Xarray中删去重复时间

转贴自Stack Overflownetcdf - Drop duplicate times in xarray - Stack Overflow

xarrray读取多维度的.nc文件时，发现会有重复的时间戳，这时候用

import numpy as np
import netCDF4 as nc4
import xarray as xr

# Create example NetCDF files
for t in range(2):
    nc    = nc4.Dataset('test{}.nc'.format(t), 'w')
    dim_t = nc.createDimension('time', None)
    var_t = nc.createVariable('time', 'f8', ('time',))
    var_s = nc.createVariable('var', 'f8', ('time',))
    var_t.setncattr('units', 'hours since 2001-01-01 00:00:00')
    var_t[:] = t*5+np.arange(6)
    var_s[:] = t*5+np.arange(6)+t
    nc.close()

# Read with xarray
f = xr.open_mfdataset(['test0.nc', 'test1.nc'])

array(['2001-01-01T00:00:00.000000000', '2001-01-01T01:00:00.000000000',
       '2001-01-01T02:00:00.000000000', '2001-01-01T03:00:00.000000000',
       '2001-01-01T04:00:00.000000000', '2001-01-01T05:00:00.000000000',
       '2001-01-01T05:00:00.000000000', '2001-01-01T06:00:00.000000000',
       '2001-01-01T07:00:00.000000000', '2001-01-01T08:00:00.000000000',
       '2001-01-01T09:00:00.000000000', '2001-01-01T10:00:00.000000000'], dtype='datetime64[ns]')

解决方案

In [7]: _, index = np.unique(f['time'], return_index=True)

In [8]: index
Out[8]: array([ 0,  1,  2,  3,  4,  5,  7,  8,  9, 10, 11])

In [9]: f.isel(time=index)
Out[9]: 
<xarray.Dataset>
Dimensions:  (time: 11)
Coordinates:
  * time     (time) datetime64[ns] 2001-01-01 2001-01-01T01:00:00 ...
Data variables:
   var      (time) float64 dask.array<shape=(11,), chunksize=(6,)>