bin coordinate name changed

Author: rabernat

xarray/core/groupby.py

@@ -189,7 +189,8 @@ def __init__(self, obj, group, squeeze=False, grouper=None, bins=None,
             raise TypeError("Can't specify both `grouper` and `bins`.")
         if bins is not None:
             group = DataArray(pd.cut(group.values, bins, **cut_kwargs),
-                                group.coords, name=group.name)
+                                group.coords, name=group.name + '_bins')
+            # RPA: we want to restore the original coordinates at some point!
         if grouper is not None:
             index = safe_cast_to_index(group)
             if not index.is_monotonic:
@@ -209,7 +210,6 @@ def __init__(self, obj, group, squeeze=False, grouper=None, bins=None,
             # assume that group already has sorted, unique values
             # (if using bins, the group will have the same name as a dimension
             # but different values)
-            print('assume that group already has sorted, unique values')
             if group.dims != (group.name,):
                 raise ValueError('`group` is required to be a coordinate if '
                                  '`group.name` is a dimension in `obj`')
@@ -429,7 +429,8 @@ def lookup_order(dimension):
 
     def _restore_multiindex(self, combined):
         if self._stacked_dim is not None and self._stacked_dim in combined.dims:
-            combined[self._stacked_dim] = self.group[self._stacked_dim]
+            stacked_dim = self.group[self._stacked_dim]
+            combined[self._stacked_dim] = stacked_dim
         return combined
 
     def apply(self, func, shortcut=False, **kwargs):

xarray/test/test_dataarray.py

@@ -1335,7 +1335,8 @@ def test_groupby_bins(self):
         # http://pandas.pydata.org/pandas-docs/stable/generated/pandas.cut.html
         bins = [0,1.5,5]
         bin_coords = ['(0, 1.5]', '(1.5, 5]']
-        expected = DataArray([1,5], dims='dim_0', coords={'dim_0': bin_coords})
+        expected = DataArray([1,5], dims='dim_0_bins',
+                        coords={'dim_0_bins': bin_coords})
         # the problem with this is that it overwrites the dimensions of array!
         #actual = array.groupby('dim_0', bins=bins).sum()
         actual = array.groupby_bins('dim_0', bins).apply(
@@ -1349,13 +1350,15 @@ def test_groupby_bins_multidim(self):
         array = self.make_groupby_multidim_example_array()
         bins = [0,15,20]
         bin_coords = ['(0, 15]', '(15, 20]']
-        expected = DataArray([16, 40], dims='lat', coords={'lat': bin_coords})
+        expected = DataArray([16, 40], dims='lat_bins',
+                                coords={'lat_bins': bin_coords})
         actual = array.groupby_bins('lat', bins).apply(
                                     lambda x : x.sum(), shortcut=False)
         self.assertDataArrayIdentical(expected, actual)
         # modify the array coordinates to be non-monotonic after unstacking
         array['lat'].data = np.array([[10., 20.], [20., 10.]])
-        expected = DataArray([28, 28], dims='lat', coords={'lat': bin_coords})
+        expected = DataArray([28, 28], dims='lat_bins',
+                    coords={'lat_bins': bin_coords})
         actual = array.groupby_bins('lat', bins).apply(
                                     lambda x : x.sum(), shortcut=False)
         self.assertDataArrayIdentical(expected, actual)