Groupby-like API for resampling

doc/environment.yml

@@ -8,7 +8,7 @@ dependencies:
   - pandas=0.20.1
   - numpydoc=0.6.0
   - matplotlib=2.0.0
-  - seaborn=0.7.1
+  - seaborn=0.8
   - dask=0.12.0
   - ipython=5.1.0
   - sphinx=1.5

doc/examples/weather-data.rst

@@ -68,7 +68,7 @@ Monthly averaging
 
 .. ipython:: python
 
-    monthly_avg = ds.resample('1MS', dim='time', how='mean')
+    monthly_avg = ds.resample(time='1MS').mean()
 
     @savefig examples_tmin_tmax_plot_mean.png
     monthly_avg.sel(location='IA').to_dataframe().plot(style='s-')

doc/time-series.rst

@@ -15,6 +15,7 @@ core functionality.
     import numpy as np
     import pandas as pd
     import xarray as xr
+
     np.random.seed(123456)
 
 Creating datetime64 data
@@ -95,8 +96,8 @@ given ``DataArray`` can be quickly computed using a special ``.dt`` accessor.
 
 .. ipython:: python
 
-    time = time = pd.date_range('2000-01-01', freq='6H', periods=365 * 4)
-    ds = xr.Dataset({'foo': ('time', np.arange(365 * 24)), 'time': time})
+    time = pd.date_range('2000-01-01', freq='6H', periods=365 * 4)
+    ds = xr.Dataset({'foo': ('time', np.arange(365 * 4)), 'time': time})
     ds.time.dt.hour
     ds.time.dt.dayofweek
 
@@ -128,6 +129,8 @@ the first letters of the corresponding months.
 
 You can use these shortcuts with both Datasets and DataArray coordinates.
 
+.. _resampling:
+
 Resampling and grouped operations
 ---------------------------------
 
@@ -150,17 +153,38 @@ For example, we can downsample our dataset from hourly to 6-hourly:
 
 .. ipython:: python
 
-    ds.resample('6H', dim='time', how='mean')
+    ds.resample(time='6H')
+
+This will create a specialized ``Resample`` object which saves information
+necessary for resampling. All of the reduction methods which work with
+``Resample`` objects can also be used for resampling:
+
+.. ipython:: python
 
-Resample also works for upsampling, in which case intervals without any
-values are marked by ``NaN``:
+   ds.resample(time='6H').mean()
+
+You can also supply an arbitrary reduction function to aggregate over each
+resampling group:
 
 .. ipython:: python
 
-    ds.resample('30Min', 'time')
+   ds.resample(time='6H').reduce(np.mean)
+
+For upsampling, xarray provides four methods: ``asfreq``, ``ffill``, ``bfill``,
+and ``interpolate``. ``interpolate`` extends ``scipy.interpolate.interp1d`` and
+supports all of its schemes. All of these resampling operations work on both
+Dataset and DataArray objects with an arbitrary number of dimensions.
+
+.. note::
+
+   The ``resample`` api was updated in version 0.10.0 to reflect similar
+   updates in pandas ``resample`` api to be more groupby-like. Older style
+   calls to ``resample`` will still be supported for a short period:
+
+   .. ipython:: python
+
+    ds.resample('6H', dim='time', how='mean')
 
-Of course, all of these resampling and groupby operation work on both Dataset
-and DataArray objects with any number of additional dimensions.
 
 For more examples of using grouped operations on a time dimension, see
 :ref:`toy weather data`.

doc/whats-new.rst

@@ -27,11 +27,42 @@ Breaking changes
   (:issue:`727`).
   By `Joe Hamman <https://github.com/jhamman>`_.
 
+- A new resampling interface to match pandas' group-by-like API was added to
+  :py:meth:`~xarray.Dataset.resample` and :py:meth:`~xarray.DataArray.resample`
+  (:issue:`1272`). :ref:`Timeseries resampling <resampling>` is
+  fully supported for data  with arbitrary dimensions as is both downsampling
+  and upsampling (including linear, quadratic, cubic, and spline interpolation).
+
+  Old syntax:
+
+  .. ipython::
+    :verbatim:
+
+    In [1]: ds.resample('24H', dim='time', how='max')
+    Out[1]:
+    <xarray.Dataset>
+    [...]
+
+  New syntax:
+
+  .. ipython::
+    :verbatim:
+
+    In [1]: ds.resample(time='24H').max()
+    Out[1]:
+    <xarray.Dataset>
+    [...]
+
+  Note that both versions are currently supported, but using the old syntax will
+  produce a warning encouraging users to adopt the new syntax. 
+  By `Daniel Rothenberg <https://github.com/darothen>`_.
+
 - ``repr`` and the Jupyter Notebook won't automatically compute dask variables.
   Datasets loaded with ``open_dataset`` won't automatically read coords from
   disk when calling ``repr`` (:issue:`1522`).
   By `Guido Imperiale <https://github.com/crusaderky>`_.
 
