使用 Python xarray 使用 'where' 进行屏蔽不再有效
Masking with 'where' using Python xarray is not working anymore
我在更新 xarray 后遇到了麻烦 运行。
我有一个盐度数据集，其尺寸为：
(u'time', u'stations', u'layer')
对于特定的站点，我想获得所选深度的盐度，比如 -10 米。维度图层包含随时间变化的深度值，即给定图层包含随时间变化的不同深度值（由于水位变化）。
之前我在做以下事情：
ds.salinity.sel(stations='mystation').where( np.ceil(ds.layer(stations='mystation')) ==-10 )
工作正常。
但现在我收到这个错误：
---------------------------------------------------------------------------
IndexError Traceback (most recent call last)
<ipython-input-27-7e83f5e839cc> in <module>()
1 fmstation = 'T1_50'
2
----> 3 sal10m = ds.salinity.sel(stations = ds.stations[ds.station_name == fmstation]).where(np.ceil(ds.Zcoordinate_c.isel(stations = ds.stations[ds.station_name == fmstation])) == -10) #.mean(axis=2).plot()
4 sal10m #.plot()
C:\Users\Smeirellesnune\AppData\Local\Continuum\Miniconda\lib\site-packages\xarray\core\common.pyc in where(self, cond)
481 * x (x) int64 0 1 2 3 4
482 """
--> 483 return self._where(cond)
484
485 # this has no runtime function - these are listed so IDEs know these methods
C:\Users\Smeirellesnune\AppData\Local\Continuum\Miniconda\lib\site-packages\xarray\core\dataarray.pyc in func(self, other)
1193 if not reflexive
1194 else f(other_variable, self.variable))
-> 1195 coords = self.coords.merge(other_coords)._variables
1196 name = self._result_name(other)
1197
C:\Users\Smeirellesnune\AppData\Local\Continuum\Miniconda\lib\site-packages\xarray\core\coordinates.pyc in merge(self, other)
139 ds = self.to_dataset()
140 if other is not None:
--> 141 conflicts = self._merge_validate(other)
142 _coord_merge_finalize(ds.coords, other, *conflicts)
143 return ds
C:\Users\Smeirellesnune\AppData\Local\Continuum\Miniconda\lib\site-packages\xarray\core\coordinates.pyc in _merge_validate(self, other)
89 self_var = self._variables[k]
90 other_var = other[k].variable
---> 91 if not self_var.broadcast_equals(other_var):
92 if k in self.dims and k in other.dims:
93 raise ValueError('index %r not aligned' % k)
C:\Users\Smeirellesnune\AppData\Local\Continuum\Miniconda\lib\site-packages\xarray\core\variable.pyc in broadcast_equals(self, other)
976 except (ValueError, AttributeError):
977 return False
--> 978 return self.equals(other)
979
980 def identical(self, other):
C:\Users\Smeirellesnune\AppData\Local\Continuum\Miniconda\lib\site-packages\xarray\core\variable.pyc in equals(self, other)
961 other = getattr(other, 'variable', other)
962 try:
--> 963 return (self.dims == other.dims and self._data_equals(other))
964 except (TypeError, AttributeError):
965 return False
C:\Users\Smeirellesnune\AppData\Local\Continuum\Miniconda\lib\site-packages\xarray\core\variable.pyc in _data_equals(self, other)
947 def _data_equals(self, other):
948 return (self._data is other._data or
--> 949 ops.array_equiv(self.data, other.data))
950
951 def equals(self, other):
C:\Users\Smeirellesnune\AppData\Local\Continuum\Miniconda\lib\site-packages\xarray\core\ops.pyc in array_equiv(arr1, arr2)
188 if arr1.shape != arr2.shape:
189 return False
--> 190 return bool(((arr1 == arr2) | (isnull(arr1) & isnull(arr2))).all())
191
192
C:\Users\Smeirellesnune\AppData\Local\Continuum\Miniconda\lib\site-packages\dask\array\core.pyc in all(self, axis, keepdims, split_every)
1146 def all(self, axis=None, keepdims=False, split_every=None):
1147 from .reductions import all
-> 1148 return all(self, axis=axis, keepdims=keepdims, split_every=split_every)
1149
1150 @wraps(np.min)
C:\Users\Smeirellesnune\AppData\Local\Continuum\Miniconda\lib\site-packages\dask\array\reductions.pyc in all(a, axis, keepdims, split_every)
161 def all(a, axis=None, keepdims=False, split_every=None):
