src

#! /usr/bin/python

import numpy as np
import matplotlib.pyplot as plt
from itertools import cycle


from sklearn import tree
from sklearn import svm, datasets
from sklearn.metrics import roc_curve, auc
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import label_binarize
from sklearn.multiclass import OneVsRestClassifier
from scipy import interp

import sklearn
import numpy
import pandas as pd
from sklearn.neighbors import KNeighborsClassifier
from sklearn.metrics import confusion_matrix

def distance(train, test):
	return numpy.linalg.norm(train-test)

def knn():
	k = 3
	X_train = pd.read_csv("3_train.csv")

	Y_train = X_train.iloc[:,(-1)].values
	X_train = X_train.iloc[:,0:-1].values

	X_test = pd.read_csv("3_test.csv")
	Y_test = X_test.iloc[:,(-1)].values
	X_test = X_test.iloc[:,0:-1].values

	res = []

	print "X treino:", X_train
	print "Y treino:", Y_train

	for test in X_test:
		print "instancia:", test

		distances = []
		for train in X_train:
			dist = distance(train,test)
			distances.append(dist)

		d, y = zip(*sorted(zip(distances, Y_train)))
		print "distancias ordenadas:", d
		print
		if(y[0:k].count(0) > y[0:k].count(1)):
			res.append(0)
		else:
			res.append(1)

	print res

def knn_():
	# usando library
	print "k = 3"
	neigh = KNeighborsClassifier(n_neighbors=3, metric="euclidean")
	X_train = pd.read_csv("3_train.csv")
	Y_train = X_train.iloc[:,(-1)]
	X_train = X_train.iloc[:,0:-1]

	neigh.fit(X_train, Y_train)

	X_test = pd.read_csv("3_test.csv")
	Y_test = X_test.iloc[:,(-1)].values
	X_test = X_test.iloc[:,0:-1]

	prediction = neigh.predict(X_test)

	print "predicted:", prediction
	print "true:", Y_test

	print confusion_matrix(Y_test, prediction)

def decision_tree():
	# using library
	X_train = pd.read_csv("3_train.csv")
	Y_train = X_train.iloc[:,(-1)]
	X_train = X_train.iloc[:,0:-1]

	X_test = pd.read_csv("3_test.csv")
	Y_test = X_test.iloc[:,(-1)].values
	X_test = X_test.iloc[:,0:-1]

	clf = tree.DecisionTreeClassifier(criterion="entropy")
	clf = clf.fit(X_train, Y_train)

	import graphviz
	dot_data = tree.export_graphviz(clf, out_file="3.out", 
                         feature_names=["Idade", "H", "J", "R", "B", "C"],  
                         class_names=["0", "1"],  
                         filled=True, rounded=True,  
                         special_characters=True)  
	graph = graphviz.Source(dot_data)  

	prediction = clf.predict(X_test)
	print "predicted:", prediction
	print "true:", Y_test

	print confusion_matrix(Y_test, prediction)
	
if __name__ == '__main__':

	
	#knn()
	#decision_tree()