In order to maintain a list of currently relevant issues, we mark issues as stale after a period of inactivity

If this issue remains relevant, please comment here or remove the stale label; otherwise it will be marked as closed automatically

xhistogram probably does what you want: https://github.com/xgcm/xhistogram

First prototype: ```python def value_counts(v, global_unique_values, newdim: str): unique_values, counts = dask.compute(*np.unique(v, return_counts=True))

# find out where in `global_unique_values` the unique values of `v` are located
_, idx1, idx2 = np.intersect1d(unique_values, global_unique_values, return_indices=True)

# assign values according to `global_unique_values`
retval = np.zeros_like(global_unique_values)
retval[idx2] = counts[idx1]

# ## alternative:
# counts = xr.DataArray(
#     counts, 
#     dims=[newdim, ],
#     coords={newdim: unique_values},
# )
# counts, = xr.align(counts, indexes={newdim: global_unique_values}, fill_value=0)

return retval

def xr_value_counts(obj, unique_values=None, **kwargs): (newdim, apply_dims), = kwargs.items()

if type(apply_dims) == str:
    # convert scalars to list
    apply_dims = [apply_dims]
if type(apply_dims) != list:
    # cast iterables to list
    apply_dims = [*apply_dims]

if not unique_values:
    # map(np.unique) and reduce(np.unique)
    unique_values = np.unique(da.map_blocks(np.unique, obj.data.flatten()).compute())
else:
    unique_values = np.sort(unique_values)

retval = xr.apply_ufunc(
    lambda v: value_counts(v, global_unique_values=unique_values, newdim=newdim),
    obj,
    input_core_dims=[apply_dims],
    output_core_dims=[[newdim]],
    dask="allowed",
    vectorize=True,
)
retval.coords[newdim] = unique_values

return retval

test_da = xr.DataArray( [ [0,1,1,1,3,4], [0,6,1,1,3,4], ], dims=["dim_0", "dim_1"], coords={"dim_1": [2,5,7,4,3,6]}, )

test_values = xr_value_counts(test_da, value_counts="dim_1")

assert np.all( test_values.values == np.array([ [1, 3, 1, 1, 0], [1, 2, 1, 1, 1] ]) )

assert np.all( test_values.value_counts == np.array([0, 1, 3, 4, 6]) ) ```

Example: ```python test_da = xr.DataArray( [ [0,1,1,1,3,4], [0,6,1,1,3,4], ], dims=["dim_0", "dim_1"], coords={"dim_1": [2,5,7,4,3,6]}, )

print(test_da)

<xarray.DataArray (dim_0: 2, dim_1: 6)>

array([[0, 1, 1, 1, 3, 4],

[0, 6, 1, 1, 3, 4]])

Coordinates:

* dim_1 (dim_1) int64 2 5 7 4 3 6

Dimensions without coordinates: dim_0

print(xr_value_counts(test_da, value_counts="dim_1"))

<xarray.DataArray (dim_0: 2, value_counts: 5)>

array([[1, 3, 1, 1, 0],

[1, 2, 1, 1, 1]])

Coordinates:

* value_counts (value_counts) int64 0 1 3 4 6

Dimensions without coordinates: dim_0

```

Probably not the fastest solution and executes eagerly but it works. What do you think?