added validated params for all classifiers

UQ_FS_fn_CALL.py

@@ -25,8 +25,16 @@ ds_lrD = fsgs(input_df = X
      , estimator = LogisticRegression(**rs)
      , var_type = 'mixed')
 
+# RF: without fs + hyperparam
+rf_allF = fsgs(input_df = X
+     , target = y
+     , param_gridLd = param_grid_rf
+     , blind_test_df = X_bts
+     , blind_test_target = y_bts
+     , estimator = RandomForestClassifier(**rs, **njobs, bootstrap = True, oob_score = True)
+     , var_type = 'mixed')
 
-
+#Fitting 10 folds for each of 31104 candidates, totalling 311040 fits
 
 
 
@@ -44,4 +52,5 @@ ds_lrD = fsgs(input_df = X
 # file = 'LR_FS.json'
 # with open(file, 'r') as f:
 #     data = json.load(f)
-##############################################################################
+##############################################################################
+

UQ_FS_mixed_eg.py

@@ -37,6 +37,7 @@ col_transform = ColumnTransformer(transformers = t
 # print(col_transform.get_feature_names_out())
 
 # foo = col_transform.fit_transform(X)
+Xm = col_transform.fit_transform(X)
 # (foo == test).all()
 #-----------------------
 

UQ_pnca_ML.py

@@ -49,7 +49,6 @@ 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, jaccard_score
 from sklearn.metrics import jaccard_score
-
 from sklearn.metrics import make_scorer
 from sklearn.metrics import classification_report
 
@@ -62,8 +61,8 @@ 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 RFE
-from sklearn.feature_selection import RFECV
+#from sklearn.feature_selection import RFECV
 import itertools
 #import seaborn as sns
 import matplotlib.pyplot as plt

