ValueError: Value passed for key 'X_umap' is of incorrect shape. Values of obsm must match dimensions (0,) of parent.

[Kalpi-ds]

Hi @basilkhuder
Thank you for the tutorial.
I am trying to get RNA velocity for two samples (I have 30 samples, I am using only 2 for testing)
Following is my code.
NDN = C19_P1_NDN.concatenate(C19_P2_NDN) #concatenate the two filtered loom files in an annData object
NDN.obs.index
NDN_index = pd.DataFrame(NDN.obs.index)
NDN_index = NDN_index.rename(columns = {0:'Cell_ID'}) #change the column name from 0 to Cell_ID)
umap_cord.insert(0, 'Cell_ID', cellID_obs ['x']) #adding Cell_ID column into umap coordinates csv file
umap_ordered = NDN_index.merge(umap_cord, on = "Cell_ID") #merge based on Cell_ID
umap_ordered = umap_ordered.iloc[:,1:]
NDN.obsm['X_umap'] = umap_ordered.values

ValueError: Value passed for key 'X_umap' is of incorrect shape. Values of obsm must match dimensions (0,) of parent. Value had shape (0, 2) while it should have had (14872,).

I think the error is at merge step because. I am merging the data frame NDN_index with umap_cord based on Cell_ID but not the actual annData object NDN. It is not clear for me what to do at this point in tutorial.
I really appreciate your help here.