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

minor changes to run combined_model

Browse source
This commit is contained in:
Tanushree Tunstall 2022-07-10 13:23:13 +01:00
parent 057c98c2f1
commit 350be30f19
3 changed files with 13 additions and 22 deletions
Download patch file Download diff file Expand all files Collapse all files

17
scripts/ml/combined_model/cm_logo_skf.py
View file

@ -172,26 +172,25 @@ def CMLogoSkf(cm_input_df
cm_bts_y = cm_test_df.loc[:, target_var]
print('\nTEST data dim:' , cm_bts_X.shape
, '\nTEST Target dim:', cm_bts_y.shape)
, '\nTEST Target dim:' , cm_bts_y.shape)
print("Running Multiple models on LOGO with SKF")
#%%:Running Multiple models on LOGO with SKF
cD3_v2 = MultModelsCl_logo_skf(input_df = cm_X
, target = cm_y
#, group = 'none'
, sel_cv = skf_cv
, blind_test_df = cm_bts_X
, blind_test_target = cm_bts_y
, tts_split_type = tts_split_type
, tts_split_type = tts_split_type
, resampling_type = 'none' # default
#, group = 'none'
, add_cm = True
, add_yn = True
, var_type = 'mixed'
, scale_numeric = ['min_max']
, run_blind_test = True
, blind_test_df = cm_bts_X
, blind_test_target = cm_bts_y
, return_formatted_output = True
, random_state = 42
, n_jobs = os.cpu_count() # the number of jobs should equal the number of CPU cores

5
scripts/ml/combined_model/running_ml_scripts.txt
View file

@ -1,7 +1,6 @@
########################################################################
# COMBINED Model
########################################################################
time ./cm_logo_skf.py 2>&1 | tee log_cm_skf.txt
time ./cm_logo_skf.py 2>&1 | tee cm_skf-$(date --iso).log

13
scripts/ml/ml_functions/MultClfs_logo_skf.py
View file

@ -90,10 +90,11 @@ scoring_fn = ({ 'mcc' : make_scorer(matthews_corrcoef)
, 'roc_auc' : make_scorer(roc_auc_score)
, 'jcc' : make_scorer(jaccard_score)
})
# for sel_cv
#skf_cv = StratifiedKFold(n_splits = 10
# #, shuffle = False, random_state= None)
# , shuffle = True,**rs)
# , shuffle = True, **rs)
#rskf_cv = RepeatedStratifiedKFold(n_splits = 10
# , n_repeats = 3
@ -188,15 +189,7 @@ def MultModelsCl_logo_skf(input_df
#%% Func globals
rs = {'random_state': random_state}
njobs = {'n_jobs': n_jobs}
skf_cv = StratifiedKFold(n_splits = 10
#, shuffle = False, random_state= None)
, shuffle = True,**rs)
rskf_cv = RepeatedStratifiedKFold(n_splits = 10
, n_repeats = 3
, **rs)
logo = LeaveOneGroupOut()
# select CV type:
# if group == None: