Remove old auto combine (#3926)

* Removed auto_combine function and argument to open_mfdataset * Removed corresponding tests * Code formatting * updated what's new * PEP8 fixes * Update doc/whats-new.rst `:py:func:` links fixed Co-Authored-By: keewis <[email protected]> * removed auto_combine from API docs * clarify that auto_combine is completely removed * concat_dim=None by default for combine='nested' * fix black formatting Co-authored-by: keewis <[email protected]> Co-authored-by: dcherian <[email protected]>
pydata · Jun 24, 2020 · 3088de2 · 3088de2
1 parent 24d755d
commit 3088de2
Show file tree

Hide file tree

Showing 8 changed files with 34 additions and 573 deletions.
diff --git a/doc/api-hidden.rst b/doc/api-hidden.rst
@@ -9,8 +9,6 @@
 .. autosummary::
    :toctree: generated/
 
-   auto_combine
-
    Dataset.nbytes
    Dataset.chunks
 

diff --git a/doc/api.rst b/doc/api.rst
@@ -21,7 +21,6 @@ Top-level functions
    broadcast
    concat
    merge
-   auto_combine
    combine_by_coords
    combine_nested
    where

diff --git a/doc/whats-new.rst b/doc/whats-new.rst
@@ -33,6 +33,13 @@ Breaking changes
   <https://matplotlib.org/api/prev_api_changes/api_changes_3.1.0.html#passing-a-line2d-s-drawstyle-together-with-the-linestyle-is-deprecated>`_.
   (:pull:`3274`)
   By `Elliott Sales de Andrade <https://github.com/QuLogic>`_
+- The old :py:func:`auto_combine` function has now been removed in
+  favour of the :py:func:`combine_by_coords` and
+  :py:func:`combine_nested` functions. This also means that
+  the default behaviour of :py:func:`open_mfdataset` has changed to use
+  ``combine='by_coords'`` as the default argument value. (:issue:`2616`, :pull:`3926`)
+  By `Tom Nicholas <https://github.com/TomNicholas>`_.
+
 
