added combined model FS code and run script

scripts/ml/boruta_test_clfs.py

@@ -0,0 +1,121 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Fri Sep  2 16:10:44 2022
+
+@author: tanu
+"""
+from sklearn.ensemble import VotingClassifier
+from sklearn.ensemble import BaggingClassifier
+from sklearn.ensemble import AdaBoostClassifier, RandomForestClassifier, ExtraTreesClassifier
+from boruta import BorutaPy
+
+fooD = combined_DF_OS(combined_df)
+
+numerical_ix = fooD['X'].select_dtypes(include=['int64', 'float64']).columns
+numerical_ix
+print("\nNo. of numerical indices:", len(numerical_ix))
+
+categorical_ix = fooD['X'].select_dtypes(include=['object', 'bool']).columns
+categorical_ix  
+print("\nNo. of categorical indices:", len(categorical_ix))
+
+
+var_type = "mixed"
+
+if var_type == 'mixed':
+   
+    t = [('num', MinMaxScaler(), numerical_ix)
+         , ('cat', OneHotEncoder(), categorical_ix)]
+    
+col_transform = ColumnTransformer(transformers = t
+                                   , remainder='passthrough')
+#--------------ALEX help
+# col_transform
+# col_transform.fit(X)
+# test = col_transform.transform(X)
+# print(col_transform.get_feature_names_out())
+
+# foo = col_transform.fit_transform(X)
+Xm_train = col_transform.fit_transform(fooD['X'])
+fooD['X'].shape
+Xm_train.shape
+
+Xm_test = col_transform.fit_transform(fooD['X_bts'])
+fooD['X_bts'].shape
+Xm_test.shape
+
+X_train = Xm_train.copy()
+X_test = Xm_test.copy()
+X_train.shape
+X_test.shape
+
+y_train = fooD['y']
+y_test = fooD['y_bts']
+y_train.shape
+y_test.shape
+
+# perhaps
+#col_transform.fit(fooD['X'])
+#encoded_colnames = pd.Index(col_transform.get_feature_names_out())
+#======================
+#  1 model
+n_jobs = os.cpu_count() 
+njobs = {'n_jobs': n_jobs }
+rs    = {'random_state': 42}
+
+rf_all_features = RandomForestClassifier(n_estimators=1000, max_depth=5
+                                         , **rs, **njobs)
+
+#rf_all_features = VotingClassifier(estimators=1000)
+rf_all_features = BaggingClassifier(random_state=1, n_estimators=100, verbose = 3, **njobs)
+rf_all_features = AdaBoostClassifier(random_state=1, n_estimators=1000)
+rf_all_features = ExtraTreesClassifier(random_state=1, n_estimators=1000, max_depth=5, verbose = 3)
+rf_all_features = DecisionTreeClassifier(random_state=1, max_depth=5)
+
+
+rf_all_features.fit(X_train, np.array(y_train))
+accuracy_score(y_test, rf_all_features.predict(X_test))
+matthews_corrcoef(y_test, rf_all_features.predict(X_test))
+
+# BORUTA
+boruta_selector = BorutaPy(rf_all_features,**rs, verbose = 3)
+boruta_selector.fit(np.array(X_train), np.array(y_train))  
+
+# Tells you how many features: GOOD
+print("Ranking: ", boruta_selector.ranking_)          
+print("No. of significant features: ", boruta_selector.n_features_) 
+
+
+cm_df = combined_df.drop(['gene_name', 'dst', 'dst_mode'], axis = 1)
+col_transform.fit(cm_df)
+col_transform.get_feature_names_out()
+    
+var_type_colnames = col_transform.get_feature_names_out()
+var_type_colnames = pd.Index(var_type_colnames)
+    
+if var_type == 'mixed':
+        print('\nVariable type is:', var_type
+              , '\nNo. of columns in input_df:', len(cm_df.columns)
+              , '\nNo. of columns post one hot encoder:', len(var_type_colnames))
+else:
+        print('\nNo. of columns in input_df:', len(input_df.columns))
+
+
+selected_rf_features = pd.DataFrame({'Feature':list(var_type_colnames),
+                                       'Ranking':boruta_selector.ranking_})
+sel_rf_features_sorted = selected_rf_features.sort_values(by='Ranking')
+
+
+sel_features = var_type_colnames[boruta_selector.support_]
+
+
+# tells you the ranking: GOOD
+#foo2 = selected_rf_features.sort_values(by='Ranking')
+
+X_important_train = boruta_selector.transform(np.array(X_train))
+X_important_test = boruta_selector.transform(np.array(X_test)) 
+
+rf_all_features.fit(X_important_train, y_train) 
+accuracy_score(y_test, rf_all_features.predict(X_important_test))
+matthews_corrcoef(y_test, rf_all_features.predict(X_important_test))

scripts/ml/combined_model/cm_logo_skf_FS.py

@@ -0,0 +1,280 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Wed Jun 29 19:44:06 2022
+
+@author: tanu
+"""
+import sys, os
+import pandas as pd
+import numpy as np
+import re
+from copy import deepcopy
+from sklearn import linear_model
+from sklearn import datasets
+from collections import Counter
+
+from sklearn.linear_model import LogisticRegression, LogisticRegressionCV
+from sklearn.linear_model import RidgeClassifier, RidgeClassifierCV, SGDClassifier, PassiveAggressiveClassifier
+
+from sklearn.naive_bayes import BernoulliNB
+from sklearn.neighbors import KNeighborsClassifier
+from sklearn.svm import SVC
+from sklearn.tree import DecisionTreeClassifier, ExtraTreeClassifier
