tanu/LSHTM_analysis
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

add chek for lin index duplicates before output

Browse source
This commit is contained in:
Tanushree Tunstall 2022-04-25 18:38:04 +01:00
parent 1371704685
commit 29e9d10e39
1 changed files with 2 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

2
scripts/data_extraction.py
View file

@ -1615,6 +1615,7 @@ else:
########################### ###########################
# magic merge happens here # magic merge happens here
########################### ###########################
# FIXME: add check here to see if the duplicated indices rows are actual duplicates as the cols I need should be summary cols
lf_lin_split.index.drop_duplicates(keep='first') lf_lin_split.index.drop_duplicates(keep='first')
lf_lin_split = lf_lin_split lf_lin_split = lf_lin_split
lf_lin_split_U = lf_lin_split[~lf_lin_split.index.duplicated(keep='first')] lf_lin_split_U = lf_lin_split[~lf_lin_split.index.duplicated(keep='first')]
@ -1640,4 +1641,5 @@ foo = gene_LF4[['mutationinformation', 'lineage', 'lineage_ucount'
, 'lineage_mode' , 'lineage_mode'
, 'lineage_list']] , 'lineage_list']]
#%% #%%
#Subset relevant columns for output and put the rest of the output here #Subset relevant columns for output and put the rest of the output here