tidying import script and moving estimators where the ML classifier func are

UQ_pnca_ML.py

@@ -14,105 +14,10 @@ print(np.__version__)
 print(pd.__version__)
 import pprint as pp
 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
-
-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
-import json
 from sklearn.impute import KNNImputer as KNN
 
-# My functions and globals
-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)
-                 , 'jcc'        : make_scorer(jaccard_score)
-            }) 
-  
-rs = {'random_state': 42}
-njobs = {'n_jobs': 10}
-skf_cv = StratifiedKFold(n_splits = 10
-                          #, shuffle = False, random_state= None)
-                           , shuffle = True,**rs)
-
-rskf_cv = RepeatedStratifiedKFold(n_splits = 10
-                                  , n_repeats = 3
-                                  , **rs)
-
-mcc_score_fn = {'mcc': make_scorer(matthews_corrcoef)}
-jacc_score_fn = {'jcc': make_scorer(jaccard_score)}
 #%%
-homedir = os.path.expanduser("~")
-os.chdir(homedir + "/git/ML_AI_training/")
-
-# my function
-#from MultClassPipe import MultClassPipeline
-from MultClassPipe2 import MultClassPipeline2
-from loopity_loop import MultClassPipeSKFLoop
-#from MultClassPipe3 import MultClassPipeSKFCV
-#from UQ_MultClassPipe4 import MultClassPipeSKFCV
-from UQ_MultModelsCl import MultModelsCl
-#gene = 'pncA'
-#drug = 'pyrazinamide'
-
-#gene = 'katG'
-#drug = 'isoniazid'
-
-
 #==============
 # directories
 #==============