+
 Backward Incompatible Changes
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 

xarray/core/common.py

@@ -3,6 +3,7 @@
 from __future__ import print_function
 import numpy as np
 import pandas as pd
+import warnings
 
 from .pycompat import basestring, suppress, dask_array_type, OrderedDict
 from . import dtypes
@@ -506,55 +507,33 @@ def rolling(self, min_periods=None, center=False, **windows):
         return self._rolling_cls(self, min_periods=min_periods,
                                  center=center, **windows)
 
-    def resample(self, freq, dim, how='mean', skipna=None, closed=None,
-                 label=None, base=0, keep_attrs=False):
-        """Resample this object to a new temporal resolution.
+    def resample(self, freq=None, dim=None, how=None, skipna=None,
+                 closed=None, label=None, base=0, keep_attrs=False, **indexer):
+        """Returns a Resample object for performing resampling operations.
 
         Handles both downsampling and upsampling. Upsampling with filling is
-        not yet supported; if any intervals contain no values in the original
+        not supported; if any intervals contain no values from the original
         object, they will be given the value ``NaN``.
 
         Parameters
         ----------
-        freq : str
-            String in the '#offset' to specify the step-size along the
-            resampled dimension, where '#' is an (optional) integer multipler
-            (default 1) and 'offset' is any pandas date offset alias. Examples
-            of valid offsets include:
-
-            * 'AS': year start
-            * 'QS-DEC': quarterly, starting on December 1
-            * 'MS': month start
-            * 'D': day
-            * 'H': hour
-            * 'Min': minute
-
-            The full list of these offset aliases is documented in pandas [1]_.
-        dim : str
-            Name of the dimension to resample along (e.g., 'time').
-        how : str or func, optional
-            Used for downsampling. If a string, ``how`` must be a valid
-            aggregation operation supported by xarray. Otherwise, ``how`` must be
-            a function that can be called like ``how(values, axis)`` to reduce
-            ndarray values along the given axis. Valid choices that can be
-            provided as a string include all the usual Dataset/DataArray
-            aggregations (``all``, ``any``, ``argmax``, ``argmin``, ``max``,
-            ``mean``, ``median``, ``min``, ``prod``, ``sum``, ``std`` and
-            ``var``), as well as ``first`` and ``last``.
         skipna : bool, optional
             Whether to skip missing values when aggregating in downsampling.
         closed : 'left' or 'right', optional
             Side of each interval to treat as closed.
         label : 'left or 'right', optional
             Side of each interval to use for labeling.
-        base : int, optionalt
+        base : int, optional
             For frequencies that evenly subdivide 1 day, the "origin" of the
             aggregated intervals. For example, for '24H' frequency, base could
             range from 0 through 23.
         keep_attrs : bool, optional
             If True, the object's attributes (`attrs`) will be copied from
             the original object to the new one.  If False (default), the new
             object will be returned without attributes.
+        **indexer : {dim: freq}
+            Dictionary with a key indicating the dimension name to resample
+            over and a value corresponding to the resampling frequency.
 
         Returns
         -------
@@ -567,18 +546,67 @@ def resample(self, freq, dim, how='mean', skipna=None, closed=None,
         .. [1] http://pandas.pydata.org/pandas-docs/stable/timeseries.html#offset-aliases
         """
         from .dataarray import DataArray
+        from .resample import RESAMPLE_DIM
+
+        if dim is not None:
+            if how is None:
+                how = 'mean'
+            return self._resample_immediately(freq, dim, how, skipna, closed,
+                                              label, base, keep_attrs)
+
+        if (how is not None) and indexer:
+            raise TypeError("If passing an 'indexer' then 'dim' "
+                            "and 'how' should not be used")
+
+        # More than one indexer is ambiguous, but we do in fact need one if
+        # "dim" was not provided, until the old API is fully deprecated
+        if len(indexer) != 1:
+            raise ValueError(
+                "Resampling only supported along single dimensions."
+            )
+        dim, freq = indexer.popitem()
 
