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

removed if clause for filenames

Browse source
This commit is contained in:
Tanushree Tunstall 2020-08-13 18:39:16 +01:00
parent 833e599550
commit 805868ce7e
1 changed files with 9 additions and 10 deletions
Download patch file Download diff file Expand all files Collapse all files

19
scripts/data_extraction.py
View file

@ -122,7 +122,7 @@ outdir = datadir + '/' + drug + '/' + 'output'
# input # input
#======= #=======
#in_filename_master_master = 'original_tanushree_data_v2.csv' #19k #in_filename_master_master = 'original_tanushree_data_v2.csv' #19k
in_filename_master = 'mtb_gwas_meta_v5.csv' #34k in_filename_master = 'mtb_gwas_meta_v6.csv' #35k
infile_master = datadir + '/' + in_filename_master infile_master = datadir + '/' + in_filename_master
print('Input file: ', infile_master print('Input file: ', infile_master
, '\n============================================================') , '\n============================================================')
@ -153,8 +153,7 @@ if in_filename_master == 'original_tanushree_data_v2.csv':
, drug , drug
, dr_muts_col , dr_muts_col
, other_muts_col]] , other_muts_col]]
else:
if in_filename_master == 'mtb_gwas_meta_v5.csv':
core_cols = ['id' core_cols = ['id'
, 'sample' , 'sample'
, 'patient_id' , 'patient_id'
@ -174,12 +173,13 @@ if in_filename_master == 'mtb_gwas_meta_v5.csv':
, 'hiv_status' , 'hiv_status'
, 'HIV_status' , 'HIV_status'
, 'tissue_type' , 'tissue_type'
, 'isolation_source'] , 'isolation_source'
, resistance_col]
variable_based_cols = [drug variable_based_cols = [drug
, dr_muts_col , dr_muts_col
, other_muts_col , other_muts_col]
, resistance_col] #, resistance_col]
cols_to_extract = core_cols + variable_based_cols cols_to_extract = core_cols + variable_based_cols
print('Extracting', len(cols_to_extract), 'columns from master data') print('Extracting', len(cols_to_extract), 'columns from master data')
@ -343,7 +343,7 @@ if in_filename_master == 'original_tanushree_data_v2.csv':
,'drtype' ,'drtype'
, drug , drug
, dr_muts_col]] , dr_muts_col]]
if in_filename_master == 'mtb_gwas_meta_v3.csv': else:
dr_based_cols = [drug, dr_muts_col] dr_based_cols = [drug, dr_muts_col]
cols_to_extract = core_cols + dr_based_cols cols_to_extract = core_cols + dr_based_cols
print('Extracting', len(cols_to_extract), 'columns from meta data') print('Extracting', len(cols_to_extract), 'columns from meta data')
@ -392,9 +392,8 @@ if in_filename_master == 'original_tanushree_data_v2.csv':
, 'sublineage' , 'sublineage'
, 'drtype' , 'drtype'
, drug , drug
, other_muts_col]] , other_muts_col]]
else:
if in_filename_master == 'mtb_gwas_meta_v3.csv':
other_based_cols = [drug, other_muts_col] other_based_cols = [drug, other_muts_col]
cols_to_extract = core_cols + other_based_cols cols_to_extract = core_cols + other_based_cols
print('Extracting', len(cols_to_extract), 'columns from meta data') print('Extracting', len(cols_to_extract), 'columns from meta data')