WIP: Feature/interpolate

.travis.yml

@@ -89,9 +89,9 @@ install:
   - python xarray/util/print_versions.py
 
 script:
+  - git diff upstream/master xarray/**/*py | flake8 --diff --exit-zero || true
   - python -OO -c "import xarray"
   - py.test xarray --cov=xarray --cov-config ci/.coveragerc --cov-report term-missing --verbose $EXTRA_FLAGS
-  - git diff upstream/master **/*py | flake8 --diff --exit-zero || true
 
 after_success:
   - coveralls

asv_bench/benchmarks/dataarray_missing.py

@@ -0,0 +1,74 @@
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+import pandas as pd
+
+try:
+    import dask
+    import dask.multiprocessing
+except ImportError:
+    pass
+
+import xarray as xr
+
+from . import randn, requires_dask
+
+
+def make_bench_data(shape, frac_nan, chunks):
+    vals = randn(shape, frac_nan)
+    coords = {'time': pd.date_range('2000-01-01', freq='D',
+              periods=shape[0])}
+    da = xr.DataArray(vals, dims=('time', 'x', 'y'), coords=coords)
+
+    if chunks is not None:
+        da = da.chunk(chunks)
+
+    return da
+
+
+def time_interpolate_na(shape, chunks, method, limit):
+    if chunks is not None:
+        requires_dask()
+    da = make_bench_data(shape, 0.1, chunks=chunks)
+    actual = da.interpolate_na(dim='time', method='linear', limit=limit)
+
+    if chunks is not None:
+        actual = actual.compute()
+
+
+time_interpolate_na.param_names = ['shape', 'chunks', 'method', 'limit']
+time_interpolate_na.params = ([(3650, 200, 400), (100, 25, 25)],
+                              [None, {'x': 25, 'y': 25}],
+                              ['linear', 'spline', 'quadratic', 'cubic'],
+                              [None, 3])
+
+
+def time_ffill(shape, chunks, limit):
+
+    da = make_bench_data(shape, 0.1, chunks=chunks)
+    actual = da.ffill(dim='time', limit=limit)
+
+    if chunks is not None:
+        actual = actual.compute()
+
+
+time_ffill.param_names = ['shape', 'chunks', 'limit']
+time_ffill.params = ([(3650, 200, 400), (100, 25, 25)],
+                     [None, {'x': 25, 'y': 25}],
+                     [None, 3])
+
+
+def time_bfill(shape, chunks, limit):
+
+    da = make_bench_data(shape, 0.1, chunks=chunks)
+    actual = da.bfill(dim='time', limit=limit)
+
+    if chunks is not None:
+        actual = actual.compute()
+
+
+time_bfill.param_names = ['shape', 'chunks', 'limit']
+time_bfill.params = ([(3650, 200, 400), (100, 25, 25)],
+                     [None, {'x': 25, 'y': 25}],
+                     [None, 3])

doc/api.rst

@@ -298,6 +298,9 @@ Computation
 :py:attr:`~DataArray.count`
 :py:attr:`~DataArray.dropna`
 :py:attr:`~DataArray.fillna`
+:py:attr:`~DataArray.ffill`
+:py:attr:`~DataArray.bfill`
+:py:attr:`~DataArray.interpolate_na`
 :py:attr:`~DataArray.where`
 
 **ndarray methods**:

xarray/core/dataarray.py

@@ -1220,6 +1220,93 @@ def fillna(self, value):
         out = ops.fillna(self, value)
         return out
 
+    def interpolate_na(self, dim=None, method='linear', limit=None,
+                       use_coordinate=True,
+                       **kwargs):
+        """Interpolate values according to different methods.
+
+        Parameters
+        ----------
+        dim : str
+            Specifies the dimension along which to interpolate.
+        method : {'linear', 'nearest', 'zero', 'slinear', 'quadratic', 'cubic',
+                  'polynomial', 'barycentric', 'krog', 'pchip',
+                  'spline'}, optional
+            String indicating which method to use for interpolation:
+
+            - 'linear': linear interpolation (Default). Additional keyword
+              arguments are passed to ``numpy.interp``
+            - 'nearest', 'zero', 'slinear', 'quadratic', 'cubic',
+              'polynomial': are passed to ``scipy.interpolate.interp1d``. If
+              method=='polynomial', the ``order`` keyword argument must also be
+              provided.
+            - 'barycentric', 'krog', 'pchip', 'spline': use their respective
+              ``scipy.interpolate`` classes.
+        use_coordinate : boolean or str, default True
+            Specifies which index to use as the x values in the interpolation
+            formulated as `y = f(x)`. If False, values are treated as if
+            eqaully-spaced along `dim`. If True, the IndexVariable `dim` is
+            used. If use_coordinate is a string, it specifies the name of a
+            coordinate variariable to use as the index.
+        limit : int, default None
+            Maximum number of consecutive NaNs to fill. Must be greater than 0
+            or None for no limit.
+
+        Returns
+        -------
+        DataArray
+
+        See also
+        --------
+        numpy.interp
+        scipy.interpolate
+        """
+        from .missing import interp_na
+        return interp_na(self, dim=dim, method=method, limit=limit,
+                         use_coordinate=use_coordinate, **kwargs)
+
+    def ffill(self, dim, limit=None):
+        '''Fill NaN values by propogating values forward
+
+        Parameters
+        ----------
+        dim : str
+            Specifies the dimension along which to propogate values when
+            filling.
+        limit : int, default None
+            The maximum number of consecutive NaN values to forward fill. In
+            other words, if there is a gap with more than this number of
+            consecutive NaNs, it will only be partially filled. Must be greater
+            than 0 or None for no limit.
+
+        Returns
+        -------
+        DataArray
+        '''
+        from .missing import ffill
+        return ffill(self, dim, limit=limit)
+
+    def bfill(self, dim, limit=None):
+        '''Fill NaN values by propogating values backward
+
+        Parameters
+        ----------
+        dim : str
+            Specifies the dimension along which to propogate values when
+            filling.
+        limit : int, default None
+            The maximum number of consecutive NaN values to backward fill. In
+            other words, if there is a gap with more than this number of
+            consecutive NaNs, it will only be partially filled. Must be greater
+            than 0 or None for no limit.
+
+        Returns
+        -------
+        DataArray
+        '''
+        from .missing import bfill
+        return bfill(self, dim, limit=limit)
+
     def combine_first(self, other):
         """Combine two DataArray objects, with union of coordinates.