import xarray as xr
import pandas as pd
import numpy as np
import dask.array as da

dates = pd.date_range('1980-01-01', '2019-12-31', freq='D')
ds = xr.Dataset(
    data_vars = {
        'x':(
            ('time', 'lat', 'lon'), 
            da.random.random(size=(dates.size, 360, 720), chunks=(1, -1, -1))),
        'clim':(
            ('dayofyear', 'lat', 'lon'), 
            da.random.random(size=(366, 360, 720), chunks=(1, -1, -1))),
    },
    coords = {
        'time': dates,
        'dayofyear': np.arange(1, 367, 1),
        'lat': np.arange(-90, 90, .5),
        'lon': np.arange(-180, 180, .5),
    }
)
# My original use case was pulling this data from disk, but it doesn't actually seem to matter
ds.to_zarr('test-data', mode='w')
ds = xr.open_zarr('test-data')
ds['anom'] = ds.x.groupby('time.dayofyear') - ds.clim
ds[['anom']].to_zarr('test-anom', mode='w')