#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Wed Jun 29 19:44:06 2022

@author: tanu
"""
import sys, os
import pandas as pd
import numpy as np
import re
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

# added
from sklearn.model_selection import train_test_split, cross_validate, cross_val_score, LeaveOneOut, KFold, RepeatedKFold, cross_val_predict

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
from sklearn.impute import KNNImputer as KNN
import json
import argparse
import re
import itertools
from sklearn.model_selection import LeaveOneGroupOut
from boruta import BorutaPy

###############################################################################
# homedir = os.path.expanduser("~")
# sys.path.append(homedir + '/git/LSHTM_analysis/scripts/ml/ml_functions')
# sys.path
###############################################################################
#outdir = "/home/tanu/git/LSHTM_ML/output/feature_selection/"

#====================
# Import ML functions 
#====================
#from ml_data_combined import *
#from MultClfs import *
#from GetMLData import *
#from SplitTTS import *

#skf_cv = StratifiedKFold(n_splits = 10 , shuffle = True, random_state = 42)

#logo = LeaveOneGroupOut()

########################################################################
# COMPLETE data: No tts_split
########################################################################
#%%
def CMLogoSkf_FS(cm_input_df
        , all_genes =  ["embb", "katg", "rpob", "pnca", "gid", "alr"]
        , bts_genes = ["embb", "katg", "rpob", "pnca", "gid"]
        , cols_to_drop = ['dst', 'dst_mode', 'gene_name']
        , target_var = 'dst_mode'
        , gene_group = 'gene_name'
        , std_gene_omit = []
        , var_type = ['numerical', 'categorical','mixed']

        ):
    
    n_jobs = os.cpu_count() 
    njobs = {'n_jobs': n_jobs }
    rs    = {'random_state': 42}
    
    cm_gene_featuresD = {}
    for bts_gene in bts_genes:
        print('\n BTS gene:', bts_gene)
        if not std_gene_omit:
            training_genesL = ['alr']
        else:
            training_genesL = []
            
        tr_gene_omit = std_gene_omit + [bts_gene]
        n_tr_genes = (len(bts_genes) - (len(std_gene_omit)))
        #n_total_genes = (len(bts_genes) - len(std_gene_omit))
        n_total_genes = len(all_genes)
        
        training_genesL = training_genesL + list(set(bts_genes) - set(tr_gene_omit))
        #training_genesL = [element for element in bts_genes if element not in tr_gene_omit]
    
        print('\nTotal genes: ', n_total_genes
              ,'\nTraining on:', n_tr_genes
              ,'\nTraining on genes:', training_genesL
              , '\nOmitted genes:', tr_gene_omit
              , '\nBlind test gene:', bts_gene) 
        
        print('\nDim of data:', cm_input_df.shape)
            
        tts_split_type = "logo_skf_BT_" + bts_gene
                           
        #-------
        # training
        #------
        cm_training_df = cm_input_df[~cm_input_df['gene_name'].isin(tr_gene_omit)]
        
        cm_X = cm_training_df.drop(cols_to_drop, axis=1, inplace=False)
        #cm_y = cm_training_df.loc[:,'dst_mode']
        cm_y = cm_training_df.loc[:, target_var]
    
        gene_group = cm_training_df.loc[:,'gene_name']
        
        print('\nTraining data dim:', cm_X.shape
              , '\nTraining Target dim:', cm_y.shape)
        
        if all(cm_X.columns.isin(cols_to_drop) == False):
            print('\nChecked training df does NOT have Target var')
        else:
            sys.exit('\nFAIL: training data contains Target var')
        
        #---------------
        # BTS: genes
        #---------------
        cm_test_df = cm_input_df[cm_input_df['gene_name'].isin([bts_gene])]
        
        cm_bts_X = cm_test_df.drop(cols_to_drop, axis = 1, inplace = False)
        #cm_bts_y = cm_test_df.loc[:, 'dst_mode']
        cm_bts_y = cm_test_df.loc[:, target_var]
    
        print('\nTEST data dim:'     , cm_bts_X.shape
              , '\nTEST Target dim:' , cm_bts_y.shape)
        
        print("Running Multiple models on LOGO with SKF")
        
