import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns #for plotting
from sklearn.ensemble import RandomForestClassifier #for the model
from sklearn.tree import DecisionTreeClassifier
from sklearn.tree import export_graphviz #plot tree
from sklearn.metrics import roc_curve, auc #for model evaluation
from sklearn.metrics import classification_report #for model evaluation
from sklearn.metrics import confusion_matrix #for model evaluation
from sklearn.model_selection import train_test_split #for data splitting


#dt is the dataset..

X_train, X_test, y_train, y_test = train_test_split(dt.drop('target', 1), dt['target'], test_size = .2, random_state=10)

model = RandomForestClassifier(max_depth=5)
model.fit(X_train, y_train)

estimator = model.estimators_[1]
feature_names = [i for i in X_train.columns]

y_train_str = y_train.astype('str')
y_train_str[y_train_str == '0'] = 'no disease'
y_train_str[y_train_str == '1'] = 'disease'
y_train_str = y_train_str.values

y_predict = model.predict(X_test)
y_pred_quant = model.predict_proba(X_test)[:, 1]
y_pred_bin = model.predict(X_test)

confusion_matrix = confusion_matrix(y_test, y_pred_bin)
confusion_matrix

total=sum(sum(confusion_matrix))

sensitivity = confusion_matrix[0,0]/(confusion_matrix[0,0]+confusion_matrix[1,0])
print('Sensitivity : ', sensitivity )

specificity = confusion_matrix[1,1]/(confusion_matrix[1,1]+confusion_matrix[0,1])
print('Specificity : ', specificity)
print('confusion_matrix :', confusion_matrix)