classification_params.py

@@ -1,479 +0,0 @@
-########################################################################
-#======================
-# AdaBoostClassifier()
-#======================
-estimator =  AdaBoostClassifier(**rs)
-
-# Define pipleline with steps
-pipe_abc = Pipeline([
-    ('pre', MinMaxScaler())
-    , ('fs', RFECV(DecisionTreeClassifier(**rs), cv = cv, scoring = 'matthews_corrcoef'))
-#    , ('fs', RFECV(estimator, cv = cv, scoring = 'matthews_corrcoef'))    
-#    , ('clf',  AdaBoostClassifier(**rs))])
-    , ('clf',  estimator)
-    ])
-
-# Define hyperparmeter space to search for
-param_grid_abc = [
-    {
-    'fs__min_features_to_select' : [1,2]
-#     , 'fs__cv': [cv]
-     },
-              
-    {
-#        'clf': [AdaBoostClassifier(**rs)],      
-         'clf__n_estimators': [1, 2, 5, 10]
-#       , 'clf__base_estimator'  : ['SVC']
-#       , 'clf__splitter'  :   ["best", "random"]
-        }
-]
-########################################################################     
-#======================
-# BaggingClassifier()
-#======================                  
-estimator = BaggingClassifier(**rs
-                          , **njobs
-                          , bootstrap = True
-                          , oob_score = True)
-
-# Define pipleline with steps
-pipe_bc = Pipeline([
-    
-    ('pre', MinMaxScaler())
-    , ('fs', RFECV(DecisionTreeClassifier(**rs), cv = cv, scoring = 'matthews_corrcoef'))
-#    , ('fs', RFECV(estimator, cv = cv, scoring = 'matthews_corrcoef'))       
-    , ('clf',  estimator)
-    ])
-
-# Define hyperparmeter space to search for
-param_grid_bc = [
-    {
-    'fs__min_features_to_select' : [1,2]
-#     , 'fs__cv': [cv]
-     },
-    
-    {
-#        'clf': [BaggingClassifier(**rs, **njobs , bootstrap = True, oob_score = True)],
-    'clf__n_estimators'    : [10, 25, 50, 100, 150, 200, 500, 700, 1000]
-#       , 'clf__base_estimator' : ['None', 'SVC()', 'KNeighborsClassifier()'] # if none, DT is used
-        }
-]
-########################################################################
-#======================  
-# BernoulliNB ()
-#======================  
-# Define estimator
-estimator =  BernoulliNB()
-
-# Define pipleline with steps
-pipe_bnb = Pipeline([
-    ('pre', MinMaxScaler())
-    , ('fs', RFECV(DecisionTreeClassifier(**rs), cv = cv, scoring = 'matthews_corrcoef'))
-#    , ('fs', RFECV(estimator, cv = cv, scoring = 'matthews_corrcoef'))       
-    , ('clf',  estimator)
-    ])
-
-# Define hyperparmeter space to search for
-param_grid_bnb = [
-    {'fs__min_features_to_select' : [1,2]
-#     , 'fs__cv': [cv]    
-     },
-    
-    {
-#        'clf': [BernoulliNB()],        
-         'clf__alpha': [1, 0]
-        , 'clf__binarize':[None, 0]
-        , 'clf__fit_prior': [True]
-        , 'clf__class_prior': [None]
-        }
-]
-########################################################################
-#===========================
-# DecisionTreeClassifier()
-#=========================== 
- 
-# Define estimator
-estimator =  DecisionTreeClassifier(**rs)
-
-# Define pipleline with steps
-pipe_dt = Pipeline([
-    ('pre', MinMaxScaler())
-    , ('fs', RFECV(DecisionTreeClassifier(**rs), cv = cv, scoring = 'matthews_corrcoef'))
-#    , ('fs', RFECV(estimator, cv = cv, scoring = 'matthews_corrcoef'))    
-    , ('clf',  estimator)
-    ])
-
-# Define hyperparmeter space to search for
-param_grid_dt = [
-    {
-    'fs__min_features_to_select' : [1,2]
-#     , 'fs__cv': [cv]
-     },    
-    
-    {
-#        'clf': [DecisionTreeClassifier(**rs)],
-         'clf__max_depth': [None, 2, 4, 6, 8, 10, 12, 16, 20]
-        , 'clf__class_weight':['balanced']
-        , 'clf__criterion': ['gini', 'entropy', 'log_loss']
-        , 'clf__max_features': [None, 'sqrt', 'log2']
-        , 'clf__min_samples_leaf': [1, 2, 3, 4, 5, 10]
-        , 'clf__min_samples_split': [2, 5, 15, 20]
-        }
-]
-
-#########################################################################
-#==============================
-# GradientBoostingClassifier()
-#==============================
-# Define estimator
-estimator =  GradientBoostingClassifier(**rs)
-
-# Define pipleline with steps
-pipe_gbc = Pipeline([
-    ('pre', MinMaxScaler())
-    , ('fs', RFECV(DecisionTreeClassifier(**rs), cv = cv, scoring = 'matthews_corrcoef'))
-#    , ('fs', RFECV(estimator, cv = cv, scoring = 'matthews_corrcoef'))       
-    , ('clf',  estimator)
-    ])
-
-# Define hyperparmeter space to search for
-param_grid_gbc = [
-    {
-    'fs__min_features_to_select' : [1,2]
-#     , 'fs__cv': [cv]
-     },
-    {
-#        'clf': [GradientBoostingClassifier(**rs)],
-         'clf__n_estimators'   : [10, 100, 200, 500, 1000]
-        , 'clf__learning_rate': [0.001, 0.01, 0.1]
-        , 'clf__subsample'    : [0.5, 0.7, 1.0]
-        , 'clf__max_depth'     : [3, 7, 9]
-        
-        }
-]
-
-#########################################################################
-#=========================== 
-# GaussianNB ()
-#=========================== 
-# Define estimator
-estimator =  GaussianNB()
-
-# Define pipleline with steps
-pipe_gnb = Pipeline([
-    ('pre', MinMaxScaler())
-    , ('fs', RFECV(DecisionTreeClassifier(**rs), cv = cv, scoring = 'matthews_corrcoef'))
-#    , ('fs', RFECV(estimator, cv = cv, scoring = 'matthews_corrcoef'))       
-    , ('clf',  estimator)
-    ])
-
-
-# Define hyperparmeter space to search for
-param_grid_gnb = [
-    {
-    'fs__min_features_to_select' : [1,2]
-#     , 'fs__cv': [cv]
-     },
-    {
-#        'clf': [GaussianNB()],       
-         'clf__priors': [None]
-        , 'clf__var_smoothing': np.logspace(0,-9, num=100)
-        }
-]
-
-#########################################################################
-#=========================== 
-# GaussianProcessClassifier()
-#=========================== 
-# Define estimator
-estimator =  GaussianProcessClassifier(**rs)
-
-# Define pipleline with steps
-pipe_gbc = Pipeline([
-    ('pre', MinMaxScaler())
-    , ('fs', RFECV(DecisionTreeClassifier(**rs), cv = cv, scoring = 'matthews_corrcoef'))
-#    , ('fs', RFECV(estimator, cv = cv, scoring = 'matthews_corrcoef'))       
-    , ('clf',  estimator)
-    ])
-
-# Define hyperparmeter space to search for
-param_grid_gbc = [
-    {
-    'fs__min_features_to_select' : [1,2]
-#     , 'fs__cv': [cv]
-     },
-         
-    {
-#        'clf': [GaussianProcessClassifier(**rs)], 
-         'clf__kernel': [1*RBF(), 1*DotProduct(), 1*Matern(), 1*RationalQuadratic(), 1*WhiteKernel()]
-        }
-]
-
-#########################################################################
-#=========================== 
-# KNeighborsClassifier ()
-#=========================== 
-# Define estimator
-estimator =  KNeighborsClassifier(**njobs)
-
-# Define pipleline with steps
-pipe_knn = Pipeline([
-    ('pre', MinMaxScaler())
-    , ('fs', RFECV(DecisionTreeClassifier(**rs), cv = cv, scoring = 'matthews_corrcoef'))
-#    , ('fs', RFECV(estimator, cv = cv, scoring = 'matthews_corrcoef'))    
-    , ('clf',  estimator)
-    ])
-
-# Define hyperparmeter space to search for
-param_grid_knn = [
-    {
-    'fs__min_features_to_select' : [1,2]
-#     , 'fs__cv': [cv]
-     },
-             
-    {
-#        'clf': [KNeighborsClassifier(**njobs)],
-        'clf__n_neighbors': range(21, 51, 2)
-        #, 'clf__n_neighbors': [5, 7, 11]
-        , 'clf__metric'     : ['euclidean', 'manhattan', 'minkowski']
-        , 'clf__weights'    : ['uniform', 'distance']
-