+from sklearn.ensemble import RandomForestClassifier, ExtraTreesClassifier, AdaBoostClassifier, GradientBoostingClassifier, BaggingClassifier
+from sklearn.naive_bayes import GaussianNB
+from sklearn.gaussian_process import GaussianProcessClassifier, kernels
+from sklearn.gaussian_process.kernels import RBF, DotProduct, Matern, RationalQuadratic, WhiteKernel
+
+from sklearn.discriminant_analysis import LinearDiscriminantAnalysis, QuadraticDiscriminantAnalysis
+from sklearn.neural_network import MLPClassifier
+
+from sklearn.svm import SVC
+from xgboost import XGBClassifier
+from sklearn.naive_bayes import MultinomialNB
+from sklearn.preprocessing import StandardScaler, MinMaxScaler, OneHotEncoder
+
+from sklearn.compose import ColumnTransformer
+from sklearn.compose import make_column_transformer
+
+from sklearn.metrics import make_scorer, confusion_matrix, accuracy_score, balanced_accuracy_score, precision_score, average_precision_score, recall_score
+from sklearn.metrics import roc_auc_score, roc_curve, f1_score, matthews_corrcoef, jaccard_score, classification_report
+
+# added
+from sklearn.model_selection import train_test_split, cross_validate, cross_val_score, LeaveOneOut, KFold, RepeatedKFold, cross_val_predict
+
+from sklearn.model_selection import train_test_split, cross_validate, cross_val_score
+from sklearn.model_selection import StratifiedKFold,RepeatedStratifiedKFold, RepeatedKFold
+
+from sklearn.pipeline import Pipeline, make_pipeline
+
+from sklearn.feature_selection import RFE, RFECV
+
+import itertools
+import seaborn as sns
+import matplotlib.pyplot as plt
+
+from statistics import mean, stdev, median, mode
+
+from imblearn.over_sampling import RandomOverSampler
+from imblearn.under_sampling import RandomUnderSampler
+from imblearn.over_sampling import SMOTE
+from sklearn.datasets import make_classification
+from imblearn.combine import SMOTEENN
+from imblearn.combine import SMOTETomek
+
+from imblearn.over_sampling import SMOTENC
+from imblearn.under_sampling import EditedNearestNeighbours
+from imblearn.under_sampling import RepeatedEditedNearestNeighbours
+
+from sklearn.model_selection import GridSearchCV
+from sklearn.base import BaseEstimator
+from sklearn.impute import KNNImputer as KNN
+import json
+import argparse
+import re
+import itertools
+from sklearn.model_selection import LeaveOneGroupOut
+from boruta import BorutaPy
+
+###############################################################################
+# homedir = os.path.expanduser("~")
+# sys.path.append(homedir + '/git/LSHTM_analysis/scripts/ml/ml_functions')
+# sys.path
+###############################################################################
+#outdir = "/home/tanu/git/LSHTM_ML/output/feature_selection/"
+
+#====================
+# Import ML functions 
+#====================
+#from ml_data_combined import *
+#from MultClfs import *
+#from GetMLData import *
+#from SplitTTS import *
+
+#skf_cv = StratifiedKFold(n_splits = 10 , shuffle = True, random_state = 42)
+
+#logo = LeaveOneGroupOut()
+
+########################################################################
+# COMPLETE data: No tts_split
+########################################################################
+#%%
+def CMLogoSkf_FS(cm_input_df
+        , all_genes =  ["embb", "katg", "rpob", "pnca", "gid", "alr"]
+        , bts_genes = ["embb", "katg", "rpob", "pnca", "gid"]
+        , cols_to_drop = ['dst', 'dst_mode', 'gene_name']
+        , target_var = 'dst_mode'
+        , gene_group = 'gene_name'
+        , std_gene_omit = []
+        , var_type = ['numerical', 'categorical','mixed']
+
+        ):
+    
+    n_jobs = os.cpu_count() 
+    njobs = {'n_jobs': n_jobs }
+    rs    = {'random_state': 42}
+    
+    cm_gene_featuresD = {}
+    for bts_gene in bts_genes:
+        print('\n BTS gene:', bts_gene)
+        if not std_gene_omit:
+            training_genesL = ['alr']
+        else:
+            training_genesL = []
+            
+        tr_gene_omit = std_gene_omit + [bts_gene]
+        n_tr_genes = (len(bts_genes) - (len(std_gene_omit)))
+        #n_total_genes = (len(bts_genes) - len(std_gene_omit))
+        n_total_genes = len(all_genes)
+        
+        training_genesL = training_genesL + list(set(bts_genes) - set(tr_gene_omit))
+        #training_genesL = [element for element in bts_genes if element not in tr_gene_omit]
+    
+        print('\nTotal genes: ', n_total_genes
+              ,'\nTraining on:', n_tr_genes
+              ,'\nTraining on genes:', training_genesL
+              , '\nOmitted genes:', tr_gene_omit
+              , '\nBlind test gene:', bts_gene) 
+        
+        print('\nDim of data:', cm_input_df.shape)
+            
+        tts_split_type = "logo_skf_BT_" + bts_gene
+                           
+        #-------
+        # training
+        #------
+        cm_training_df = cm_input_df[~cm_input_df['gene_name'].isin(tr_gene_omit)]
+        
+        cm_X = cm_training_df.drop(cols_to_drop, axis=1, inplace=False)
+        #cm_y = cm_training_df.loc[:,'dst_mode']
+        cm_y = cm_training_df.loc[:, target_var]
+    
+        gene_group = cm_training_df.loc[:,'gene_name']
+        
+        print('\nTraining data dim:', cm_X.shape
+              , '\nTraining Target dim:', cm_y.shape)
+        
+        if all(cm_X.columns.isin(cols_to_drop) == False):
+            print('\nChecked training df does NOT have Target var')
+        else:
+            sys.exit('\nFAIL: training data contains Target var')
+        
+        #---------------
+        # BTS: genes
+        #---------------
+        cm_test_df = cm_input_df[cm_input_df['gene_name'].isin([bts_gene])]
+        
+        cm_bts_X = cm_test_df.drop(cols_to_drop, axis = 1, inplace = False)
+        #cm_bts_y = cm_test_df.loc[:, 'dst_mode']
+        cm_bts_y = cm_test_df.loc[:, target_var]
+    
+        print('\nTEST data dim:'     , cm_bts_X.shape
+              , '\nTEST Target dim:' , cm_bts_y.shape)
+        
+        print("Running Multiple models on LOGO with SKF")
+        
+        
+        # REASSIGN for simplicity
+        # X
+        X_train = cm_X.copy()
+        X_test = cm_bts_X.copy()
+        X_train.shape
+        X_test.shape
+        
+        # Y
+        y_train = cm_y.copy()
+        y_test = cm_bts_y.copy()
+        y_train.shape
+        y_test.shape
+        
+        
+##############################################################################
+       #PREPROCESS
+        
+        numerical_ix = X_train.select_dtypes(include=['int64', 'float64']).columns
+        numerical_ix
+        print("\nNo. of numerical indices:", len(numerical_ix))
+
+        categorical_ix = X_train.select_dtypes(include=['object', 'bool']).columns
+        categorical_ix  
+        print("\nNo. of categorical indices:", len(categorical_ix))
+
+        #======================================================
+        # Determine preprocessing steps ~ var_type
+        #======================================================
+        
+        if var_type  == 'numerical':
+            t = [('num', MinMaxScaler(), numerical_ix)]
+            
+        if var_type == 'categorical':
+            t = [('cat', OneHotEncoder(), categorical_ix)]
+            
+        if var_type  == 'mixed':
+            t = [('num', MinMaxScaler(), numerical_ix)
+                 , ('cat', OneHotEncoder(), categorical_ix)]            
+            
+        col_transform = ColumnTransformer(transformers = t
+                                           , remainder='passthrough')
+            
+        col_transform.fit(X_train)
+        col_transform.get_feature_names_out()
+            
+        var_type_colnames = col_transform.get_feature_names_out()
+        var_type_colnames = pd.Index(var_type_colnames)
+            
+        if var_type == 'mixed':
+                print('\nVariable type is:', var_type
+                      , '\nNo. of columns in input_df:', len(X_train.columns)
+                      , '\nNo. of columns post one hot encoder:', len(var_type_colnames))
+        else:
+                print('\nNo. of columns in input_df:', len(cm_input_df.columns))
+
+
+##############################################################################
+        # FS: Random Forest + Boruta
+        
+        X_train = col_transform.fit_transform(X_train)
+        X_test = col_transform.fit_transform(X_test)
+
+        fs_clf = "RandomForestClassifier"
+        rf_all_features = RandomForestClassifier(n_estimators=1000, max_depth=5
+                                                 , **rs, **njobs)
+        
+        # fit 
+        rf_all_features.fit(np.array(X_train), np.array(y_train))
+        print("RF, baseline MCC:", matthews_corrcoef(y_test, rf_all_features.predict(X_test)))
+
+        # BORUTA and fit
+        boruta_selector = BorutaPy(rf_all_features,**rs, verbose = 3)
+        boruta_selector.fit(np.array(X_train), np.array(y_train))  
+
+        # Get chosen features
+        print("Ranking: ", boruta_selector.ranking_)          
+        print("No. of significant features: ", boruta_selector.n_features_) 
+        
+        
+        X_important_train = boruta_selector.transform(np.array(X_train))
+        X_important_test = boruta_selector.transform(np.array(X_test)) 
+        
+        # just retesting with selected features on RF itselfs       
+        rf_all_features.fit(X_important_train, y_train) 
+        print("RF, Boruta MCC:", matthews_corrcoef(y_test, rf_all_features.predict(X_important_test)))
+        
+        selected_rf_features = pd.DataFrame({'Feature':list(var_type_colnames),
+                                               'Ranking':boruta_selector.ranking_})
+        
+        sel_rf_features_sorted = selected_rf_features.sort_values(by='Ranking')
+
+
