Skip to content

Commit 356d4ed

Browse files
committed
update get_pmatrix to handle chunks
1 parent b02f0dd commit 356d4ed

File tree

1 file changed

+7
-0
lines changed

1 file changed

+7
-0
lines changed

src/oggmap/orthomap2tei.py

Lines changed: 7 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -766,6 +766,7 @@ def get_pmatrix(adata,
766766
"""
767767
adata_pmatrix_chunks = []
768768
all_phylostrata_chunks = []
769+
all_var_names_df_chunks = []
769770
all_id_age_df_keep_subset_chunks = []
770771
for i in range(0, adata.shape[0], chunk_size):
771772
adata_subset = adata[i:i+chunk_size]
@@ -799,6 +800,7 @@ def get_pmatrix(adata,
799800
adata_pmatrix_chunks.append(adata_pmatrix_chunk)
800801
all_phylostrata_chunks.append(phylostrata_chunk)
801802
all_id_age_df_keep_subset_chunks.append(id_age_df_keep_subset_chunk)
803+
all_var_names_df_chunks.append(var_names_df_chunk)
802804
adata_pmatrix = ad.concat(adata_pmatrix_chunks)
803805
if add_obs:
804806
for ko in adata.obs.keys():
@@ -809,6 +811,11 @@ def get_pmatrix(adata,
809811
right=adata.var[kv][adata.var_names.isin(all_id_age_df_keep_subset_chunks[0]['GeneID'])],
810812
left_index=True,
811813
right_index=True)[kv]
814+
adata_pmatrix.var['Phylostrata'] = list(pd.merge(left=pd.DataFrame(adata_pmatrix.var_names.values,
815+
columns=['GeneID']),
816+
right=all_var_names_df_chunks[0],
817+
how='left',
818+
on='GeneID')['Phylostrata'])
812819
return adata_pmatrix
813820

814821

0 commit comments

Comments
 (0)