Optional indexes

Author: shoyer

doc/api.rst

@@ -44,6 +44,7 @@ Attributes
    Dataset.coords
    Dataset.attrs
    Dataset.indexes
+   Dataset.get_index
 
 Dictionary interface
 --------------------
@@ -193,6 +194,7 @@ Attributes
    DataArray.attrs
    DataArray.encoding
    DataArray.indexes
+   DataArray.get_index
 
 **ndarray attributes**:
 :py:attr:`~DataArray.ndim`

doc/whats-new.rst

@@ -21,6 +21,26 @@ v0.9.0 (unreleased)
 Breaking changes
 ~~~~~~~~~~~~~~~~
 
+- Index coordinates for each dimensions are now optional, and no longer created
+  by default. This has a number of implications:
+
+  - :py:func:`~align` and :py:meth:`~Dataset.reindex` can now error, if
+    dimensions labels are missing and dimensions have different sizes.
+  - Because pandas does not support missing indexes, methods such as
+    ``to_dataframe``/``from_dataframe`` and ``stack``/``unstack`` no longer
+    roundtrip faithfully on all inputs. Use :py:meth:`~Dataset.reset_index` to
+    remove undesired indexes.
+  - ``Dataset.__delitem__`` and :py:meth:`~Dataset.drop` no longer delete/drop
+    variables that have dimensions matching a deleted/dropped variable.
+  - ``DataArray.coords.__delitem__`` is now allowed on variables matching
+    dimension names.
+  - ``.sel`` and ``.loc`` now handle indexing along a dimension with a
+    coordinate label by doing integer based indexing.
+  - :py:attr:`~Dataset.indexes` is no longer guaranteed to include all
+    dimensions names as keys. The new method :py:meth:`~Dataset.get_index` has
+    been added to get an index for a dimension guaranteed, falling back to
+    produce a default ``RangeIndex`` if necessary.
+
 - The default behavior of ``merge`` is now ``compat='no_conflicts'``, so some
   merges will now succeed in cases that previously raised
   ``xarray.MergeError``. Set ``compat='broadcast_equals'`` to restore the
@@ -113,6 +133,13 @@ Bug fixes
 - ``Dataset.concat()`` now preserves variables order (:issue:`1027`).
   By `Fabien Maussion <https://github.com/fmaussion>`_.
 
+- Grouping over an dimension with non-unique values with ``groupby`` gives
+  correct groups.
+
+- Fixed accessing coordinate variables with non-string names from ``.coords``
+  (:issue:`TBD`).
+  By `Stephan Hoyer <https://github.com/shoyer>`_.
+
 .. _whats-new.0.8.2:
 
 v0.8.2 (18 August 2016)

xarray/backends/common.py

@@ -30,25 +30,6 @@ def _decode_variable_name(name):
     return name
 
 
-def is_trivial_index(var):
-    """
-    Determines if in index is 'trivial' meaning that it is
-    equivalent to np.arange().  This is determined by
-    checking if there are any attributes or encodings,
-    if ndims is one, dtype is int and finally by comparing
-    the actual values to np.arange()
-    """
-    # if either attributes or encodings are defined
-    # the index is not trivial.
-    if len(var.attrs) or len(var.encoding):
-        return False
-    # if the index is not a 1d integer array
-    if var.ndim > 1 or not var.dtype.kind == 'i':
-        return False
-    arange = np.arange(var.size, dtype=var.dtype)
-    return np.all(var.values == arange)
-
-
 def robust_getitem(array, key, catch=Exception, max_retries=6,
                    initial_delay=500):
     """
@@ -200,12 +181,6 @@ def store_dataset(self, dataset):
 
     def store(self, variables, attributes, check_encoding_set=frozenset()):
         self.set_attributes(attributes)
-        neccesary_dims = [v.dims for v in variables.values()]
-        neccesary_dims = set(itertools.chain(*neccesary_dims))
-        # set all non-indexes and any index which is not trivial.
-        variables = OrderedDict((k, v) for k, v in iteritems(variables)
-                                if not (k in neccesary_dims and
-                                        is_trivial_index(v)))
         self.set_variables(variables, check_encoding_set)
 
     def set_attributes(self, attributes):

xarray/conventions.py

@@ -910,7 +910,7 @@ def decode_cf(obj, concat_characters=True, mask_and_scale=True,
         identify coordinates.
     drop_variables: string or iterable, optional
         A variable or list of variables to exclude from being parsed from the
-        dataset.This may be useful to drop variables with problems or
+        dataset. This may be useful to drop variables with problems or
         inconsistent values.
 
     Returns
@@ -936,7 +936,7 @@ def decode_cf(obj, concat_characters=True, mask_and_scale=True,
         vars, attrs, concat_characters, mask_and_scale, decode_times,
         decode_coords, drop_variables=drop_variables)
     ds = Dataset(vars, attrs=attrs)
-    ds = ds.set_coords(coord_names.union(extra_coords))
+    ds = ds.set_coords(coord_names.union(extra_coords).intersection(vars))
     ds._file_obj = file_obj
     return ds