+        sel_features = var_type_colnames[boruta_selector.support_]
+        cm_gene_featuresD.update({bts_gene: {
+            "sel_features": sel_features
+            , "fs_ranking" : sel_rf_features_sorted
+            , "fs_model_name": fs_clf
+            }
+            }
+            )
+        
+        
+    return(cm_gene_featuresD)

scripts/ml/combined_model/run_cm_logo.py

@@ -0,0 +1,32 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Sat Sep  3 09:43:22 2022
+
+@author: tanu
+"""
+
+###############################################################################
+homedir = os.path.expanduser("~")
+sys.path.append(homedir + '/home/tanu/git/LSHTM_analysis/scripts/ml/combined_model')
+sys.path.append(homedir + '/home/tanu/git/LSHTM_analysis/scripts/ml/ml_functions')
+sys.path.append(homedir + '/home/tanu/git/LSHTM_analysis/scripts/ml')
+
+from MultClfs import *
+###############################################################################
+
+#%%  RUN: Combined model Baseline
+outdir_cg = "/home/tanu/git/LSHTM_ML/output/combined/"
+#===============
+# Complete Data
+#===============
+CombinedModelML(cm_input_df = combined_df,  outdir = outdir_cg, file_suffix = "complete")
+CombinedModelML(cm_input_df = combined_df,  outdir = outdir_cg, std_gene_omit=['alr'], file_suffix = "complete")
+
+#===============
+# Actual Data
+#===============
+CombinedModelML(cm_input_df = combined_df_actual,  outdir = outdir_cg, file_suffix = "actual")
+CombinedModelML(cm_input_df = combined_df_actual,  outdir = outdir_cg, std_gene_omit=['alr'], file_suffix = "actual")
+
+

scripts/ml/combined_model/run_cm_logo_FS.py

@@ -0,0 +1,204 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Fri Sep  2 19:17:46 2022
+
+@author: tanu
+"""
+###############################################################################
+homedir = os.path.expanduser("~")
+sys.path.append(homedir + '/home/tanu/git/LSHTM_analysis/scripts/ml/combined_model')
+sys.path.append(homedir + '/home/tanu/git/LSHTM_analysis/scripts/ml/ml_functions')
+sys.path.append(homedir + '/home/tanu/git/LSHTM_analysis/scripts/ml')
+
+from MultClfs import *
+from cm_logo_skf_FS import *
+
+###############################################################################
+#%% FS with all genes in training
+###############################################################################
+
+# 1. Select Features
+boruta_features = CMLogoSkf_FS(cm_input_df = combined_df,var_type = 'mixed', file_suffix = "complete")
+
+# 2. Find original column names of features
+# if it starts with num__, get rid of num__
+# if it starts with cat__, get rid of cat__ and the _<number> at the end
+for i in boruta_features:
+    print(i)
+    boruta_features[i]['sel_features']=[re.sub('^num__|cat__(.*)_\d*$',r'\1', current_thing) for current_thing in boruta_features[i]['sel_features']]
+    boruta_features[i]['sel_features'] = list(set(boruta_features[i]['sel_features']))
+
+# write json
+OutFile_6Tgenes = "/home/tanu/git/LSHTM_ML/output/feature_selection/boruta_features_6_Tgenes.json"
+pd.DataFrame(boruta_features).to_json(path_or_buf=OutFile_6Tgenes)
+
+# 3. Run all classification models using original column names from (2)
+combined_df_embb=combined_df[boruta_features['embb']['sel_features']+['dst', 'dst_mode', 'gene_name']]
+combined_df_katg=combined_df[boruta_features['katg']['sel_features']+['dst', 'dst_mode', 'gene_name']]
+combined_df_pnca=combined_df[boruta_features['pnca']['sel_features']+['dst', 'dst_mode', 'gene_name']]
+combined_df_gid= combined_df[boruta_features['gid' ]['sel_features']+['dst', 'dst_mode', 'gene_name']]
+combined_df_rpob= combined_df[boruta_features['rpob' ]['sel_features']+['dst', 'dst_mode', 'gene_name']]
+
+
+# from /home/tanu/git/LSHTM_analysis/scripts/ml/ml_functions/MultClf.py
+CombinedModelML(combined_df_embb
+        , all_genes =  ["embb", "katg", "rpob", "pnca", "gid", "alr"]
+        , bts_genes = ["embb"]
+        , cols_to_drop = ['dst', 'dst_mode', 'gene_name']
+        , target_var = 'dst_mode'
+        , gene_group = 'gene_name'
+        , std_gene_omit = []
+        , output_dir = "/home/tanu/git/LSHTM_ML/output/feature_selection/"
+        , file_suffix = "FS"
+        )
+
+
+CombinedModelML(combined_df_katg
+        , all_genes =  ["embb", "katg", "rpob", "pnca", "gid", "alr"]
+        , bts_genes = ["katg"]
+        , cols_to_drop = ['dst', 'dst_mode', 'gene_name']
+        , target_var = 'dst_mode'
+        , gene_group = 'gene_name'
+        , std_gene_omit = []
+        , output_dir = "/home/tanu/git/LSHTM_ML/output/feature_selection/"
+        , file_suffix = "FS"
+        )
+
+
+CombinedModelML(combined_df_pnca
+        , all_genes =  ["embb", "katg", "rpob", "pnca", "gid", "alr"]
+        , bts_genes = ["pnca"]
+        , cols_to_drop = ['dst', 'dst_mode', 'gene_name']
+        , target_var = 'dst_mode'
+        , gene_group = 'gene_name'
+        , std_gene_omit = []
+        , output_dir = "/home/tanu/git/LSHTM_ML/output/feature_selection/"
+        , file_suffix = "FS"
+        )
+
+CombinedModelML(combined_df_gid
+        , all_genes =  ["embb", "katg", "rpob", "pnca", "gid", "alr"]
+        , bts_genes = ["gid"]
+        , cols_to_drop = ['dst', 'dst_mode', 'gene_name']
+        , target_var = 'dst_mode'
+        , gene_group = 'gene_name'
+        , std_gene_omit = []
+        , output_dir = "/home/tanu/git/LSHTM_ML/output/feature_selection/"
+        , file_suffix = "FS"
+        )
+
+CombinedModelML(combined_df_rpob
+        , all_genes =  ["embb", "katg", "rpob", "pnca", "gid", "alr"]
+        , bts_genes = ["rpob"]
+        , cols_to_drop = ['dst', 'dst_mode', 'gene_name']
+        , target_var = 'dst_mode'
+        , gene_group = 'gene_name'
+        , std_gene_omit = []
+        , output_dir = "/home/tanu/git/LSHTM_ML/output/feature_selection/"
+        , file_suffix = "FS"
+        )
+
+
+# write all feature rankings
+for i in boruta_features:
+    print (i)
+    gene_fs_ranking = boruta_features[i]['fs_ranking']
+    gene_fs_ranking.to_csv("/home/tanu/git/LSHTM_ML/output/feature_selection/"+ i + "_boruta_featues_6Tgenes.csv")
+   
+   
+###############################################################################
+#%% FS withour training including ALR
+###############################################################################
+# With training omitting alr
+boruta_features_omit_alr = CMLogoSkf_FS(cm_input_df = combined_df
+                                        , std_gene_omit = ['alr']
+                                        , var_type = 'mixed')
+
+# 2. Find original column names of features
+# if it starts with num__, get rid of num__
+# if it starts with cat__, get rid of cat__ and the _<number> at the end
+for i in boruta_features_omit_alr:
+    print(i)
+    boruta_features_omit_alr[i]['sel_features']=[re.sub('^num__|cat__(.*)_\d*$',r'\1', current_thing) for current_thing in boruta_features[i]['sel_features']]
+    boruta_features_omit_alr[i]['sel_features'] = list(set(boruta_features_omit_alr[i]['sel_features']))
+
+# write json
+OutFile_5Tgenes = "/home/tanu/git/LSHTM_ML/output/feature_selection/boruta_features_5_Tgenes.json"
+pd.DataFrame(boruta_features_omit_alr).to_json(path_or_buf=OutFile_5Tgenes)
+
+# 3. Run all classification models using original column names from (2)
+cm_input_df5 =  combined_df[~combined_df['gene_name'].isin(omit_gene_alr)]
+
+combined_df_embb_no_alr = cm_input_df5[boruta_features_omit_alr['embb']['sel_features']+['dst', 'dst_mode', 'gene_name']]
+combined_df_katg_no_alr = cm_input_df5[boruta_features_omit_alr['katg']['sel_features']+['dst', 'dst_mode', 'gene_name']]
+combined_df_pnca_no_alr = cm_input_df5[boruta_features_omit_alr['pnca']['sel_features']+['dst', 'dst_mode', 'gene_name']]
+combined_df_gid_no_alr  = cm_input_df5[boruta_features_omit_alr['gid' ]['sel_features']+['dst', 'dst_mode', 'gene_name']]
+combined_df_rpob_no_alr = cm_input_df5[boruta_features_omit_alr['rpob' ]['sel_features']+['dst', 'dst_mode', 'gene_name']]
+
+
+CombinedModelML(combined_df_embb_no_alr
+        , all_genes =  ["embb", "katg", "rpob", "pnca", "gid", "alr"]
+        , bts_genes = ["embb"]
+        , cols_to_drop = ['dst', 'dst_mode', 'gene_name']
+        , target_var = 'dst_mode'
+        , gene_group = 'gene_name'
+        , std_gene_omit = ["alr"]
+        , output_dir = "/home/tanu/git/LSHTM_ML/output/feature_selection/"
+        , file_suffix = "FS_no_Talr"
+        )
+
+
+CombinedModelML(combined_df_katg_no_alr
+        , all_genes =  ["embb", "katg", "rpob", "pnca", "gid", "alr"]
+        , bts_genes = ["katg"]
+        , cols_to_drop = ['dst', 'dst_mode', 'gene_name']
+        , target_var = 'dst_mode'
+        , gene_group = 'gene_name'
+        , std_gene_omit = ["alr"]
+        , output_dir = "/home/tanu/git/LSHTM_ML/output/feature_selection/"
+        , file_suffix = "FS_no_Talr"
+        )
+
+
+CombinedModelML(combined_df_pnca_no_alr
+        , all_genes =  ["embb", "katg", "rpob", "pnca", "gid", "alr"]
+        , bts_genes = ["pnca"]
+        , cols_to_drop = ['dst', 'dst_mode', 'gene_name']
+        , target_var = 'dst_mode'
+        , gene_group = 'gene_name'
+        , std_gene_omit = ["alr"]
+        , output_dir = "/home/tanu/git/LSHTM_ML/output/feature_selection/"
+        , file_suffix = "FS_no_Talr"
+        )
+
+CombinedModelML(combined_df_gid_no_alr
+        , all_genes =  ["embb", "katg", "rpob", "pnca", "gid", "alr"]
+        , bts_genes = ["gid"]
+        , cols_to_drop = ['dst', 'dst_mode', 'gene_name']
+        , target_var = 'dst_mode'
+        , gene_group = 'gene_name'
+        , std_gene_omit = ["alr"]
+        , output_dir = "/home/tanu/git/LSHTM_ML/output/feature_selection/"
+        , file_suffix = "FS_no_Talr"
+        )
+
