diff --git a/imports_v1.py b/imports_v1.py
new file mode 100644
index 0000000..aea85bc
--- /dev/null
+++ b/imports_v1.py
@@ -0,0 +1,229 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Sun Mar  6 13:41:54 2022
+
+@author: tanu
+"""
+import os, sys
+import pandas as pd
+import numpy as np
+#from copy import deepcopy
+from sklearn import linear_model
+from sklearn.linear_model import LogisticRegression, LinearRegression
+from sklearn.naive_bayes import BernoulliNB
+from sklearn.neighbors import KNeighborsClassifier
+from sklearn.svm import SVC
+from sklearn.tree import DecisionTreeClassifier
+from sklearn.ensemble import RandomForestClassifier, ExtraTreesClassifier
+from sklearn.neural_network import MLPClassifier
+from xgboost import XGBClassifier
+from sklearn.preprocessing import StandardScaler, MinMaxScaler, OneHotEncoder
+
+from sklearn.compose import ColumnTransformer
+from sklearn.compose import make_column_transformer
+
+from sklearn.metrics import confusion_matrix, accuracy_score, precision_score, recall_score 
+from sklearn.metrics import roc_auc_score, roc_curve, f1_score, matthews_corrcoef
+from sklearn.metrics import make_scorer
+from sklearn.metrics import classification_report
+
+
+from sklearn.metrics import average_precision_score
+
+from sklearn.model_selection import cross_validate
+from sklearn.model_selection import train_test_split
+from sklearn.model_selection import StratifiedKFold
+
+from sklearn.pipeline import Pipeline
+from sklearn.pipeline import make_pipeline
+
+from sklearn.feature_selection import RFE
+from sklearn.feature_selection import RFECV
+
+import itertools
+import seaborn as sns
+import matplotlib.pyplot as plt
+import numpy as np
+print(np.__version__)
+print(pd.__version__)
+from statistics import mean, stdev, median, mode
+
+#%%
+homedir = os.path.expanduser("~")
+os.chdir(homedir + "/git/ML_AI_training/")
+
+# my function
+from MultClassPipe import MultClassPipeline
+from MultClassPipe2 import MultClassPipeline2
+from loopity_loop import MultClassPipeSKF
+
+gene = 'pncA'
+drug = 'pyrazinamide'
+
+#==============
+# directories
+#==============
+datadir = homedir + '/git/Data/'
+indir   = datadir + drug + '/input/'
+outdir  = datadir + drug + '/output/'
+
+#=======
+# input
+#=======
+infile_ml1 = outdir + gene.lower() + '_merged_df3.csv' 
+#infile_ml2 = outdir + gene.lower() + '_merged_df2.csv'
+
+my_df = pd.read_csv(infile_ml1)
+my_df.dtypes
+my_df_cols = my_df.columns
+
+geneL_basic     = ['pnca']
+geneL_na        = ['gid']
+geneL_na_ppi2   = ['rpob']
+geneL_ppi2      = ['alr', 'embb', 'katg']
+#%% get cols
+mycols = my_df.columns
+
+my_df['active_aa_pos'].dtype
+my_df['active_aa_pos'] = my_df['active_aa_pos'].astype(object)
+
+if gene.lower() in geneL_na_ppi2:
+    #D1148 get rid of
+    na_index = my_df['mutationinformation'].index[my_df['mcsm_na_affinity'].apply(np.isnan)]
+    my_df = my_df.drop(index=na_index)
+
+#%%============================================================================
+# GET Y
+
+# Target1: mutation_info_labels
+dm_om_map = {'DM': 1, 'OM': 0}
+target1 = my_df['mutation_info_labels'].map(dm_om_map)
+target1.value_counts()
+
+# Target2: drug
+drug_labels = drug + '_labels'
+drug_labels
+my_df[drug_labels] = my_df[drug].map({1: 'resistant', 0: 'sensitive'})
+my_df[drug_labels].value_counts()
+my_df[drug_labels] = my_df[drug_labels].fillna('unknown')
+my_df[drug_labels].value_counts()
+target2 = my_df[drug_labels]
+
+# Target3: drtype [Binary]
