Rank genes on custom cluster labels

[Khalid-Usman]

Hi,

I applied scanpy on 1.3 millions neurons, [https://github.com/theislab/scanpy_usage/blob/master/170522_visualizing_one_million_cells/cluster.py], but i have different cluster labels (not predicted by louvain in scanpy). So i want to use my custom labels to plot umap and rank genes, but i got error.

adata.obs['louvain'] = Y_pred

where Y_pred are my custom labels,

sc.tl.rank_genes_groups(adata, 'louvain')

I run this command and got following error,

Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/home/khalid/.local/lib/python3.7/site-packages/scanpy/tools/_rank_genes_groups.py", line 128, in rank_genes_groups
    adata, groups_order, groupby)
  File "/home/khalid/.local/lib/python3.7/site-packages/scanpy/utils.py", line 724, in select_groups
    groups_order = adata.obs[key].cat.categories
  File "/home/khalid/anaconda3/lib/python3.7/site-packages/pandas/core/generic.py", line 5175, in __getattr__
    return object.__getattribute__(self, name)
  File "/home/khalid/anaconda3/lib/python3.7/site-packages/pandas/core/accessor.py", line 175, in __get__
    accessor_obj = self._accessor(obj)
  File "/home/khalid/anaconda3/lib/python3.7/site-packages/pandas/core/arrays/categorical.py", line 2593, in __init__
    self._validate(data)
  File "/home/khalid/anaconda3/lib/python3.7/site-packages/pandas/core/arrays/categorical.py", line 2603, in _validate
    "Can only use .cat accessor with a " "'category' dtype"
AttributeError: Can only use .cat accessor with a 'category' dtype