162 return reduction(a, chunk.all, chunk.all, axis=axis, keepdims=keepdims,
--> 163 dtype='bool', split_every=split_every)
164
165
C:\Users\Smeirellesnune\AppData\Local\Continuum\Miniconda\lib\site-packages\dask\array\reductions.pyc in reduction(x, chunk, aggregate, axis, keepdims, dtype, split_every, combine, name)
42
43 return _tree_reduce(tmp, aggregate, axis, keepdims, dtype, split_every,
---> 44 combine, name=name)
45
46
C:\Users\Smeirellesnune\AppData\Local\Continuum\Miniconda\lib\site-packages\dask\array\reductions.pyc in _tree_reduce(x, aggregate, axis, keepdims, dtype, split_every, combine, name)
75 return partial_reduce(func, x, split_every, keepdims=keepdims,
76 dtype=dtype,
---> 77 name=(name or funcname(aggregate)) + '-aggregate')
78
79
C:\Users\Smeirellesnune\AppData\Local\Continuum\Miniconda\lib\site-packages\dask\array\reductions.pyc in partial_reduce(func, x, split_every, keepdims, dtype, name)
105 out_axis = [i for i in range(x.ndim) if i not in split_every]
106 getter = lambda k: get(out_axis, k)
--> 107 keys = map(getter, keys)
108 out_chunks = list(getter(out_chunks))
109 dsk = {}
C:\Users\Smeirellesnune\AppData\Local\Continuum\Miniconda\lib\site-packages\dask\array\reductions.pyc in <lambda>(k)
104 if not keepdims:
105 out_axis = [i for i in range(x.ndim) if i not in split_every]
--> 106 getter = lambda k: get(out_axis, k)
107 keys = map(getter, keys)
108 out_chunks = list(getter(out_chunks))
C:\Users\Smeirellesnune\AppData\Local\Continuum\Miniconda\lib\site-packages\toolz\itertoolz.pyc in get(ind, seq, default)
374 return operator.itemgetter(*ind)(seq)
375 else:
--> 376 return (seq[ind[0]],)
377 else:
378 return tuple(_get(i, seq, default) for i in ind)
IndexError: list index out of range
有人知道这是怎么回事吗？
或者是否有更智能的方法来切分我的数据集？
我使用的xarray版本是：
xarray 0.7.2
sys.version:
'2.7.11 |Anaconda 2.1.0 (64-bit)| (default, Feb 16 2016, 09:58:36) [MSC v.1500 64 bit (AMD64)]'
编辑：添加数据集详细信息
<xarray.Dataset>
Dimensions: (cross_section: 15, cross_section_pts: 3, laydim: 20, laydimw: 21, stations: 979, time: 2512)
Coordinates:
station_x_coordinate (stations) float64 4.194 4.008 ...
station_y_coordinate (stations) float64 52.07 51.99 52.0 ...
station_name (stations) |S64 'zmBoei_wav' ...
Zcoordinate_c (time, stations, laydim) float64 -10.98 ...
Zcoordinate_w (time, stations, laydimw) float64 -11.28 ...
cross_section_name (cross_section) |S64 'L1' 'L2' 'L3' ...
* time (time) datetime64[ns] 2014-10-02T06:00:00 ...
* cross_section (cross_section) int64 0 1 2 3 4 5 6 ...
* cross_section_pts (cross_section_pts) int64 0 1 2
* laydim (laydim) int64 0 1 2 3 4 5 6 7 8 9 ...
* laydimw (laydimw) int64 0 1 2 3 4 5 6 7 8 9 ...
* stations (stations) int64 0 1 2 3 4 5 6 7 8 ...
Data variables:
station_id (stations) |S64 'zmBoei_wav' ...
waterlevel (time, stations) float64 0.6178 ...
Waterdepth (time, stations) float64 11.9 20.36 ...
x_velocity (time, stations, laydim) float64 0.1941 ...
y_velocity (time, stations, laydim) float64 0.0954 ...
z_velocity (time, stations, laydim) float64 0.000392 ...
Tke (time, stations, laydimw) float64 1e-32 ...
Eps (time, stations, laydimw) float64 1e-32 ...
Vicww (time, stations, laydimw) float64 0.0 ...
salinity (time, stations, laydim) float64 26.26 ...
cross_section_x_coordinate (cross_section, cross_section_pts) float64 4.206 ...
cross_section_y_coordinate (cross_section, cross_section_pts) float64 51.94 ...
cross_section_discharge (time, cross_section) float64 0.0 ...
cross_section_area (time, cross_section) float64 8.762e+03 ...
cross_section_velocity (time, cross_section) float64 0.0 ...
cross_section_salt (time, cross_section) float64 -1.142e+05 ...
