Closed hongruhu closed 1 year ago
Hi Hongru,
Thanks for your interest in our work. I downloaded the data scvi provided and find that they are encoded in the format of the dense matrices. Therefore, I think we need to transform the data into sparse matrices first, for example,
smfish = scvi.data.smfish()
cortex = scvi.data.cortex()
smfish.X = scipy.sparse.csr_matrix(smfish.X)
cortex.X = scipy.sparse.csr_matrix(cortex.X)
Then, we can preprocess and integrate the data.
Thanks, Kai
oh I see the issue. @caokai1073 thanks for clarifying!
Hi uniPort authors,
First, thanks your great work!
However, when I tried to run uniPort on the sample data provided by scvi-tools (
from scvi.data import smfish, cortex
), there was error reported.The error is due to the broadcast issue of the sparse matrix, which is led by the line 247 of the data_loader.py file.
x = scipy.sparse.vstack((x, scipy.sparse.hstack((x_c, x_s))))
I made the
x_s
toscipy.sparse.coo_matrix(x_s)
.At least for now, it runs okay, but not sure if it was just for me.
Thanks, Hongru