Merge pull request #809 from CCI-Tools/jg-805-coreg-id-grids

Jg 805 coreg id grids

CHANGES.md

@@ -9,6 +9,8 @@
 * Cate now distinguishes network connection problems from errors of other origin. Introduced new 
   error type `cate.core.ds.NetworkError` that is raised if a connection to e.g. 
   CCI ODP services can not be established. [#789](https://github.com/CCI-Tools/cate/issues/789)
+* In coregistration make sure the replica dataset is simply returned if it is
+  already on master grid. [#805](https://github.com/CCI-Tools/cate/issues/805)
 
 ## Version 2.0.0.dev23
 

cate/ops/coregistration.py

@@ -100,6 +100,10 @@ def coregister(ds_master: xr.Dataset,
                               ' case spatial dimensions have different'
                               ' names'.format(ds_master.dims, ds_replica.dims))
 
+    # Don't do anything if datasets already have the same spatial definition
+    if _grids_equal(ds_master, ds_replica):
+        return ds_replica
+
     # Check if all arrays of the replica dataset have the required dimensionality
     for key in ds_replica.data_vars:
         if not _is_valid_array(ds_replica[key]):
@@ -310,13 +314,36 @@ def _resample_dataset(ds_master: xr.Dataset, ds_replica: xr.Dataset, method_us:
     lat = ds_master['lat'].sel(lat=lat_slice)
     ds_replica = ds_replica.sel(lon=lon_slice, lat=lat_slice)
 
+    # Don't do anything if datasets already have the same spatial definition
+    if _grids_equal(ds_master, ds_replica):
+        return ds_replica
+
     with monitor.starting("coregister dataset", len(ds_replica.data_vars)):
         kwargs = {'lon': lon, 'lat': lat, 'method_us': method_us, 'method_ds': method_ds, 'parent_monitor': monitor}
         retset = ds_replica.apply(_resample_array, keep_attrs=True, **kwargs)
 
     return adjust_spatial_attrs(retset)
 
 
+def _grids_equal(master: xr.Dataset,
+                 replica: xr.Dataset) -> bool:
+    """
+    Check if the spatial grid of the given datasets is (almost) equal
+
+    :param master: Master dataset
+    :param replica: Replica dataset
+    """
+    if len(master.lon) != len(replica.lon) or \
+       len(master.lat) != len(replica.lat):
+        return False
+
+    if not np.allclose(master.lon.values, replica.lon.values) or \
+       not np.allclose(master.lat.values, replica.lat.values):
+        return False
+
+    return True
+
+
 def _find_intersection(first: np.ndarray,
                        second: np.ndarray,
                        global_bounds: Tuple[float, float]) -> Tuple[float, float]:

test/ops/test_coregistration.py

@@ -742,3 +742,31 @@ def test_int_array(self):
             'time': np.array([1, 2])})
 
         assert_almost_equal(ds_fine_resampled['first'].values, expected['first'].values)
+
+    def test_same_grid(self):
+        """
+        Test the case when both datasets already have the same geospatial definition
+        """
+        ds_fine = xr.Dataset({
+            'first': (['time', 'lat', 'lon'], np.array([np.eye(4, 8), np.eye(4, 8)])),
+            'second': (['time', 'lat', 'lon'], np.array([np.eye(4, 8), np.eye(4, 8)])),
+            'lat': np.linspace(-67.5, 67.5, 4),
+            'lon': np.linspace(-157.5, 157.5, 8),
+            'time': np.array([1, 2])}).chunk(chunks={'lat': 2, 'lon': 4})
+
+        rm = RecordingMonitor()
+        ds_same = coregister(ds_fine, ds_fine, monitor=rm)
+        # Make sure it returned the input as opposed to going through with
+        # coregistration
+        self.assertEqual([], rm.records)
+
+        assert_almost_equal(ds_same['first'].values, ds_fine['first'].values)
+
+        # Test that a subset is performed, but no coregistration done
+        lat_slice = slice(-70, 70)
+        lon_slice = slice(-40, 40)
+        ds_subset = ds_fine.sel(lat=lat_slice, lon=lon_slice)
+
+        ds_coreg = coregister(ds_subset, ds_fine, monitor=rm)
+        self.assertEqual([], rm.records)
+        assert_almost_equal(ds_coreg['first'].values, ds_subset['first'].values)