WaterBalance_total_volume (time) float64 0.0 1.227e+11 ...
WaterBalance_storage (time) float64 0.0 1.227e+11 ...
WaterBalance_volume_error (time) float64 0.0 -1.499e+07 ...
WaterBalance_boundaries_in (time) float64 0.0 3.827e+08 ...
WaterBalance_boundaries_out (time) float64 0.0 6.048e+07 ...
WaterBalance_boundaries_total (time) float64 0.0 3.222e+08 ...
WaterBalance_exchange_with_1D_in (time) float64 0.0 0.0 0.0 0.0 0.0 ...
WaterBalance_exchange_with_1D_out (time) float64 0.0 0.0 0.0 0.0 0.0 ...
WaterBalance_exchange_with_1D_total (time) float64 0.0 0.0 0.0 0.0 0.0 ...
WaterBalance_precipitation (time) float64 0.0 0.0 0.0 0.0 0.0 ...
WaterBalance_source_sink (time) float64 0.0 0.0 0.0 0.0 0.0 ...
Attributes:
institution: Deltares
references: http://www.deltares.nl
source: Deltares, D-Flow FM Version 1.1.182.45395, Apr 07 2016, 10:16:58, model
history: Created on 2016-05-23T21:50:20+0200, D-Flow FM
date_created: 2016-05-23T21:50:20+0200
date_modified: 2016-05-23T21:50:20+0200
Conventions: CF-1.5 Deltares-0.1
从 IOOS 频道安装软件包和 dask 解决了这个问题。要设置 IOOS Python 环境，请按照以下步骤操作：
https://github.com/ioos/conda-recipes/wiki/Setting-up-the-IOOS-Python-environment
正如@Stephan 指出的那样：通用 "conda-forge" 渠道现在应该比 IOOS 更受青睐。 了解更多信息：
https://conda-forge.github.io/
其次，安装dask如下：
conda install dask -c conda-forge
开机前激活IOOS Python:
source activate IOOS #(OSX and Linux)
activate IOOS #(Windows)
我在更新 xarray 后遇到了麻烦 运行。
我有一个盐度数据集，其尺寸为：
(u'time', u'stations', u'layer')
对于特定的站点，我想获得所选深度的盐度，比如 -10 米。维度图层包含随时间变化的深度值，即给定图层包含随时间变化的不同深度值（由于水位变化）。
之前我在做以下事情：
ds.salinity.sel(stations='mystation').where( np.ceil(ds.layer(stations='mystation')) ==-10 )
工作正常。
但现在我收到这个错误：
---------------------------------------------------------------------------
IndexError Traceback (most recent call last)
<ipython-input-27-7e83f5e839cc> in <module>()
1 fmstation = 'T1_50'
2
----> 3 sal10m = ds.salinity.sel(stations = ds.stations[ds.station_name == fmstation]).where(np.ceil(ds.Zcoordinate_c.isel(stations = ds.stations[ds.station_name == fmstation])) == -10) #.mean(axis=2).plot()
4 sal10m #.plot()
C:\Users\Smeirellesnune\AppData\Local\Continuum\Miniconda\lib\site-packages\xarray\core\common.pyc in where(self, cond)
481 * x (x) int64 0 1 2 3 4
482 """
--> 483 return self._where(cond)
484
485 # this has no runtime function - these are listed so IDEs know these methods
C:\Users\Smeirellesnune\AppData\Local\Continuum\Miniconda\lib\site-packages\xarray\core\dataarray.pyc in func(self, other)
1193 if not reflexive
1194 else f(other_variable, self.variable))
-> 1195 coords = self.coords.merge(other_coords)._variables
1196 name = self._result_name(other)
1197
C:\Users\Smeirellesnune\AppData\Local\Continuum\Miniconda\lib\site-packages\xarray\core\coordinates.pyc in merge(self, other)
139 ds = self.to_dataset()
140 if other is not None:
--> 141 conflicts = self._merge_validate(other)
142 _coord_merge_finalize(ds.coords, other, *conflicts)
143 return ds
C:\Users\Smeirellesnune\AppData\Local\Continuum\Miniconda\lib\site-packages\xarray\core\coordinates.pyc in _merge_validate(self, other)
89 self_var = self._variables[k]
90 other_var = other[k].variable
---> 91 if not self_var.broadcast_equals(other_var):
92 if k in self.dims and k in other.dims:
93 raise ValueError('index %r not aligned' % k)
C:\Users\Smeirellesnune\AppData\Local\Continuum\Miniconda\lib\site-packages\xarray\core\variable.pyc in broadcast_equals(self, other)
976 except (ValueError, AttributeError):
977 return False
--> 978 return self.equals(other)
979
980 def identical(self, other):
