数据集获取参考：blog.csdn.net/nima1994/ar…
关键步骤如下：
1.数据处理
通常数据集划分为训练集：测试集=67:33
2.相似度度量
欧氏距离：空间中的实际距离
汉明距离：两个（相同长度）字对应位不同的数量
3.近邻查找
4.预测与测试\
代码如下：
import csv
import random
import math
import numpy as np
def euclideanDistance(instance1, instance2, length):
distance = 0
for x in range(length):
distance += pow((instance1[x] - instance2[x]), 2)
return math.sqrt(distance)
def loadDataset(filename, split, trainingSet=[] , testSet=[]):
with open(filename) as csvfile:
lines = csv.reader(csvfile)
dataset = list(lines)
for x in range(len(dataset)-1):
for y in range(length):
dataset[x][y] = float(dataset[x][y])
if random.random()<split:
trainingSet.append(dataset[x])
else:
testSet.append(dataset[x])
def getNeighbors(trainingSet, testInstance, length,k):
neighbors = []
for x in np.argsort(np.array([euclideanDistance(testInstance, t, length) for t in trainingSet]))[:k]:
neighbors.append(trainingSet[x])
return neighbors
def getResponse(neighbors):
classVotes = {}
for x in neighbors:
response = x[-1]
if response in classVotes:
classVotes[response] += 1
else:
classVotes[response] = 1
classVotes=sorted(classVotes.items(),key=lambda item:item[1],reverse=True)
return classVotes[0][0]
def getAccuracy(testSet, predictions):
correct = 0
for x in range(len(testSet)):
if testSet[x][-1]==predictions[x]:
correct += 1
return (correct/float(len(testSet))) * 100.0
trainingSet=[]
testSet=[]
predictions=[]
length=4
#初始化训练集和测试集
loadDataset('d:/iris.data', 0.67, trainingSet, testSet)
for x in testSet:
# 得到近邻
neighbors = getNeighbors(trainingSet, x, length, 5)
result = getResponse(neighbors)
predictions.append(result)
accuracy = getAccuracy(testSet, predictions)
print('Accuracy: ' + repr(accuracy) + '%')
运行结果如：
