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

added metadata output for running multiple models

Browse source
This commit is contained in:
Tanushree Tunstall 2022-06-23 21:25:00 +01:00
parent 5dea35f97c
commit 4fe62c072b
7 changed files with 325 additions and 88 deletions
Download patch file Download diff file Expand all files Collapse all files

11
scripts/ml/ml_data_7030.py
View file

@ -37,6 +37,8 @@ def setvars(gene,drug):
import argparse
import re
#%% GLOBALS
tts_split = "70/30"
rs = {'random_state': 42}
njobs = {'n_jobs': 10}
@ -58,12 +60,10 @@ def setvars(gene,drug):
, **rs)
mcc_score_fn = {'mcc': make_scorer(matthews_corrcoef)}
jacc_score_fn = {'jcc': make_scorer(jaccard_score)}
jacc_score_fn = {'jcc': make_scorer(jaccard_score)}
#%% FOR LATER: Combine ED logo data
###########################################################################
rs = {'random_state': 42}
njobs = {'n_jobs': 10}
homedir = os.path.expanduser("~")
geneL_basic = ['pnca']
@ -689,7 +689,8 @@ def setvars(gene,drug):
print('\n-------------------------------------------------------------'
, '\nSuccessfully split data: ALL features'
, '\nactual values: training set'
, '\nimputed values: blind test set'
, '\nSplit:', tts_split
#, '\nimputed values: blind test set'
, '\n\nTotal data size:', len(X) + len(X_bts)