        
        # REASSIGN for simplicity
        # X
        X_train = cm_X.copy()
        X_test = cm_bts_X.copy()
        X_train.shape
        X_test.shape
        
        # Y
        y_train = cm_y.copy()
        y_test = cm_bts_y.copy()
        y_train.shape
        y_test.shape
        
        
##############################################################################
       #PREPROCESS
        
        numerical_ix = X_train.select_dtypes(include=['int64', 'float64']).columns
        numerical_ix
        print("\nNo. of numerical indices:", len(numerical_ix))

        categorical_ix = X_train.select_dtypes(include=['object', 'bool']).columns
        categorical_ix  
        print("\nNo. of categorical indices:", len(categorical_ix))

        #======================================================
        # Determine preprocessing steps ~ var_type
        #======================================================
        
        if var_type  == 'numerical':
            t = [('num', MinMaxScaler(), numerical_ix)]
            
        if var_type == 'categorical':
            t = [('cat', OneHotEncoder(), categorical_ix)]
            
        if var_type  == 'mixed':
            t = [('num', MinMaxScaler(), numerical_ix)
                 , ('cat', OneHotEncoder(), categorical_ix)]            
            
        col_transform = ColumnTransformer(transformers = t
                                           , remainder='passthrough')
            
        col_transform.fit(X_train)
        col_transform.get_feature_names_out()
            
        var_type_colnames = col_transform.get_feature_names_out()
        var_type_colnames = pd.Index(var_type_colnames)
            
        if var_type == 'mixed':
                print('\nVariable type is:', var_type
                      , '\nNo. of columns in input_df:', len(X_train.columns)
                      , '\nNo. of columns post one hot encoder:', len(var_type_colnames))
        else:
                print('\nNo. of columns in input_df:', len(cm_input_df.columns))


##############################################################################
        # FS: Random Forest + Boruta
        
        X_train = col_transform.fit_transform(X_train)
        X_test = col_transform.fit_transform(X_test)

        fs_clf = "RandomForestClassifier"
        rf_all_features = RandomForestClassifier(n_estimators=1000, max_depth=5
                                                 , **rs, **njobs)
        
        # fit 
        rf_all_features.fit(np.array(X_train), np.array(y_train))
        print("RF, baseline MCC:", matthews_corrcoef(y_test, rf_all_features.predict(X_test)))

        # BORUTA and fit
        boruta_selector = BorutaPy(rf_all_features,**rs, verbose = 3)
        boruta_selector.fit(np.array(X_train), np.array(y_train))  

        # Get chosen features
        print("Ranking: ", boruta_selector.ranking_)          
        print("No. of significant features: ", boruta_selector.n_features_) 
        
        
        X_important_train = boruta_selector.transform(np.array(X_train))
        X_important_test = boruta_selector.transform(np.array(X_test)) 
        
        # just retesting with selected features on RF itselfs       
        rf_all_features.fit(X_important_train, y_train) 
        print("RF, Boruta MCC:", matthews_corrcoef(y_test, rf_all_features.predict(X_important_test)))
        
        selected_rf_features = pd.DataFrame({'Feature':list(var_type_colnames),
                                               'Ranking':boruta_selector.ranking_})
        
        sel_rf_features_sorted = selected_rf_features.sort_values(by='Ranking')


        sel_features = var_type_colnames[boruta_selector.support_]
        cm_gene_featuresD.update({bts_gene: {
            "sel_features": sel_features
            , "fs_ranking" : sel_rf_features_sorted
            , "fs_model_name": fs_clf
            }
            }
            )
        
        
    return(cm_gene_featuresD)