-        }
-]
-#########################################################################
-#=========================== 
-# LogisticRegression ()
-#=========================== 
-# Define estimator
-estimator =  LogisticRegression(**rs)
-
-# Define pipleline with steps
-pipe_lr = Pipeline([
-    ('pre', MinMaxScaler())
-    , ('fs', RFECV(LogisticRegression(**rs), cv = rskf_cv, scoring = 'matthews_corrcoef'))
-#    , ('fs', RFECV(estimator, cv = cv, scoring = 'matthews_corrcoef'))       
-    , ('clf',  estimator)])
-
-# Define hyperparmeter space to search for
-param_grid_lr = [
-    
-    {'fs__min_features_to_select' : [1,2]
-#     , 'fs__cv': [rskf_cv]
-     },
-    
-    {
-#       'clf': [LogisticRegression(**rs)],
-        'clf__C': np.logspace(0, 4, 10),
-        'clf__penalty': ['none', 'l1', 'l2', 'elasticnet'],
-        'clf__max_iter': list(range(100,800,100)),
-        'clf__solver': ['saga']
-    },
-    {
-#        'clf': [LogisticRegression(**rs)],
-        'clf__C': np.logspace(0, 4, 10),
-        'clf__penalty': ['l2', 'none'],
-        'clf__max_iter': list(range(100,800,100)),
-        'clf__solver': ['newton-cg', 'lbfgs', 'sag']
-    }, 
-    {
-#        'clf': [LogisticRegression(**rs)],
-        'clf__C': np.logspace(0, 4, 10),
-        'clf__penalty': ['l1', 'l2'],
-        'clf__max_iter': list(range(100,800,100)),
-        'clf__solver': ['liblinear']
-    }
-
-]
-#########################################################################
-#================== 
-# MLPClassifier()
-#================== 
-# Define estimator
-estimator =  MLPClassifier(**rs)
-
-# Define pipleline with steps
-pipe_mlp = Pipeline([
-    ('pre', MinMaxScaler())
-    , ('fs', RFECV(DecisionTreeClassifier(**rs), cv = cv, scoring = 'matthews_corrcoef'))
-#    , ('fs', RFECV(estimator, cv = cv, scoring = 'matthews_corrcoef'))        
-    , ('clf',  estimator)
-    ])
-
-param_grid_mlp = [    {
-    'fs__min_features_to_select' : [1,2]
-#     , 'fs__cv': [cv]
-     },
-    
-    {
-#        'clf': [MLPClassifier(**rs, max_iter = 1000)],
-         'clf__max_iter': [1000, 2000]
-        , 'clf__hidden_layer_sizes': [(1), (2), (3), (5), (10)]
-        , 'clf__solver': ['lbfgs', 'sgd', 'adam']
-        , 'clf__learning_rate': ['constant', 'invscaling', 'adaptive']
-        #, 'clf__learning_rate': ['constant']
-        
-        }
-]
-
-#########################################################################
-#==================================
-# QuadraticDiscriminantAnalysis()
-#==================================
-# Define estimator
-estimator =  QuadraticDiscriminantAnalysis(**rs)
-
-# Define pipleline with steps
-pipe_qda = Pipeline([
-    ('pre', MinMaxScaler())
-    , ('fs', RFECV(DecisionTreeClassifier(**rs), cv = cv, scoring = 'matthews_corrcoef'))
-#    , ('fs', RFECV(estimator, cv = cv, scoring = 'matthews_corrcoef'))    
-    , ('clf',  estimator)
-    ])
-
-# Define hyperparmeter space to search for
-param_grid_qda = [
-    {
-    'fs__min_features_to_select' : [1,2]
-#     , 'fs__cv': [cv]
-     },
-    
-    {
-#        'clf': [QuadraticDiscriminantAnalysis()],
-        'clf__priors': [None]
-
-        }
-]
-
-#########################################################################
-#====================
-# RidgeClassifier()
-#====================
-
-# Define estimator
-estimator =  RidgeClassifier(**rs)
-
-# Define pipleline with steps
-pipe_rc = Pipeline([
-    ('pre', MinMaxScaler())
-    , ('fs', RFECV(DecisionTreeClassifier(**rs), cv = cv, scoring = 'matthews_corrcoef'))
-#    , ('fs', RFECV(estimator, cv = cv, scoring = 'matthews_corrcoef'))
-    , ('clf',  estimator)
-    ])
-
-param_grid_rc = [
-    {
-    'fs__min_features_to_select' : [1,2]
-#     , 'fs__cv': [cv]
-     },
-    
-    {
-     #'clf' : [RidgeClassifier(**rs)],
-      'clf__alpha': [0.1, 0.2, 0.5, 0.8, 1.0]
-     }
-]
-#######################################################################
-#=========================== 
-# RandomForestClassifier()
-#=========================== 
-# Define estimator
-estimator =  [RandomForestClassifier(**rs, **njobs, bootstrap = True, oob_score = True)](**rs)
-
-# Define pipleline with steps
-pipe_rf = Pipeline([
-    ('pre', MinMaxScaler())
-    , ('fs', RFECV(DecisionTreeClassifier(**rs), cv = cv, scoring = 'matthews_corrcoef'))
-#    , ('fs', RFECV(estimator, cv = cv, scoring = 'matthews_corrcoef'))
-    , ('clf',  estimator)
-    ])
-
-# Define hyperparmeter space to search for
-param_grid_rf = [
-    {
-    'fs__min_features_to_select' : [1,2]
-#     , 'fs__cv': [cv]
-     },
-           
-    {
-#        'clf': [RandomForestClassifier(**rs, **njobs, bootstrap = True, oob_score = True)],
-        'clf__max_depth': [4, 6, 8, 10, 12, 16, 20, None]
-        , 'clf__class_weight':['balanced','balanced_subsample']
-        , 'clf__n_estimators': [10, 25, 50, 100, 200, 300] # go upto a 100
-        , 'clf__criterion': ['gini', 'entropy', 'log_loss']
-        , 'clf__max_features': ['sqrt', 'log2', None] #deafult is sqrt
-        , 'clf__min_samples_leaf': [1, 2, 3, 4, 5, 10]
-        , 'clf__min_samples_split': [2, 5, 15, 20]
-        }
-]
-#######################################################################
-#========
-# SVC()
-#========
-
-estimator =  SVC(**rs)
-
-# Define pipleline with steps
-pipe_svc = Pipeline([
-    ('pre', MinMaxScaler())
-    , ('fs', RFECV(DecisionTreeClassifier(**rs), cv = cv, scoring = 'matthews_corrcoef'))
-#    , ('fs', RFECV(estimator, cv = cv, scoring = 'matthews_corrcoef'))
-    , ('clf',  estimator)
-    ])
-
-# Define hyperparmeter space to search for
-param_grid_svc = [
-    {
-    'fs__min_features_to_select' : [1,2]
-#     , 'fs__cv': [cv]
-     },
-             
-    {
-#        'clf': [SVC(**rs)],    
-        'clf__kernel': ['poly', 'rbf', 'sigmoid']
-        #, 'clf__kernel': ['linear']
-       , 'clf__C'    : [50, 10, 1.0, 0.1, 0.01]
-       , 'clf__gamma': ['scale', 'auto'] 
-        
-        }
-]
-
-#######################################################################
-#================= 
-# XGBClassifier ()
-#================= 
-
-# Define estimator
-#https://www.datatechnotes.com/2019/07/classification-example-with.html
-# XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
-#        colsample_bynode=1, colsample_bytree=1, gamma=0, learning_rate=0.1,
-#        max_delta_step=0, max_depth=3, min_child_weight=1, missing=None,
-#        n_estimators=100, n_jobs=1, nthread=None,
-#        objective='multi:softprob', random_state=0, reg_alpha=0,
-#        reg_lambda=1, scale_pos_weight=1, seed=None, silent=None,
-#        subsample=1, verbosity=1)
-estimator =  XGBClassifier(**rs, **njobs, verbose = 3)
-
-# Define pipleline with steps
-pipe_xgb = Pipeline([
-    ('pre', MinMaxScaler())
-    , ('fs', RFECV(DecisionTreeClassifier(**rs), cv = cv, scoring = 'matthews_corrcoef'))
-#    , ('fs', RFECV(estimator, cv = cv, scoring = 'matthews_corrcoef'))
-    , ('clf',  estimator)
-    ])
-
-param_grid_xgb = [
-    {
-    'fs__min_features_to_select' : [1,2]
-#     , 'fs__cv': [cv]
-     },
-    {
-#        'clf': [XGBClassifier(**rs , **njobs, verbose = 3)],
-         'clf__learning_rate': [0.01, 0.05, 0.1, 0.2]
-        , 'clf__max_depth'   : [4, 6, 8, 10, 12, 16, 20]
-        , 'clf__n_estimators': [10, 25, 50, 100, 200, 300]
-        #, 'clf__min_samples_leaf': [4, 8, 12, 16, 20]
-        #, 'clf__max_features': ['auto', 'sqrt']
-        }
-]
-
-#######################################################################
-

classification_params_FS.py

@@ -1,6 +1,31 @@
+# Date: 25/05/2020
+# https://scikit-learn.org/stable/supervised_learning.html
+
+
+# try features from Autosklearn: 
+# autosklearn --> pipleine --> components --> classification
+# https://github.com/automl/auto-sklearn/tree/master/autosklearn/pipeline/components/classification
+
+# TOADD: 
+# Extra Trees
+https://github.com/automl/auto-sklearn/blob/master/autosklearn/pipeline/components/classification/extra_trees.py
+# LDA
+https://github.com/automl/auto-sklearn/blob/master/autosklearn/pipeline/components/classification/lda.py
+# Multinomial_nb
+https://github.com/automl/auto-sklearn/blob/master/autosklearn/pipeline/components/classification/multinomial_nb.py
+# passive_aggressive
+https://github.com/automl/auto-sklearn/blob/master/autosklearn/pipeline/components/classification/passive_aggressive.py
+# SGD
+https://github.com/automl/auto-sklearn/blob/master/autosklearn/pipeline/components/classification/sgd.py
+
+
+######https://scikit-learn.org/stable/supervised_learning.html
+
 ########################################################################
 #======================
 # AdaBoostClassifier()
+#https://github.com/automl/auto-sklearn/blob/master/autosklearn/pipeline/components/classification/adaboost.py
+#https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.AdaBoostClassifier.html
 #======================
 estimator =  AdaBoostClassifier(**rs)
 
