diff --git a/scripts/ml/feature_selection_iterator.py b/scripts/ml/feature_selection_iterator.py
index f4571b9..3340d41 100755
--- a/scripts/ml/feature_selection_iterator.py
+++ b/scripts/ml/feature_selection_iterator.py
@@ -9,7 +9,7 @@ import sys, os
 import pandas as pd
 import numpy as np
 import re
-#import prettyprint as pp    
+#import prettyprint as pp 
 ###############################################################################
 homedir = os.path.expanduser("~")
 sys.path.append(homedir + '/git/LSHTM_analysis/scripts/ml/ml_functions')
@@ -18,7 +18,7 @@ sys.path
 outdir = homedir + '/git/LSHTM_ML/output/fs/'
 
 #====================
-# Import ML functions 
+# Import ML functions
 #====================
 
 from MultClfs import *
@@ -27,43 +27,45 @@ from SplitTTS import *
 from FS import *
 # param dict for getmldata()
 combined_model_paramD = {'data_combined_model'   : False
-                    , 'use_or'                   : False
-                    , 'omit_all_genomic_features': False
-                    , 'write_maskfile'           : False
-                    , 'write_outfile'            : False }
+        , 'use_or'                   : False
+        , 'omit_all_genomic_features': False
+        , 'write_maskfile'           : False
+        , 'write_outfile'            : 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, "⚠️ ⚠️ ⚠️'")