tidying script to run from cmd and via ssh

classification_params_FS.py

@@ -6,17 +6,7 @@
 # autosklearn --> pipleine --> components --> classification
 # https://github.com/automl/auto-sklearn/tree/master/autosklearn/pipeline/components/classification
 
-# TOADD: 
-# 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
-
-
+# ADDED 27/05/2022: Extra Tree + LRCV and RCCV
 ######https://scikit-learn.org/stable/supervised_learning.html
 
 ########################################################################
@@ -57,7 +47,7 @@ param_grid_abc = [
 #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)
+estimator =  ExtraTreesClassifier(**rs)
 
 # Define pipleline with steps
 pipe_abc = Pipeline([
@@ -85,6 +75,40 @@ param_grid_abc = [
         }
 ]
 
+
+#======================
+# Extra TreeClassifier()
+
+https://scikit-learn.org/stable/modules/generated/sklearn.tree.ExtraTreeClassifier.html
+#======================
+estimator =  ExtraTreeClassifier(**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': [ExtraTreeClassifier(**rs)],
+         '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
@@ -304,8 +328,8 @@ param_grid_gbc = [
 #########################################################################
 #=========================== 
 # 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
+#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()
@@ -439,12 +463,58 @@ param_grid_lr = [
         'clf__solver': ['liblinear']
     }
 
+]
+
+#########################################################################
+#=========================== 
+# LogisticRegressionCV () *
+# https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegressionCV.html
+#=========================== 
+# Define estimator
+estimator =  LogisticRegressionCV(cv = 10, **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': [LogisticRegressionCV(cv = 10, **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': [LogisticRegressionCV(cv = 10, **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': [LogisticRegressionCV(cv = 10, **rs)],
+        'clf__C': np.logspace(0, 4, 10),
+        'clf__penalty': ['l1', 'l2'],
+        'clf__max_iter': list(range(100,800,100)),
+        'clf__solver': ['liblinear']
+    }
+
 ]
 #########################################################################
 #================== 
 # 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
+#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)
@@ -531,6 +601,35 @@ param_grid_rc = [
       'clf__alpha': [0.1, 0.2, 0.5, 0.8, 1.0]
      }
 ]
+
+#######################################################################
+#====================
+# RidgeClassifier() *
+https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.RidgeClassifierCV.html
+#====================
+
+# Define estimator
+estimator =  RidgeClassifierCV(cv = 10, **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' : [RidgeClassifierCV(cv = 10, **rs)],
+      'clf__alpha': [0.1, 0.2, 0.5, 0.8, 1.0]
+     }
+]
 #######################################################################
 #========
 # SVC()