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

iterator

Browse source
This commit is contained in:
Tanushree Tunstall 2022-07-10 12:33:17 +01:00
parent 01ff9d5be6
commit 4d5b848471
1 changed files with 36 additions and 31 deletions
Download patch file Download diff file Expand all files Collapse all files

53
scripts/ml/feature_selection_iterator.py
View file

@ -35,35 +35,37 @@ combined_model_paramD = {'data_combined_model' : False
#ml_genes = ["pncA", "embB", "katG", "rpoB", "gid"]
# outdir = homedir + '/git/Data/ml_combined/fs/'
ml_gene_drugD = {'pncA' : 'pyrazinamide'
# , 'embB' : 'ethambutol'
# , 'katG' : 'isoniazid'
# , 'rpoB' : 'rifampicin'
# , 'gid' : 'streptomycin'
ml_gene_drugD = {
'pncA' : 'pyrazinamide', # NOTE: may need re-run for 80_20 and sl
#'embB' : 'ethambutol',
#'katG' : 'isoniazid', #NOTE: RF only for all split-types actual
#'rpoB' : 'rifampicin',
#'gid' : 'streptomycin' # NOTE: for gid, run 'actual' on 80/20 and sl only
}
gene_dataD={}
# NOTE: for gid, run 'actual' on 80/20 and sl only
split_types = ['70_30', '80_20', 'sl']
split_data_types = ['actual', 'complete']
#split_types = ['70_30']
#split_types = ['70_30', '80_20', 'sl']
#split_data_types = ['actual', 'complete']
#fs_models = [('Logistic Regression' , LogisticRegression(**rs) )]
split_types = ['70_30']
#split_data_types = ['actual', 'complete']
split_data_types = ['actual']
fs_models = [
('Logistic Regression' , LogisticRegression(**rs) )
, ('Ridge Classifier' , RidgeClassifier(**rs) )
#, ('AdaBoost Classifier' , AdaBoostClassifier(**rs) )
#, ('Decision Tree' , DecisionTreeClassifier(**rs) )
#, ('Extra Tree' , ExtraTreeClassifier(**rs) )
#, ('Extra Trees' , ExtraTreesClassifier(**rs) )
#, ('Gradient Boosting' , GradientBoostingClassifier(**rs) )
#, ('LDA' , LinearDiscriminantAnalysis() )
#, ('Logistic RegressionCV' , LogisticRegressionCV(cv = 3, **rs))
#, ('Passive Aggresive' , PassiveAggressiveClassifier(**rs, **njobs) )
#, ('Random Forest' , RandomForestClassifier(**rs, n_estimators = 1000 ) )
#, ('Ridge ClassifierCV' , RidgeClassifierCV(cv = 3) )
#, ('Stochastic GDescent' , SGDClassifier(**rs, **njobs) )
#('Ridge Classifier' , RidgeClassifier(**rs) ),
#('Ridge ClassifierCV' , RidgeClassifierCV(cv = 3) ),
#('Logistic Regression' , LogisticRegression(**rs, **njobs) ),
#('AdaBoost Classifier' , AdaBoostClassifier(**rs) ),
#('Gradient Boosting' , GradientBoostingClassifier(**rs) ),
#('Stochastic GDescent' , SGDClassifier(**rs, **njobs) ),
#('Decision Tree' , DecisionTreeClassifier(**rs) ),
#('Extra Trees' , ExtraTreesClassifier(**rs, **njobs) ),
#('Extra Tree' , ExtraTreeClassifier(**rs) ),
#('LDA' , LinearDiscriminantAnalysis() ),
#('Logistic RegressionCV' , LogisticRegressionCV(cv = 3, **rs, **njobs) ),
#('Passive Aggresive' , PassiveAggressiveClassifier(**rs, **njobs) )
#('Random Forest' , RandomForestClassifier(n_estimators = 1000, verbose=3, **rs, **njobs ) )
('XGBoost' , XGBClassifier(verbosity=3, use_label_encoder=False, **rs, **njobs) )
]
for gene, drug in ml_gene_drugD.items():
@ -122,9 +124,10 @@ for gene, drug in ml_gene_drugD.items():
index = index+1
#out_fsD[model_name] = {}
current_model = {}
model_name_clean = model_name.replace(' ','-')
for k, v in paramD.items():
out_filename = gene.lower() + '_' + split_type + '_' + data_type + '_' + model_name + '_' + k + '.json'
out_filename = outdir + gene.lower() + '_' + split_type + '_' + data_type + '_' + model_name_clean + '_' + k + '.json'
fsD_params=paramD[k]
#out_fsD[model_name][k] = fsgs_rfecv(
@ -145,6 +148,8 @@ for gene, drug in ml_gene_drugD.items():
# write current model to disk
#print(current_model)
print("⚠️ ⚠️ ⚠️ WRITING TO FILE: ", out_filename, "⚠️ ⚠️ ⚠️'")
out_json = json.dumps(current_model)
with open(out_filename, 'w', encoding="utf-8") as file:
file.write(out_json)
print("⚠️ ⚠️ ⚠️ Finished writing to: ", out_filename, "⚠️ ⚠️ ⚠️'")