# -*- coding: utf-8 -*-
"""
Created on Tue Nov 12 09:05:11 2019

@author: A6319
"""

import pandas as pd
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import train_test_split
from sklearn import metrics

def readFile(file):
    f = pd.read_csv(file)
    X = f.loc[:,f.columns != "Outcome"]
    y = f.Outcome
    return X, y

def decisionTree(X, y):
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 1)

    """
    clf = DecisionTreeClassifier()
    clf = clf.fit(X_train, y_train)
    y_pred = clf.predict(X_test)
    print("Acuracy: ", metrics.accuracy_score(y_test, y_pred))
    """

    clf = DecisionTreeClassifier(criterion="gini", max_depth=3)
    clf = clf.fit(X_train, y_train)
    y_pred = clf.predict(X_test)
    print("Acuracy: ", metrics.accuracy_score(y_test, y_pred))
    #print(clf.score(X_test,y_test))


def main():
    X, y = readFile("diabetes.csv")
    decisionTree(X, y)



if __name__ == "__main__":
    main()