modified loopity and multclass3 to have skf_cv as a parameters for cv

imports.py

@@ -17,8 +17,12 @@ from sklearn.neighbors import KNeighborsClassifier
 from sklearn.svm import SVC
 from sklearn.tree import DecisionTreeClassifier
 from sklearn.ensemble import RandomForestClassifier, ExtraTreesClassifier
+from sklearn.ensemble import AdaBoostClassifier
+from sklearn.ensemble import GradientBoostingClassifier
 from sklearn.neural_network import MLPClassifier
 from xgboost import XGBClassifier
+from sklearn.naive_bayes import MultinomialNB
+from sklearn.linear_model import SGDClassifier
 from sklearn.preprocessing import StandardScaler, MinMaxScaler, OneHotEncoder
 
 from sklearn.compose import ColumnTransformer
@@ -52,11 +56,29 @@ from imblearn.over_sampling import RandomOverSampler
 from imblearn.over_sampling import SMOTE
 from imblearn.pipeline import Pipeline
 #from sklearn.datasets import make_classification
-from sklearn.model_selection import cross_validate
+from sklearn.model_selection import cross_validate, cross_val_score
 from sklearn.model_selection import RepeatedStratifiedKFold
 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
+
+scoring_fn =  ({'accuracy'      : make_scorer(accuracy_score)
+                 , 'fscore'     : make_scorer(f1_score)
+                 , 'mcc'        : make_scorer(matthews_corrcoef)
+                 ,  'precision' : make_scorer(precision_score)
+                 ,  'recall'    : make_scorer(recall_score)
+                 ,  'roc_auc'   : make_scorer(roc_auc_score)
+            }) 
+  
+rs = {'random_state': 42}
+njobs = {'n_jobs': 10}
+skf_cv = StratifiedKFold(n_splits = 10
+                          #, shuffle = False, random_state= None)
+                           , shuffle = True,**rs)
+
 #%%
 homedir = os.path.expanduser("~")
 os.chdir(homedir + "/git/ML_AI_training/")
@@ -64,8 +86,8 @@ os.chdir(homedir + "/git/ML_AI_training/")
 # my function
 from MultClassPipe import MultClassPipeline
 from MultClassPipe2 import MultClassPipeline2
-from loopity_loop import MultClassPipeSKF
-from MultClassPipe3 import MultClassPipelineCV
+from loopity_loop import MultClassPipeSKFLoop
+from MultClassPipe3 import MultClassPipeSKFCV
 
 
 gene = 'pncA'
@@ -199,3 +221,16 @@ cat_df_wtgt.shape
 
 all_df_wtgt = my_df[numerical_FN + categorical_FN + ['mutation_class']]
 all_df_wtgt.shape
+
+#%%
+#%% Get train-test split and scoring functions
+X = num_df_wtgt[numerical_FN]
+y = num_df_wtgt['mutation_class']
+
+X_train, X_test, y_train, y_test = train_test_split(X
+                                            ,y
+                                            , test_size    = 0.33
+                                            , random_state = 2
+                                            , shuffle      = True
+                                            , stratify     = y)
+