variables not one dimensional: {','.join(data_not_one_d)}"
+
+        # All vars equal sized
+        shapes = sorted(set(str(self[var].shape[0]) for var in var_names))
+        if len(shapes) != 1:
+            return False, f"Variables of unequal length: {','.join(shapes)}"
+
+        return True, "Variables form a data frame"
+
 
 def merge_continuous_data_files(
     data_options: dict[str, Any], continuous_data_files: list[Path]