+CombinedModelML(combined_df_rpob_no_alr
+        , all_genes =  ["embb", "katg", "rpob", "pnca", "gid", "alr"]
+        , bts_genes = ["rpob"]
+        , cols_to_drop = ['dst', 'dst_mode', 'gene_name']
+        , target_var = 'dst_mode'
+        , gene_group = 'gene_name'
+        , std_gene_omit = ["alr"]
+        , output_dir = "/home/tanu/git/LSHTM_ML/output/feature_selection/"
+        , file_suffix = "FS_no_Talr"
+        )
+
+
+# write all feature rankings
+for i in boruta_features_omit_alr:
+    print (i)
+    gene_fs_ranking_no_alr = boruta_features_omit_alr[i]['fs_ranking']
+    gene_fs_ranking_no_alr.to_csv("/home/tanu/git/LSHTM_ML/output/feature_selection/"+ i + "_boruta_featues_5Tgenes.csv")
+   
+   

scripts/ml/untitled5.py

@@ -0,0 +1,52 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Fri Sep  2 11:11:49 2022
+
+@author: tanu
+"""
+# https://towardsdatascience.com/explain-feature-variation-employing-pca-in-scikit-learn-6711e0a5c0b7
+from sklearn.decomposition import PCA
+#import tensorflow as tf
+#from tensorflow import keras
+import numpy as np
+import pandas as pd
+import seaborn as sns
+from sklearn.metrics import matthews_corrcoef
+
+# pca = PCA().fit(X)
+# plt.plot(np.cumsum(pca.explained_variance_ratio_))
+# plt.xlabel(‘number of components’)
+# plt.ylabel(‘cumulative explained variance’)
+
+# from old scripts
+fooD = combined_DF_OS(combined_df)
+
+numerical_ix = fooD['X'].select_dtypes(include=['int64', 'float64']).columns
+numerical_ix
+num_featuresL = list(numerical_ix)
+numerical_colind = fooD['X'].columns.get_indexer(list(numerical_ix) )
+numerical_colind
+
+numF = fooD['X'][numerical_ix]
+
+categorical_ix = fooD['X'].select_dtypes(include=['object', 'bool']).columns
+categorical_ix    
+categorical_colind = fooD['X'].columns.get_indexer(list(categorical_ix))
+categorical_colind
+
+##############
+
+X_train,X_test,y_train,y_test=train_test_split(numF,fooD['y'],test_size=0.2)
+
+pca=PCA(n_components=50) 
+X_train_new=pca.fit_transform(X_train)
+X_test_new=pca.transform(X_test)
+print(X_train.shape)
+print(X_train_new.shape)
+
+pca.explained_variance_ratio_
+clf=KNeighborsClassifier(n_neighbors=5)
+clf.fit(X_train_new,y_train)
+y_pred_new=clf.predict(X_test_new)
+matthews_corrcoef(y_test,y_pred_new)

scripts/ml/untitled6.py

@@ -0,0 +1,136 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Fri Sep  2 11:30:18 2022
+
+@author: tanu
+"""
+#https://github.com/yuneeham/PCA-and-feature-selection_sklearn/blob/main/Report%20-%20PCA%20and%20Feature%20Selection.pdf
+
+#Load Libraries 
+import numpy as np
+import pandas as pd
+from sklearn.decomposition import PCA
+from sklearn import datasets
+from sklearn.preprocessing import scale
+from sklearn.preprocessing import StandardScaler
+from sklearn.model_selection import train_test_split
+from sklearn.ensemble import RandomForestRegressor
+from sklearn import metrics
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.metrics import classification_report
+import matplotlib.pyplot as plt
+from sklearn.feature_selection import SelectFromModel
+
+#Load Data 
+df = pd.read_csv("/home/tanu/Downloads/data.csv")
+X = df.loc[:, ' ROA(C) before interest and depreciation before interest':' Equity to Liability'].values
+y = df.loc[:,['Bankrupt?']].values
+
+fn = df.loc[:, ' ROA(C) before interest and depreciation before interest':' Equity to Liability'].keys()
+
+#Scaler/normalize 
+scaler = StandardScaler()
+Xn = scaler.fit_transform(X)
+
+#PCA 
+pca_prep = PCA().fit(Xn)
+pca_prep.n_components_
+
+
+#PCA Explained Variance 
+pca_prep.explained_variance_
+plt.plot(pca_prep.explained_variance_ratio_)
+
+#Graph plot - PCA components 
+plt.plot(pca_prep.explained_variance_ratio_)
+plt.xlabel('k number of components')
+plt.ylabel('Explained variance')
+plt.grid(True)
+plt.show()
+
+#Number of components 
+n_pc = 17
+pca = PCA(n_components = n_pc).fit(Xn)
+Xp = pca.transform(Xn)
+print(f'After PCA, we use {pca.n_components_} components. \n')
+
+
+# Split the data into training and testing subsets.
+X_train, X_test, y_train, y_test = train_test_split(X,y,test_size =.2,random_state=1234,stratify=y)
+Xp_train, Xp_test, yp_train, yp_test = train_test_split(Xp,y,test_size =.2,random_state=1234,stratify=y)
+
+
+#Random Forest Model
+rfcm = RandomForestClassifier().fit(X_train, y_train) #Original Data
+rfcm_p = RandomForestClassifier().fit(Xp_train, yp_train) #Reduced Data
+
+
+#Prediction
+y_pred = rfcm.predict(X_test) 
+y_pred_p = rfcm_p.predict(Xp_test) 
+
+
+# Compare the performance of each mode
+report_original = classification_report(y_test, y_pred)
+report_pca = classification_report(yp_test, y_pred_p)
+print(f'Classification Report - original\n{report_original}')
+print(f'Classification Report - pca\n{report_pca}')
+
+
+
+## Feature selection and performance comparison 
+
+# Draw a bar chart to see the sorted importance values with feature names.
