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

updated ml_iterator function args

Browse source
This commit is contained in:
Tanushree Tunstall 2022-07-10 13:03:14 +01:00
parent 9594d0a328
commit e37442efd2
1 changed files with 20 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

25
scripts/ml/ml_iterator.py
View file

@ -24,6 +24,14 @@ from MultClfs import *
from GetMLData import *
from SplitTTS import *
skf_cv = StratifiedKFold(n_splits = 10
#, shuffle = False, random_state= None)
, shuffle = True,**rs)
#rskf_cv = RepeatedStratifiedKFold(n_splits = 10
# , n_repeats = 3
# , **rs)
# param dict for getmldata()
gene_model_paramD = {'data_combined_model' : False
, 'use_or' : False
@ -89,14 +97,21 @@ for gene, drug in ml_gene_drugD.items():
mmDD = {}
for k, v in paramD.items():
scoresD = MultModelsCl(**paramD[k]
, tts_split_type = split_type
, sel_cv = skf_cv
, blind_test_df = tempD['X_bts']
, blind_test_target = tempD['y_bts']
, scale_numeric = ['min_max']
, tts_split_type = split_type
, add_cm = True
, add_yn = True
, return_formatted_output = True)
, scale_numeric = ['min_max']
, run_blind_test = True
, blind_test_df = tempD['X_bts']
, blind_test_target = tempD['y_bts']
, return_formatted_output = True
, random_state = 42
, n_jobs = os.cpu_count()
)
mmDD[k] = scoresD
# Extracting the dfs from within the dict and concatenating to output as one df