trying under and oversampling

MultClassPipe3.py

@@ -60,6 +60,18 @@ from sklearn.ensemble import AdaBoostClassifier
 from imblearn.combine import SMOTEENN
 from imblearn.under_sampling import EditedNearestNeighbours
 
+from sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis
+from sklearn.neural_network import MLPClassifier
+
+from sklearn.linear_model import RidgeClassifier, SGDClassifier, PassiveAggressiveClassifier
+from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
+from sklearn.svm import SVC
+from xgboost import XGBClassifier
+from sklearn.naive_bayes import MultinomialNB
+from sklearn.linear_model import SGDClassifier
+from sklearn.preprocessing import StandardScaler, MinMaxScaler, OneHotEncoder
+
+
 #%%
 rs = {'random_state': 42}
 njobs = {'n_jobs': 10}
@@ -122,8 +134,7 @@ def MultClassPipeSKFCV(input_df, target, skf_cv, var_type = ['numerical', 'categ
     mlp     = MLPClassifier(max_iter = 500, **rs)
     dt      = DecisionTreeClassifier(**rs)
     et      = ExtraTreesClassifier(**rs)
-    rf      = RandomForestClassifier(**rs,
-                                    n_estimators     = 1000 )
+    rf      = RandomForestClassifier(**rs, n_estimators = 1000 )
     rf2     = RandomForestClassifier(
                           min_samples_leaf = 5
                           , n_estimators     = 100 #10
@@ -136,7 +147,7 @@ def MultClassPipeSKFCV(input_df, target, skf_cv, var_type = ['numerical', 'categ
                         
     lda = LinearDiscriminantAnalysis()
     
-    mnb = MultinomialNB(**rs)
+    mnb = MultinomialNB()
     
     pa  = PassiveAggressiveClassifier(**rs, **njobs)
     

MultClassPipe3_CALL.py

@@ -7,7 +7,7 @@ Created on Tue Mar 15 11:09:50 2022
 """
 #%% Data
 X = all_df_wtgt[numerical_FN+categorical_FN]
-y = all_df_wtgt['mutation_class']
+y = all_df_wtgt[drug]
 #y = all_df_wtgt['dst_mode']
 #%% variables
 
@@ -17,9 +17,40 @@ mm_skf_scoresD = MultClassPipeSKFCV(input_df = X
                                         , var_type = 'mixed'
                                         , skf_cv = skf_cv)
 
-
 mm_skf_scores_df_all = pd.DataFrame(mm_skf_scoresD)
 mm_skf_scores_df_all
 mm_skf_scores_df_test = mm_skf_scores_df_all.filter(like='test_', axis=0)
 mm_skf_scores_df_train = mm_skf_scores_df_all.filter(like='train_', axis=0) # helps to see if you trust the results
-]
+
+#%%
+mm_skf_scoresD2 = MultClassPipeSKFCV(input_df = X_sm
+                                        , target = y_sm
+                                        , var_type = 'mixed'
+                                        , skf_cv = skf_cv)
+sm_all = pd.DataFrame(mm_skf_scoresD2)
+sm_df_CT = sm_all.filter(like='test_', axis=0)
+
+#%%
+mm_skf_scoresD3 = MultClassPipeSKFCV(input_df = X_ros
+                                        , target = y_ros
+                                        , var_type = 'mixed'
+                                        , skf_cv = skf_cv)
+ros_all = pd.DataFrame(mm_skf_scoresD3)
+ros_CT = ros_all.filter(like='test_', axis=0)
+
+#%%
+mm_skf_scoresD4 = MultClassPipeSKFCV(input_df = X_rus
+                                        , target = y_rus
+                                        , var_type = 'mixed'
+                                        , skf_cv = skf_cv)
+rus_all = pd.DataFrame(mm_skf_scoresD4)
+rus_CT = rus_all.filter(like='test_', axis=0)
+
+#%%
+mm_skf_scoresD5 = MultClassPipeSKFCV(input_df = X_enn
+                                        , target = y_enn
+                                        , var_type = 'mixed'
+                                        , skf_cv = skf_cv)
+enn_all = pd.DataFrame(mm_skf_scoresD5)
+enn_CT = enn_all.filter(like='test_', axis=0)
+

UQ_pnca_ML.py

@@ -36,7 +36,8 @@ from sklearn.gaussian_process.kernels import WhiteKernel
 from sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis
 from sklearn.neural_network import MLPClassifier
 
-from sklearn.linear_model import RidgeClassifier
+from sklearn.linear_model import RidgeClassifier, SGDClassifier, PassiveAggressiveClassifier
+from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
 from sklearn.svm import SVC
 from xgboost import XGBClassifier
 from sklearn.naive_bayes import MultinomialNB
@@ -72,6 +73,7 @@ print(pd.__version__)
 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 imblearn.pipeline import Pipeline
 from sklearn.datasets import make_classification
@@ -81,6 +83,7 @@ from sklearn.ensemble import AdaBoostClassifier
 from imblearn.combine import SMOTEENN
 from imblearn.under_sampling import EditedNearestNeighbours
 
+
 from sklearn.model_selection import GridSearchCV
 from sklearn.base import BaseEstimator
 import json
@@ -119,6 +122,10 @@ from MultClassPipe3 import MultClassPipeSKFCV
 gene = 'pncA'
 drug = 'pyrazinamide'
 
+#gene = 'katG'
+#drug = 'isoniazid'
+
+
 #==============
 # directories
 #==============
@@ -234,13 +241,13 @@ numerical_FN = common_cols_stabiltyN + foldX_cols + X_strFN + X_evolFN + X_genom
 