+        if isinstance(dim, basestring):
+            dim_name = dim
+            dim = self[dim]
+        else:
+            raise TypeError("Dimension name should be a string; "
+                            "was passed %r" % dim)
+        group = DataArray(dim, [(dim.dims, dim)], name=RESAMPLE_DIM)
+        time_grouper = pd.TimeGrouper(freq=freq, closed=closed,
+                                      label=label, base=base)
+        resampler = self._resample_cls(self, group=group, dim=dim_name,
+                                       grouper=time_grouper,
+                                       resample_dim=RESAMPLE_DIM)
+
+        return resampler
+
+    def _resample_immediately(self, freq, dim, how, skipna,
+                              closed, label, base, keep_attrs):
+        """Implement the original version of .resample() which immediately
+        executes the desired resampling operation. """
+        from .dataarray import DataArray
         RESAMPLE_DIM = '__resample_dim__'
+
+        warnings.warn("\n.resample() has been modified to defer "
+                      "calculations. Instead of passing 'dim' and "
+                      "'how=\"{how}\", instead consider using "
+                      ".resample({dim}=\"{freq}\").{how}() ".format(
+                            dim=dim, freq=freq, how=how
+                      ), DeprecationWarning, stacklevel=3)
+
         if isinstance(dim, basestring):
             dim = self[dim]
-        group = DataArray(dim, [(RESAMPLE_DIM, dim)], name=RESAMPLE_DIM)
+        group = DataArray(dim, [(dim.dims, dim)], name=RESAMPLE_DIM)
         time_grouper = pd.TimeGrouper(freq=freq, how=how, closed=closed,
                                       label=label, base=base)
         gb = self._groupby_cls(self, group, grouper=time_grouper)
         if isinstance(how, basestring):
             f = getattr(gb, how)
             if how in ['first', 'last']:
                 result = f(skipna=skipna, keep_attrs=keep_attrs)
+            elif how == 'count':
+                result = f(dim=dim.name, keep_attrs=keep_attrs)
             else:
                 result = f(dim=dim.name, skipna=skipna, keep_attrs=keep_attrs)
         else:

xarray/core/dataarray.py

@@ -12,6 +12,7 @@
 from . import duck_array_ops
 from . import indexing
 from . import groupby
+from . import resample
 from . import rolling
 from . import ops
 from . import utils
@@ -34,7 +35,7 @@ def _infer_coords_and_dims(shape, coords, dims):
     """All the logic for creating a new DataArray"""
 
     if (coords is not None and not utils.is_dict_like(coords) and
-            len(coords) != len(shape)):
+        len(coords) != len(shape)):
         raise ValueError('coords is not dict-like, but it has %s items, '
                          'which does not match the %s dimensions of the '
                          'data' % (len(coords), len(shape)))
@@ -115,6 +116,7 @@ class _ThisArray(object):
     """An instance of this object is used as the key corresponding to the
     variable when converting arbitrary DataArray objects to datasets
     """
+
     def __repr__(self):
         return '<this-array>'
 
@@ -159,6 +161,8 @@ class DataArray(AbstractArray, BaseDataObject):
     """
     _groupby_cls = groupby.DataArrayGroupBy
     _rolling_cls = rolling.DataArrayRolling
+    _resample_cls = resample.DataArrayResample
+
     dt = property(DatetimeAccessor)
 
     def __init__(self, data, coords=None, dims=None, name=None,
@@ -1490,8 +1494,10 @@ def from_cdms2(cls, variable):
 
     def _all_compat(self, other, compat_str):
         """Helper function for equals and identical"""
+
         def compat(x, y):
             return getattr(x.variable, compat_str)(y.variable)
+
         return (utils.dict_equiv(self.coords, other.coords, compat=compat) and
                 compat(self, other))
 
@@ -1565,6 +1571,7 @@ def _unary_op(f):
         @functools.wraps(f)
         def func(self, *args, **kwargs):
             return self.__array_wrap__(f(self.variable.data, *args, **kwargs))
+
         return func
 
     @staticmethod
@@ -1574,7 +1581,8 @@ def func(self, other):
             if isinstance(other, (Dataset, groupby.GroupBy)):
                 return NotImplemented
             if hasattr(other, 'indexes'):
-                align_type = OPTIONS['arithmetic_join'] if join is None else join
+                align_type = (OPTIONS['arithmetic_join']
+                              if join is None else join)
                 self, other = align(self, other, join=align_type, copy=False)
             other_variable = getattr(other, 'variable', other)
             other_coords = getattr(other, 'coords', None)
@@ -1586,6 +1594,7 @@ def func(self, other):
             name = self._result_name(other)
 
             return self._replace(variable, coords, name)
+
         return func
 
     @staticmethod
@@ -1604,6 +1613,7 @@ def func(self, other):
             with self.coords._merge_inplace(other_coords):
                 f(self.variable, other_variable)
             return self
+
         return func
 
     def _copy_attrs_from(self, other):

xarray/core/dataset.py

@@ -14,6 +14,7 @@
 from . import ops
 from . import utils
 from . import groupby
+from . import resample
 from . import rolling
 from . import indexing
 from . import alignment
@@ -305,6 +306,7 @@ class Dataset(Mapping, ImplementsDatasetReduce, BaseDataObject,
     """
     _groupby_cls = groupby.DatasetGroupBy
     _rolling_cls = rolling.DatasetRolling
+    _resample_cls = resample.DatasetResample
 
     def __init__(self, data_vars=None, coords=None, attrs=None,
                  compat='broadcast_equals'):