ValueError: Length mismatch: Expected 1050 rows, received array of length 2170 when trying to cluster cells #709
-
|
When clustering my cells after segmentation then pixel clustering, I receive this error. ValueError: Length mismatch: Expected 1050 rows, received array of length 2170
The only things I adjusted were my paths to specific directories, and the path to the cell_table_size_normalized.csv.
My cell_table dimensions are Any advice if I am applying the wrong cell_table or other table with incorrect dimensions? Thank you for all your help! |
Beta Was this translation helpful? Give feedback.
Replies: 2 comments 6 replies
-
|
@alex-l-kong any advice? |
Beta Was this translation helpful? Give feedback.
-
|
All of my values are 1! |
Beta Was this translation helpful? Give feedback.
-
|
@whitneyt1 hmm, seems like you have a lot of duplicate cell labels of 0 in each FOV too, which is likely causing the error. The easiest solution is to directly remove these label 0 cells from your cell table, they're likely background noise. Can you also ensure you have the most up-to-date version of our code ( |
Beta Was this translation helpful? Give feedback.
-
|
great. I updated and am still receiving the errors. Can I use |
Beta Was this translation helpful? Give feedback.
-
|
I would say wait until we've released the updated version of the codebase this week that resolves the size-zero cells error. That way we can be sure we're not troubleshooting something that's already been fixed |
Beta Was this translation helpful? Give feedback.
-
|
[@ngreenwald] I am also getting the similar issue with cell labels. Of the 32016 rows from a test set, I am seeing 16338 are labelled as "0". And then the remaining cell labels also skip numbers and there are duplicate labels. See attached.
|
Beta Was this translation helpful? Give feedback.
-
|
We've just made a new release that addresses this issue. Once you follow the instructions for updating, this should be resolved. I would recommend starting from the beginning of the whole pipeline in a clean folder to make sure you're using only updated files for all steps. |
Beta Was this translation helpful? Give feedback.
We've just made a new release that addresses this issue. Once you follow the instructions for updating, this should be resolved. I would recommend starting from the beginning of the whole pipeline in a clean folder to make sure you're using only updated files for all steps.