Skip to content
Snippets Groups Projects
Commit 10fdccc3 authored by Hanna  JULIENNE's avatar Hanna JULIENNE
Browse files

remove duplicated index in imputed SNPs

parent 879e4dd9
No related branches found
No related tags found
No related merge requests found
......@@ -32,8 +32,15 @@ def realigned_zfiles_on_panel(ref_panel, zscore):
- ref_panel (pd.dataframe) : snp of reference on the imputed chromosome
- zscore (pd.dataframe):
"""
zscore.drop_duplicates(keep='first', inplace=True)
ref_panel.drop_duplicates(keep='first', inplace=True)
# Remove SNPs with duplicated index
print("Duplicated SNPs to be removed")
print(ref_panel[ref_panel.index.duplicated(keep='first')])
print(zscore[zscore.index.duplicated(keep='first')])
zscore = zscore[~zscore.index.duplicated(keep='first')]
ref_panel = ref_panel[~ref_panel.index.duplicated(keep='first')]
inter_id = zscore.index.intersection(ref_panel.index).drop_duplicates(keep='first')
zscore = zscore.loc[inter_id]
......@@ -41,7 +48,6 @@ def realigned_zfiles_on_panel(ref_panel, zscore):
zscore.sort_index(inplace=True)
sub_ref_panel.sort_index(inplace=True)
allele_inverted = (sub_ref_panel.Ref_all != zscore.A0)
zscore.loc[allele_inverted, "A0"] = sub_ref_panel.loc[allele_inverted].Ref_all
......
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment