#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Mon May 16 05:59:12 2022

@author: tanu
"""
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Tue Mar 15 11:09:50 2022

@author: tanu
"""
#%% Import libraries, data, and scoring func: UQ_pnca_ML.py
rs = {'random_state': 42}
njobs = {'n_jobs': 10}
#%% Logistic Regression + hyperparam: BaseEstimator: ClfSwitcher()

class ClfSwitcher(BaseEstimator):
    def __init__(
        self, 
        estimator = SGDClassifier(),
        #feature = RFECV()
    ):
        """
        A Custom BaseEstimator that can switch between classifiers.
        :param estimator: sklearn object - The classifier
        """ 
        self.estimator = estimator
    
    def fit(self, X, y=None, **kwargs):
        self.estimator.fit(X, y)
        return self

    def predict(self, X, y=None):
        return self.estimator.predict(X)
    
    def predict_proba(self, X):
        return self.estimator.predict_proba(X)
    
    def score(self, X, y):
        return self.estimator.score(X, y)
    
parameters = [
    # {'feature__fs__estimator': LogisticRegression(**rs)
    #  , 'feature__fs__cv': [10]
    #  , 'feature__fs__scoring': ['matthews_corrcoef']
    #  },
    
    {
        'clf__estimator': [LogisticRegression(**rs)],
        'clf__estimator__C': [0.001, 0.01, 0.1, 1, 10, 100, 1000],
        #'clf__estimator__C': np.logspace(0, 4, 10),
        'clf__estimator__penalty': ['none', 'l1', 'l2', 'elasticnet'],
        'clf__estimator__max_iter': list(range(100,800,100)),
        'clf__estimator__solver': ['saga']
    }#,
    # {
    #     'clf__estimator': [MODEL2(**rs)],
    #     #'clf__estimator__C': [0.001, 0.01, 0.1, 1, 10, 100, 1000],
    #     'clf__estimator__C': np.logspace(0, 4, 10),
    #     'clf__estimator__penalty': ['l2', 'none'],
    #     'clf__estimator__max_iter': list(range(100,800,100)),
    #     'clf__estimator__solver': ['newton-cg', 'lbfgs', 'sag']
    # }, 
]    
#%% Create pipeline
pipeline = Pipeline([
    ('pre', MinMaxScaler())
#   , ('fs',  RFECV(LogisticRegression(**rs), cv = rskf_cv, scoring = 'matthews_corrcoef'))
   , ('selector', SelectKBest(mutual_info_classif, k=6))
   , ('clf', ClfSwitcher())
])

#%% Grid search i.e hyperparameter tuning and refitting on mcc
mod_fs = GridSearchCV(pipeline
                    , parameters
                    , scoring = mcc_score_fn, refit = 'mcc'
                    , cv = skf_cv
                    , **njobs
                    , return_train_score = False
                    , verbose = 3)

#%% Fit 
mod_fs_fit = mod_fs.fit(X, y)
mod_fs_fbm = mod_fs_fit.best_params_
mod_fs_fbmr = mod_fs_fit.cv_results_
mod_fs_fbs = mod_fs_fit.best_score_
print('Best model:\n', mod_fs_fbm)
print('Best models score:\n', mod_fs_fbs, ':' , round(mod_fs_fbs, 2))

#print('\nMean test score from fit results:', round(mean(mod_fs_fbmr['mean_test_mcc']),2))
print('\nMean test score from fit results:', round(np.nanmean(mod_fs_fbmr['mean_test_mcc']),2))

###############################################################################
#%% Blind test
######################################
#         Blind test
######################################
test_predict = mod_fs_fit.predict(X_bts)
print(test_predict)
print('\nMCC on Blind test:'     , round(matthews_corrcoef(y_bts, test_predict),2))
print('\nAccuracy on Blind test:', round(accuracy_score(y_bts, test_predict),2))