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

resolving missing mutation info in combining script

Browse source
This commit is contained in:
Tanushree Tunstall 2020-09-04 20:55:55 +01:00
parent d6552628e4
commit c48c5177ca
3 changed files with 87 additions and 17 deletions
Download patch file Download diff file Expand all files Collapse all files

4
scripts/or_kinship_link.py
View file

@ -104,7 +104,7 @@ or_df.columns
#%% snp_info file: master and gene specific ones
# gene info
info_df2 = pd.read_csv(gene_info, sep = '\t', header = 0) #447, 10
info_df2 = pd.read_csv(gene_info, sep = '\t', header = 0) #447, 11
#info_df2 = pd.read_csv(gene_info, sep = ',', header = 0) #447 10
mis_mut_cover = (info_df2['chromosome_number'].nunique()/info_df2['chromosome_number'].count()) * 100
print('*****RESULT*****'
@ -212,7 +212,7 @@ else:
#PENDING Jody's reply
# !!!!!!!!
# drop nan from dfm2_mis as these are not useful
# drop nan from dfm2_mis as these are not useful and JP confirmed the same
print('Dropping NAs before further processing...')
dfm2_mis = dfm2[dfm2['mut_type'].notnull()]
# !!!!!!!!