 #categorical feature names
 categorical_FN = ['ss_class'
-             , 'wt_prop_water'
+#             , 'wt_prop_water'
             # , 'lineage_labels' # misleading if using merged_df3
-             , 'mut_prop_water'
-             , 'wt_prop_polarity'
-             , 'mut_prop_polarity'
-             , 'wt_calcprop'
-             , 'mut_calcprop'
+#             , 'mut_prop_water'
+#             , 'wt_prop_polarity'
+#             , 'mut_prop_polarity'
+#             , 'wt_calcprop'
+#             , 'mut_calcprop'
              #, 'active_aa_pos'
              ]
 
@@ -278,9 +285,9 @@ all_df_wtgt.shape
 #------
 # X
 #------
-X     = all_df_wtgt[numerical_FN + categorical_FN] # training data ALL
+#X     = all_df_wtgt[numerical_FN + categorical_FN] # training data ALL
 X_bts = blind_test_df[numerical_FN + categorical_FN] # blind test data ALL
-#X = all_df_wtgt[numerical_FN] # training numerical only
+X = all_df_wtgt[numerical_FN] # training numerical only
 #X_bts = blind_test_df[numerical_FN] # blind test data numerical
 
 #------

classification_params_FS.py

@@ -574,6 +574,7 @@ param_grid_svc = [
 #========
 # LDA
 # https://github.com/automl/auto-sklearn/blob/master/autosklearn/pipeline/components/classification/lda.py
+# https://scikit-learn.org/stable/modules/generated/sklearn.discriminant_analysis.LinearDiscriminantAnalysis.html
 #========
 
 estimator =  LinearDiscriminantAnalysis()
@@ -605,9 +606,10 @@ param_grid_lda = [
 #========
 # Multinomial_nb
 # https://github.com/automl/auto-sklearn/blob/master/autosklearn/pipeline/components/classification/multinomial_nb.py
+# https://scikit-learn.org/stable/modules/generated/sklearn.naive_bayes.MultinomialNB.html
 #========
 
-estimator =  MultinomialNB(**rs)
+estimator =  MultinomialNB()
 
 # Define pipleline with steps
 pipe_mnb = Pipeline([
@@ -635,6 +637,7 @@ param_grid_mnb = [
 #========
 # passive_aggressive
 # https://github.com/automl/auto-sklearn/blob/master/autosklearn/pipeline/components/classification/passive_aggressive.py
+# https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.PassiveAggressiveClassifier.html
 #========
 
 estimator =  PassiveAggressiveClassifier(**rs, **njobs)
@@ -668,6 +671,7 @@ param_grid_pa = [
 #========
 # SGD
 # https://github.com/automl/auto-sklearn/blob/master/autosklearn/pipeline/components/classification/sgd.py
+# https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.SGDClassifier.html
 #========
 
 estimator =  SGDClassifier(**rs, **njobs)

uq_ml_models_FS/scriptfsycm.py

@@ -0,0 +1,60 @@
+import pandas as pd
+import numpy as np
+import scipy as sp
+import time
+import sys
+import os
+import re
+import argparse
+from math import sqrt
+from scipy import stats
+import joblib
+# Alogorithm
+from xgboost.sklearn import XGBClassifier
+from sklearn import svm
+from sklearn.ensemble import RandomForestClassifier, ExtraTreesClassifier, GradientBoostingClassifier
+from sklearn.gaussian_process import GaussianProcessClassifier
+from sklearn.ensemble import AdaBoostClassifier
+from sklearn.neighbors import KNeighborsClassifier
+from sklearn.neural_network import MLPRegressor
+from sklearn.utils import all_estimators
+# Pre-processing
+from sklearn import preprocessing
+from sklearn.preprocessing import StandardScaler
+from sklearn.datasets import make_classification
+from sklearn.pipeline import Pipeline, make_pipeline
+from sklearn.model_selection import train_test_split, cross_validate, cross_val_score, LeaveOneOut, KFold, RepeatedKFold, cross_val_predict
+# Metric
+from sklearn.metrics import mean_squared_error, make_scorer, roc_auc_score, f1_score, matthews_corrcoef, accuracy_score, balanced_accuracy_score, confusion_matrix, classification_report
+
+def run_all_ML(input_pd, target_label):
+    #y = input_pd[target_label]
+    #X = input_pd.drop(target_label,axis=1)
+    y = target_label
+    X = input_pd
+    
+    result_pd = pd.DataFrame()
+    for name, algorithm in all_estimators(type_filter="classifier"):
+        try:
+            estmator = algorithm()
+            temp_pd = pd.DataFrame()
+            temp_cm = pd.DataFrame()
+            
+            pipe = Pipeline([
+                ("model", algorithm())
+            ])
+            y_pred = cross_val_predict(pipe, X, y, cv = 10, n_jobs=10)
+            _mcc = round(matthews_corrcoef(y_pred, y), 3)
+            _bacc = round(balanced_accuracy_score(y_pred, y), 3)
+            _f1 = round(f1_score(y_pred, y), 3)
+            _roc_auc = round(roc_auc_score(y_pred, y), 3)
+            _tn, _fp, _fn, _tp = confusion_matrix(y_pred, y).ravel()
+            
+            result_pd = result_pd.append(pd.DataFrame(np.column_stack([name, _tp, _tn, _fp, _fn, _roc_auc, _mcc, _bacc, _f1]),\
+                                                      columns=['estimator', 'TP', 'TN', 'FP', 'FN',
+                                                               'roc_auc', 'matthew', 'bacc', 'f1']),\
+                                         ignore_index=True)
+        except Exception as e:
+            print("Got an error while running {}".format(name))
+            print(e)
+    return(result_pd)