NumericalDataClassification.py

import csv
import random
import operator 
import math


def euclideanDistance(instance1, instance2, length):
	distance = 0
	for x in range(length):
		distance += pow((instance1[x] - instance2[x]), 2)
	return math.sqrt(distance)

def getNeighbors(trainingSet, testInstance, k):
	distances = []
	length = len(testInstance)-1
	for x in range(len(trainingSet)):
		dist = euclideanDistance(testInstance, trainingSet[x], length)
		distances.append((trainingSet[x], dist))
	distances.sort(key=operator.itemgetter(1))
	neighbors = []
	for x in range(k):
		neighbors.append(distances[x][0])
	return neighbors
	
trainSet = [[2, 2, 2, 'a'], [4, 4, 4, 'b']]
testInstance = [5, 5, 5]
k = 1
neighbors = getNeighbors(trainSet, testInstance, 1)
print(neighbors)

exit(0)

def loadDataset(filename, split, trainingSet=[] , testSet=[]):
	with open(filename, 'rb') as csvfile:
	    lines = csv.reader(csvfile)
	    dataset = list(lines)
	    for x in range(len(dataset)-1):
	        for y in range(4):
	            dataset[x][y] = float(dataset[x][y])
	        if random.random() < split:
	            trainingSet.append(dataset[x])
	        else:
	            testSet.append(dataset[x])
trainingSet=[]
testSet=[]
loadDataset('irisdata.txt', 0.66, trainingSet, testSet)
print 'Train: ' + repr(len(trainingSet))
print 'Test: ' + repr(len(testSet))