 Enhancements
 ~~~~~~~~~~~~

diff --git a/xarray/__init__.py b/xarray/__init__.py
@@ -16,7 +16,7 @@
 from .coding.frequencies import infer_freq
 from .conventions import SerializationWarning, decode_cf
 from .core.alignment import align, broadcast
-from .core.combine import auto_combine, combine_by_coords, combine_nested
+from .core.combine import combine_by_coords, combine_nested
 from .core.common import ALL_DIMS, full_like, ones_like, zeros_like
 from .core.computation import apply_ufunc, corr, cov, dot, polyval, where
 from .core.concat import concat
@@ -47,7 +47,6 @@
     "align",
     "apply_ufunc",
     "as_variable",
-    "auto_combine",
     "broadcast",
     "cftime_range",
     "combine_by_coords",

diff --git a/xarray/backends/api.py b/xarray/backends/api.py
@@ -4,7 +4,6 @@
 from io import BytesIO
 from numbers import Number
 from pathlib import Path
-from textwrap import dedent
 from typing import (
     TYPE_CHECKING,
     Callable,
@@ -23,7 +22,6 @@
 from ..core.combine import (
     _infer_concat_order_from_positions,
     _nested_combine,
-    auto_combine,
     combine_by_coords,
 )
 from ..core.dataarray import DataArray
@@ -726,14 +724,14 @@ def close(self):
 def open_mfdataset(
     paths,
     chunks=None,
-    concat_dim="_not_supplied",
+    concat_dim=None,
     compat="no_conflicts",
     preprocess=None,
     engine=None,
     lock=None,
     data_vars="all",
     coords="different",
-    combine="_old_auto",
+    combine="by_coords",
     autoclose=None,
     parallel=False,
     join="outer",
@@ -746,9 +744,8 @@ def open_mfdataset(
     the datasets into one before returning the result, and if combine='nested' then
     ``combine_nested`` is used. The filepaths must be structured according to which
     combining function is used, the details of which are given in the documentation for
-    ``combine_by_coords`` and ``combine_nested``. By default the old (now deprecated)
-    ``auto_combine`` will be used, please specify either ``combine='by_coords'`` or
-    ``combine='nested'`` in future. Requires dask to be installed. See documentation for
+    ``combine_by_coords`` and ``combine_nested``. By default ``combine='by_coords'``
+    will be used. Requires dask to be installed. See documentation for
     details on dask [1]_. Global attributes from the ``attrs_file`` are used
     for the combined dataset.
 
@@ -758,7 +755,7 @@ def open_mfdataset(
         Either a string glob in the form ``"path/to/my/files/*.nc"`` or an explicit list of
         files to open. Paths can be given as strings or as pathlib Paths. If
         concatenation along more than one dimension is desired, then ``paths`` must be a
-        nested list-of-lists (see ``manual_combine`` for details). (A string glob will
+        nested list-of-lists (see ``combine_nested`` for details). (A string glob will
         be expanded to a 1-dimensional list.)
     chunks : int or dict, optional
         Dictionary with keys given by dimension names and values given by chunk sizes.
@@ -768,15 +765,16 @@ def open_mfdataset(
         see the full documentation for more details [2]_.
     concat_dim : str, or list of str, DataArray, Index or None, optional
         Dimensions to concatenate files along.  You only need to provide this argument
-        if any of the dimensions along which you want to concatenate is not a dimension
-        in the original datasets, e.g., if you want to stack a collection of 2D arrays
-        along a third dimension. Set ``concat_dim=[..., None, ...]`` explicitly to
-        disable concatenation along a particular dimension.
+        if ``combine='by_coords'``, and if any of the dimensions along which you want to
+        concatenate is not a dimension in the original datasets, e.g., if you want to
+        stack a collection of 2D arrays along a third dimension. Set
+        ``concat_dim=[..., None, ...]`` explicitly to disable concatenation along a
+        particular dimension. Default is None, which for a 1D list of filepaths is
+        equivalent to opening the files separately and then merging them with
+        ``xarray.merge``.
     combine : {'by_coords', 'nested'}, optional
         Whether ``xarray.combine_by_coords`` or ``xarray.combine_nested`` is used to
-        combine all the data. If this argument is not provided, `xarray.auto_combine` is
-        used, but in the future this behavior will switch to use
-        `xarray.combine_by_coords` by default.
+        combine all the data. Default is to use ``xarray.combine_by_coords``.
     compat : {'identical', 'equals', 'broadcast_equals',
               'no_conflicts', 'override'}, optional
         String indicating how to compare variables of the same name for
@@ -869,7 +867,6 @@ def open_mfdataset(
     --------
     combine_by_coords
     combine_nested
-    auto_combine
     open_dataset
 
     References
@@ -897,11 +894,8 @@ def open_mfdataset(
     # If combine='nested' then this creates a flat list which is easier to
     # iterate over, while saving the originally-supplied structure as "ids"
     if combine == "nested":
-        if str(concat_dim) == "_not_supplied":
-            raise ValueError("Must supply concat_dim when using " "combine='nested'")
-        else:
-            if isinstance(concat_dim, (str, DataArray)) or concat_dim is None:
-                concat_dim = [concat_dim]
+        if isinstance(concat_dim, (str, DataArray)) or concat_dim is None:
+            concat_dim = [concat_dim]
     combined_ids_paths = _infer_concat_order_from_positions(paths)
     ids, paths = (list(combined_ids_paths.keys()), list(combined_ids_paths.values()))
 
@@ -933,30 +927,7 @@ def open_mfdataset(
 
     # Combine all datasets, closing them in case of a ValueError
     try:
-        if combine == "_old_auto":
-            # Use the old auto_combine for now
-            # Remove this after deprecation cycle from #2616 is complete
-            basic_msg = dedent(
-                """\
-            In xarray version 0.15 the default behaviour of `open_mfdataset`
-            will change. To retain the existing behavior, pass
-            combine='nested'. To use future default behavior, pass
-            combine='by_coords'. See
-            http://xarray.pydata.org/en/stable/combining.html#combining-multi
-            """
-            )
-            warnings.warn(basic_msg, FutureWarning, stacklevel=2)
-
-            combined = auto_combine(
-                datasets,
-                concat_dim=concat_dim,
-                compat=compat,
-                data_vars=data_vars,
-                coords=coords,
-                join=join,
-                from_openmfds=True,
-            )
-        elif combine == "nested":
+        if combine == "nested":
             # Combined nested list by successive concat and merge operations
             # along each dimension, using structure given by "ids"
             combined = _nested_combine(