@@ -22,14 +47,162 @@ param_grid_abc = [
               
     {
 #        'clf': [AdaBoostClassifier(**rs)],      
-         'clf__n_estimators': [1, 2, 5, 10]
+#         'clf__n_estimators': [50, 100, 150, 200, 250, 300, 350, 400, 450, 500]
-#       , 'clf__base_estimator'  : ['SVC']
+         'clf__n_estimators': [50, 100, 200, 300, 400, 500],
-#       , 'clf__splitter'  :   ["best", "random"]
+         'clf__learning_rate': [0.01, 0.1, 1, 1.5, 2],
+         'clf__max_depth': [1, 5, 10],
+#         'clf__base_estimator'  : ['SVC']
         }
 ]
+#======================
+# Extra TreesClassifier()
+#https://github.com/automl/auto-sklearn/blob/master/autosklearn/pipeline/components/classification/extra_trees.py
+#https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.ExtraTreesClassifier.html
+#======================
+estimator =  ExtraTreesClassifier**rs)
+
+# Define pipleline with steps
+pipe_abc = Pipeline([
+    ('pre', MinMaxScaler())
+    , ('fs', RFECV(DecisionTreeClassifier(**rs), cv = cv, scoring = 'matthews_corrcoef'))
+#    , ('fs', RFECV(estimator, cv = cv, scoring = 'matthews_corrcoef'))    
+#    , ('clf',  ExtraTreesClassifier(**rs))])
+    , ('clf',  estimator)
+    ])
+
+# Define hyperparmeter space to search for
+param_grid_abc = [
+    {
+    'fs__min_features_to_select' : [1,2]
+#     , 'fs__cv': [cv]
+     },
+              
+#        'clf': [ExtraTreesClassifier(**rs)],
+         'clf__n_estimators': [100, 300, 500], # sklearn has no tuning
+         'clf__max_depth': [None],
+         'clf__criterion': ['gini', 'entropy'],
+         'clf__max_features': [None, 'sqrt', 'log2', 0.5, 1],
+         'clf__min_samples_leaf': [1, 5, 10, 15, 20],
+         'clf__min_samples_split': [2, 5, 10, 15, 20]
+        }
+]
+
+#===========================
+# DecisionTreeClassifier()
+https://github.com/automl/auto-sklearn/blob/master/autosklearn/pipeline/components/classification/decision_tree.py
+https://scikit-learn.org/stable/modules/generated/sklearn.tree.DecisionTreeClassifier.html
+#=========================== 
+# Define estimator
+estimator =  DecisionTreeClassifier(**rs)
+
+# Define pipleline with steps
+pipe_dt = Pipeline([
+    ('pre', MinMaxScaler())
+    , ('fs', RFECV(DecisionTreeClassifier(**rs), cv = cv, scoring = 'matthews_corrcoef'))
+#    , ('fs', RFECV(estimator, cv = cv, scoring = 'matthews_corrcoef'))    
+    , ('clf',  estimator)
+    ])
+
+# Define hyperparmeter space to search for
+param_grid_dt = [
+    {
+    'fs__min_features_to_select' : [1,2]
+#     , 'fs__cv': [cv]
+     },    
+    
+    {
+#        'clf': [DecisionTreeClassifier(**rs)],
+#         'clf__max_depth': [None, 2, 6, 10, 14, 16, 20],
+         'clf__max_depth': [None, 0, 0.2, 0.5],
+         'clf__class_weight':[None, 'balanced'],
+         'clf__criterion': ['gini', 'entropy'],
+         'clf__max_features': [None, 'sqrt', 'log2', 1],
+         'clf__min_samples_leaf': [1, 5, 10, 15, 20],
+         'clf__min_samples_split': [2, 5, 10, 15, 20]
+        }
+]
+
+########################################################################
+#=========================== 
+# RandomForestClassifier()
+https://github.com/automl/auto-sklearn/blob/master/autosklearn/pipeline/components/classification/random_forest.py
+https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.RandomForestClassifier.html
+#=========================== 
+
+# Define estimator
+estimator =  [RandomForestClassifier(**rs, **njobs, bootstrap = True, oob_score = True)](**rs)
+
+# Define pipleline with steps
+pipe_rf = Pipeline([
+    ('pre', MinMaxScaler())
+    , ('fs', RFECV(DecisionTreeClassifier(**rs), cv = cv, scoring = 'matthews_corrcoef'))
+#    , ('fs', RFECV(estimator, cv = cv, scoring = 'matthews_corrcoef'))
+    , ('clf',  estimator)
+    ])
+
+# Define hyperparmeter space to search for
+param_grid_rf = [
+    {
+    'fs__min_features_to_select' : [1,2]
+#     , 'fs__cv': [cv]
+     },
+           
+    {
+#        'clf': [RandomForestClassifier(**rs, **njobs, bootstrap = True, oob_score = True)],
+#        'clf__max_depth': [4, 6, 8, 10, 12, 16, 20, None]
+        'clf__max_depth': [None, 2, 6, 10, 14, 16, 20] #autosk: None
+        , 'clf__class_weight':[None, 'balanced']
+        , 'clf__n_estimators': [50, 100, 200, 300] # autodesk: no
+        , 'clf__criterion': ['gini', 'entropy']
+        , 'clf__max_features': ['sqrt', 'log2', None, 0, 0.5, 1]
+        , 'clf__min_samples_leaf': [1, 5, 10, 15, 20]
+        , 'clf__min_samples_split': [2, 5, 15, 20]
+        }
+]
+
+#================= 
+# XGBClassifier ()
+#================= 
+# https://www.kaggle.com/code/stuarthallows/using-xgboost-with-scikit-learn/notebook
+# Define estimator
+#https://www.datatechnotes.com/2019/07/classification-example-with.html
+# XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
+#        colsample_bynode=1, colsample_bytree=1, gamma=0, learning_rate=0.1,
+#        max_delta_step=0, max_depth=3, min_child_weight=1, missing=None,
+#        n_estimators=100, n_jobs=1, nthread=None,
+#        objective='multi:softprob', random_state=0, reg_alpha=0,
+#        reg_lambda=1, scale_pos_weight=1, seed=None, silent=None,
+#        subsample=1, verbosity=1)
+estimator =  XGBClassifier(**rs, **njobs, verbose = 3)
+
+# Define pipleline with steps
+pipe_xgb = Pipeline([
+    ('pre', MinMaxScaler())
+    , ('fs', RFECV(DecisionTreeClassifier(**rs), cv = cv, scoring = 'matthews_corrcoef'))
+#    , ('fs', RFECV(estimator, cv = cv, scoring = 'matthews_corrcoef'))
+    , ('clf',  estimator)
+    ])
+
+param_grid_xgb = [
+    {
+    'fs__min_features_to_select' : [1,2]
+#     , 'fs__cv': [cv]
+     },
+    {
+#        'clf': [XGBClassifier(**rs , **njobs, verbose = 3)],
+         'clf__learning_rate': [0.01, 0.05, 0.1, 0.2]
+        , 'clf__max_depth'   : [3, 8, 10, 12, 16, 20]
+        , 'clf__n_estimators': [50, 100, 200, 300]
+        }
+]
+
+#######################################################################
+
+
 ########################################################################     
 #======================
-# BaggingClassifier()
+# BaggingClassifier()*
+#https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.BaggingClassifier.html
 #======================                  
 estimator = BaggingClassifier(**rs
                           , **njobs
@@ -53,7 +226,7 @@ param_grid_bc = [
      },
     
