#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Wed May 18 06:03:24 2022

@author: tanu
"""

#%%
#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)

#%% XGBoost + hyperparam: BaseEstimator: ClfSwitcher()
class ClfSwitcher(BaseEstimator):
    def __init__(
        self, 
        estimator = SGDClassifier(),
    ):
        """
        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 = [
    {
        'clf__estimator': [XGBClassifier(**rs , **njobs, verbose = 3)]      
        , 'clf__estimator__learning_rate': [0.01, 0.05, 0.1, 0.2]
        , 'clf__estimator__max_depth': [4, 6, 8, 10, 12, 16, 20]
        #, 'clf__estimator__min_samples_leaf': [4, 8, 12, 16, 20]
        #, 'clf__estimator__max_features': ['auto', 'sqrt']
        }
]

# Create pipeline
pipeline = Pipeline([
    ('pre', MinMaxScaler()),
    ('clf', ClfSwitcher()),
])

# Grid search i.e hyperparameter tuning and refitting on mcc
gscv_xgb = GridSearchCV(pipeline
                    , parameters
                    #, scoring = 'f1', refit = 'f1'
                    , scoring = mcc_score_fn, refit = 'mcc'
                    , cv = skf_cv
                    , **njobs
                    , return_train_score = False
                    , verbose = 3)

# Fit 
gscv_xgb_fit  = gscv_xgb.fit(X, y)

gscv_xgb_fit_be_mod = gscv_xgb_fit.best_params_
gscv_xgb_fit_be_res = gscv_xgb_fit.cv_results_

print('Best model:\n', gscv_xgb_fit_be_mod)
print('Best models score:\n', gscv_xgb_fit.best_score_, ':' , round(gscv_xgb_fit.best_score_, 2))

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

######################################
# Blind test
######################################

# See how it does on the BLIND test
#print('\nBlind test score, mcc:', )

test_predict = gscv_xgb_fit.predict(X_bts)
print(test_predict)
print(np.array(y_bts))
y_btsf = np.array(y_bts)

print(accuracy_score(y_btsf, test_predict))
print(matthews_corrcoef(y_btsf, test_predict))

# create a dict with all scores
xgb_bts_dict = {#'best_model': list(gscv_xgb_fit_be_mod.items())
               'bts_fscore'     : None
               , 'bts_mcc'      : None
               , 'bts_precision': None
               , 'bts_recall'   : None
               , 'bts_accuracy' : None
               , 'bts_roc_auc'  : None
               , 'bts_jaccard'  : None }
xgb_bts_dict
xgb_bts_dict['bts_fscore']    = round(f1_score(y_bts, test_predict),2)
xgb_bts_dict['bts_mcc']       = round(matthews_corrcoef(y_bts, test_predict),2)
xgb_bts_dict['bts_precision'] = round(precision_score(y_bts, test_predict),2)
xgb_bts_dict['bts_recall']    = round(recall_score(y_bts, test_predict),2)
xgb_bts_dict['bts_accuracy']  = round(accuracy_score(y_bts, test_predict),2)
xgb_bts_dict['bts_roc_auc']   = round(roc_auc_score(y_bts, test_predict),2)
xgb_bts_dict['bts_jaccard']   = round(jaccard_score(y_bts, test_predict),2)
xgb_bts_dict

# Create a df from dict with all scores
xgb_bts_df = pd.DataFrame.from_dict(xgb_bts_dict,orient = 'index')
xgb_bts_df.columns = ['XGBoost']
print(xgb_bts_df)

# Create df with best model params
model_params = pd.Series(['best_model_params',  list(gscv_xgb_fit_be_mod.items() )])
model_params_df = model_params.to_frame()
model_params_df
model_params_df.columns = ['XGBoost']
model_params_df.columns

# Combine the df of scores and the best model params
xgb_bts_df.columns
xgb_output = pd.concat([model_params_df, xgb_bts_df], axis = 0)
xgb_output

# Format the combined df
# Drop the best_model_params row from xgb_output
xgb_df = xgb_output.drop([0], axis = 0)
xgb_df

#FIXME: tidy the index of the formatted df

###############################################################################