+# Horizontal Bar Chart 
+# %matplotlib auto
+# %matplotlib inline
+
+importances = rfcm.feature_importances_
+np.sum(importances)
+plt.barh(fn,importances)
+
+df_importances = pd.DataFrame(data=importances, index=fn, 
+                              columns=['importance_value'])
+df_importances.sort_values(by = 'importance_value', ascending=True, 
+                            inplace=True)
+
+plt.barh(df_importances.index,df_importances.importance_value)
+
+
+# Build a model with a subset of those features.  
+selector = SelectFromModel(estimator=RandomForestClassifier(),threshold=0.015)
+X_reduced = selector.fit_transform(X,y)
+selector.threshold_ 
+selected_TF = selector.get_support()
+print(f'\n** {selected_TF.sum()} features are selected.')  
+X_reduced.shape
+
+
+# Show those selected features.
+selected_features = []
+for i,j in zip(selected_TF, fn):
+    if i: selected_features.append(j)
+print(f'Selected Features: {selected_features}') 
+
+
+# First 5 features
+print(selected_features[0:5])
+
+
+# Build a model using those reduced number of features.
+X_reduced_train, X_reduced_test, y_reduced_train, y_reduced_test \
+       = train_test_split(X_reduced,y,test_size =.3, stratify=y)
+
+
+# Build a model with the reduced number of features.
+rfcm2 = RandomForestClassifier().fit(X_reduced_train, y_reduced_train)
+y_reduced_pred = rfcm2.predict(X_reduced_test)
+
+
+#Classification for Reduced Data 
+print('\nClassification Report after feature reduction\n')
+print(metrics.classification_report(y_reduced_test,y_reduced_pred))
+
+
+

scripts/ml/untitled7_boruta.py

@@ -0,0 +1,221 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Fri Sep  2 12:13:53 2022
+
+@author: tanu
+"""
+# https://analyticsindiamag.com/hands-on-guide-to-automated-feature-selection-using-boruta/
+import pandas as pd
+import numpy as np
+from sklearn.ensemble import RandomForestClassifier
+from boruta import BorutaPy
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import accuracy_score 
+from sklearn.metrics import matthews_corrcoef
+
+
+URL = "https://raw.githubusercontent.com/Aditya1001001/English-Premier-League/master/pos_modelling_data.csv"
+data = pd.read_csv(URL)
+data.info()
+X = data.drop('Position', axis = 1)
+y = data['Position']
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = .2, random_state = 1) 
+
+rf_all_features = RandomForestClassifier(random_state=1, n_estimators=1000, max_depth=5)
+rf_all_features.fit(X_train, y_train) 
+
+
+y_pred = rf_all_features.predict(X_test)
+
+accuracy_score(y_test, rf_all_features.predict(X_test))
+accuracy_score(y_test, y_pred)
+matthews_corrcoef(y_test, rf_all_features.predict(X_test))
+
+# BORUTA
+rfc = RandomForestClassifier(random_state=1, n_estimators=1000, max_depth=5)
+boruta_selector = BorutaPy(rfc, n_estimators='auto', verbose=2, random_state=1)
+boruta_selector.fit(np.array(X_train), np.array(y_train))  
+
+# Tells you how many features: GOOD
+print("Ranking: ",boruta_selector.ranking_)          
+print("No. of significant features: ", boruta_selector.n_features_) 
+
+selected_rf_features = pd.DataFrame({'Feature':list(X_train.columns),
+                                       'Ranking':boruta_selector.ranking_})
+
+# tells you the ranking: GOOD
+selected_rf_features.sort_values(by='Ranking') 
+
+X_important_train = boruta_selector.transform(np.array(X_train))
+X_important_test = boruta_selector.transform(np.array(X_test)) 
+
+rf_boruta = RandomForestClassifier(random_state=1, n_estimators=1000, max_depth=5)
+rf_boruta.fit(X_important_train, y_train) 
+accuracy_score(y_test, rf_boruta.predict(X_important_test))
+matthews_corrcoef(y_test, rf_boruta.predict(X_important_test))
+
+
+
+##############################################################################
+# my data : ONLY numerical values
+# from old scripts (cm_logo_skf_v2.py)
+fooD = combined_DF_OS(combined_df)
+
+allF = fooD['X']
+numerical_ix = fooD['X'].select_dtypes(include=['int64', 'float64']).columns
+numerical_ix
+# just numerical for X_train and X_test
+X_train_numF = fooD['X'][numerical_ix]
+X_test_numF = fooD['X_bts'][numerical_ix]
+#X_train = allF
+
+X_train = X_train_numF 
+X_test = X_test_numF
+
+y_train = fooD['y']
+y_test = fooD['y_bts']
+
+#  1 model
+rf_all_features = RandomForestClassifier(random_state=1, n_estimators=1000, max_depth=5)
+rf_all_features.fit(X_train, y_train) 
+
+accuracy_score(y_test, rf_all_features.predict(X_test))
+matthews_corrcoef(y_test, rf_all_features.predict(X_test))
+
+
+# BORUTA
+rfc = RandomForestClassifier(random_state=1, n_estimators=1000, max_depth=5)
+boruta_selector = BorutaPy(rfc, n_estimators='auto', verbose=2, random_state=1)
+boruta_selector.fit(np.array(X_train), np.array(y_train))  
+
+# Tells you how many features: GOOD
+print("Ranking: ",boruta_selector.ranking_)          
+print("No. of significant features: ", boruta_selector.n_features_) 
+
+selected_rf_features = pd.DataFrame({'Feature':list(X_train.columns),
+                                       'Ranking':boruta_selector.ranking_})
+
+# tells you the ranking: GOOD
+selected_rf_features.sort_values(by='Ranking') 
+
+X_important_train = boruta_selector.transform(np.array(X_train))
+X_important_test = boruta_selector.transform(np.array(X_test)) 
+
+rf_boruta = RandomForestClassifier(random_state=1, n_estimators=1000, max_depth=5)
+rf_boruta.fit(X_important_train, y_train) 
+accuracy_score(y_test, rf_boruta.predict(X_important_test))
+matthews_corrcoef(y_test, rf_boruta.predict(X_important_test))
+
+##############################################################################
+# my data : using both numerical and categorical
+# from old scripts (cm_logo_skf_v2.py)
+fooD = combined_DF_OS(combined_df)
+
+numerical_ix = fooD['X'].select_dtypes(include=['int64', 'float64']).columns
+numerical_ix
+print("\nNo. of numerical indices:", len(numerical_ix))
+
+categorical_ix = fooD['X'].select_dtypes(include=['object', 'bool']).columns
+categorical_ix  
+print("\nNo. of categorical indices:", len(categorical_ix))
+
+
+var_type = "mixeds"
+
+if var_type == 'mixed':
+   
+    t = [('num', MinMaxScaler(), numerical_ix)
+         , ('cat', OneHotEncoder(), categorical_ix)]
+    
+col_transform = ColumnTransformer(transformers = t
+                                   , remainder='passthrough')
+#--------------ALEX help
+# col_transform
+# col_transform.fit(X)
+# test = col_transform.transform(X)
+# print(col_transform.get_feature_names_out())
+
+# foo = col_transform.fit_transform(X)
+Xm_train = col_transform.fit_transform(fooD['X'])
+fooD['X'].shape
+Xm_train.shape
+
+Xm_test = col_transform.fit_transform(fooD['X_bts'])
+fooD['X_bts'].shape
+Xm_test.shape
+
+X_train = Xm_train.copy()
+X_test = Xm_test.copy()
+X_train.shape
+X_test.shape
+
+y_train = fooD['y']
+y_test = fooD['y_bts']
+y_train.shape
+y_test.shape
+
+# perhaps
+#col_transform.fit(fooD['X'])
+#encoded_colnames = pd.Index(col_transform.get_feature_names_out())
+#======================
+#  1 model
+rf_all_features = RandomForestClassifier(random_state=1, n_estimators=1000, max_depth=5)
+rf_all_features.fit(X_train, y_train) 
+
+accuracy_score(y_test, rf_all_features.predict(X_test))
+matthews_corrcoef(y_test, rf_all_features.predict(X_test))
+
+
+# BORUTA
+rfc = RandomForestClassifier(random_state=1, n_estimators=1000, max_depth=5)
+boruta_selector = BorutaPy(rfc, n_estimators='auto', verbose=2, random_state=1)
+boruta_selector.fit(np.array(X_train), np.array(y_train))  
+
+# Tells you how many features: GOOD
+print("Ranking: ",boruta_selector.ranking_)          
+print("No. of significant features: ", boruta_selector.n_features_) 
+
+#selected_rf_features = pd.DataFrame({'Feature':list(X_train.columns),
+#                                       'Ranking':boruta_selector.ranking_})
+
+# tells you the ranking: GOOD
+foo2 = selected_rf_features.sort_values(by='Ranking') 
+
+X_important_train = boruta_selector.transform(np.array(X_train))
+X_important_test = boruta_selector.transform(np.array(X_test)) 
+
+rf_boruta = RandomForestClassifier(random_state=1, n_estimators=1000, max_depth=5)
+rf_boruta.fit(X_important_train, y_train) 
+accuracy_score(y_test, rf_boruta.predict(X_important_test))
+matthews_corrcoef(y_test, rf_boruta.predict(X_important_test))
+##################################
+# trying to one hot encode at start
+# perhaps
+#col_transform.fit(fooD['X'])
+#encoded_colnames = pd.Index(col_transform.get_feature_names_out())
+
+# def encode_and_bind(original_dataframe, feature_to_encode):
+#     dummies = pd.get_dummies(original_dataframe[[feature_to_encode]])
+#     res = pd.concat([original_dataframe, dummies], axis=1)
+#     res = res.drop([feature_to_encode], axis=1)
+#     return(res) 
+
+# features_to_encode = ['feature_1', 'feature_2', 'feature_3',
+#                       'feature_4']
+
+# features_to_encode = list(categorical_ix.copy())
+
+# for feature in features_to_encode:
+#     X_train_enc = encode_and_bind(fooD['X'], feature)
+#     X_test_enc  = encode_and_bind(fooD['X_bts'], feature)
+    
+# c1 = X_train_enc.columns
+# c2 = X_test_enc.columns
+# X_train_enc.shape   
+# X_test_enc.shape   
+
+# This one is better!
+a = pd.get_dummies(combined_df, columns=features_to_encode)
+a1=a.columns
+a2 = a.drop(['gene_name', 'dst', 'dst_mode'])