# Importing the libraries

import numpy as np

import matplotlib.pyplot as plt

import pandas as pd

from sklearn.ensemble import RandomForestClassifier

from sklearn.model_selection import train_test_split, cross_val_score

from sklearn.model_selection import GridSearchCV

from sklearn.metrics import accuracy_score, roc_auc_score, roc_curve

# Importing the dataset

dataset = pd.read_csv('../Dataset/diabetes.csv')

X = dataset.iloc[:, :-1].values

y = dataset.iloc[:, 8].values

# Splitting the dataset into the Training set and Test set

from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.25, 

                                                    random_state = 42)

# Feature Scaling

from sklearn.preprocessing import StandardScaler

sc = StandardScaler()

X_train = sc.fit_transform(X_train)

X_test = sc.transform(X_test)

# Parameter evaluation

rfclf = RandomForestClassifier(random_state=42)

parameters={'n_estimators': [50, 100],

            'max_features': ['auto', 'sqrt', 'log2'],

            'max_depth' : [4,5,6,7],

            'criterion' :['gini', 'entropy']

}

gridsearch=GridSearchCV(rfclf, parameters, cv=50, scoring='roc_auc', n_jobs = -1)

gridsearch.fit(X, y)

print(gridsearch.best_params_)

print(gridsearch.best_score_)

rf = RandomForestClassifier(n_estimators=100, criterion = 'gini', max_depth = 6, 

                            max_features = 'auto', random_state=0)

rf.fit(X_train, y_train)

print("Accuracy on training set: {:.3f}".format(rf.score(X_train, y_train)))

print("Accuracy on test set: {:.3f}".format(rf.score(X_test, y_test)))

y_pred = rf.predict(X_test)

# Making the Confusion Matrix

from sklearn.metrics import classification_report, confusion_matrix

cm = confusion_matrix(y_test, y_pred)

print('TP - True Negative {}'.format(cm[0,0]))

print('FP - False Positive {}'.format(cm[0,1]))

print('FN - False Negative {}'.format(cm[1,0]))

print('TP - True Positive {}'.format(cm[1,1]))

print('Accuracy Rate: {}'.format(np.divide(np.sum([cm[0,0],cm[1,1]]),np.sum(cm))))

print('Misclassification Rate: {}'.format(np.divide(np.sum([cm[0,1],cm[1,0]]),np.sum(cm))))

round(roc_auc_score(y_test,y_pred),5)