sldyns/scace

scAce: an adaptive embedding and clustering method for scRNA-seq data

scace's Issues

about true label

if we don't have the true cell label. how can we calculate nmi . if not ，how we evaluate the clustering result.looking forward to your reply! thanks!

sc.pp.normalize_per_cell(adata)

hi!
thanks for developing the wonderful algorithm!!
when I run the tutorial sc.pp.normalize_per_cell(adata),
the error occurUFuncTypeError: Cannot cast ufunc 'divide' output from dtype('float64') to dtype('int64') with casting rule 'same_kind',
when I change the code tosc.pp.normalize_total(adata),comes another errorAttributeError: 'DataFrame' object has no attribute 'n_counts'.
could you give some advice?Thanks!!!

pip install fails

Hi, I'm trying to install scace using:

pip install scace

I get the error:

Collecting scace
  Downloading scace-0.1.2-py3-none-any.whl (13 kB)
Requirement already satisfied: numpy in /home/mark/miniconda3/envs/scvi10i/lib/python3.8/site-packages (from scace) (1.21.5)
Collecting sklearn
  Downloading sklearn-0.0.post12.tar.gz (2.6 kB)
  Preparing metadata (setup.py) ... error
  error: subprocess-exited-with-error
  
  × python setup.py egg_info did not run successfully.
  │ exit code: 1
  ╰─> [15 lines of output]
      The 'sklearn' PyPI package is deprecated, use 'scikit-learn'
      rather than 'sklearn' for pip commands.
      
      Here is how to fix this error in the main use cases:
      - use 'pip install scikit-learn' rather than 'pip install sklearn'
      - replace 'sklearn' by 'scikit-learn' in your pip requirements files
        (requirements.txt, setup.py, setup.cfg, Pipfile, etc ...)
      - if the 'sklearn' package is used by one of your dependencies,
        it would be great if you take some time to track which package uses
        'sklearn' instead of 'scikit-learn' and report it to their issue tracker
      - as a last resort, set the environment variable
        SKLEARN_ALLOW_DEPRECATED_SKLEARN_PACKAGE_INSTALL=True to avoid this error
      
      More information is available at
      https://github.com/scikit-learn/sklearn-pypi-package
      [end of output]
  
  note: This error originates from a subprocess, and is likely not a problem with pip.
error: metadata-generation-failed

× Encountered error while generating package metadata.
╰─> See above for output.

note: This is an issue with the package mentioned above, not pip.
hint: See above for details.

setup.py contains:

install_requires=[
        "numpy",
        "scanpy",
        "torch",
        "pandas",
        "tqdm",
        "scipy",
        "sklearn"
        ],

I'm not clear on the best way to resolve this, can you plase advise?

thank you

error after training

Thanks for developing this interesting program. While I am trying to run the algo, after training it fails giving the following:
88 if init_cluster is not None:
89 cluster_centers = compute_mu(scace_emb.cpu().numpy(), init_cluster)
---> 91 data_1 = np.concatenate([scace_emb.cpu().numpy(), np.array(init_cluster).reshape(-1, 1)], axis=1)
92 mu, y_pred = centroid_split(scace_emb.cpu().numpy(), data_1, cluster_centers, np.array(init_cluster))
94 return y_pred, mu, scace_emb.cpu().numpy()

File <array_function internals>:200, in concatenate(*args, **kwargs)

ValueError: all the input array dimensions except for the concatenation axis must match exactly, but along dimension 0, the array at index 0 has size 1341 and the array at index 1 has size 1

i tried with different adata, get the same error