def fix_variant_number_discrepancy(var_df, var_filt_df, filt_ids, ccert_ids, ccert, snvs):
n_to_assign = len(var_df)
var_df = pd.concat([var_df, var_filt_df])
var_in_ccert = np.array([var_id in ccert_ids for var_id in filt_ids])
var_filt_df = var_filt_df[var_in_ccert]
filt_ids = get_var_ids(var_filt_df, snvs)
ccert_in_df = np.array([cc_id in filt_ids for cc_id in ccert_ids])
ccert = ccert[ccert_in_df]
to_assign = np.concatenate([ np.array([True] * n_to_assign, dtype=bool),
np.invert(var_in_ccert) ])
var_df.index = range(len(var_df))
var_df = var_df[to_assign]
return(var_df, var_filt_df, ccert)
评论列表
文章目录