C:\Users\Smeirellesnune\AppData\Local\Continuum\Miniconda\lib\site-packages\xarray\core\variable.pyc in equals(self, other)
961 other = getattr(other, 'variable', other)
962 try:
--> 963 return (self.dims == other.dims and self._data_equals(other))
964 except (TypeError, AttributeError):
965 return False
C:\Users\Smeirellesnune\AppData\Local\Continuum\Miniconda\lib\site-packages\xarray\core\variable.pyc in _data_equals(self, other)
947 def _data_equals(self, other):
948 return (self._data is other._data or
--> 949 ops.array_equiv(self.data, other.data))
950
951 def equals(self, other):
C:\Users\Smeirellesnune\AppData\Local\Continuum\Miniconda\lib\site-packages\xarray\core\ops.pyc in array_equiv(arr1, arr2)
188 if arr1.shape != arr2.shape:
189 return False
--> 190 return bool(((arr1 == arr2) | (isnull(arr1) & isnull(arr2))).all())
191
192
C:\Users\Smeirellesnune\AppData\Local\Continuum\Miniconda\lib\site-packages\dask\array\core.pyc in all(self, axis, keepdims, split_every)
1146 def all(self, axis=None, keepdims=False, split_every=None):
1147 from .reductions import all
-> 1148 return all(self, axis=axis, keepdims=keepdims, split_every=split_every)
1149
1150 @wraps(np.min)
C:\Users\Smeirellesnune\AppData\Local\Continuum\Miniconda\lib\site-packages\dask\array\reductions.pyc in all(a, axis, keepdims, split_every)
161 def all(a, axis=None, keepdims=False, split_every=None):
162 return reduction(a, chunk.all, chunk.all, axis=axis, keepdims=keepdims,
--> 163 dtype='bool', split_every=split_every)
164
165
C:\Users\Smeirellesnune\AppData\Local\Continuum\Miniconda\lib\site-packages\dask\array\reductions.pyc in reduction(x, chunk, aggregate, axis, keepdims, dtype, split_every, combine, name)
42
43 return _tree_reduce(tmp, aggregate, axis, keepdims, dtype, split_every,
---> 44 combine, name=name)
45
46
C:\Users\Smeirellesnune\AppData\Local\Continuum\Miniconda\lib\site-packages\dask\array\reductions.pyc in _tree_reduce(x, aggregate, axis, keepdims, dtype, split_every, combine, name)
75 return partial_reduce(func, x, split_every, keepdims=keepdims,
76 dtype=dtype,
---> 77 name=(name or funcname(aggregate)) + '-aggregate')
78
79
C:\Users\Smeirellesnune\AppData\Local\Continuum\Miniconda\lib\site-packages\dask\array\reductions.pyc in partial_reduce(func, x, split_every, keepdims, dtype, name)
105 out_axis = [i for i in range(x.ndim) if i not in split_every]
106 getter = lambda k: get(out_axis, k)
--> 107 keys = map(getter, keys)
108 out_chunks = list(getter(out_chunks))
109 dsk = {}
C:\Users\Smeirellesnune\AppData\Local\Continuum\Miniconda\lib\site-packages\dask\array\reductions.pyc in <lambda>(k)
104 if not keepdims:
105 out_axis = [i for i in range(x.ndim) if i not in split_every]
--> 106 getter = lambda k: get(out_axis, k)
107 keys = map(getter, keys)
108 out_chunks = list(getter(out_chunks))
C:\Users\Smeirellesnune\AppData\Local\Continuum\Miniconda\lib\site-packages\toolz\itertoolz.pyc in get(ind, seq, default)
374 return operator.itemgetter(*ind)(seq)
375 else:
--> 376 return (seq[ind[0]],)
377 else:
378 return tuple(_get(i, seq, default) for i in ind)
IndexError: list index out of range
有人知道这是怎么回事吗？
或者是否有更智能的方法来切分我的数据集？
我使用的xarray版本是：
xarray 0.7.2
sys.version:
'2.7.11 |Anaconda 2.1.0 (64-bit)| (default, Feb 16 2016, 09:58:36) [MSC v.1500 64 bit (AMD64)]'
编辑：添加数据集详细信息
<xarray.Dataset>
Dimensions: (cross_section: 15, cross_section_pts: 3, laydim: 20, laydimw: 21, stations: 979, time: 2512)
Coordinates:
station_x_coordinate (stations) float64 4.194 4.008 ...
station_y_coordinate (stations) float64 52.07 51.99 52.0 ...
station_name (stations) |S64 'zmBoei_wav' ...
Zcoordinate_c (time, stations, laydim) float64 -10.98 ...
Zcoordinate_w (time, stations, laydimw) float64 -11.28 ...
cross_section_name (cross_section) |S64 'L1' 'L2' 'L3' ...
* time (time) datetime64[ns] 2014-10-02T06:00:00 ...
* cross_section (cross_section) int64 0 1 2 3 4 5 6 ...
* cross_section_pts (cross_section_pts) int64 0 1 2
* laydim (laydim) int64 0 1 2 3 4 5 6 7 8 9 ...
* laydimw (laydimw) int64 0 1 2 3 4 5 6 7 8 9 ...
* stations (stations) int64 0 1 2 3 4 5 6 7 8 ...
Data variables:
station_id (stations) |S64 'zmBoei_wav' ...
waterlevel (time, stations) float64 0.6178 ...
Waterdepth (time, stations) float64 11.9 20.36 ...
x_velocity (time, stations, laydim) float64 0.1941 ...
y_velocity (time, stations, laydim) float64 0.0954 ...
z_velocity (time, stations, laydim) float64 0.000392 ...
Tke (time, stations, laydimw) float64 1e-32 ...
Eps (time, stations, laydimw) float64 1e-32 ...
Vicww (time, stations, laydimw) float64 0.0 ...
salinity (time, stations, laydim) float64 26.26 ...
cross_section_x_coordinate (cross_section, cross_section_pts) float64 4.206 ...
cross_section_y_coordinate (cross_section, cross_section_pts) float64 51.94 ...
cross_section_discharge (time, cross_section) float64 0.0 ...
cross_section_area (time, cross_section) float64 8.762e+03 ...
cross_section_velocity (time, cross_section) float64 0.0 ...
cross_section_salt (time, cross_section) float64 -1.142e+05 ...
WaterBalance_total_volume (time) float64 0.0 1.227e+11 ...
WaterBalance_storage (time) float64 0.0 1.227e+11 ...
WaterBalance_volume_error (time) float64 0.0 -1.499e+07 ...
WaterBalance_boundaries_in (time) float64 0.0 3.827e+08 ...
WaterBalance_boundaries_out (time) float64 0.0 6.048e+07 ...
WaterBalance_boundaries_total (time) float64 0.0 3.222e+08 ...
WaterBalance_exchange_with_1D_in (time) float64 0.0 0.0 0.0 0.0 0.0 ...
WaterBalance_exchange_with_1D_out (time) float64 0.0 0.0 0.0 0.0 0.0 ...
WaterBalance_exchange_with_1D_total (time) float64 0.0 0.0 0.0 0.0 0.0 ...
WaterBalance_precipitation (time) float64 0.0 0.0 0.0 0.0 0.0 ...
WaterBalance_source_sink (time) float64 0.0 0.0 0.0 0.0 0.0 ...
Attributes:
institution: Deltares
references: http://www.deltares.nl
source: Deltares, D-Flow FM Version 1.1.182.45395, Apr 07 2016, 10:16:58, model
history: Created on 2016-05-23T21:50:20+0200, D-Flow FM
date_created: 2016-05-23T21:50:20+0200
date_modified: 2016-05-23T21:50:20+0200
Conventions: CF-1.5 Deltares-0.1
从 IOOS 频道安装软件包和 dask 解决了这个问题。要设置 IOOS Python 环境，请按照以下步骤操作：
https://github.com/ioos/conda-recipes/wiki/Setting-up-the-IOOS-Python-environment
正如@Stephan 指出的那样：通用 "conda-forge" 渠道现在应该比 IOOS 更受青睐。 了解更多信息：
https://conda-forge.github.io/
其次，安装dask如下：
conda install dask -c conda-forge
开机前激活IOOS Python:
source activate IOOS #(OSX and Linux)
activate IOOS #(Windows)