search

SCCAF / sccaf

Single-Cell Clustering Assessment Framework
MIT License
85 stars 18 forks source link

Error when running with plot=TRUE #34

Open s2hui opened 4 years ago

s2hui commented 4 years ago

Hello,

When I execute SCCAF_optimize_all() with plot = TRUE, it will eventually seem to hang after plotting the ROC plots. I have to close the figure window inorder to gain back control of the terminal and then the run terminates with an error (see below). I am not sure what the problem could be.

Thanks for your help, shui

SCCAF_optimize_all(ad=adata, plot=True, min_acc=0.9, prefix ='L1', use='pca',n_iter=150) R1norm_cutoff: 0.500000 R2norm_cutoff: 0.050000 Accuracy: 0.000000

Round1 ... Mean CV accuracy: 0.8820 Accuracy on the training set: 0.9449 Accuracy on the hold-out set: 0.8499 Accuracy on the training set: 0.9427 Accuracy on the hold-out set: 0.8489 Accuracy on the training set: 0.9464 Accuracy on the hold-out set: 0.8447 Max R1mat: 0.691489 Max R2mat: 0.005358 min_acc: 0.844728 IGRAPH U-W- 50 2 --

  • attr: weight (e)
  • edges: 11--45 11--45 ... storing 'L1_Round1' as categorical Round2 ... Mean CV accuracy: 0.8823 Accuracy on the training set: 0.9440 Accuracy on the hold-out set: 0.8455 ... storing 'L1_Round1_self-projection' as categorical Accuracy on the training set: 0.9432 Accuracy on the hold-out set: 0.8524 Accuracy on the training set: 0.9438 Accuracy on the hold-out set: 0.8514 Max R1mat: 0.394737 Max R2mat: 0.005553 min_acc: 0.845477 IGRAPH U-W- 49 0 --

  • attr: weight (e) Converge SCCAF_optimize no. cluster! m1: 0.394737 m2: 0.005553 Accuracy: 0.845477 start_iter: 1 ****R1norm_cutoff: 0.384737 R2norm_cutoff: 0.004553 Accuracy: 0.845477

    Round2 ... Mean CV accuracy: 0.8808 Accuracy on the training set: 0.9489 Accuracy on the hold-out set: 0.8495 ... storing 'L1_Round1_self-projection' as categorical Accuracy on the training set: 0.9415 Accuracy on the hold-out set: 0.8468 Accuracy on the training set: 0.9444 Accuracy on the hold-out set: 0.8499 Max R1mat: 1.125000 Max R2mat: 0.005300 min_acc: 0.846835 IGRAPH U-W- 49 8 --

  • attr: weight (e)
  • edges: 0--2 0--2 2--21 3--14 13--48 3--14 2--21 13--48 ... storing 'L1_Round2' as categorical Traceback (most recent call last): File "", line 1, in File "/usr/local/bin/miniconda2/envs/myPythonEnv/lib/python3.7/site-packages/SCCAF/init.py", line 654, in SCCAF_optimize_all *args, kwargs) File "/usr/local/bin/miniconda2/envs/myPythonEnv/lib/python3.7/site-packages/SCCAF/init.py", line 876, in SCCAF_optimize show=(mplotlib_backend is None)) File "/usr/local/bin/miniconda2/envs/myPythonEnv/lib/python3.7/site-packages/scanpy/plotting/_anndata.py", line 120, in scatter return _scatter_obs(args) File "/usr/local/bin/miniconda2/envs/myPythonEnv/lib/python3.7/site-packages/scanpy/plotting/_anndata.py", line 388, in _scatter_obs alpha=alpha, File "/usr/local/bin/miniconda2/envs/myPythonEnv/lib/python3.7/site-packages/scanpy/plotting/_utils.py", line 542, in scatter_group color = adata.uns[key + '_colors'][imask] IndexError: list index out of range