#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Fri Mar  4 15:25:33 2022

@author: tanu
"""
#%%
import os, sys
import pandas as pd
from sklearn.linear_model import LogisticRegression
from sklearn.naive_bayes import BernoulliNB
from sklearn.neighbors import KNeighborsClassifier
from sklearn.svm import SVC
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier, ExtraTreesClassifier
from sklearn.neural_network import MLPClassifier
from sklearn.pipeline import Pipeline
from xgboost import XGBClassifier
from sklearn.preprocessing import StandardScaler
from sklearn.preprocessing import MinMaxScaler
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score, confusion_matrix, precision_score, recall_score, roc_auc_score, roc_curve, f1_score
#%%
rs = {'random_state': 42}

# Multiple Classification - Model Pipeline
def MultClassPipeline(X_train, X_test, y_train, y_test):

    log_reg = LogisticRegression(**rs)
    nb = BernoulliNB()
    knn = KNeighborsClassifier()
    svm = SVC(**rs)
    mlp = MLPClassifier(max_iter=500, **rs)
    dt = DecisionTreeClassifier(**rs)
    et = ExtraTreesClassifier(**rs)
    rf = RandomForestClassifier(**rs)
    xgb = XGBClassifier(**rs, verbosity=0)

    clfs = [
            ('Logistic Regression', log_reg), 
            ('Naive Bayes', nb),
            ('K-Nearest Neighbors', knn), 
            ('SVM', svm), 
            ('MLP', mlp), 
            ('Decision Tree', dt), 
            ('Extra Trees', et), 
            ('Random Forest', rf), 
            ('XGBoost', xgb)
            ]


    pipelines = []

    scores_df = pd.DataFrame(columns=['Model', 'F1_Score', 'Precision', 'Recall', 'Accuracy', 'ROC_AUC'])

    for clf_name, clf in clfs:

        pipeline = Pipeline(steps=[
                                   ('scaler', MinMaxScaler()),
                                   #('scaler', StandardScaler()),
                                   ('classifier', clf)
                                   ]
                            )
        pipeline.fit(X_train, y_train)

        # Model predictions
        y_pred  = pipeline.predict(X_test)
        
        # F1-Score
        fscore  = f1_score(y_test, y_pred)
        # Precision
        pres    = precision_score(y_test, y_pred)
        # Recall
        rcall   = recall_score(y_test, y_pred)
        # Accuracy
        accu    = accuracy_score(y_test, y_pred)
        # ROC_AUC
        roc_auc = roc_auc_score(y_test, y_pred)

        pipelines.append(pipeline)

        scores_df = scores_df.append({
                                      'Model'     : clf_name, 
                                      'F1_Score'  : fscore,
                                      'Precision' : pres,
                                      'Recall'    : rcall,
                                      'Accuracy'  : accu,
                                      'ROC_AUC'   : roc_auc
                                      
                                      }, 
                                     ignore_index = True)
        
    return pipelines, scores_df