     {
-#        'clf': [BaggingClassifier(**rs, **njobs , bootstrap = True, oob_score = True)],
+#    'clf': [BaggingClassifier(**rs, **njobs , bootstrap = True, oob_score = True)],
     'clf__n_estimators'    : [10, 25, 50, 100, 150, 200, 500, 700, 1000]
 #       , 'clf__base_estimator' : ['None', 'SVC()', 'KNeighborsClassifier()'] # if none, DT is used
         }
@@ -61,6 +234,8 @@ param_grid_bc = [
 ########################################################################
 #======================  
 # BernoulliNB ()
+#https://github.com/automl/auto-sklearn/blob/master/autosklearn/pipeline/components/classification/bernoulli_nb.py
+#https://scikit-learn.org/stable/modules/generated/sklearn.naive_bayes.BernoulliNB.html
 #======================  
 # Define estimator
 estimator =  BernoulliNB()
@@ -81,49 +256,18 @@ param_grid_bnb = [
     
     {
 #        'clf': [BernoulliNB()],        
-         'clf__alpha': [1, 0]
+         'clf__alpha': [0.01, 0, 1, 10, 100]
-        , 'clf__binarize':[None, 0]
+        , 'clf__binarize':[None, 0] # autosk has no, maybe just use None
         , 'clf__fit_prior': [True]
         , 'clf__class_prior': [None]
         }
 ]
-########################################################################
-#===========================
-# DecisionTreeClassifier()
-#=========================== 
- 
-# Define estimator
-estimator =  DecisionTreeClassifier(**rs)
-
-# Define pipleline with steps
-pipe_dt = Pipeline([
-    ('pre', MinMaxScaler())
-    , ('fs', RFECV(DecisionTreeClassifier(**rs), cv = cv, scoring = 'matthews_corrcoef'))
-#    , ('fs', RFECV(estimator, cv = cv, scoring = 'matthews_corrcoef'))    
-    , ('clf',  estimator)
-    ])
-
-# Define hyperparmeter space to search for
-param_grid_dt = [
-    {
-    'fs__min_features_to_select' : [1,2]
-#     , 'fs__cv': [cv]
-     },    
-    
-    {
-#        'clf': [DecisionTreeClassifier(**rs)],
-         'clf__max_depth': [None, 2, 4, 6, 8, 10, 12, 16, 20]
-        , 'clf__class_weight':['balanced']
-        , 'clf__criterion': ['gini', 'entropy', 'log_loss']
-        , 'clf__max_features': [None, 'sqrt', 'log2']
-        , 'clf__min_samples_leaf': [1, 2, 3, 4, 5, 10]
-        , 'clf__min_samples_split': [2, 5, 15, 20]
-        }
-]
 
 #########################################################################
 #==============================
 # GradientBoostingClassifier()
+#https://github.com/automl/auto-sklearn/blob/master/autosklearn/pipeline/components/classification/gradient_boosting.py
+#https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.GradientBoostingClassifier.html
 #==============================
 # Define estimator
 estimator =  GradientBoostingClassifier(**rs)
@@ -144,17 +288,26 @@ param_grid_gbc = [
      },
     {
 #        'clf': [GradientBoostingClassifier(**rs)],
-         'clf__n_estimators'   : [10, 100, 200, 500, 1000]
+         'clf__loss'             : ['log_loss', 'exponential'],
-        , 'clf__learning_rate': [0.001, 0.01, 0.1]
+        'clf__n_estimators'      : [10, 100, 200, 500, 1000], # autosklearn: not there
-        , 'clf__subsample'    : [0.5, 0.7, 1.0]
+        'clf__learning_rate'     : [0.01,0.1, 0, 0.5, 1],
-        , 'clf__max_depth'     : [3, 7, 9]
+        'clf__subsample'         : [0.5, 0.7, 1.0],
+        'clf__max_depth'         : [3, 7, 9],
+        'clf__min_samples_leaf'  : [1, 20, 50, 100, 150, 200],
+        'clf__max_depth'         : [None],
+        'clf__max_leaf_nodes'    : [3, 31, 51, 331, 2047] # autosklearn: log = T
+        'clf__l2_regularization' : [0.0000000001, 0.000001, 0.0001, 0.01, 0.1, 1], #lower=1E-10, upper=1, log = T
+        'n_iter_no_change'       : [None, 1, 5, 10, 15, 20], # autsk: 1, 20
+        'validation_fraction'    : [0.01, 0.03, 0.2, 0.3, 0.4] # autosk: 0.01, 0.4
         
         }
 ]
 
 #########################################################################
 #=========================== 
-# GaussianNB ()
+# GaussianNB()
+https://github.com/automl/auto-sklearn/blob/master/autosklearn/pipeline/components/classification/gaussian_nb.py
+https://scikit-learn.org/stable/modules/generated/sklearn.naive_bayes.GaussianNB.html
 #=========================== 
 # Define estimator
 estimator =  GaussianNB()
@@ -183,7 +336,8 @@ param_grid_gnb = [
 
 #########################################################################
 #=========================== 
-# GaussianProcessClassifier()
+# GaussianProcessClassifier() *
+# https://scikit-learn.org/stable/modules/generated/sklearn.gaussian_process.GaussianProcessClassifier.html
 #=========================== 
 # Define estimator
 estimator =  GaussianProcessClassifier(**rs)
@@ -212,6 +366,8 @@ param_grid_gbc = [
 #########################################################################
 #=========================== 
 # KNeighborsClassifier ()
+#https://github.com/automl/auto-sklearn/blob/master/autosklearn/pipeline/components/classification/k_nearest_neighbors.py
+#https://scikit-learn.org/stable/modules/generated/sklearn.neighbors.KNeighborsClassifier.html
 #=========================== 
 # Define estimator
 estimator =  KNeighborsClassifier(**njobs)
@@ -233,16 +389,18 @@ param_grid_knn = [
              
     {
 #        'clf': [KNeighborsClassifier(**njobs)],
-        'clf__n_neighbors': range(21, 51, 2)
         #, 'clf__n_neighbors': [5, 7, 11]
-        , 'clf__metric'     : ['euclidean', 'manhattan', 'minkowski']
+        #'clf__n_neighbors': list(range(21, 51, 4),)
-        , 'clf__weights'    : ['uniform', 'distance']
+        'clf__n_neighbors'  : [1, 11, 21, 51, 71, 101],
+        'clf__metric'     : ['euclidean', 'manhattan', 'minkowski'],
+        'clf__weights'    : ['uniform', 'distance']
 
         }
 ]
 #########################################################################
 #=========================== 
-# LogisticRegression ()
+# LogisticRegression () *
+# https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html
 #=========================== 
 # Define estimator
 estimator =  LogisticRegression(**rs)
@@ -287,6 +445,8 @@ param_grid_lr = [
 #########################################################################
 #================== 
 # MLPClassifier()
+https://github.com/automl/auto-sklearn/blob/master/autosklearn/pipeline/components/classification/mlp.py
+https://scikit-learn.org/stable/modules/generated/sklearn.neural_network.MLPClassifier.html
 #================== 
 # Define estimator
 estimator =  MLPClassifier(**rs)
@@ -306,11 +466,10 @@ param_grid_mlp = [    {
     
     {
 #        'clf': [MLPClassifier(**rs, max_iter = 1000)],
-         'clf__max_iter': [1000, 2000]
+        'clf__max_iter': [200, 500, 1000, 2000], # no autosklearn
-        , 'clf__hidden_layer_sizes': [(1), (2), (3), (5), (10)]
+        'clf__hidden_layer_sizes': [(100), (1), (2), (3), (5), (10) ], #no autosklearn
-        , 'clf__solver': ['lbfgs', 'sgd', 'adam']
+        'clf__solver': ['lbfgs', 'sgd', 'adam'], #no autosklearn
-        , 'clf__learning_rate': ['constant', 'invscaling', 'adaptive']
+        'clf__learning_rate': ['constant', 'invscaling', 'adaptive'] #no autosklearn
-        #, 'clf__learning_rate': ['constant']
         
         }
 ]
@@ -318,6 +477,8 @@ param_grid_mlp = [    {
 #########################################################################
 #==================================
 # QuadraticDiscriminantAnalysis()
+https://github.com/automl/auto-sklearn/blob/master/autosklearn/pipeline/components/classification/qda.py
+https://scikit-learn.org/stable/modules/generated/sklearn.discriminant_analysis.QuadraticDiscriminantAnalysis.html
 #==================================
 # Define estimator
 estimator =  QuadraticDiscriminantAnalysis(**rs)
@@ -339,14 +500,15 @@ param_grid_qda = [
     