+drtype_labels = 'drtype_labels'
+my_df[drtype_labels] = my_df['drtype'].map({'Sensitive'      : 0
+                                                 , 'Other'   : 0
+                                                 , 'Pre-MDR' : 1
+                                                 , 'MDR'     : 1
+                                                 , 'Pre-XDR' : 1
+                                                 , 'XDR'     : 1})
+# target3 = 'drtype' [Multinomial]
+target3 = my_df[drtype_labels]
+
+# target4
+drtype_labels2 = 'drtype_labels2'
+my_df[drtype_labels2] = my_df['drtype'].map({'Sensitive'     : 0
+                                                 , 'Other'   : 0
+                                                 , 'Pre-MDR' : 1
+                                                 , 'MDR'     : 1
+                                                 , 'Pre-XDR' : 2
+                                                 , 'XDR'     : 2})
+target4 = my_df[drtype_labels2]
+
+# sanity checks
+target1.value_counts()
+my_df['mutation_info_labels'].value_counts()
+
+target2.value_counts()
+my_df[drug_labels].value_counts()
+
+target3.value_counts()
+my_df['drtype'].value_counts()
+target4.value_counts()
+my_df['drtype'].value_counts()
+
+#%%
+# GET X
+common_cols_stabiltyN = ['ligand_distance'
+           , 'ligand_affinity_change'
+           , 'duet_stability_change'
+           , 'ddg_foldx'
+           , 'deepddg'
+           , 'ddg_dynamut2']
+
+# Build stability columns ~ gene
+if gene.lower() in geneL_basic:
+    x_stabilityN = common_cols_stabiltyN
+    
+if gene.lower() in geneL_ppi2:
+    x_stabilityN = common_cols_stabiltyN + ['mcsm_ppi2_affinity'
+                                               , 'interface_dist'] 
+if gene.lower() in geneL_na:
+    x_stabilityN = common_cols_stabiltyN + ['mcsm_na_affinity'] 
+
+if gene.lower() in geneL_na_ppi2:
+    x_stabilityN = common_cols_stabiltyN + ['mcsm_na_affinity'] + ['mcsm_ppi2_affinity', 'interface_dist'] 
+    #D1148 get rid of
+    #na_index = my_df['mutationinformation'].index[my_df['mcsm_na_affinity'].apply(np.isnan)]
+    #my_df = my_df.drop(index=na_index)
+    
+X_strFN =  ['asa'
+           , 'rsa'
+           , 'kd_values'
+           , 'rd_values']    
+
+X_evolFN =  ['consurf_score'
+           , 'snap2_score'
+           , 'snap2_accuracy_pc']
+
+# TODO: ADD ED values
+# Problematic due to NA: filling NA with unknown or string will make it categorical
+# OPTIONS
+# 1. Imputing: KNN or MICE or from distribution
+# 2. Fill na with median or mode
+# 3. Separate datset without including genomic features AT ALL for ML, then using this as a 'blind test set'
+    # this means the size of the training data gets reduced!
+# 4. Remove genomic features from ML COMPLETELEY!
+
+# X_genomicFN =  ['af'
+#            , 'or_mychisq'
+#            , 'or_logistic'
+#            , 'or_fisher'
+#            , 'pval_fisher']
+
+#%% try combinations
+X_vars1 = my_df[x_stabilityN] 
+X_vars2 = my_df[X_strFN] 
+X_vars3 = my_df[X_evolFN] 
+
+X_vars5  = my_df[x_stabilityN + X_strFN]
+X_vars6  = my_df[x_stabilityN + X_evolFN]
+#X_vars7  = my_df[x_stabilityN + X_genomicFN]
+X_vars8  = my_df[X_strFN + X_evolFN]
+#X_vars9  = my_df[X_strFN + X_genomicFN]
+#X_vars10 = my_df[X_evolFN + X_genomicFN]
+X_vars11 = my_df[x_stabilityN + X_strFN + X_evolFN]
+#X_vars12 = my_df[x_stabilityN + X_strFN + X_evolFN + X_genomicFN]
+
+numerical_features_names = x_stabilityN + X_strFN + X_evolFN
+
+# separate ones for foldx?
+categorical_features_names = ['ss_class'
+                           , 'wt_prop_water'
+                          # , 'lineage_labels' # misleading if using merged_df3
+                           , 'mut_prop_water'
+                           , 'wt_prop_polarity'
+                           , 'mut_prop_polarity'
+                           , 'wt_calcprop'
+                           , 'mut_calcprop'
+                           , 'active_aa_pos']
+
+numerical_features_df = my_df[numerical_features_names]
+numerical_features_df.shape
+
+categorical_features_df = my_df[categorical_features_names]
+categorical_features_df.shape
+
+all_features_df = my_df[numerical_features_names + categorical_features_names]
+all_features_df.shape
diff --git a/loopity_loop_CALL.py b/loopity_loop_CALL.py
index 72d33b0..5f8833a 100644
--- a/loopity_loop_CALL.py
+++ b/loopity_loop_CALL.py
@@ -19,11 +19,6 @@ model_name = 'Logistic Regression'
 model_name = 'Naive Bayes'
 model_name = 'K-Nearest Neighbors'
 model_name = 'SVM'
-
-
-
-
-
 #%%
 model_metric = 'F1_score'
 
@@ -48,10 +43,9 @@ print(log_reg_mccM)
 
 log_reg_mccdf = pd.DataFrame({model_name: [log_reg_mccM]}, index = [model_metric])
 log_reg_mccdf
-
 #%%
-
-
+################################################################
+# extract items from wwithin a nested dict
 #%% Classification Metrics we need to mean()
 classification_metrics = {
     'F1_score': []
diff --git a/loopity_loop_CALL_single b/loopity_loop_CALL_single
new file mode 100644
index 0000000..4916d2b
--- /dev/null
+++ b/loopity_loop_CALL_single
@@ -0,0 +1,90 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Fri Mar 11 11:15:50 2022
+
+@author: tanu
+"""
+#%%
+del(t3_res)
+t3_res = MultClassPipeSKF(input_df = numerical_features_df
+                          , y_targetF = target1
+                          , var_type = 'numerical'
+                          , skf_splits = 10)
+pp.pprint(t3_res)
+#print(t3_res)
+
+#%% Manually: mean for each model, each metric
+model_name = 'Logistic Regression'
+model_name = 'Naive Bayes'
+model_name = 'K-Nearest Neighbors'
+model_name = 'SVM'
+
+#%%
+model_metric = 'F1_score'
+
+log_reg_f1 = []
+for key in t3_res[model_name]:
+    log_reg_f1.append(t3_res[model_name][key][model_metric])
+    log_reg_f1M = mean(log_reg_f1)
+    print('key:', key, model_metric, ':', log_reg_f1)
+print(log_reg_f1M)
+
+log_reg_f1df = pd.DataFrame({model_name: [log_reg_f1M]}, index = [model_metric])
+log_reg_f1df
+
+#%%
+model_metric = 'MCC'
+log_reg_mcc = []
+for key in t3_res[model_name]:
+    log_reg_mcc.append(t3_res[model_name][key][model_metric])
+    log_reg_mccM = mean(log_reg_mcc)
+    print('key:', key, model_metric, ':', log_reg_mcc)
+print(log_reg_mccM)
+
+log_reg_mccdf = pd.DataFrame({model_name: [log_reg_mccM]}, index = [model_metric])
+log_reg_mccdf
+#%%
+model_metric = 'Precision'
+log_reg_pres = []
+for key in t3_res[model_name]:
+    log_reg_pres.append(t3_res[model_name][key][model_metric])
+    log_reg_presM = mean(log_reg_pres)
+    print('key:', key, model_metric, ':', log_reg_pres)
+print(log_reg_presM)
+
+log_reg_presdf = pd.DataFrame({model_name: [log_reg_presM]}, index = [model_metric])
+log_reg_presdf
+#%%
+model_metric = 'Recall'
+log_reg_recall = []
+for key in t3_res[model_name]:
+    log_reg_recall.append(t3_res[model_name][key][model_metric])
+    log_reg_recallM = mean(log_reg_recall)
+    print('key:', key, model_metric, ':', log_reg_recall)
+print(log_reg_recallM)
+
+log_reg_recalldf = pd.DataFrame({model_name: [log_reg_recallM]}, index = [model_metric])
+log_reg_recalldf
+#%%
+model_metric = 'Accuracy'
+log_reg_accu = []
+for key in t3_res[model_name]:
+    log_reg_accu.append(t3_res[model_name][key][model_metric])
+    log_reg_accuM = mean(log_reg_accu)
+    print('key:', key, model_metric, ':', log_reg_accu)
+print(log_reg_accuM)
+
+log_reg_accudf = pd.DataFrame({model_name: [log_reg_accuM]}, index = [model_metric])
+log_reg_accudf
+#%% 
+model_metric = 'ROC_AUC'
+log_reg_roc_auc = []
+for key in t3_res[model_name]:
+    log_reg_roc_auc.append(t3_res[model_name][key][model_metric])
+    log_reg_roc_aucM = mean(log_reg_roc_auc)
+    print('key:', key, model_metric, ':', log_reg_roc_auc)
+print(log_reg_roc_aucM)
+
+log_reg_roc_aucdf = pd.DataFrame({model_name: [log_reg_roc_aucM]}, index = [model_metric])
+log_reg_roc_aucdf
\ No newline at end of file