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

added 3 cols for snp counts for ML

Browse source
This commit is contained in:
Tanushree Tunstall 2022-09-01 16:11:23 +01:00
parent 2bf91681b4
commit de9e6a709b
2 changed files with 6 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

5
scripts/ml/ml_functions/GetMLData.py
View file

@ -57,7 +57,10 @@ def getmldata(gene, drug
, 'dist_lineage_proportion'
#, 'lineage' # could be included as a category but it has L2;L4 formatting
, 'lineage_count_all'
, 'lineage_count_unique']
, 'lineage_count_unique'
, 'snp_frequency' # NEW
, 'df2_pos_count_all'# NEW
, 'pos_count'] # NEW
# X_gn_Fcat = ['drtype_mode_labels' # beware then you can't use it to predict [USED it for uq_v1, not v2]
# #, 'gene_name'] # will be required for the combined stuff

3
scripts/ml/ml_iterator_CVs.py Normal file → Executable file
View file

@ -15,7 +15,8 @@ homedir = os.path.expanduser("~")
sys.path.append(homedir + '/git/LSHTM_analysis/scripts/ml/ml_functions')
sys.path
###############################################################################
outdir = homedir + '/git/LSHTM_ML/output/genes/'
#outdir = homedir + '/git/LSHTM_ML/output/genes/'
outdir = homedir + '/git/Misc/'
#====================
# Import ML functions