     {
 #        'clf': [QuadraticDiscriminantAnalysis()],
-        'clf__priors': [None]
+        'clf__priors': [None],
-
+        'clf__reg_param': [0, 1]
         }
 ]
 
 #########################################################################
 #====================
-# RidgeClassifier()
+# RidgeClassifier() *
+https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.RidgeClassifier.html
 #====================
 
 # Define estimator
@@ -372,41 +534,14 @@ param_grid_rc = [
      }
 ]
 #######################################################################
-#=========================== 
-# RandomForestClassifier()
-#=========================== 
-# Define estimator
-estimator =  [RandomForestClassifier(**rs, **njobs, bootstrap = True, oob_score = True)](**rs)
-
-# Define pipleline with steps
-pipe_rf = Pipeline([
-    ('pre', MinMaxScaler())
-    , ('fs', RFECV(DecisionTreeClassifier(**rs), cv = cv, scoring = 'matthews_corrcoef'))
-#    , ('fs', RFECV(estimator, cv = cv, scoring = 'matthews_corrcoef'))
-    , ('clf',  estimator)
-    ])
-
-# Define hyperparmeter space to search for
-param_grid_rf = [
-    {
-    'fs__min_features_to_select' : [1,2]
-#     , 'fs__cv': [cv]
-     },
-           
-    {
-#        'clf': [RandomForestClassifier(**rs, **njobs, bootstrap = True, oob_score = True)],
-        'clf__max_depth': [4, 6, 8, 10, 12, 16, 20, None]
-        , 'clf__class_weight':['balanced','balanced_subsample']
-        , 'clf__n_estimators': [10, 25, 50, 100, 200, 300] # go upto a 100
-        , 'clf__criterion': ['gini', 'entropy', 'log_loss']
-        , 'clf__max_features': ['sqrt', 'log2', None] #deafult is sqrt
-        , 'clf__min_samples_leaf': [1, 2, 3, 4, 5, 10]
-        , 'clf__min_samples_split': [2, 5, 15, 20]
-        }
-]
-#######################################################################
 #========
 # SVC()
+# https://github.com/automl/auto-sklearn/blob/master/autosklearn/pipeline/components/classification/libsvm_svc.py
+# paper that supports libSVM/SVC param searching
+# https://www.csie.ntu.edu.tw/~cjlin/papers/guide/guide.pdf
+https://scikit-learn.org/stable/modules/generated/sklearn.svm.SVC.html
+
+##########https://github.com/automl/auto-sklearn/blob/master/autosklearn/pipeline/components/classification/liblinear_svc.py (NOT the one used, but they are very similar!)
 #========
 
 estimator =  SVC(**rs)
@@ -428,52 +563,15 @@ param_grid_svc = [
              
     {
 #        'clf': [SVC(**rs)],    
-        'clf__kernel': ['poly', 'rbf', 'sigmoid']
+#        'clf__kernel': ['poly', 'rbf', 'sigmoid']
-        #, 'clf__kernel': ['linear']
+       , 'clf__kernel': ['rbf']
-       , 'clf__C'    : [50, 10, 1.0, 0.1, 0.01]
+       , 'clf__C'     : [50, 10, 1.0, 0.1, 0.01]
-       , 'clf__gamma': ['scale', 'auto'] 
+       , 'clf__C'     : [1, 0.03, 10, 100, 1000, 10000, 32768]
+       , 'clf__gamma' : ['scale', 'auto'] 
         
         }
 ]
 
 #######################################################################
-#================= 
-# XGBClassifier ()
-#================= 
 
-# Define estimator
-#https://www.datatechnotes.com/2019/07/classification-example-with.html
-# XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
-#        colsample_bynode=1, colsample_bytree=1, gamma=0, learning_rate=0.1,
-#        max_delta_step=0, max_depth=3, min_child_weight=1, missing=None,
-#        n_estimators=100, n_jobs=1, nthread=None,
-#        objective='multi:softprob', random_state=0, reg_alpha=0,
-#        reg_lambda=1, scale_pos_weight=1, seed=None, silent=None,
-#        subsample=1, verbosity=1)
-estimator =  XGBClassifier(**rs, **njobs, verbose = 3)
-
-# Define pipleline with steps
-pipe_xgb = Pipeline([
-    ('pre', MinMaxScaler())
-    , ('fs', RFECV(DecisionTreeClassifier(**rs), cv = cv, scoring = 'matthews_corrcoef'))
-#    , ('fs', RFECV(estimator, cv = cv, scoring = 'matthews_corrcoef'))
-    , ('clf',  estimator)
-    ])
-
-param_grid_xgb = [
-    {
-    'fs__min_features_to_select' : [1,2]
-#     , 'fs__cv': [cv]
-     },
-    {
-#        'clf': [XGBClassifier(**rs , **njobs, verbose = 3)],
-         'clf__learning_rate': [0.01, 0.05, 0.1, 0.2]
-        , 'clf__max_depth'   : [4, 6, 8, 10, 12, 16, 20]
-        , 'clf__n_estimators': [10, 25, 50, 100, 200, 300]
-        #, 'clf__min_samples_leaf': [4, 8, 12, 16, 20]
-        #, 'clf__max_features': ['auto', 'sqrt']
-        }
-]
-
-#######################################################################